2195 files changed, 34258 insertions, 20319 deletions

diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index eda519519f12..a7362b1096c4 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -521,6 +521,7 @@ What:		/sys/devices/system/cpu/vulnerabilities
 		/sys/devices/system/cpu/vulnerabilities/tsx_async_abort
 		/sys/devices/system/cpu/vulnerabilities/itlb_multihit
 		/sys/devices/system/cpu/vulnerabilities/mmio_stale_data
+		/sys/devices/system/cpu/vulnerabilities/retbleed
 Date:		January 2018
 Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
 Description:	Information about CPU vulnerabilities
diff --git a/Documentation/ABI/testing/sysfs-driver-xen-blkback b/Documentation/ABI/testing/sysfs-driver-xen-blkback
index ac2947b98950..3d5de44cbbee 100644
--- a/Documentation/ABI/testing/sysfs-driver-xen-blkback
+++ b/Documentation/ABI/testing/sysfs-driver-xen-blkback
@@ -42,5 +42,5 @@ KernelVersion:  5.10
 Contact:        SeongJae Park <sjpark@amazon.de>
 Description:
                 Whether to enable the persistent grants feature or not.  Note
-                that this option only takes effect on newly created backends.
+                that this option only takes effect on newly connected backends.
                 The default is Y (enable).
diff --git a/Documentation/ABI/testing/sysfs-driver-xen-blkfront b/Documentation/ABI/testing/sysfs-driver-xen-blkfront
index 28008905615f..1f7659aa085c 100644
--- a/Documentation/ABI/testing/sysfs-driver-xen-blkfront
+++ b/Documentation/ABI/testing/sysfs-driver-xen-blkfront
@@ -15,5 +15,5 @@ KernelVersion:  5.10
 Contact:        SeongJae Park <sjpark@amazon.de>
 Description:
                 Whether to enable the persistent grants feature or not.  Note
-                that this option only takes effect on newly created frontends.
+                that this option only takes effect on newly connected frontends.
                 The default is Y (enable).
diff --git a/Documentation/admin-guide/device-mapper/writecache.rst b/Documentation/admin-guide/device-mapper/writecache.rst
index 10429779a91a..724e028d1858 100644
--- a/Documentation/admin-guide/device-mapper/writecache.rst
+++ b/Documentation/admin-guide/device-mapper/writecache.rst
@@ -78,16 +78,16 @@ Status:
 2. the number of blocks
 3. the number of free blocks
 4. the number of blocks under writeback
-5. the number of read requests
-6. the number of read requests that hit the cache
-7. the number of write requests
-8. the number of write requests that hit uncommitted block
-9. the number of write requests that hit committed block
-10. the number of write requests that bypass the cache
-11. the number of write requests that are allocated in the cache
+5. the number of read blocks
+6. the number of read blocks that hit the cache
+7. the number of write blocks
+8. the number of write blocks that hit uncommitted block
+9. the number of write blocks that hit committed block
+10. the number of write blocks that bypass the cache
+11. the number of write blocks that are allocated in the cache
 12. the number of write requests that are blocked on the freelist
 13. the number of flush requests
-14. the number of discard requests
+14. the number of discarded blocks
 
 Messages:
 	flush
diff --git a/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst b/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst
index 9393c50b5afc..c98fd11907cc 100644
--- a/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst
+++ b/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst
@@ -230,6 +230,20 @@ The possible values in this file are:
      * - 'Mitigation: Clear CPU buffers'
        - The processor is vulnerable and the CPU buffer clearing mitigation is
          enabled.
+     * - 'Unknown: No mitigations'
+       - The processor vulnerability status is unknown because it is
+	 out of Servicing period. Mitigation is not attempted.
+
+Definitions:
+------------
+
+Servicing period: The process of providing functional and security updates to
+Intel processors or platforms, utilizing the Intel Platform Update (IPU)
+process or other similar mechanisms.
+
+End of Servicing Updates (ESU): ESU is the date at which Intel will no
+longer provide Servicing, such as through IPU or other similar update
+processes. ESU dates will typically be aligned to end of quarter.
 
 If the processor is vulnerable then the following information is appended to
 the above information:
diff --git a/Documentation/admin-guide/hw-vuln/spectre.rst b/Documentation/admin-guide/hw-vuln/spectre.rst
index 6bd97cd50d62..7e061ed449aa 100644
--- a/Documentation/admin-guide/hw-vuln/spectre.rst
+++ b/Documentation/admin-guide/hw-vuln/spectre.rst
@@ -422,6 +422,14 @@ The possible values in this file are:
   'RSB filling'   Protection of RSB on context switch enabled
   =============   ===========================================
 
+  - EIBRS Post-barrier Return Stack Buffer (PBRSB) protection status:
+
+  ===========================  =======================================================
+  'PBRSB-eIBRS: SW sequence'   CPU is affected and protection of RSB on VMEXIT enabled
+  'PBRSB-eIBRS: Vulnerable'    CPU is vulnerable
+  'PBRSB-eIBRS: Not affected'  CPU is not affected by PBRSB
+  ===========================  =======================================================
+
 Full mitigation might require a microcode update from the CPU
 vendor. When the necessary microcode is not available, the kernel will
 report vulnerability.
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 205ad5cfe63d..8f57db7356a9 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3020,6 +3020,7 @@
 					       no_entry_flush [PPC]
 					       no_uaccess_flush [PPC]
 					       mmio_stale_data=off [X86]
+					       retbleed=off [X86]
 
 				Exceptions:
 					       This does not have any effect on
@@ -3042,6 +3043,7 @@
 					       mds=full,nosmt [X86]
 					       tsx_async_abort=full,nosmt [X86]
 					       mmio_stale_data=full,nosmt [X86]
+					       retbleed=auto,nosmt [X86]
 
 	mminit_loglevel=
 			[KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this
@@ -4968,6 +4970,43 @@
 
 	retain_initrd	[RAM] Keep initrd memory after extraction
 
+	retbleed=	[X86] Control mitigation of RETBleed (Arbitrary
+			Speculative Code Execution with Return Instructions)
+			vulnerability.
+
+			AMD-based UNRET and IBPB mitigations alone do not stop
+			sibling threads from influencing the predictions of other
+			sibling threads. For that reason, STIBP is used on pro-
+			cessors that support it, and mitigate SMT on processors
+			that don't.
+
+			off          - no mitigation
+			auto         - automatically select a migitation
+			auto,nosmt   - automatically select a mitigation,
+				       disabling SMT if necessary for
+				       the full mitigation (only on Zen1
+				       and older without STIBP).
+			ibpb         - On AMD, mitigate short speculation
+				       windows on basic block boundaries too.
+				       Safe, highest perf impact. It also
+				       enables STIBP if present. Not suitable
+				       on Intel.
+			ibpb,nosmt   - Like "ibpb" above but will disable SMT
+				       when STIBP is not available. This is
+				       the alternative for systems which do not
+				       have STIBP.
+			unret        - Force enable untrained return thunks,
+				       only effective on AMD f15h-f17h based
+				       systems.
+			unret,nosmt  - Like unret, but will disable SMT when STIBP
+				       is not available. This is the alternative for
+				       systems which do not have STIBP.
+
+			Selecting 'auto' will choose a mitigation method at run
+			time according to the CPU.
+
+			Not specifying this option is equivalent to retbleed=auto.
+
 	rfkill.default_state=
 		0	"airplane mode".  All wifi, bluetooth, wimax, gps, fm,
 			etc. communication is blocked by default.
@@ -5314,6 +5353,7 @@
 			eibrs		  - enhanced IBRS
 			eibrs,retpoline   - enhanced IBRS + Retpolines
 			eibrs,lfence      - enhanced IBRS + LFENCE
+			ibrs		  - use IBRS to protect kernel
 
 			Not specifying this option is equivalent to
 			spectre_v2=auto.
diff --git a/Documentation/admin-guide/pm/cpuidle.rst b/Documentation/admin-guide/pm/cpuidle.rst
index aec2cd2aaea7..19754beb5a4e 100644
--- a/Documentation/admin-guide/pm/cpuidle.rst
+++ b/Documentation/admin-guide/pm/cpuidle.rst
@@ -612,8 +612,8 @@ the ``menu`` governor to be used on the systems that use the ``ladder`` governor
 by default this way, for example.
 
 The other kernel command line parameters controlling CPU idle time management
-described below are only relevant for the *x86* architecture and some of
-them affect Intel processors only.
+described below are only relevant for the *x86* architecture and references
+to ``intel_idle`` affect Intel processors only.
 
 The *x86* architecture support code recognizes three kernel command line
 options related to CPU idle time management: ``idle=poll``, ``idle=halt``,
@@ -635,10 +635,13 @@ idle, so it very well may hurt single-thread computations performance as well as
 energy-efficiency.  Thus using it for performance reasons may not be a good idea
 at all.]
 
-The ``idle=nomwait`` option disables the ``intel_idle`` driver and causes
-``acpi_idle`` to be used (as long as all of the information needed by it is
-there in the system's ACPI tables), but it is not allowed to use the
-``MWAIT`` instruction of the CPUs to ask the hardware to enter idle states.
+The ``idle=nomwait`` option prevents the use of ``MWAIT`` instruction of
+the CPU to enter idle states. When this option is used, the ``acpi_idle``
+driver will use the ``HLT`` instruction instead of ``MWAIT``. On systems
+running Intel processors, this option disables the ``intel_idle`` driver
+and forces the use of the ``acpi_idle`` driver instead. Note that in either
+case, ``acpi_idle`` driver will function only if all the information needed
+by it is in the system's ACPI tables.
 
 In addition to the architecture-level kernel command line options affecting CPU
 idle time management, there are parameters affecting individual ``CPUIdle``
diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst
index 4150f74c521a..5310f398794c 100644
--- a/Documentation/admin-guide/sysctl/net.rst
+++ b/Documentation/admin-guide/sysctl/net.rst
@@ -271,7 +271,7 @@ poll cycle or the number of packets processed reaches netdev_budget.
 netdev_max_backlog
 ------------------
 
-Maximum number  of  packets,  queued  on  the  INPUT  side, when the interface
+Maximum number of packets, queued on the INPUT side, when the interface
 receives packets faster than kernel can process them.
 
 netdev_rss_key
diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst
index 5e795202111f..f4804ce37c58 100644
--- a/Documentation/admin-guide/sysctl/vm.rst
+++ b/Documentation/admin-guide/sysctl/vm.rst
@@ -948,7 +948,7 @@ how much memory needs to be free before kswapd goes back to sleep.
 
 The unit is in fractions of 10,000. The default value of 10 means the
 distances between watermarks are 0.1% of the available memory in the
-node/system. The maximum value is 1000, or 10% of memory.
+node/system. The maximum value is 3000, or 30% of memory.
 
 A high rate of threads entering direct reclaim (allocstall) or kswapd
 going to sleep prematurely (kswapd_low_wmark_hit_quickly) can indicate
diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst
index 7c1750bcc5bd..663001f69773 100644
--- a/Documentation/arm64/silicon-errata.rst
+++ b/Documentation/arm64/silicon-errata.rst
@@ -92,6 +92,10 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A77      | #1508412        | ARM64_ERRATUM_1508412       |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Cortex-A510     | #2441009        | ARM64_ERRATUM_2441009       |
++----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Cortex-A510     | #2457168        | ARM64_ERRATUM_2457168       |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-N1     | #1188873,1418040| ARM64_ERRATUM_1418040       |
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-N1     | #1349291        | N/A                         |
diff --git a/Documentation/atomic_bitops.txt b/Documentation/atomic_bitops.txt
index 093cdaefdb37..d8b101c97031 100644
--- a/Documentation/atomic_bitops.txt
+++ b/Documentation/atomic_bitops.txt
@@ -59,7 +59,7 @@ Like with atomic_t, the rule of thumb is:
  - RMW operations that have a return value are fully ordered.
 
  - RMW operations that are conditional are unordered on FAILURE,
-   otherwise the above rules apply. In the case of test_and_{}_bit() operations,
+   otherwise the above rules apply. In the case of test_and_set_bit_lock(),
    if the bit in memory is unchanged by the operation then it is deemed to have
    failed.
 
diff --git a/Documentation/devicetree/bindings/arm/qcom.yaml b/Documentation/devicetree/bindings/arm/qcom.yaml
index 880ddafc634e..a702a18d845e 100644
--- a/Documentation/devicetree/bindings/arm/qcom.yaml
+++ b/Documentation/devicetree/bindings/arm/qcom.yaml
@@ -135,28 +135,34 @@ properties:
           - const: qcom,msm8974
 
       - items:
-          - enum:
-              - alcatel,idol347
-          - const: qcom,msm8916-mtp/1
           - const: qcom,msm8916-mtp
+          - const: qcom,msm8916-mtp/1
           - const: qcom,msm8916
 
       - items:
           - enum:
-              - longcheer,l8150
+              - alcatel,idol347
               - samsung,a3u-eur
               - samsung,a5u-eur
           - const: qcom,msm8916
 
       - items:
+          - const: longcheer,l8150
+          - const: qcom,msm8916-v1-qrd/9-v1
+          - const: qcom,msm8916
+
+      - items:
           - enum:
               - sony,karin_windy
+          - const: qcom,apq8094
+
+      - items:
+          - enum:
               - sony,karin-row
               - sony,satsuki-row
               - sony,sumire-row
               - sony,suzuran-row
-              - qcom,msm8994
-          - const: qcom,apq8094
+          - const: qcom,msm8994
 
       - items:
           - const: qcom,msm8996-mtp
diff --git a/Documentation/devicetree/bindings/clock/qcom,gcc-msm8996.yaml b/Documentation/devicetree/bindings/clock/qcom,gcc-msm8996.yaml
index 5a5b2214f0ca..005e0edd4609 100644
--- a/Documentation/devicetree/bindings/clock/qcom,gcc-msm8996.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,gcc-msm8996.yaml
@@ -22,16 +22,32 @@ properties:
     const: qcom,gcc-msm8996
 
   clocks:
+    minItems: 3
     items:
       - description: XO source
       - description: Second XO source
       - description: Sleep clock source
+      - description: PCIe 0 PIPE clock (optional)
+      - description: PCIe 1 PIPE clock (optional)
+      - description: PCIe 2 PIPE clock (optional)
+      - description: USB3 PIPE clock (optional)
+      - description: UFS RX symbol 0 clock (optional)
+      - description: UFS RX symbol 1 clock (optional)
+      - description: UFS TX symbol 0 clock (optional)
 
   clock-names:
+    minItems: 3
     items:
       - const: cxo
       - const: cxo2
       - const: sleep_clk
+      - const: pcie_0_pipe_clk_src
+      - const: pcie_1_pipe_clk_src
+      - const: pcie_2_pipe_clk_src
+      - const: usb3_phy_pipe_clk_src
+      - const: ufs_rx_symbol_0_clk_src
+      - const: ufs_rx_symbol_1_clk_src
+      - const: ufs_tx_symbol_0_clk_src
 
   '#clock-cells':
     const: 1
diff --git a/Documentation/devicetree/bindings/dma/allwinner,sun50i-a64-dma.yaml b/Documentation/devicetree/bindings/dma/allwinner,sun50i-a64-dma.yaml
index b6e1ebfaf366..bb3cbc30d912 100644
--- a/Documentation/devicetree/bindings/dma/allwinner,sun50i-a64-dma.yaml
+++ b/Documentation/devicetree/bindings/dma/allwinner,sun50i-a64-dma.yaml
@@ -64,7 +64,7 @@ if:
 then:
   properties:
     clocks:
-      maxItems: 2
+      minItems: 2
 
   required:
     - clock-names
diff --git a/Documentation/devicetree/bindings/gpio/gpio-zynq.yaml b/Documentation/devicetree/bindings/gpio/gpio-zynq.yaml
index 378da2649e66..980f92ad9eba 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-zynq.yaml
+++ b/Documentation/devicetree/bindings/gpio/gpio-zynq.yaml
@@ -11,7 +11,11 @@ maintainers:
 
 properties:
   compatible:
-    const: xlnx,zynq-gpio-1.0
+    enum:
+      - xlnx,zynq-gpio-1.0
+      - xlnx,zynqmp-gpio-1.0
+      - xlnx,versal-gpio-1.0
+      - xlnx,pmc-gpio-1.0
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/iio/accel/adi,adxl355.yaml b/Documentation/devicetree/bindings/iio/accel/adi,adxl355.yaml
new file mode 100644
index 000000000000..ba54d6998f2e
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/accel/adi,adxl355.yaml
@@ -0,0 +1,88 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iio/accel/adi,adxl355.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Analog Devices ADXL355 3-Axis, Low noise MEMS Accelerometer
+
+maintainers:
+  - Puranjay Mohan <puranjay12@gmail.com>
+
+description: |
+  Analog Devices ADXL355 3-Axis, Low noise MEMS Accelerometer that supports
+  both I2C & SPI interfaces
+    https://www.analog.com/en/products/adxl355.html
+
+properties:
+  compatible:
+    enum:
+      - adi,adxl355
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    minItems: 1
+    maxItems: 3
+    description: |
+      Type for DRDY should be IRQ_TYPE_EDGE_RISING.
+      Three configurable interrupt lines exist.
+
+  interrupt-names:
+    description: Specify which interrupt line is in use.
+    items:
+      enum:
+        - INT1
+        - INT2
+        - DRDY
+    minItems: 1
+    maxItems: 3
+
+  vdd-supply:
+    description: Regulator that provides power to the sensor
+
+  vddio-supply:
+    description: Regulator that provides power to the bus
+
+  spi-max-frequency: true
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+        #include <dt-bindings/gpio/gpio.h>
+        #include <dt-bindings/interrupt-controller/irq.h>
+        i2c {
+                #address-cells = <1>;
+                #size-cells = <0>;
+
+                /* Example for a I2C device node */
+                accelerometer@1d {
+                        compatible = "adi,adxl355";
+                        reg = <0x1d>;
+                        interrupt-parent = <&gpio>;
+                        interrupts = <25 IRQ_TYPE_EDGE_RISING>;
+                        interrupt-names = "DRDY";
+                };
+        };
+  - |
+        #include <dt-bindings/gpio/gpio.h>
+        #include <dt-bindings/interrupt-controller/irq.h>
+        spi {
+                #address-cells = <1>;
+                #size-cells = <0>;
+
+                accelerometer@0 {
+                        compatible = "adi,adxl355";
+                        reg = <0>;
+                        spi-max-frequency = <1000000>;
+                        interrupt-parent = <&gpio>;
+                        interrupts = <25 IRQ_TYPE_EDGE_RISING>;
+                        interrupt-names = "DRDY";
+                };
+        };
diff --git a/Documentation/devicetree/bindings/iio/gyroscope/bosch,bmg160.yaml b/Documentation/devicetree/bindings/iio/gyroscope/bosch,bmg160.yaml
index b6bbc312a7cf..1414ba9977c1 100644
--- a/Documentation/devicetree/bindings/iio/gyroscope/bosch,bmg160.yaml
+++ b/Documentation/devicetree/bindings/iio/gyroscope/bosch,bmg160.yaml
@@ -24,8 +24,10 @@ properties:
 
   interrupts:
     minItems: 1
+    maxItems: 2
     description:
       Should be configured with type IRQ_TYPE_EDGE_RISING.
+      If two interrupts are provided, expected order is INT1 and INT2.
 
 required:
   - compatible
diff --git a/Documentation/devicetree/bindings/net/broadcom-bluetooth.yaml b/Documentation/devicetree/bindings/net/broadcom-bluetooth.yaml
index fbdc2083bec4..20ee96584aba 100644
--- a/Documentation/devicetree/bindings/net/broadcom-bluetooth.yaml
+++ b/Documentation/devicetree/bindings/net/broadcom-bluetooth.yaml
@@ -23,6 +23,7 @@ properties:
       - brcm,bcm4345c5
       - brcm,bcm43540-bt
       - brcm,bcm4335a0
+      - brcm,bcm4349-bt
 
   shutdown-gpios:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/regulator/nxp,pca9450-regulator.yaml b/Documentation/devicetree/bindings/regulator/nxp,pca9450-regulator.yaml
index 84c59ccc7e65..5f6ebaa5acf7 100644
--- a/Documentation/devicetree/bindings/regulator/nxp,pca9450-regulator.yaml
+++ b/Documentation/devicetree/bindings/regulator/nxp,pca9450-regulator.yaml
@@ -48,12 +48,6 @@ properties:
         description:
           Properties for single LDO regulator.
 
-        properties:
-          regulator-name:
-            pattern: "^LDO[1-5]$"
-            description:
-              should be "LDO1", ..., "LDO5"
-
         unevaluatedProperties: false
 
       "^BUCK[1-6]$":
@@ -63,11 +57,6 @@ properties:
           Properties for single BUCK regulator.
 
         properties:
-          regulator-name:
-            pattern: "^BUCK[1-6]$"
-            description:
-              should be "BUCK1", ..., "BUCK6"
-
           nxp,dvs-run-voltage:
             $ref: "/schemas/types.yaml#/definitions/uint32"
             minimum: 600000
diff --git a/Documentation/devicetree/bindings/riscv/sifive-l2-cache.yaml b/Documentation/devicetree/bindings/riscv/sifive-l2-cache.yaml
index 2b1f91603897..b72ec404adcd 100644
--- a/Documentation/devicetree/bindings/riscv/sifive-l2-cache.yaml
+++ b/Documentation/devicetree/bindings/riscv/sifive-l2-cache.yaml
@@ -47,7 +47,7 @@ properties:
     const: 2
 
   cache-sets:
-    const: 1024
+    enum: [1024, 2048]
 
   cache-size:
     const: 2097152
@@ -85,6 +85,8 @@ then:
       description: |
         Must contain entries for DirError, DataError and DataFail signals.
       maxItems: 3
+    cache-sets:
+      const: 1024
 
 else:
   properties:
@@ -92,6 +94,8 @@ else:
       description: |
         Must contain entries for DirError, DataError, DataFail, DirFail signals.
       minItems: 4
+    cache-sets:
+      const: 2048
 
 additionalProperties: false
 
diff --git a/Documentation/devicetree/bindings/soc/qcom/qcom,smd-rpm.yaml b/Documentation/devicetree/bindings/soc/qcom/qcom,smd-rpm.yaml
index cc3fe5ed7421..1b0062e3c1a4 100644
--- a/Documentation/devicetree/bindings/soc/qcom/qcom,smd-rpm.yaml
+++ b/Documentation/devicetree/bindings/soc/qcom/qcom,smd-rpm.yaml
@@ -34,6 +34,8 @@ properties:
       - qcom,rpm-ipq6018
       - qcom,rpm-msm8226
       - qcom,rpm-msm8916
+      - qcom,rpm-msm8936
+      - qcom,rpm-msm8953
       - qcom,rpm-msm8974
       - qcom,rpm-msm8976
       - qcom,rpm-msm8996
@@ -57,6 +59,7 @@ if:
           - qcom,rpm-apq8084
           - qcom,rpm-msm8916
           - qcom,rpm-msm8974
+          - qcom,rpm-msm8953
 then:
   required:
     - qcom,smd-channels
diff --git a/Documentation/devicetree/bindings/spi/spi-cadence.yaml b/Documentation/devicetree/bindings/spi/spi-cadence.yaml
index 9787be21318e..82d0ca5c00f3 100644
--- a/Documentation/devicetree/bindings/spi/spi-cadence.yaml
+++ b/Documentation/devicetree/bindings/spi/spi-cadence.yaml
@@ -49,6 +49,13 @@ properties:
     enum: [ 0, 1 ]
     default: 0
 
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clock-names
+  - clocks
+
 unevaluatedProperties: false
 
 examples:
diff --git a/Documentation/devicetree/bindings/spi/spi-zynqmp-qspi.yaml b/Documentation/devicetree/bindings/spi/spi-zynqmp-qspi.yaml
index ea72c8001256..fafde1c06be6 100644
--- a/Documentation/devicetree/bindings/spi/spi-zynqmp-qspi.yaml
+++ b/Documentation/devicetree/bindings/spi/spi-zynqmp-qspi.yaml
@@ -30,6 +30,13 @@ properties:
   clocks:
     maxItems: 2
 
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clock-names
+  - clocks
+
 unevaluatedProperties: false
 
 examples:
diff --git a/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.yaml b/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.yaml
index 11f7bacd4e2b..620cbf00bedb 100644
--- a/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.yaml
+++ b/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.yaml
@@ -56,6 +56,7 @@ properties:
       - description: optional, wakeup interrupt used to support runtime PM
 
   interrupt-names:
+    minItems: 1
     items:
       - const: host
       - const: wakeup
diff --git a/Documentation/driver-api/firmware/other_interfaces.rst b/Documentation/driver-api/firmware/other_interfaces.rst
index b81794e0cfbb..06ac89adaafb 100644
--- a/Documentation/driver-api/firmware/other_interfaces.rst
+++ b/Documentation/driver-api/firmware/other_interfaces.rst
@@ -13,6 +13,12 @@ EDD Interfaces
 .. kernel-doc:: drivers/firmware/edd.c
    :internal:
 
+Generic System Framebuffers Interface
+-------------------------------------
+
+.. kernel-doc:: drivers/firmware/sysfb.c
+   :export:
+
 Intel Stratix10 SoC Service Layer
 ---------------------------------
 Some features of the Intel Stratix10 SoC require a level of privilege
diff --git a/Documentation/firmware-guide/acpi/apei/einj.rst b/Documentation/firmware-guide/acpi/apei/einj.rst
index c042176e1707..50ac87fa2295 100644
--- a/Documentation/firmware-guide/acpi/apei/einj.rst
+++ b/Documentation/firmware-guide/acpi/apei/einj.rst
@@ -168,7 +168,7 @@ An error injection example::
   0x00000008	Memory Correctable
   0x00000010	Memory Uncorrectable non-fatal
   # echo 0x12345000 > param1		# Set memory address for injection
-  # echo $((-1 << 12)) > param2		# Mask 0xfffffffffffff000 - anywhere in this page
+  # echo 0xfffffffffffff000 > param2		# Mask - anywhere in this page
   # echo 0x8 > error_type			# Choose correctable memory error
   # echo 1 > error_inject			# Inject now
 
diff --git a/Documentation/input/joydev/joystick.rst b/Documentation/input/joydev/joystick.rst
index f615906a0821..6d721396717a 100644
--- a/Documentation/input/joydev/joystick.rst
+++ b/Documentation/input/joydev/joystick.rst
@@ -517,6 +517,7 @@ All I-Force devices are supported by the iforce module. This includes:
 * AVB Mag Turbo Force
 * AVB Top Shot Pegasus
 * AVB Top Shot Force Feedback Racing Wheel
+* Boeder Force Feedback Wheel
 * Logitech WingMan Force
 * Logitech WingMan Force Wheel
 * Guillemot Race Leader Force Feedback
diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index d91ab28718d4..ba0e8e6337c0 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -1063,7 +1063,7 @@ cipso_cache_enable - BOOLEAN
 cipso_cache_bucket_size - INTEGER
 	The CIPSO label cache consists of a fixed size hash table with each
 	hash bucket containing a number of cache entries.  This variable limits
-	the number of entries in each hash bucket; the larger the value the
+	the number of entries in each hash bucket; the larger the value is, the
 	more CIPSO label mappings that can be cached.  When the number of
 	entries in a given hash bucket reaches this limit adding new entries
 	causes the oldest entry in the bucket to be removed to make room.
@@ -1157,7 +1157,7 @@ ip_autobind_reuse - BOOLEAN
 	option should only be set by experts.
 	Default: 0
 
-ip_dynaddr - BOOLEAN
+ip_dynaddr - INTEGER
 	If set non-zero, enables support for dynamic addresses.
 	If set to a non-zero value larger than 1, a kernel log
 	message will be printed when dynamic address rewriting
@@ -2808,7 +2808,14 @@ sctp_rmem - vector of 3 INTEGERs: min, default, max
 	Default: 4K
 
 sctp_wmem  - vector of 3 INTEGERs: min, default, max
-	Currently this tunable has no effect.
+	Only the first value ("min") is used, "default" and "max" are
+	ignored.
+
+	min: Minimum size of send buffer that can be used by SCTP sockets.
+	It is guaranteed to each SCTP socket (but not association) even
+	under moderate memory pressure.
+
+	Default: 4K
 
 addr_scope_policy - INTEGER
 	Control IPv4 address scoping - draft-stewart-tsvwg-sctp-ipv4-00
diff --git a/Documentation/tty/device_drivers/oxsemi-tornado.rst b/Documentation/tty/device_drivers/oxsemi-tornado.rst
new file mode 100644
index 000000000000..0180d8bb0881
--- /dev/null
+++ b/Documentation/tty/device_drivers/oxsemi-tornado.rst
@@ -0,0 +1,129 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+====================================================================
+Notes on Oxford Semiconductor PCIe (Tornado) 950 serial port devices
+====================================================================
+
+Oxford Semiconductor PCIe (Tornado) 950 serial port devices are driven
+by a fixed 62.5MHz clock input derived from the 100MHz PCI Express clock.
+
+The baud rate produced by the baud generator is obtained from this input
+frequency by dividing it by the clock prescaler, which can be set to any
+value from 1 to 63.875 in increments of 0.125, and then the usual 16-bit
+divisor is used as with the original 8250, to divide the frequency by a
+value from 1 to 65535.  Finally a programmable oversampling rate is used
+that can take any value from 4 to 16 to divide the frequency further and
+determine the actual baud rate used.  Baud rates from 15625000bps down
+to 0.933bps can be obtained this way.
+
+By default the oversampling rate is set to 16 and the clock prescaler is
+set to 33.875, meaning that the frequency to be used as the reference
+for the usual 16-bit divisor is 115313.653, which is close enough to the
+frequency of 115200 used by the original 8250 for the same values to be
+used for the divisor to obtain the requested baud rates by software that
+is unaware of the extra clock controls available.
+
+The oversampling rate is programmed with the TCR register and the clock
+prescaler is programmed with the CPR/CPR2 register pair[1][2][3][4].
+To switch away from the default value of 33.875 for the prescaler the
+the enhanced mode has to be explicitly enabled though, by setting bit 4
+of the EFR.  In that mode setting bit 7 in the MCR enables the prescaler
+or otherwise it is bypassed as if the value of 1 was used.  Additionally
+writing any value to CPR clears CPR2 for compatibility with old software
+written for older conventional PCI Oxford Semiconductor devices that do
+not have the extra prescaler's 9th bit in CPR2, so the CPR/CPR2 register
+pair has to be programmed in the right order.
+
+By using these parameters rates from 15625000bps down to 1bps can be
+obtained, with either exact or highly-accurate actual bit rates for
+standard and many non-standard rates.
+
+Here are the figures for the standard and some non-standard baud rates
+(including those quoted in Oxford Semiconductor documentation), giving
+the requested rate (r), the actual rate yielded (a) and its deviation
+from the requested rate (d), and the values of the oversampling rate
+(tcr), the clock prescaler (cpr) and the divisor (div) produced by the
+new `get_divisor' handler:
+
+r: 15625000, a: 15625000.00, d:  0.0000%, tcr:  4, cpr:  1.000, div:     1
+r: 12500000, a: 12500000.00, d:  0.0000%, tcr:  5, cpr:  1.000, div:     1
+r: 10416666, a: 10416666.67, d:  0.0000%, tcr:  6, cpr:  1.000, div:     1
+r:  8928571, a:  8928571.43, d:  0.0000%, tcr:  7, cpr:  1.000, div:     1
+r:  7812500, a:  7812500.00, d:  0.0000%, tcr:  8, cpr:  1.000, div:     1
+r:  4000000, a:  4000000.00, d:  0.0000%, tcr:  5, cpr:  3.125, div:     1
+r:  3686400, a:  3676470.59, d: -0.2694%, tcr:  8, cpr:  2.125, div:     1
+r:  3500000, a:  3496503.50, d: -0.0999%, tcr: 13, cpr:  1.375, div:     1
+r:  3000000, a:  2976190.48, d: -0.7937%, tcr: 14, cpr:  1.500, div:     1
+r:  2500000, a:  2500000.00, d:  0.0000%, tcr: 10, cpr:  2.500, div:     1
+r:  2000000, a:  2000000.00, d:  0.0000%, tcr: 10, cpr:  3.125, div:     1
+r:  1843200, a:  1838235.29, d: -0.2694%, tcr: 16, cpr:  2.125, div:     1
+r:  1500000, a:  1492537.31, d: -0.4975%, tcr:  5, cpr:  8.375, div:     1
+r:  1152000, a:  1152073.73, d:  0.0064%, tcr: 14, cpr:  3.875, div:     1
+r:   921600, a:   919117.65, d: -0.2694%, tcr: 16, cpr:  2.125, div:     2
+r:   576000, a:   576036.87, d:  0.0064%, tcr: 14, cpr:  3.875, div:     2
+r:   460800, a:   460829.49, d:  0.0064%, tcr:  7, cpr:  3.875, div:     5
+r:   230400, a:   230414.75, d:  0.0064%, tcr: 14, cpr:  3.875, div:     5
+r:   115200, a:   115207.37, d:  0.0064%, tcr: 14, cpr:  1.250, div:    31
+r:    57600, a:    57603.69, d:  0.0064%, tcr:  8, cpr:  3.875, div:    35
+r:    38400, a:    38402.46, d:  0.0064%, tcr: 14, cpr:  3.875, div:    30
+r:    19200, a:    19201.23, d:  0.0064%, tcr:  8, cpr:  3.875, div:   105
+r:     9600, a:     9600.06, d:  0.0006%, tcr:  9, cpr:  1.125, div:   643
+r:     4800, a:     4799.98, d: -0.0004%, tcr:  7, cpr:  2.875, div:   647
+r:     2400, a:     2400.02, d:  0.0008%, tcr:  9, cpr:  2.250, div:  1286
+r:     1200, a:     1200.00, d:  0.0000%, tcr: 14, cpr:  2.875, div:  1294
+r:      300, a:      300.00, d:  0.0000%, tcr: 11, cpr:  2.625, div:  7215
+r:      200, a:      200.00, d:  0.0000%, tcr: 16, cpr:  1.250, div: 15625
+r:      150, a:      150.00, d:  0.0000%, tcr: 13, cpr:  2.250, div: 14245
+r:      134, a:      134.00, d:  0.0000%, tcr: 11, cpr:  2.625, div: 16153
+r:      110, a:      110.00, d:  0.0000%, tcr: 12, cpr:  1.000, div: 47348
+r:       75, a:       75.00, d:  0.0000%, tcr:  4, cpr:  5.875, div: 35461
+r:       50, a:       50.00, d:  0.0000%, tcr: 16, cpr:  1.250, div: 62500
+r:       25, a:       25.00, d:  0.0000%, tcr: 16, cpr:  2.500, div: 62500
+r:        4, a:        4.00, d:  0.0000%, tcr: 16, cpr: 20.000, div: 48828
+r:        2, a:        2.00, d:  0.0000%, tcr: 16, cpr: 40.000, div: 48828
+r:        1, a:        1.00, d:  0.0000%, tcr: 16, cpr: 63.875, div: 61154
+
+With the baud base set to 15625000 and the unsigned 16-bit UART_DIV_MAX
+limitation imposed by `serial8250_get_baud_rate' standard baud rates
+below 300bps become unavailable in the regular way, e.g. the rate of
+200bps requires the baud base to be divided by 78125 and that is beyond
+the unsigned 16-bit range.  The historic spd_cust feature can still be
+used by encoding the values for, the prescaler, the oversampling rate
+and the clock divisor (DLM/DLL) as follows to obtain such rates if so
+required:
+
+ 31 29 28             20 19   16 15                            0
++-----+-----------------+-------+-------------------------------+
+|0 0 0|    CPR2:CPR     |  TCR  |            DLM:DLL            |
++-----+-----------------+-------+-------------------------------+
+
+Use a value such encoded for the `custom_divisor' field along with the
+ASYNC_SPD_CUST flag set in the `flags' field in `struct serial_struct'
+passed with the TIOCSSERIAL ioctl(2), such as with the setserial(8)
+utility and its `divisor' and `spd_cust' parameters, and the select
+the baud rate of 38400bps.  Note that the value of 0 in TCR sets the
+oversampling rate to 16 and prescaler values below 1 in CPR2/CPR are
+clamped by the driver to 1.
+
+For example the value of 0x1f4004e2 will set CPR2/CPR, TCR and DLM/DLL
+respectively to 0x1f4, 0x0 and 0x04e2, choosing the prescaler value,
+the oversampling rate and the clock divisor of 62.500, 16 and 1250
+respectively.  These parameters will set the baud rate for the serial
+port to 62500000 / 62.500 / 1250 / 16 = 50bps.
+
+References:
+
+[1] "OXPCIe200 PCI Express Multi-Port Bridge", Oxford Semiconductor,
+    Inc., DS-0045, 10 Nov 2008, Section "950 Mode", pp. 64-65
+
+[2] "OXPCIe952 PCI Express Bridge to Dual Serial & Parallel Port",
+    Oxford Semiconductor, Inc., DS-0046, Mar 06 08, Section "950 Mode",
+    p. 20
+
+[3] "OXPCIe954 PCI Express Bridge to Quad Serial Port", Oxford
+    Semiconductor, Inc., DS-0047, Feb 08, Section "950 Mode", p. 20
+
+[4] "OXPCIe958 PCI Express Bridge to Octal Serial Port", Oxford
+    Semiconductor, Inc., DS-0048, Feb 08, Section "950 Mode", p. 20
+
+Maciej W. Rozycki  <macro@orcam.me.uk>
diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
index 976d34445a24..f1421cf1a1b3 100644
--- a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
+++ b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
@@ -3326,15 +3326,15 @@ enum v4l2_mpeg_video_hevc_size_of_length_field -
     * - __u8
       - ``poc_st_curr_before[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]``
       - PocStCurrBefore as described in section 8.3.2 "Decoding process for reference
-        picture set.
+        picture set": provides the index of the short term before references in DPB array.
     * - __u8
       - ``poc_st_curr_after[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]``
       - PocStCurrAfter as described in section 8.3.2 "Decoding process for reference
-        picture set.
+        picture set": provides the index of the short term after references in DPB array.
     * - __u8
       - ``poc_lt_curr[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]``
       - PocLtCurr as described in section 8.3.2 "Decoding process for reference
-        picture set.
+        picture set": provides the index of the long term references in DPB array.
     * - __u64
       - ``flags``
       - See :ref:`Decode Parameters Flags <hevc_decode_params_flags>`
diff --git a/MAINTAINERS b/MAINTAINERS
index 4cc54b2e2b2e..020e28d95fc7 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7970,9 +7970,10 @@ F:	drivers/media/usb/go7007/
 
 GOODIX TOUCHSCREEN
 M:	Bastien Nocera <hadess@hadess.net>
+M:	Hans de Goede <hdegoede@redhat.com>
 L:	linux-input@vger.kernel.org
 S:	Maintained
-F:	drivers/input/touchscreen/goodix.c
+F:	drivers/input/touchscreen/goodix*
 
 GOOGLE ETHERNET DRIVERS
 M:	Jeroen de Borst <jeroendb@google.com>
@@ -20628,6 +20629,7 @@ F:	drivers/xen/*swiotlb*
 
 XFS FILESYSTEM
 C:	irc://irc.oftc.net/xfs
+M:	Leah Rumancik <leah.rumancik@gmail.com>
 M:	Darrick J. Wong <djwong@kernel.org>
 M:	linux-xfs@vger.kernel.org
 L:	linux-xfs@vger.kernel.org
diff --git a/Makefile b/Makefile
index 777e0a0eeccd..e815677ec011 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 15
-SUBLEVEL = 52
+SUBLEVEL = 70
 EXTRAVERSION =
 NAME = Trick or Treat
 
@@ -480,6 +480,8 @@ LZ4		= lz4c
 XZ		= xz
 ZSTD		= zstd
 
+PAHOLE_FLAGS	= $(shell PAHOLE=$(PAHOLE) $(srctree)/scripts/pahole-flags.sh)
+
 CHECKFLAGS     := -D__linux__ -Dlinux -D__STDC__ -Dunix -D__unix__ \
 		  -Wbitwise -Wno-return-void -Wno-unknown-attribute $(CF)
 NOSTDINC_FLAGS :=
@@ -534,6 +536,7 @@ export KBUILD_CFLAGS CFLAGS_KERNEL CFLAGS_MODULE
 export KBUILD_AFLAGS AFLAGS_KERNEL AFLAGS_MODULE
 export KBUILD_AFLAGS_MODULE KBUILD_CFLAGS_MODULE KBUILD_LDFLAGS_MODULE
 export KBUILD_AFLAGS_KERNEL KBUILD_CFLAGS_KERNEL
+export PAHOLE_FLAGS
 
 # Files to ignore in find ... statements
 
@@ -687,12 +690,19 @@ endif
 
 ifdef CONFIG_CC_IS_GCC
 RETPOLINE_CFLAGS	:= $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register)
+RETPOLINE_CFLAGS	+= $(call cc-option,-mindirect-branch-cs-prefix)
 RETPOLINE_VDSO_CFLAGS	:= $(call cc-option,-mindirect-branch=thunk-inline -mindirect-branch-register)
 endif
 ifdef CONFIG_CC_IS_CLANG
 RETPOLINE_CFLAGS	:= -mretpoline-external-thunk
 RETPOLINE_VDSO_CFLAGS	:= -mretpoline
 endif
+
+ifdef CONFIG_RETHUNK
+RETHUNK_CFLAGS         := -mfunction-return=thunk-extern
+RETPOLINE_CFLAGS       += $(RETHUNK_CFLAGS)
+endif
+
 export RETPOLINE_CFLAGS
 export RETPOLINE_VDSO_CFLAGS
 
@@ -1011,6 +1021,21 @@ ifdef CONFIG_CC_IS_GCC
 KBUILD_CFLAGS += -Wno-maybe-uninitialized
 endif
 
+ifdef CONFIG_CC_IS_GCC
+# The allocators already balk at large sizes, so silence the compiler
+# warnings for bounds checks involving those possible values. While
+# -Wno-alloc-size-larger-than would normally be used here, earlier versions
+# of gcc (<9.1) weirdly don't handle the option correctly when _other_
+# warnings are produced (?!). Using -Walloc-size-larger-than=SIZE_MAX
+# doesn't work (as it is documented to), silently resolving to "0" prior to
+# version 9.1 (and producing an error more recently). Numeric values larger
+# than PTRDIFF_MAX also don't work prior to version 9.1, which are silently
+# ignored, continuing to default to PTRDIFF_MAX. So, left with no other
+# choice, we must perform a versioned check to disable this warning.
+# https://lore.kernel.org/lkml/20210824115859.187f272f@canb.auug.org.au
+KBUILD_CFLAGS += $(call cc-ifversion, -ge, 0901, -Wno-alloc-size-larger-than)
+endif
+
 # disable invalid "can't wrap" optimizations for signed / pointers
 KBUILD_CFLAGS	+= -fno-strict-overflow
 
@@ -1056,6 +1081,11 @@ KBUILD_CFLAGS   += $(KCFLAGS)
 KBUILD_LDFLAGS_MODULE += --build-id=sha1
 LDFLAGS_vmlinux += --build-id=sha1
 
+KBUILD_LDFLAGS	+= -z noexecstack
+ifeq ($(CONFIG_LD_IS_BFD),y)
+KBUILD_LDFLAGS	+= $(call ld-option,--no-warn-rwx-segments)
+endif
+
 ifeq ($(CONFIG_STRIP_ASM_SYMS),y)
 LDFLAGS_vmlinux	+= $(call ld-option, -X,)
 endif
@@ -1128,13 +1158,11 @@ vmlinux-alldirs	:= $(sort $(vmlinux-dirs) Documentation \
 		     $(patsubst %/,%,$(filter %/, $(core-) \
 			$(drivers-) $(libs-))))
 
-subdir-modorder := $(addsuffix modules.order,$(filter %/, \
-			$(core-y) $(core-m) $(libs-y) $(libs-m) \
-			$(drivers-y) $(drivers-m)))
-
 build-dirs	:= $(vmlinux-dirs)
 clean-dirs	:= $(vmlinux-alldirs)
 
+subdir-modorder := $(addsuffix /modules.order, $(build-dirs))
+
 # Externally visible symbols (used by link-vmlinux.sh)
 KBUILD_VMLINUX_OBJS := $(head-y) $(patsubst %/,%/built-in.a, $(core-y))
 KBUILD_VMLINUX_OBJS += $(addsuffix built-in.a, $(filter %/, $(libs-y)))
@@ -1304,8 +1332,7 @@ hdr-inst := -f $(srctree)/scripts/Makefile.headersinst obj
 
 PHONY += headers
 headers: $(version_h) scripts_unifdef uapi-asm-generic archheaders archscripts
-	$(if $(wildcard $(srctree)/arch/$(SRCARCH)/include/uapi/asm/Kbuild),, \
-	  $(error Headers not exportable for the $(SRCARCH) architecture))
+	$(if $(filter um, $(SRCARCH)), $(error Headers not exportable for UML))
 	$(Q)$(MAKE) $(hdr-inst)=include/uapi
 	$(Q)$(MAKE) $(hdr-inst)=arch/$(SRCARCH)/include/uapi
 
diff --git a/arch/Kconfig b/arch/Kconfig
index 191589f26b1a..5987363b41c2 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -200,6 +200,9 @@ config HAVE_NMI
 config TRACE_IRQFLAGS_SUPPORT
 	bool
 
+config TRACE_IRQFLAGS_NMI_SUPPORT
+	bool
+
 #
 # An arch should select this if it provides all these things:
 #
diff --git a/arch/alpha/kernel/srmcons.c b/arch/alpha/kernel/srmcons.c
index 90635ef5dafa..6dc952b0df4a 100644
--- a/arch/alpha/kernel/srmcons.c
+++ b/arch/alpha/kernel/srmcons.c
@@ -59,7 +59,7 @@ srmcons_do_receive_chars(struct tty_port *port)
 	} while((result.bits.status & 1) && (++loops < 10));
 
 	if (count)
-		tty_schedule_flip(port);
+		tty_flip_buffer_push(port);
 
 	return count;
 }
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index 2f9b63b5a14b..12ce9965f55b 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -127,6 +127,7 @@ dtb-$(CONFIG_ARCH_BCM_5301X) += \
 	bcm47094-luxul-xwr-3150-v1.dtb \
 	bcm47094-netgear-r8500.dtb \
 	bcm47094-phicomm-k3.dtb \
+	bcm53015-meraki-mr26.dtb \
 	bcm53016-meraki-mr32.dtb \
 	bcm94708.dtb \
 	bcm94709.dtb \
diff --git a/arch/arm/boot/dts/aspeed-ast2500-evb.dts b/arch/arm/boot/dts/aspeed-ast2500-evb.dts
index 1d24b394ea4c..a497dd135491 100644
--- a/arch/arm/boot/dts/aspeed-ast2500-evb.dts
+++ b/arch/arm/boot/dts/aspeed-ast2500-evb.dts
@@ -5,7 +5,7 @@
 
 / {
 	model = "AST2500 EVB";
-	compatible = "aspeed,ast2500";
+	compatible = "aspeed,ast2500-evb", "aspeed,ast2500";
 
 	aliases {
 		serial4 = &uart5;
diff --git a/arch/arm/boot/dts/aspeed-ast2600-evb-a1.dts b/arch/arm/boot/dts/aspeed-ast2600-evb-a1.dts
index dd7148060c4a..d0a5c2ff0fec 100644
--- a/arch/arm/boot/dts/aspeed-ast2600-evb-a1.dts
+++ b/arch/arm/boot/dts/aspeed-ast2600-evb-a1.dts
@@ -5,6 +5,7 @@
 
 / {
 	model = "AST2600 A1 EVB";
+	compatible = "aspeed,ast2600-evb-a1", "aspeed,ast2600";
 
 	/delete-node/regulator-vcc-sdhci0;
 	/delete-node/regulator-vcc-sdhci1;
diff --git a/arch/arm/boot/dts/aspeed-ast2600-evb.dts b/arch/arm/boot/dts/aspeed-ast2600-evb.dts
index 788448cdd6b3..b8e55bf167aa 100644
--- a/arch/arm/boot/dts/aspeed-ast2600-evb.dts
+++ b/arch/arm/boot/dts/aspeed-ast2600-evb.dts
@@ -8,7 +8,7 @@
 
 / {
 	model = "AST2600 EVB";
-	compatible = "aspeed,ast2600";
+	compatible = "aspeed,ast2600-evb-a1", "aspeed,ast2600";
 
 	aliases {
 		serial4 = &uart5;
diff --git a/arch/arm/boot/dts/at91-sam9x60ek.dts b/arch/arm/boot/dts/at91-sam9x60ek.dts
index b1068cca4228..fd8dc1183b3e 100644
--- a/arch/arm/boot/dts/at91-sam9x60ek.dts
+++ b/arch/arm/boot/dts/at91-sam9x60ek.dts
@@ -233,10 +233,9 @@
 		status = "okay";
 
 		eeprom@53 {
-			compatible = "atmel,24c32";
+			compatible = "atmel,24c02";
 			reg = <0x53>;
 			pagesize = <16>;
-			size = <128>;
 			status = "okay";
 		};
 	};
diff --git a/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi b/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi
index 025a78310e3a..a818e8ebd638 100644
--- a/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi
+++ b/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi
@@ -68,8 +68,8 @@
 		regulators {
 			vdd_3v3: VDD_IO {
 				regulator-name = "VDD_IO";
-				regulator-min-microvolt = <1200000>;
-				regulator-max-microvolt = <3700000>;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
 				regulator-initial-mode = <2>;
 				regulator-allowed-modes = <2>, <4>;
 				regulator-always-on;
@@ -87,8 +87,8 @@
 
 			vddio_ddr: VDD_DDR {
 				regulator-name = "VDD_DDR";
-				regulator-min-microvolt = <600000>;
-				regulator-max-microvolt = <1850000>;
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
 				regulator-initial-mode = <2>;
 				regulator-allowed-modes = <2>, <4>;
 				regulator-always-on;
@@ -110,8 +110,8 @@
 
 			vdd_core: VDD_CORE {
 				regulator-name = "VDD_CORE";
-				regulator-min-microvolt = <600000>;
-				regulator-max-microvolt = <1850000>;
+				regulator-min-microvolt = <1250000>;
+				regulator-max-microvolt = <1250000>;
 				regulator-initial-mode = <2>;
 				regulator-allowed-modes = <2>, <4>;
 				regulator-always-on;
@@ -152,8 +152,8 @@
 
 			LDO1 {
 				regulator-name = "LDO1";
-				regulator-min-microvolt = <1200000>;
-				regulator-max-microvolt = <3700000>;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
 				regulator-always-on;
 
 				regulator-state-standby {
@@ -167,9 +167,8 @@
 
 			LDO2 {
 				regulator-name = "LDO2";
-				regulator-min-microvolt = <1200000>;
-				regulator-max-microvolt = <3700000>;
-				regulator-always-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
 
 				regulator-state-standby {
 					regulator-on-in-suspend;
diff --git a/arch/arm/boot/dts/at91-sama5d2_icp.dts b/arch/arm/boot/dts/at91-sama5d2_icp.dts
index e06b58724ca8..4ebbbe65c0ce 100644
--- a/arch/arm/boot/dts/at91-sama5d2_icp.dts
+++ b/arch/arm/boot/dts/at91-sama5d2_icp.dts
@@ -197,8 +197,8 @@
 			regulators {
 				vdd_io_reg: VDD_IO {
 					regulator-name = "VDD_IO";
-					regulator-min-microvolt = <1200000>;
-					regulator-max-microvolt = <3700000>;
+					regulator-min-microvolt = <3300000>;
+					regulator-max-microvolt = <3300000>;
 					regulator-initial-mode = <2>;
 					regulator-allowed-modes = <2>, <4>;
 					regulator-always-on;
@@ -216,8 +216,8 @@
 
 				VDD_DDR {
 					regulator-name = "VDD_DDR";
-					regulator-min-microvolt = <600000>;
-					regulator-max-microvolt = <1850000>;
+					regulator-min-microvolt = <1350000>;
+					regulator-max-microvolt = <1350000>;
 					regulator-initial-mode = <2>;
 					regulator-allowed-modes = <2>, <4>;
 					regulator-always-on;
@@ -235,8 +235,8 @@
 
 				VDD_CORE {
 					regulator-name = "VDD_CORE";
-					regulator-min-microvolt = <600000>;
-					regulator-max-microvolt = <1850000>;
+					regulator-min-microvolt = <1250000>;
+					regulator-max-microvolt = <1250000>;
 					regulator-initial-mode = <2>;
 					regulator-allowed-modes = <2>, <4>;
 					regulator-always-on;
@@ -258,7 +258,6 @@
 					regulator-max-microvolt = <1850000>;
 					regulator-initial-mode = <2>;
 					regulator-allowed-modes = <2>, <4>;
-					regulator-always-on;
 
 					regulator-state-standby {
 						regulator-on-in-suspend;
@@ -273,8 +272,8 @@
 
 				LDO1 {
 					regulator-name = "LDO1";
-					regulator-min-microvolt = <1200000>;
-					regulator-max-microvolt = <3700000>;
+					regulator-min-microvolt = <2500000>;
+					regulator-max-microvolt = <2500000>;
 					regulator-always-on;
 
 					regulator-state-standby {
@@ -288,8 +287,8 @@
 
 				LDO2 {
 					regulator-name = "LDO2";
-					regulator-min-microvolt = <1200000>;
-					regulator-max-microvolt = <3700000>;
+					regulator-min-microvolt = <3300000>;
+					regulator-max-microvolt = <3300000>;
 					regulator-always-on;
 
 					regulator-state-standby {
@@ -323,21 +322,21 @@
 	status = "okay";
 
 	eeprom@50 {
-		compatible = "atmel,24c32";
+		compatible = "atmel,24c02";
 		reg = <0x50>;
 		pagesize = <16>;
 		status = "okay";
 	};
 
 	eeprom@52 {
-		compatible = "atmel,24c32";
+		compatible = "atmel,24c02";
 		reg = <0x52>;
 		pagesize = <16>;
 		status = "disabled";
 	};
 
 	eeprom@53 {
-		compatible = "atmel,24c32";
+		compatible = "atmel,24c02";
 		reg = <0x53>;
 		pagesize = <16>;
 		status = "disabled";
diff --git a/arch/arm/boot/dts/at91-sama7g5ek.dts b/arch/arm/boot/dts/at91-sama7g5ek.dts
index bac0e49cc577..2038e387be28 100644
--- a/arch/arm/boot/dts/at91-sama7g5ek.dts
+++ b/arch/arm/boot/dts/at91-sama7g5ek.dts
@@ -169,8 +169,8 @@
 			regulators {
 				vdd_3v3: VDD_IO {
 					regulator-name = "VDD_IO";
-					regulator-min-microvolt = <1200000>;
-					regulator-max-microvolt = <3700000>;
+					regulator-min-microvolt = <3300000>;
+					regulator-max-microvolt = <3300000>;
 					regulator-initial-mode = <2>;
 					regulator-allowed-modes = <2>, <4>;
 					regulator-always-on;
@@ -188,8 +188,8 @@
 
 				vddioddr: VDD_DDR {
 					regulator-name = "VDD_DDR";
-					regulator-min-microvolt = <1300000>;
-					regulator-max-microvolt = <1450000>;
+					regulator-min-microvolt = <1350000>;
+					regulator-max-microvolt = <1350000>;
 					regulator-initial-mode = <2>;
 					regulator-allowed-modes = <2>, <4>;
 					regulator-always-on;
@@ -209,8 +209,8 @@
 
 				vddcore: VDD_CORE {
 					regulator-name = "VDD_CORE";
-					regulator-min-microvolt = <1100000>;
-					regulator-max-microvolt = <1850000>;
+					regulator-min-microvolt = <1150000>;
+					regulator-max-microvolt = <1150000>;
 					regulator-initial-mode = <2>;
 					regulator-allowed-modes = <2>, <4>;
 					regulator-always-on;
@@ -228,8 +228,8 @@
 
 				vddcpu: VDD_OTHER {
 					regulator-name = "VDD_OTHER";
-					regulator-min-microvolt = <1125000>;
-					regulator-max-microvolt = <1850000>;
+					regulator-min-microvolt = <1050000>;
+					regulator-max-microvolt = <1250000>;
 					regulator-initial-mode = <2>;
 					regulator-allowed-modes = <2>, <4>;
 					regulator-ramp-delay = <3125>;
@@ -248,8 +248,8 @@
 
 				vldo1: LDO1 {
 					regulator-name = "LDO1";
-					regulator-min-microvolt = <1200000>;
-					regulator-max-microvolt = <3700000>;
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
 					regulator-always-on;
 
 					regulator-state-standby {
diff --git a/arch/arm/boot/dts/bcm53015-meraki-mr26.dts b/arch/arm/boot/dts/bcm53015-meraki-mr26.dts
new file mode 100644
index 000000000000..14f58033efeb
--- /dev/null
+++ b/arch/arm/boot/dts/bcm53015-meraki-mr26.dts
@@ -0,0 +1,166 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/*
+ * Broadcom BCM470X / BCM5301X ARM platform code.
+ * DTS for Meraki MR26 / Codename: Venom
+ *
+ * Copyright (C) 2022 Christian Lamparter <chunkeey@gmail.com>
+ */
+
+/dts-v1/;
+
+#include "bcm4708.dtsi"
+#include "bcm5301x-nand-cs0-bch8.dtsi"
+#include <dt-bindings/leds/common.h>
+
+/ {
+	compatible = "meraki,mr26", "brcm,bcm53015", "brcm,bcm4708";
+	model = "Meraki MR26";
+
+	memory@0 {
+		reg = <0x00000000 0x08000000>;
+		device_type = "memory";
+	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		led-0 {
+			function = LED_FUNCTION_FAULT;
+			color = <LED_COLOR_ID_AMBER>;
+			gpios = <&chipcommon 13 GPIO_ACTIVE_HIGH>;
+			panic-indicator;
+		};
+		led-1 {
+			function = LED_FUNCTION_INDICATOR;
+			color = <LED_COLOR_ID_WHITE>;
+			gpios = <&chipcommon 12 GPIO_ACTIVE_HIGH>;
+		};
+	};
+
+	keys {
+		compatible = "gpio-keys";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		key-restart {
+			label = "Reset";
+			linux,code = <KEY_RESTART>;
+			gpios = <&chipcommon 11 GPIO_ACTIVE_LOW>;
+		};
+	};
+};
+
+&uart0 {
+	clock-frequency = <50000000>;
+	/delete-property/ clocks;
+};
+
+&uart1 {
+	status = "disabled";
+};
+
+&gmac0 {
+	status = "okay";
+};
+
+&gmac1 {
+	status = "disabled";
+};
+&gmac2 {
+	status = "disabled";
+};
+&gmac3 {
+	status = "disabled";
+};
+
+&nandcs {
+	nand-ecc-algo = "hw";
+
+	partitions {
+		compatible = "fixed-partitions";
+		#address-cells = <0x1>;
+		#size-cells = <0x1>;
+
+		partition@0 {
+			label = "u-boot";
+			reg = <0x0 0x200000>;
+			read-only;
+		};
+
+		partition@200000 {
+			label = "u-boot-env";
+			reg = <0x200000 0x200000>;
+			/* empty */
+		};
+
+		partition@400000 {
+			label = "u-boot-backup";
+			reg = <0x400000 0x200000>;
+			/* empty */
+		};
+
+		partition@600000 {
+			label = "u-boot-env-backup";
+			reg = <0x600000 0x200000>;
+			/* empty */
+		};
+
+		partition@800000 {
+			label = "ubi";
+			reg = <0x800000 0x7780000>;
+		};
+	};
+};
+
+&srab {
+	status = "okay";
+
+	ports {
+		port@0 {
+			reg = <0>;
+			label = "poe";
+		};
+
+		port@5 {
+			reg = <5>;
+			label = "cpu";
+			ethernet = <&gmac0>;
+
+			fixed-link {
+				speed = <1000>;
+				duplex-full;
+			};
+		};
+	};
+};
+
+&i2c0 {
+	status = "okay";
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinmux_i2c>;
+
+	clock-frequency = <100000>;
+
+	ina219@40 {
+		compatible = "ti,ina219"; /* PoE power */
+		reg = <0x40>;
+		shunt-resistor = <60000>; /* = 60 mOhms */
+	};
+
+	eeprom@56 {
+		compatible = "atmel,24c64";
+		reg = <0x56>;
+		pagesize = <32>;
+		read-only;
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		/* it's empty */
+	};
+};
+
+&thermal {
+	status = "disabled";
+	/* does not work, reads 418 degree Celsius */
+};
diff --git a/arch/arm/boot/dts/imx28-evk.dts b/arch/arm/boot/dts/imx28-evk.dts
index 7e2b0f198dfa..1053b7c584d8 100644
--- a/arch/arm/boot/dts/imx28-evk.dts
+++ b/arch/arm/boot/dts/imx28-evk.dts
@@ -129,7 +129,7 @@
 				pinctrl-0 = <&spi2_pins_a>;
 				status = "okay";
 
-				flash: m25p80@0 {
+				flash: flash@0 {
 					#address-cells = <1>;
 					#size-cells = <1>;
 					compatible = "sst,sst25vf016b", "jedec,spi-nor";
diff --git a/arch/arm/boot/dts/imx28-m28evk.dts b/arch/arm/boot/dts/imx28-m28evk.dts
index f3bddc5ada4b..13acdc7916b9 100644
--- a/arch/arm/boot/dts/imx28-m28evk.dts
+++ b/arch/arm/boot/dts/imx28-m28evk.dts
@@ -33,7 +33,7 @@
 				pinctrl-0 = <&spi2_pins_a>;
 				status = "okay";
 
-				flash: m25p80@0 {
+				flash: flash@0 {
 					#address-cells = <1>;
 					#size-cells = <1>;
 					compatible = "m25p80", "jedec,spi-nor";
diff --git a/arch/arm/boot/dts/imx28-sps1.dts b/arch/arm/boot/dts/imx28-sps1.dts
index 43be7a6a769b..90928db0df70 100644
--- a/arch/arm/boot/dts/imx28-sps1.dts
+++ b/arch/arm/boot/dts/imx28-sps1.dts
@@ -51,7 +51,7 @@
 				pinctrl-0 = <&spi2_pins_a>;
 				status = "okay";
 
-				flash: m25p80@0 {
+				flash: flash@0 {
 					#address-cells = <1>;
 					#size-cells = <1>;
 					compatible = "everspin,mr25h256", "mr25h256";
diff --git a/arch/arm/boot/dts/imx6dl-rex-basic.dts b/arch/arm/boot/dts/imx6dl-rex-basic.dts
index 0f1616bfa9a8..b72f8ea1e6f6 100644
--- a/arch/arm/boot/dts/imx6dl-rex-basic.dts
+++ b/arch/arm/boot/dts/imx6dl-rex-basic.dts
@@ -19,7 +19,7 @@
 };
 
 &ecspi3 {
-	flash: m25p80@0 {
+	flash: flash@0 {
 		compatible = "sst,sst25vf016b", "jedec,spi-nor";
 		spi-max-frequency = <20000000>;
 		reg = <0>;
diff --git a/arch/arm/boot/dts/imx6q-ba16.dtsi b/arch/arm/boot/dts/imx6q-ba16.dtsi
index 6330d75f8f39..f266f1b7e0cf 100644
--- a/arch/arm/boot/dts/imx6q-ba16.dtsi
+++ b/arch/arm/boot/dts/imx6q-ba16.dtsi
@@ -142,7 +142,7 @@
 	pinctrl-0 = <&pinctrl_ecspi1>;
 	status = "okay";
 
-	flash: n25q032@0 {
+	flash: flash@0 {
 		compatible = "jedec,spi-nor";
 		#address-cells = <1>;
 		#size-cells = <1>;
diff --git a/arch/arm/boot/dts/imx6q-bx50v3.dtsi b/arch/arm/boot/dts/imx6q-bx50v3.dtsi
index 10922375c51e..ead83091e193 100644
--- a/arch/arm/boot/dts/imx6q-bx50v3.dtsi
+++ b/arch/arm/boot/dts/imx6q-bx50v3.dtsi
@@ -160,7 +160,7 @@
 	pinctrl-0 = <&pinctrl_ecspi5>;
 	status = "okay";
 
-	m25_eeprom: m25p80@0 {
+	m25_eeprom: flash@0 {
 		compatible = "atmel,at25";
 		spi-max-frequency = <10000000>;
 		size = <0x8000>;
diff --git a/arch/arm/boot/dts/imx6q-cm-fx6.dts b/arch/arm/boot/dts/imx6q-cm-fx6.dts
index bfb530f29d9d..1ad41c944b4b 100644
--- a/arch/arm/boot/dts/imx6q-cm-fx6.dts
+++ b/arch/arm/boot/dts/imx6q-cm-fx6.dts
@@ -260,7 +260,7 @@
 	pinctrl-0 = <&pinctrl_ecspi1>;
 	status = "okay";
 
-	m25p80@0 {
+	flash@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
 		compatible = "st,m25p", "jedec,spi-nor";
diff --git a/arch/arm/boot/dts/imx6q-dmo-edmqmx6.dts b/arch/arm/boot/dts/imx6q-dmo-edmqmx6.dts
index c713ac03b3b9..9591848cbd37 100644
--- a/arch/arm/boot/dts/imx6q-dmo-edmqmx6.dts
+++ b/arch/arm/boot/dts/imx6q-dmo-edmqmx6.dts
@@ -102,7 +102,7 @@
 	cs-gpios = <&gpio1 12 GPIO_ACTIVE_LOW>;
 	status = "okay";
 
-	flash: m25p80@0 {
+	flash: flash@0 {
 		compatible = "m25p80", "jedec,spi-nor";
 		spi-max-frequency = <40000000>;
 		reg = <0>;
diff --git a/arch/arm/boot/dts/imx6q-dms-ba16.dts b/arch/arm/boot/dts/imx6q-dms-ba16.dts
index 48fb47e715f6..137db38f0d27 100644
--- a/arch/arm/boot/dts/imx6q-dms-ba16.dts
+++ b/arch/arm/boot/dts/imx6q-dms-ba16.dts
@@ -47,7 +47,7 @@
 	pinctrl-0 = <&pinctrl_ecspi5>;
 	status = "okay";
 
-	m25_eeprom: m25p80@0 {
+	m25_eeprom: flash@0 {
 		compatible = "atmel,at25256B", "atmel,at25";
 		spi-max-frequency = <20000000>;
 		size = <0x8000>;
diff --git a/arch/arm/boot/dts/imx6q-gw5400-a.dts b/arch/arm/boot/dts/imx6q-gw5400-a.dts
index 4cde45d5c90c..e894faba571f 100644
--- a/arch/arm/boot/dts/imx6q-gw5400-a.dts
+++ b/arch/arm/boot/dts/imx6q-gw5400-a.dts
@@ -137,7 +137,7 @@
 	pinctrl-0 = <&pinctrl_ecspi1>;
 	status = "okay";
 
-	flash: m25p80@0 {
+	flash: flash@0 {
 		compatible = "sst,w25q256", "jedec,spi-nor";
 		spi-max-frequency = <30000000>;
 		reg = <0>;
diff --git a/arch/arm/boot/dts/imx6q-marsboard.dts b/arch/arm/boot/dts/imx6q-marsboard.dts
index 05ee28388229..cc1801002394 100644
--- a/arch/arm/boot/dts/imx6q-marsboard.dts
+++ b/arch/arm/boot/dts/imx6q-marsboard.dts
@@ -100,7 +100,7 @@
 	cs-gpios = <&gpio2 30 GPIO_ACTIVE_LOW>;
 	status = "okay";
 
-	m25p80@0 {
+	flash@0 {
 		compatible = "microchip,sst25vf016b";
 		spi-max-frequency = <20000000>;
 		reg = <0>;
diff --git a/arch/arm/boot/dts/imx6q-rex-pro.dts b/arch/arm/boot/dts/imx6q-rex-pro.dts
index 1767e1a3cd53..271f4b2d9b9f 100644
--- a/arch/arm/boot/dts/imx6q-rex-pro.dts
+++ b/arch/arm/boot/dts/imx6q-rex-pro.dts
@@ -19,7 +19,7 @@
 };
 
 &ecspi3 {
-	flash: m25p80@0 {
+	flash: flash@0 {
 		compatible = "sst,sst25vf032b", "jedec,spi-nor";
 		spi-max-frequency = <20000000>;
 		reg = <0>;
diff --git a/arch/arm/boot/dts/imx6qdl-aristainetos.dtsi b/arch/arm/boot/dts/imx6qdl-aristainetos.dtsi
index e21f6ac864e5..baa197c90060 100644
--- a/arch/arm/boot/dts/imx6qdl-aristainetos.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-aristainetos.dtsi
@@ -96,7 +96,7 @@
 	pinctrl-0 = <&pinctrl_ecspi4>;
 	status = "okay";
 
-	flash: m25p80@0 {
+	flash: flash@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
 		compatible = "micron,n25q128a11", "jedec,spi-nor";
diff --git a/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi b/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi
index 563bf9d44fe0..2ba577e602e7 100644
--- a/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi
@@ -131,7 +131,7 @@
 	pinctrl-0 = <&pinctrl_ecspi4>;
 	status = "okay";
 
-	flash: m25p80@1 {
+	flash: flash@1 {
 		#address-cells = <1>;
 		#size-cells = <1>;
 		compatible = "micron,n25q128a11", "jedec,spi-nor";
diff --git a/arch/arm/boot/dts/imx6qdl-dfi-fs700-m60.dtsi b/arch/arm/boot/dts/imx6qdl-dfi-fs700-m60.dtsi
index 648f5fcb72e6..2c1d6f28e695 100644
--- a/arch/arm/boot/dts/imx6qdl-dfi-fs700-m60.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-dfi-fs700-m60.dtsi
@@ -35,7 +35,7 @@
 	pinctrl-0 = <&pinctrl_ecspi3>;
 	status = "okay";
 
-	flash: m25p80@0 {
+	flash: flash@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
 		compatible = "sst,sst25vf040b", "jedec,spi-nor";
diff --git a/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi b/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi
index b167b33bd108..6b791d515e29 100644
--- a/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi
@@ -51,16 +51,6 @@
 		vin-supply = <&reg_3p3v_s5>;
 	};
 
-	reg_3p3v_s0: regulator-3p3v-s0 {
-		compatible = "regulator-fixed";
-		regulator-name = "V_3V3_S0";
-		regulator-min-microvolt = <3300000>;
-		regulator-max-microvolt = <3300000>;
-		regulator-always-on;
-		regulator-boot-on;
-		vin-supply = <&reg_3p3v_s5>;
-	};
-
 	reg_3p3v_s5: regulator-3p3v-s5 {
 		compatible = "regulator-fixed";
 		regulator-name = "V_3V3_S5";
@@ -258,8 +248,8 @@
 	status = "okay";
 
 	/* default boot source: workaround #1 for errata ERR006282 */
-	smarc_flash: spi-flash@0 {
-		compatible = "winbond,w25q16dw", "jedec,spi-nor";
+	smarc_flash: flash@0 {
+		compatible = "jedec,spi-nor";
 		reg = <0>;
 		spi-max-frequency = <20000000>;
 	};
diff --git a/arch/arm/boot/dts/imx6qdl-nit6xlite.dtsi b/arch/arm/boot/dts/imx6qdl-nit6xlite.dtsi
index ac34709e9741..0ad4cb4f1e82 100644
--- a/arch/arm/boot/dts/imx6qdl-nit6xlite.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-nit6xlite.dtsi
@@ -179,7 +179,7 @@
 	pinctrl-0 = <&pinctrl_ecspi1>;
 	status = "okay";
 
-	flash: m25p80@0 {
+	flash: flash@0 {
 		compatible = "microchip,sst25vf016b";
 		spi-max-frequency = <20000000>;
 		reg = <0>;
diff --git a/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi b/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi
index c96f4d7e1e0d..beaa2dcd436c 100644
--- a/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi
@@ -321,7 +321,7 @@
 	pinctrl-0 = <&pinctrl_ecspi1>;
 	status = "okay";
 
-	flash: m25p80@0 {
+	flash: flash@0 {
 		compatible = "microchip,sst25vf016b";
 		spi-max-frequency = <20000000>;
 		reg = <0>;
diff --git a/arch/arm/boot/dts/imx6qdl-nitrogen6_som2.dtsi b/arch/arm/boot/dts/imx6qdl-nitrogen6_som2.dtsi
index 92d09a3ebe0e..ee7e2371f94b 100644
--- a/arch/arm/boot/dts/imx6qdl-nitrogen6_som2.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-nitrogen6_som2.dtsi
@@ -252,7 +252,7 @@
 	pinctrl-0 = <&pinctrl_ecspi1>;
 	status = "okay";
 
-	flash: m25p80@0 {
+	flash: flash@0 {
 		compatible = "microchip,sst25vf016b";
 		spi-max-frequency = <20000000>;
 		reg = <0>;
diff --git a/arch/arm/boot/dts/imx6qdl-nitrogen6x.dtsi b/arch/arm/boot/dts/imx6qdl-nitrogen6x.dtsi
index 49da30d7510c..904d5d051d63 100644
--- a/arch/arm/boot/dts/imx6qdl-nitrogen6x.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-nitrogen6x.dtsi
@@ -237,7 +237,7 @@
 	pinctrl-0 = <&pinctrl_ecspi1>;
 	status = "okay";
 
-	flash: m25p80@0 {
+	flash: flash@0 {
 		compatible = "sst,sst25vf016b", "jedec,spi-nor";
 		spi-max-frequency = <20000000>;
 		reg = <0>;
diff --git a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi
index 698208ca4257..534698248c6b 100644
--- a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi
@@ -424,7 +424,7 @@
 	pinctrl-0 = <&pinctrl_ecspi1 &pinctrl_ecspi1_cs>;
 	status = "disabled"; /* pin conflict with WEIM NOR */
 
-	flash: m25p80@0 {
+	flash: flash@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
 		compatible = "st,m25p32", "jedec,spi-nor";
diff --git a/arch/arm/boot/dts/imx6qdl-sabrelite.dtsi b/arch/arm/boot/dts/imx6qdl-sabrelite.dtsi
index eb9a0b104f1c..901b9a761b66 100644
--- a/arch/arm/boot/dts/imx6qdl-sabrelite.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-sabrelite.dtsi
@@ -313,7 +313,7 @@
 	pinctrl-0 = <&pinctrl_ecspi1>;
 	status = "okay";
 
-	flash: m25p80@0 {
+	flash: flash@0 {
 		compatible = "sst,sst25vf016b", "jedec,spi-nor";
 		spi-max-frequency = <20000000>;
 		reg = <0>;
diff --git a/arch/arm/boot/dts/imx6qdl-sabresd.dtsi b/arch/arm/boot/dts/imx6qdl-sabresd.dtsi
index 4a026d1e4090..6f77006ac5b2 100644
--- a/arch/arm/boot/dts/imx6qdl-sabresd.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-sabresd.dtsi
@@ -333,7 +333,7 @@
 	pinctrl-0 = <&pinctrl_ecspi1>;
 	status = "okay";
 
-	flash: m25p80@0 {
+	flash: flash@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
 		compatible = "st,m25p32", "jedec,spi-nor";
diff --git a/arch/arm/boot/dts/imx6qdl-ts7970.dtsi b/arch/arm/boot/dts/imx6qdl-ts7970.dtsi
index fded07f370b3..d6ba4b2a60f6 100644
--- a/arch/arm/boot/dts/imx6qdl-ts7970.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-ts7970.dtsi
@@ -226,7 +226,7 @@
 		reg = <0x28>;
 		#gpio-cells = <2>;
 		gpio-controller;
-		ngpio = <32>;
+		ngpios = <62>;
 	};
 
 	sgtl5000: codec@a {
diff --git a/arch/arm/boot/dts/imx6sl-evk.dts b/arch/arm/boot/dts/imx6sl-evk.dts
index 2857953211ef..2f580ab0300d 100644
--- a/arch/arm/boot/dts/imx6sl-evk.dts
+++ b/arch/arm/boot/dts/imx6sl-evk.dts
@@ -176,7 +176,7 @@
 	pinctrl-0 = <&pinctrl_ecspi1>;
 	status = "okay";
 
-	flash: m25p80@0 {
+	flash: flash@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
 		compatible = "st,m25p32", "jedec,spi-nor";
diff --git a/arch/arm/boot/dts/imx6sx-nitrogen6sx.dts b/arch/arm/boot/dts/imx6sx-nitrogen6sx.dts
index 66af78e83b70..a2c79bcf9a11 100644
--- a/arch/arm/boot/dts/imx6sx-nitrogen6sx.dts
+++ b/arch/arm/boot/dts/imx6sx-nitrogen6sx.dts
@@ -107,7 +107,7 @@
 	pinctrl-0 = <&pinctrl_ecspi1>;
 	status = "okay";
 
-	flash: m25p80@0 {
+	flash: flash@0 {
 		compatible = "microchip,sst25vf016b";
 		spi-max-frequency = <20000000>;
 		reg = <0>;
diff --git a/arch/arm/boot/dts/imx6sx-sdb-reva.dts b/arch/arm/boot/dts/imx6sx-sdb-reva.dts
index dce5dcf96c25..7dda42553f4b 100644
--- a/arch/arm/boot/dts/imx6sx-sdb-reva.dts
+++ b/arch/arm/boot/dts/imx6sx-sdb-reva.dts
@@ -123,7 +123,7 @@
 	pinctrl-0 = <&pinctrl_qspi2>;
 	status = "okay";
 
-	flash0: s25fl128s@0 {
+	flash0: flash@0 {
 		reg = <0>;
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -133,7 +133,7 @@
 		spi-tx-bus-width = <4>;
 	};
 
-	flash1: s25fl128s@2 {
+	flash1: flash@2 {
 		reg = <2>;
 		#address-cells = <1>;
 		#size-cells = <1>;
diff --git a/arch/arm/boot/dts/imx6sx-sdb.dts b/arch/arm/boot/dts/imx6sx-sdb.dts
index e9aa48767057..9a9c25bc4eb2 100644
--- a/arch/arm/boot/dts/imx6sx-sdb.dts
+++ b/arch/arm/boot/dts/imx6sx-sdb.dts
@@ -125,7 +125,7 @@
 	pinctrl-0 = <&pinctrl_qspi2>;
 	status = "okay";
 
-	flash0: n25q256a@0 {
+	flash0: flash@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
 		compatible = "micron,n25q256a", "jedec,spi-nor";
@@ -135,7 +135,7 @@
 		reg = <0>;
 	};
 
-	flash1: n25q256a@2 {
+	flash1: flash@2 {
 		#address-cells = <1>;
 		#size-cells = <1>;
 		compatible = "micron,n25q256a", "jedec,spi-nor";
diff --git a/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi b/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi
index 547709685b31..178247627819 100644
--- a/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi
+++ b/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi
@@ -323,7 +323,7 @@
 	pinctrl-0 = <&pinctrl_qspi>;
 	status = "okay";
 
-	flash0: n25q256a@0 {
+	flash0: flash@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
 		compatible = "micron,n25q256a", "jedec,spi-nor";
diff --git a/arch/arm/boot/dts/imx6ul-kontron-n6310-som.dtsi b/arch/arm/boot/dts/imx6ul-kontron-n6310-som.dtsi
index 47d3ce5d255f..acd936540d89 100644
--- a/arch/arm/boot/dts/imx6ul-kontron-n6310-som.dtsi
+++ b/arch/arm/boot/dts/imx6ul-kontron-n6310-som.dtsi
@@ -19,7 +19,7 @@
 };
 
 &qspi {
-	spi-flash@0 {
+	flash@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
 		compatible = "spi-nand";
diff --git a/arch/arm/boot/dts/imx6ul-kontron-n6311-som.dtsi b/arch/arm/boot/dts/imx6ul-kontron-n6311-som.dtsi
index a095a7654ac6..29ed38dce580 100644
--- a/arch/arm/boot/dts/imx6ul-kontron-n6311-som.dtsi
+++ b/arch/arm/boot/dts/imx6ul-kontron-n6311-som.dtsi
@@ -18,7 +18,7 @@
 };
 
 &qspi {
-	spi-flash@0 {
+	flash@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
 		compatible = "spi-nand";
diff --git a/arch/arm/boot/dts/imx6ul-kontron-n6x1x-som-common.dtsi b/arch/arm/boot/dts/imx6ul-kontron-n6x1x-som-common.dtsi
index 2a449a3c1ae2..09a83dbdf651 100644
--- a/arch/arm/boot/dts/imx6ul-kontron-n6x1x-som-common.dtsi
+++ b/arch/arm/boot/dts/imx6ul-kontron-n6x1x-som-common.dtsi
@@ -19,7 +19,7 @@
 	pinctrl-0 = <&pinctrl_ecspi2>;
 	status = "okay";
 
-	spi-flash@0 {
+	flash@0 {
 		compatible = "mxicy,mx25v8035f", "jedec,spi-nor";
 		spi-max-frequency = <50000000>;
 		reg = <0>;
diff --git a/arch/arm/boot/dts/imx6ul.dtsi b/arch/arm/boot/dts/imx6ul.dtsi
index 354aff1fa7bf..f7b3939d1609 100644
--- a/arch/arm/boot/dts/imx6ul.dtsi
+++ b/arch/arm/boot/dts/imx6ul.dtsi
@@ -64,20 +64,18 @@
 			clock-frequency = <696000000>;
 			clock-latency = <61036>; /* two CLK32 periods */
 			#cooling-cells = <2>;
-			operating-points = <
+			operating-points =
 				/* kHz	uV */
-				696000	1275000
-				528000	1175000
-				396000	1025000
-				198000	950000
-			>;
-			fsl,soc-operating-points = <
+				<696000	1275000>,
+				<528000	1175000>,
+				<396000	1025000>,
+				<198000	950000>;
+			fsl,soc-operating-points =
 				/* KHz	uV */
-				696000	1275000
-				528000	1175000
-				396000	1175000
-				198000	1175000
-			>;
+				<696000	1275000>,
+				<528000	1175000>,
+				<396000	1175000>,
+				<198000	1175000>;
 			clocks = <&clks IMX6UL_CLK_ARM>,
 				 <&clks IMX6UL_CLK_PLL2_BUS>,
 				 <&clks IMX6UL_CLK_PLL2_PFD2>,
@@ -591,7 +589,7 @@
 			};
 
 			kpp: keypad@20b8000 {
-				compatible = "fsl,imx6ul-kpp", "fsl,imx6q-kpp", "fsl,imx21-kpp";
+				compatible = "fsl,imx6ul-kpp", "fsl,imx21-kpp";
 				reg = <0x020b8000 0x4000>;
 				interrupts = <GIC_SPI 82 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks IMX6UL_CLK_KPP>;
@@ -1088,7 +1086,7 @@
 			};
 
 			lcdif: lcdif@21c8000 {
-				compatible = "fsl,imx6ul-lcdif", "fsl,imx28-lcdif";
+				compatible = "fsl,imx6ul-lcdif", "fsl,imx6sx-lcdif";
 				reg = <0x021c8000 0x4000>;
 				interrupts = <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks IMX6UL_CLK_LCDIF_PIX>,
@@ -1111,7 +1109,7 @@
 			qspi: spi@21e0000 {
 				#address-cells = <1>;
 				#size-cells = <0>;
-				compatible = "fsl,imx6ul-qspi", "fsl,imx6sx-qspi";
+				compatible = "fsl,imx6ul-qspi";
 				reg = <0x021e0000 0x4000>, <0x60000000 0x10000000>;
 				reg-names = "QuadSPI", "QuadSPI-memory";
 				interrupts = <GIC_SPI 107 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm/boot/dts/imx6ull-kontron-n6411-som.dtsi b/arch/arm/boot/dts/imx6ull-kontron-n6411-som.dtsi
index b7e984284e1a..d000606c0704 100644
--- a/arch/arm/boot/dts/imx6ull-kontron-n6411-som.dtsi
+++ b/arch/arm/boot/dts/imx6ull-kontron-n6411-som.dtsi
@@ -18,7 +18,7 @@
 };
 
 &qspi {
-	spi-flash@0 {
+	flash@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
 		compatible = "spi-nand";
diff --git a/arch/arm/boot/dts/imx7d-colibri-emmc.dtsi b/arch/arm/boot/dts/imx7d-colibri-emmc.dtsi
index af39e5370fa1..045e4413d339 100644
--- a/arch/arm/boot/dts/imx7d-colibri-emmc.dtsi
+++ b/arch/arm/boot/dts/imx7d-colibri-emmc.dtsi
@@ -13,6 +13,10 @@
 	};
 };
 
+&cpu1 {
+	cpu-supply = <&reg_DCDC2>;
+};
+
 &gpio6 {
 	gpio-line-names = "",
 			  "",
diff --git a/arch/arm/boot/dts/qcom-mdm9615.dtsi b/arch/arm/boot/dts/qcom-mdm9615.dtsi
index dda2ceec6591..ad9b52d53ef9 100644
--- a/arch/arm/boot/dts/qcom-mdm9615.dtsi
+++ b/arch/arm/boot/dts/qcom-mdm9615.dtsi
@@ -324,6 +324,7 @@
 
 				pmicgpio: gpio@150 {
 					compatible = "qcom,pm8018-gpio", "qcom,ssbi-gpio";
+					reg = <0x150>;
 					interrupt-controller;
 					#interrupt-cells = <2>;
 					gpio-controller;
diff --git a/arch/arm/boot/dts/qcom-msm8974.dtsi b/arch/arm/boot/dts/qcom-msm8974.dtsi
index 2b01bc29ddf2..05d51839d40a 100644
--- a/arch/arm/boot/dts/qcom-msm8974.dtsi
+++ b/arch/arm/boot/dts/qcom-msm8974.dtsi
@@ -718,7 +718,7 @@
 		blsp2_uart7: serial@f995d000 {
 			compatible = "qcom,msm-uartdm-v1.4", "qcom,msm-uartdm";
 			reg = <0xf995d000 0x1000>;
-			interrupts = <GIC_SPI 113 IRQ_TYPE_NONE>;
+			interrupts = <GIC_SPI 113 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&gcc GCC_BLSP2_UART1_APPS_CLK>, <&gcc GCC_BLSP2_AHB_CLK>;
 			clock-names = "core", "iface";
 			status = "disabled";
diff --git a/arch/arm/boot/dts/qcom-pm8841.dtsi b/arch/arm/boot/dts/qcom-pm8841.dtsi
index 2fd59c440903..c73e5b149ac5 100644
--- a/arch/arm/boot/dts/qcom-pm8841.dtsi
+++ b/arch/arm/boot/dts/qcom-pm8841.dtsi
@@ -25,6 +25,7 @@
 			compatible = "qcom,spmi-temp-alarm";
 			reg = <0x2400>;
 			interrupts = <4 0x24 0 IRQ_TYPE_EDGE_RISING>;
+			#thermal-sensor-cells = <0>;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/qcom-sdx55.dtsi b/arch/arm/boot/dts/qcom-sdx55.dtsi
index b5b784c5c65e..0e76d03087fe 100644
--- a/arch/arm/boot/dts/qcom-sdx55.dtsi
+++ b/arch/arm/boot/dts/qcom-sdx55.dtsi
@@ -205,7 +205,7 @@
 		blsp1_uart3: serial@831000 {
 			compatible = "qcom,msm-uartdm-v1.4", "qcom,msm-uartdm";
 			reg = <0x00831000 0x200>;
-			interrupts = <GIC_SPI 26 IRQ_TYPE_LEVEL_LOW>;
+			interrupts = <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&gcc 30>,
 				 <&gcc 9>;
 			clock-names = "core", "iface";
diff --git a/arch/arm/boot/dts/sama5d2.dtsi b/arch/arm/boot/dts/sama5d2.dtsi
index de88eb484718..4c87c2aa8fc8 100644
--- a/arch/arm/boot/dts/sama5d2.dtsi
+++ b/arch/arm/boot/dts/sama5d2.dtsi
@@ -1125,7 +1125,7 @@
 				clocks = <&pmc PMC_TYPE_PERIPHERAL 55>, <&pmc PMC_TYPE_GCK 55>;
 				clock-names = "pclk", "gclk";
 				assigned-clocks = <&pmc PMC_TYPE_CORE PMC_I2S1_MUX>;
-				assigned-parrents = <&pmc PMC_TYPE_GCK 55>;
+				assigned-clock-parents = <&pmc PMC_TYPE_GCK 55>;
 				status = "disabled";
 			};
 
diff --git a/arch/arm/boot/dts/ste-ux500-samsung-codina.dts b/arch/arm/boot/dts/ste-ux500-samsung-codina.dts
index 952606e607ed..ce62ba877da1 100644
--- a/arch/arm/boot/dts/ste-ux500-samsung-codina.dts
+++ b/arch/arm/boot/dts/ste-ux500-samsung-codina.dts
@@ -544,8 +544,8 @@
 				reg = <0x19>;
 				vdd-supply = <&ab8500_ldo_aux1_reg>; // 3V
 				vddio-supply = <&ab8500_ldo_aux2_reg>; // 1.8V
-				mount-matrix = "0", "-1", "0",
-					       "1", "0", "0",
+				mount-matrix = "0", "1", "0",
+					       "-1", "0", "0",
 					       "0", "0", "1";
 			};
 		};
diff --git a/arch/arm/boot/dts/ste-ux500-samsung-gavini.dts b/arch/arm/boot/dts/ste-ux500-samsung-gavini.dts
index fabc390ccb0c..6c9e812ef03f 100644
--- a/arch/arm/boot/dts/ste-ux500-samsung-gavini.dts
+++ b/arch/arm/boot/dts/ste-ux500-samsung-gavini.dts
@@ -502,8 +502,8 @@
 					accelerometer@18 {
 						compatible = "bosch,bma222e";
 						reg = <0x18>;
-						mount-matrix = "0", "1", "0",
-							       "-1", "0", "0",
+						mount-matrix = "0", "-1", "0",
+							       "1", "0", "0",
 							       "0", "0", "1";
 						vddio-supply = <&ab8500_ldo_aux2_reg>; // 1.8V
 						vdd-supply = <&ab8500_ldo_aux1_reg>; // 3V
diff --git a/arch/arm/boot/dts/stm32mp151.dtsi b/arch/arm/boot/dts/stm32mp151.dtsi
index 6992a4b0ba79..e0d483318798 100644
--- a/arch/arm/boot/dts/stm32mp151.dtsi
+++ b/arch/arm/boot/dts/stm32mp151.dtsi
@@ -553,7 +553,7 @@
 			compatible = "st,stm32-cec";
 			reg = <0x40016000 0x400>;
 			interrupts = <GIC_SPI 94 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&rcc CEC_K>, <&clk_lse>;
+			clocks = <&rcc CEC_K>, <&rcc CEC>;
 			clock-names = "cec", "hdmi-cec";
 			status = "disabled";
 		};
@@ -1452,7 +1452,7 @@
 		usbh_ohci: usb@5800c000 {
 			compatible = "generic-ohci";
 			reg = <0x5800c000 0x1000>;
-			clocks = <&rcc USBH>;
+			clocks = <&usbphyc>, <&rcc USBH>;
 			resets = <&rcc USBH_R>;
 			interrupts = <GIC_SPI 74 IRQ_TYPE_LEVEL_HIGH>;
 			status = "disabled";
@@ -1461,7 +1461,7 @@
 		usbh_ehci: usb@5800d000 {
 			compatible = "generic-ehci";
 			reg = <0x5800d000 0x1000>;
-			clocks = <&rcc USBH>;
+			clocks = <&usbphyc>, <&rcc USBH>;
 			resets = <&rcc USBH_R>;
 			interrupts = <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>;
 			companion = <&usbh_ohci>;
diff --git a/arch/arm/boot/dts/sun8i-h2-plus-orangepi-zero.dts b/arch/arm/boot/dts/sun8i-h2-plus-orangepi-zero.dts
index f19ed981da9d..3706216ffb40 100644
--- a/arch/arm/boot/dts/sun8i-h2-plus-orangepi-zero.dts
+++ b/arch/arm/boot/dts/sun8i-h2-plus-orangepi-zero.dts
@@ -169,7 +169,7 @@
 	flash@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
-		compatible = "mxicy,mx25l1606e", "winbond,w25q128";
+		compatible = "mxicy,mx25l1606e", "jedec,spi-nor";
 		reg = <0>;
 		spi-max-frequency = <40000000>;
 	};
diff --git a/arch/arm/boot/dts/uniphier-pxs2.dtsi b/arch/arm/boot/dts/uniphier-pxs2.dtsi
index e81e5937a60a..03301ddb3403 100644
--- a/arch/arm/boot/dts/uniphier-pxs2.dtsi
+++ b/arch/arm/boot/dts/uniphier-pxs2.dtsi
@@ -597,8 +597,8 @@
 			compatible = "socionext,uniphier-dwc3", "snps,dwc3";
 			status = "disabled";
 			reg = <0x65a00000 0xcd00>;
-			interrupt-names = "host", "peripheral";
-			interrupts = <0 134 4>, <0 135 4>;
+			interrupt-names = "dwc_usb3";
+			interrupts = <0 134 4>;
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinctrl_usb0>, <&pinctrl_usb2>;
 			clock-names = "ref", "bus_early", "suspend";
@@ -693,8 +693,8 @@
 			compatible = "socionext,uniphier-dwc3", "snps,dwc3";
 			status = "disabled";
 			reg = <0x65c00000 0xcd00>;
-			interrupt-names = "host", "peripheral";
-			interrupts = <0 137 4>, <0 138 4>;
+			interrupt-names = "dwc_usb3";
+			interrupts = <0 137 4>;
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinctrl_usb1>, <&pinctrl_usb3>;
 			clock-names = "ref", "bus_early", "suspend";
diff --git a/arch/arm/configs/mxs_defconfig b/arch/arm/configs/mxs_defconfig
index ca32446b187f..f53086ddc48b 100644
--- a/arch/arm/configs/mxs_defconfig
+++ b/arch/arm/configs/mxs_defconfig
@@ -93,6 +93,7 @@ CONFIG_REGULATOR_FIXED_VOLTAGE=y
 CONFIG_DRM=y
 CONFIG_DRM_PANEL_SEIKO_43WVF1G=y
 CONFIG_DRM_MXSFB=y
+CONFIG_FB=y
 CONFIG_FB_MODE_HELPERS=y
 CONFIG_LCD_CLASS_DEVICE=y
 CONFIG_BACKLIGHT_CLASS_DEVICE=y
diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index e4dba5461cb3..149a5bd6b88c 100644
--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -63,7 +63,7 @@ config CRYPTO_SHA512_ARM
 	  using optimized ARM assembler and NEON, when available.
 
 config CRYPTO_BLAKE2S_ARM
-	tristate "BLAKE2s digest algorithm (ARM)"
+	bool "BLAKE2s digest algorithm (ARM)"
 	select CRYPTO_ARCH_HAVE_LIB_BLAKE2S
 	help
 	  BLAKE2s digest algorithm optimized with ARM scalar instructions.  This
diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
index 0274f81cc8ea..971e74546fb1 100644
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -9,8 +9,7 @@ obj-$(CONFIG_CRYPTO_SHA1_ARM) += sha1-arm.o
 obj-$(CONFIG_CRYPTO_SHA1_ARM_NEON) += sha1-arm-neon.o
 obj-$(CONFIG_CRYPTO_SHA256_ARM) += sha256-arm.o
 obj-$(CONFIG_CRYPTO_SHA512_ARM) += sha512-arm.o
-obj-$(CONFIG_CRYPTO_BLAKE2S_ARM) += blake2s-arm.o
-obj-$(if $(CONFIG_CRYPTO_BLAKE2S_ARM),y) += libblake2s-arm.o
+obj-$(CONFIG_CRYPTO_BLAKE2S_ARM) += libblake2s-arm.o
 obj-$(CONFIG_CRYPTO_BLAKE2B_NEON) += blake2b-neon.o
 obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha-neon.o
 obj-$(CONFIG_CRYPTO_POLY1305_ARM) += poly1305-arm.o
@@ -32,7 +31,6 @@ sha256-arm-neon-$(CONFIG_KERNEL_MODE_NEON) := sha256_neon_glue.o
 sha256-arm-y	:= sha256-core.o sha256_glue.o $(sha256-arm-neon-y)
 sha512-arm-neon-$(CONFIG_KERNEL_MODE_NEON) := sha512-neon-glue.o
 sha512-arm-y	:= sha512-core.o sha512-glue.o $(sha512-arm-neon-y)
-blake2s-arm-y   := blake2s-shash.o
 libblake2s-arm-y:= blake2s-core.o blake2s-glue.o
 blake2b-neon-y  := blake2b-neon-core.o blake2b-neon-glue.o
 sha1-arm-ce-y	:= sha1-ce-core.o sha1-ce-glue.o
diff --git a/arch/arm/crypto/blake2s-shash.c b/arch/arm/crypto/blake2s-shash.c
deleted file mode 100644
index 763c73beea2d..000000000000
--- a/arch/arm/crypto/blake2s-shash.c
+++ /dev/null
@@ -1,75 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * BLAKE2s digest algorithm, ARM scalar implementation
- *
- * Copyright 2020 Google LLC
- */
-
-#include <crypto/internal/blake2s.h>
-#include <crypto/internal/hash.h>
-
-#include <linux/module.h>
-
-static int crypto_blake2s_update_arm(struct shash_desc *desc,
-				     const u8 *in, unsigned int inlen)
-{
-	return crypto_blake2s_update(desc, in, inlen, false);
-}
-
-static int crypto_blake2s_final_arm(struct shash_desc *desc, u8 *out)
-{
-	return crypto_blake2s_final(desc, out, false);
-}
-
-#define BLAKE2S_ALG(name, driver_name, digest_size)			\
-	{								\
-		.base.cra_name		= name,				\
-		.base.cra_driver_name	= driver_name,			\
-		.base.cra_priority	= 200,				\
-		.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,	\
-		.base.cra_blocksize	= BLAKE2S_BLOCK_SIZE,		\
-		.base.cra_ctxsize	= sizeof(struct blake2s_tfm_ctx), \
-		.base.cra_module	= THIS_MODULE,			\
-		.digestsize		= digest_size,			\
-		.setkey			= crypto_blake2s_setkey,	\
-		.init			= crypto_blake2s_init,		\
-		.update			= crypto_blake2s_update_arm,	\
-		.final			= crypto_blake2s_final_arm,	\
-		.descsize		= sizeof(struct blake2s_state),	\
-	}
-
-static struct shash_alg blake2s_arm_algs[] = {
-	BLAKE2S_ALG("blake2s-128", "blake2s-128-arm", BLAKE2S_128_HASH_SIZE),
-	BLAKE2S_ALG("blake2s-160", "blake2s-160-arm", BLAKE2S_160_HASH_SIZE),
-	BLAKE2S_ALG("blake2s-224", "blake2s-224-arm", BLAKE2S_224_HASH_SIZE),
-	BLAKE2S_ALG("blake2s-256", "blake2s-256-arm", BLAKE2S_256_HASH_SIZE),
-};
-
-static int __init blake2s_arm_mod_init(void)
-{
-	return IS_REACHABLE(CONFIG_CRYPTO_HASH) ?
-		crypto_register_shashes(blake2s_arm_algs,
-					ARRAY_SIZE(blake2s_arm_algs)) : 0;
-}
-
-static void __exit blake2s_arm_mod_exit(void)
-{
-	if (IS_REACHABLE(CONFIG_CRYPTO_HASH))
-		crypto_unregister_shashes(blake2s_arm_algs,
-					  ARRAY_SIZE(blake2s_arm_algs));
-}
-
-module_init(blake2s_arm_mod_init);
-module_exit(blake2s_arm_mod_exit);
-
-MODULE_DESCRIPTION("BLAKE2s digest algorithm, ARM scalar implementation");
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Eric Biggers <ebiggers@google.com>");
-MODULE_ALIAS_CRYPTO("blake2s-128");
-MODULE_ALIAS_CRYPTO("blake2s-128-arm");
-MODULE_ALIAS_CRYPTO("blake2s-160");
-MODULE_ALIAS_CRYPTO("blake2s-160-arm");
-MODULE_ALIAS_CRYPTO("blake2s-224");
-MODULE_ALIAS_CRYPTO("blake2s-224-arm");
-MODULE_ALIAS_CRYPTO("blake2s-256");
-MODULE_ALIAS_CRYPTO("blake2s-256-arm");
diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h
index 413abfb42989..f82a819eb0db 100644
--- a/arch/arm/include/asm/arch_gicv3.h
+++ b/arch/arm/include/asm/arch_gicv3.h
@@ -48,6 +48,7 @@ static inline u32 read_ ## a64(void)		\
 	return read_sysreg(a32); 		\
 }						\
 
+CPUIF_MAP(ICC_EOIR1, ICC_EOIR1_EL1)
 CPUIF_MAP(ICC_PMR, ICC_PMR_EL1)
 CPUIF_MAP(ICC_AP0R0, ICC_AP0R0_EL1)
 CPUIF_MAP(ICC_AP0R1, ICC_AP0R1_EL1)
@@ -63,12 +64,6 @@ CPUIF_MAP(ICC_AP1R3, ICC_AP1R3_EL1)
 
 /* Low-level accessors */
 
-static inline void gic_write_eoir(u32 irq)
-{
-	write_sysreg(irq, ICC_EOIR1);
-	isb();
-}
-
 static inline void gic_write_dir(u32 val)
 {
 	write_sysreg(val, ICC_DIR);
diff --git a/arch/arm/include/asm/dma.h b/arch/arm/include/asm/dma.h
index a81dda65c576..45180a2cc47c 100644
--- a/arch/arm/include/asm/dma.h
+++ b/arch/arm/include/asm/dma.h
@@ -10,7 +10,7 @@
 #else
 #define MAX_DMA_ADDRESS	({ \
 	extern phys_addr_t arm_dma_zone_size; \
-	arm_dma_zone_size && arm_dma_zone_size < (0x10000000 - PAGE_OFFSET) ? \
+	arm_dma_zone_size && arm_dma_zone_size < (0x100000000ULL - PAGE_OFFSET) ? \
 		(PAGE_OFFSET + arm_dma_zone_size) : 0xffffffffUL; })
 #endif
 
diff --git a/arch/arm/include/asm/entry-macro-multi.S b/arch/arm/include/asm/entry-macro-multi.S
index dfc6bfa43012..24486dad9e19 100644
--- a/arch/arm/include/asm/entry-macro-multi.S
+++ b/arch/arm/include/asm/entry-macro-multi.S
@@ -13,28 +13,4 @@
 	@
 	badrne	lr, 1b
 	bne	asm_do_IRQ
-
-#ifdef CONFIG_SMP
-	/*
-	 * XXX
-	 *
-	 * this macro assumes that irqstat (r2) and base (r6) are
-	 * preserved from get_irqnr_and_base above
-	 */
-	ALT_SMP(test_for_ipi r0, r2, r6, lr)
-	ALT_UP_B(9997f)
-	movne	r1, sp
-	badrne	lr, 1b
-	bne	do_IPI
-#endif
-9997:
-	.endm
-
-	.macro	arch_irq_handler, symbol_name
-	.align	5
-	.global \symbol_name
-\symbol_name:
-	mov	r8, lr
-	arch_irq_handler_default
-	ret	r8
 	.endm
diff --git a/arch/arm/include/asm/mach/map.h b/arch/arm/include/asm/mach/map.h
index 05e1af2179f9..1a25ab8edb5d 100644
--- a/arch/arm/include/asm/mach/map.h
+++ b/arch/arm/include/asm/mach/map.h
@@ -27,6 +27,7 @@ enum {
 	MT_HIGH_VECTORS,
 	MT_MEMORY_RWX,
 	MT_MEMORY_RW,
+	MT_MEMORY_RO,
 	MT_ROM,
 	MT_MEMORY_RWX_NONCACHED,
 	MT_MEMORY_RW_DTCM,
diff --git a/arch/arm/include/asm/ptrace.h b/arch/arm/include/asm/ptrace.h
index 91d6b7856be4..73c83f4d33b3 100644
--- a/arch/arm/include/asm/ptrace.h
+++ b/arch/arm/include/asm/ptrace.h
@@ -164,5 +164,31 @@ static inline unsigned long user_stack_pointer(struct pt_regs *regs)
 		((current_stack_pointer | (THREAD_SIZE - 1)) - 7) - 1;	\
 })
 
+
+/*
+ * Update ITSTATE after normal execution of an IT block instruction.
+ *
+ * The 8 IT state bits are split into two parts in CPSR:
+ *	ITSTATE<1:0> are in CPSR<26:25>
+ *	ITSTATE<7:2> are in CPSR<15:10>
+ */
+static inline unsigned long it_advance(unsigned long cpsr)
+{
+	if ((cpsr & 0x06000400) == 0) {
+		/* ITSTATE<2:0> == 0 means end of IT block, so clear IT state */
+		cpsr &= ~PSR_IT_MASK;
+	} else {
+		/* We need to shift left ITSTATE<4:0> */
+		const unsigned long mask = 0x06001c00;  /* Mask ITSTATE<4:0> */
+		unsigned long it = cpsr & mask;
+		it <<= 1;
+		it |= it >> (27 - 10);  /* Carry ITSTATE<2> to correct place */
+		it &= mask;
+		cpsr &= ~mask;
+		cpsr |= it;
+	}
+	return cpsr;
+}
+
 #endif /* __ASSEMBLY__ */
 #endif
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index 5d508f5d56c4..fc11ddf13b8f 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -25,11 +25,6 @@ struct seq_file;
 extern void show_ipi_list(struct seq_file *, int);
 
 /*
- * Called from assembly code, this handles an IPI.
- */
-asmlinkage void do_IPI(int ipinr, struct pt_regs *regs);
-
-/*
  * Called from C code, this handles an IPI.
  */
 void handle_IPI(int ipinr, struct pt_regs *regs);
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 842427ff2b3c..23d369ab7e03 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -622,11 +622,6 @@ static void ipi_complete(unsigned int cpu)
 /*
  * Main handler for inter-processor interrupts
  */
-asmlinkage void __exception_irq_entry do_IPI(int ipinr, struct pt_regs *regs)
-{
-	handle_IPI(ipinr, regs);
-}
-
 static void do_handle_IPI(int ipinr)
 {
 	unsigned int cpu = smp_processor_id();
diff --git a/arch/arm/lib/findbit.S b/arch/arm/lib/findbit.S
index b5e8b9ae4c7d..7fd3600db8ef 100644
--- a/arch/arm/lib/findbit.S
+++ b/arch/arm/lib/findbit.S
@@ -40,8 +40,8 @@ ENDPROC(_find_first_zero_bit_le)
  * Prototype: int find_next_zero_bit(void *addr, unsigned int maxbit, int offset)
  */
 ENTRY(_find_next_zero_bit_le)
-		teq	r1, #0
-		beq	3b
+		cmp	r2, r1
+		bhs	3b
 		ands	ip, r2, #7
 		beq	1b			@ If new byte, goto old routine
  ARM(		ldrb	r3, [r0, r2, lsr #3]	)
@@ -81,8 +81,8 @@ ENDPROC(_find_first_bit_le)
  * Prototype: int find_next_zero_bit(void *addr, unsigned int maxbit, int offset)
  */
 ENTRY(_find_next_bit_le)
-		teq	r1, #0
-		beq	3b
+		cmp	r2, r1
+		bhs	3b
 		ands	ip, r2, #7
 		beq	1b			@ If new byte, goto old routine
  ARM(		ldrb	r3, [r0, r2, lsr #3]	)
@@ -115,8 +115,8 @@ ENTRY(_find_first_zero_bit_be)
 ENDPROC(_find_first_zero_bit_be)
 
 ENTRY(_find_next_zero_bit_be)
-		teq	r1, #0
-		beq	3b
+		cmp	r2, r1
+		bhs	3b
 		ands	ip, r2, #7
 		beq	1b			@ If new byte, goto old routine
 		eor	r3, r2, #0x18		@ big endian byte ordering
@@ -149,8 +149,8 @@ ENTRY(_find_first_bit_be)
 ENDPROC(_find_first_bit_be)
 
 ENTRY(_find_next_bit_be)
-		teq	r1, #0
-		beq	3b
+		cmp	r2, r1
+		bhs	3b
 		ands	ip, r2, #7
 		beq	1b			@ If new byte, goto old routine
 		eor	r3, r2, #0x18		@ big endian byte ordering
diff --git a/arch/arm/lib/xor-neon.c b/arch/arm/lib/xor-neon.c
index b99dd8e1c93f..7ba6cf826162 100644
--- a/arch/arm/lib/xor-neon.c
+++ b/arch/arm/lib/xor-neon.c
@@ -26,8 +26,9 @@ MODULE_LICENSE("GPL");
  * While older versions of GCC do not generate incorrect code, they fail to
  * recognize the parallel nature of these functions, and emit plain ARM code,
  * which is known to be slower than the optimized ARM code in asm-arm/xor.h.
+ *
+ * #warning This code requires at least version 4.6 of GCC
  */
-#warning This code requires at least version 4.6 of GCC
 #endif
 
 #pragma GCC diagnostic ignored "-Wunused-variable"
diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c
index 8711d6824c1f..c8cc993ca8ca 100644
--- a/arch/arm/mach-at91/pm.c
+++ b/arch/arm/mach-at91/pm.c
@@ -146,7 +146,7 @@ static const struct wakeup_source_info ws_info[] = {
 
 static const struct of_device_id sama5d2_ws_ids[] = {
 	{ .compatible = "atmel,sama5d2-gem",		.data = &ws_info[0] },
-	{ .compatible = "atmel,at91rm9200-rtc",		.data = &ws_info[1] },
+	{ .compatible = "atmel,sama5d2-rtc",		.data = &ws_info[1] },
 	{ .compatible = "atmel,sama5d3-udc",		.data = &ws_info[2] },
 	{ .compatible = "atmel,at91rm9200-ohci",	.data = &ws_info[2] },
 	{ .compatible = "usb-ohci",			.data = &ws_info[2] },
@@ -157,24 +157,24 @@ static const struct of_device_id sama5d2_ws_ids[] = {
 };
 
 static const struct of_device_id sam9x60_ws_ids[] = {
-	{ .compatible = "atmel,at91sam9x5-rtc",		.data = &ws_info[1] },
+	{ .compatible = "microchip,sam9x60-rtc",	.data = &ws_info[1] },
 	{ .compatible = "atmel,at91rm9200-ohci",	.data = &ws_info[2] },
 	{ .compatible = "usb-ohci",			.data = &ws_info[2] },
 	{ .compatible = "atmel,at91sam9g45-ehci",	.data = &ws_info[2] },
 	{ .compatible = "usb-ehci",			.data = &ws_info[2] },
-	{ .compatible = "atmel,at91sam9260-rtt",	.data = &ws_info[4] },
+	{ .compatible = "microchip,sam9x60-rtt",	.data = &ws_info[4] },
 	{ .compatible = "cdns,sam9x60-macb",		.data = &ws_info[5] },
 	{ /* sentinel */ }
 };
 
 static const struct of_device_id sama7g5_ws_ids[] = {
-	{ .compatible = "atmel,at91sam9x5-rtc",		.data = &ws_info[1] },
+	{ .compatible = "microchip,sama7g5-rtc",	.data = &ws_info[1] },
 	{ .compatible = "microchip,sama7g5-ohci",	.data = &ws_info[2] },
 	{ .compatible = "usb-ohci",			.data = &ws_info[2] },
 	{ .compatible = "atmel,at91sam9g45-ehci",	.data = &ws_info[2] },
 	{ .compatible = "usb-ehci",			.data = &ws_info[2] },
 	{ .compatible = "microchip,sama7g5-sdhci",	.data = &ws_info[3] },
-	{ .compatible = "atmel,at91sam9260-rtt",	.data = &ws_info[4] },
+	{ .compatible = "microchip,sama7g5-rtt",	.data = &ws_info[4] },
 	{ /* sentinel */ }
 };
 
@@ -350,10 +350,42 @@ extern u32 at91_pm_suspend_in_sram_sz;
 
 static int at91_suspend_finish(unsigned long val)
 {
+	unsigned char modified_gray_code[] = {
+		0x00, 0x01, 0x02, 0x03, 0x06, 0x07, 0x04, 0x05, 0x0c, 0x0d,
+		0x0e, 0x0f, 0x0a, 0x0b, 0x08, 0x09, 0x18, 0x19, 0x1a, 0x1b,
+		0x1e, 0x1f, 0x1c, 0x1d, 0x14, 0x15, 0x16, 0x17, 0x12, 0x13,
+		0x10, 0x11,
+	};
+	unsigned int tmp, index;
 	int i;
 
 	if (soc_pm.data.mode == AT91_PM_BACKUP && soc_pm.data.ramc_phy) {
 		/*
+		 * Bootloader will perform DDR recalibration and will try to
+		 * restore the ZQ0SR0 with the value saved here. But the
+		 * calibration is buggy and restoring some values from ZQ0SR0
+		 * is forbidden and risky thus we need to provide processed
+		 * values for these (modified gray code values).
+		 */
+		tmp = readl(soc_pm.data.ramc_phy + DDR3PHY_ZQ0SR0);
+
+		/* Store pull-down output impedance select. */
+		index = (tmp >> DDR3PHY_ZQ0SR0_PDO_OFF) & 0x1f;
+		soc_pm.bu->ddr_phy_calibration[0] = modified_gray_code[index];
+
+		/* Store pull-up output impedance select. */
+		index = (tmp >> DDR3PHY_ZQ0SR0_PUO_OFF) & 0x1f;
+		soc_pm.bu->ddr_phy_calibration[0] |= modified_gray_code[index];
+
+		/* Store pull-down on-die termination impedance select. */
+		index = (tmp >> DDR3PHY_ZQ0SR0_PDODT_OFF) & 0x1f;
+		soc_pm.bu->ddr_phy_calibration[0] |= modified_gray_code[index];
+
+		/* Store pull-up on-die termination impedance select. */
+		index = (tmp >> DDR3PHY_ZQ0SRO_PUODT_OFF) & 0x1f;
+		soc_pm.bu->ddr_phy_calibration[0] |= modified_gray_code[index];
+
+		/*
 		 * The 1st 8 words of memory might get corrupted in the process
 		 * of DDR PHY recalibration; it is saved here in securam and it
 		 * will be restored later, after recalibration, by bootloader
@@ -841,10 +873,6 @@ static int __init at91_pm_backup_init(void)
 		of_scan_flat_dt(at91_pm_backup_scan_memcs, &located);
 		if (!located)
 			goto securam_fail;
-
-		/* DDR3PHY_ZQ0SR0 */
-		soc_pm.bu->ddr_phy_calibration[0] = readl(soc_pm.data.ramc_phy +
-							  0x188);
 	}
 
 	return 0;
diff --git a/arch/arm/mach-at91/pm_suspend.S b/arch/arm/mach-at91/pm_suspend.S
index fdb4f63ecde4..65cfcc19a936 100644
--- a/arch/arm/mach-at91/pm_suspend.S
+++ b/arch/arm/mach-at91/pm_suspend.S
@@ -172,9 +172,15 @@ sr_ena_2:
 	/* Put DDR PHY's DLL in bypass mode for non-backup modes. */
 	cmp	r7, #AT91_PM_BACKUP
 	beq	sr_ena_3
-	ldr	tmp1, [r3, #DDR3PHY_PIR]
-	orr	tmp1, tmp1, #DDR3PHY_PIR_DLLBYP
-	str	tmp1, [r3, #DDR3PHY_PIR]
+
+	/* Disable DX DLLs. */
+	ldr	tmp1, [r3, #DDR3PHY_DX0DLLCR]
+	orr	tmp1, tmp1, #DDR3PHY_DXDLLCR_DLLDIS
+	str	tmp1, [r3, #DDR3PHY_DX0DLLCR]
+
+	ldr	tmp1, [r3, #DDR3PHY_DX1DLLCR]
+	orr	tmp1, tmp1, #DDR3PHY_DXDLLCR_DLLDIS
+	str	tmp1, [r3, #DDR3PHY_DX1DLLCR]
 
 sr_ena_3:
 	/* Power down DDR PHY data receivers. */
@@ -221,10 +227,14 @@ sr_ena_3:
 	bic	tmp1, tmp1, #DDR3PHY_DSGCR_ODTPDD_ODT0
 	str	tmp1, [r3, #DDR3PHY_DSGCR]
 
-	/* Take DDR PHY's DLL out of bypass mode. */
-	ldr	tmp1, [r3, #DDR3PHY_PIR]
-	bic	tmp1, tmp1, #DDR3PHY_PIR_DLLBYP
-	str	tmp1, [r3, #DDR3PHY_PIR]
+	/* Enable DX DLLs. */
+	ldr	tmp1, [r3, #DDR3PHY_DX0DLLCR]
+	bic	tmp1, tmp1, #DDR3PHY_DXDLLCR_DLLDIS
+	str	tmp1, [r3, #DDR3PHY_DX0DLLCR]
+
+	ldr	tmp1, [r3, #DDR3PHY_DX1DLLCR]
+	bic	tmp1, tmp1, #DDR3PHY_DXDLLCR_DLLDIS
+	str	tmp1, [r3, #DDR3PHY_DX1DLLCR]
 
 	/* Enable quasi-dynamic programming. */
 	mov	tmp1, #0
diff --git a/arch/arm/mach-bcm/bcm_kona_smc.c b/arch/arm/mach-bcm/bcm_kona_smc.c
index 43829e49ad93..347bfb7f03e2 100644
--- a/arch/arm/mach-bcm/bcm_kona_smc.c
+++ b/arch/arm/mach-bcm/bcm_kona_smc.c
@@ -52,6 +52,7 @@ int __init bcm_kona_smc_init(void)
 		return -ENODEV;
 
 	prop_val = of_get_address(node, 0, &prop_size, NULL);
+	of_node_put(node);
 	if (!prop_val)
 		return -EINVAL;
 
diff --git a/arch/arm/mach-meson/platsmp.c b/arch/arm/mach-meson/platsmp.c
index 4b8ad728bb42..32ac60b89fdc 100644
--- a/arch/arm/mach-meson/platsmp.c
+++ b/arch/arm/mach-meson/platsmp.c
@@ -71,6 +71,7 @@ static void __init meson_smp_prepare_cpus(const char *scu_compatible,
 	}
 
 	sram_base = of_iomap(node, 0);
+	of_node_put(node);
 	if (!sram_base) {
 		pr_err("Couldn't map SRAM registers\n");
 		return;
@@ -91,6 +92,7 @@ static void __init meson_smp_prepare_cpus(const char *scu_compatible,
 	}
 
 	scu_base = of_iomap(node, 0);
+	of_node_put(node);
 	if (!scu_base) {
 		pr_err("Couldn't map SCU registers\n");
 		return;
diff --git a/arch/arm/mach-omap2/display.c b/arch/arm/mach-omap2/display.c
index 21413a9b7b6c..8d829f3dafe7 100644
--- a/arch/arm/mach-omap2/display.c
+++ b/arch/arm/mach-omap2/display.c
@@ -211,6 +211,7 @@ static int __init omapdss_init_fbdev(void)
 	node = of_find_node_by_name(NULL, "omap4_padconf_global");
 	if (node)
 		omap4_dsi_mux_syscon = syscon_node_to_regmap(node);
+	of_node_put(node);
 
 	return 0;
 }
@@ -259,11 +260,13 @@ static int __init omapdss_init_of(void)
 
 	if (!pdev) {
 		pr_err("Unable to find DSS platform device\n");
+		of_node_put(node);
 		return -ENODEV;
 	}
 
 	r = of_platform_populate(node, NULL, NULL, &pdev->dev);
 	put_device(&pdev->dev);
+	of_node_put(node);
 	if (r) {
 		pr_err("Unable to populate DSS submodule devices\n");
 		return r;
diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c
index 765809b214e7..bf50acd6b8a3 100644
--- a/arch/arm/mach-omap2/pdata-quirks.c
+++ b/arch/arm/mach-omap2/pdata-quirks.c
@@ -587,6 +587,8 @@ pdata_quirks_init_clocks(const struct of_device_id *omap_dt_match_table)
 
 		of_platform_populate(np, omap_dt_match_table,
 				     omap_auxdata_lookup, NULL);
+
+		of_node_put(np);
 	}
 }
 
diff --git a/arch/arm/mach-omap2/prm3xxx.c b/arch/arm/mach-omap2/prm3xxx.c
index 1b442b128569..63e73e9b82bc 100644
--- a/arch/arm/mach-omap2/prm3xxx.c
+++ b/arch/arm/mach-omap2/prm3xxx.c
@@ -708,6 +708,7 @@ static int omap3xxx_prm_late_init(void)
 	}
 
 	irq_num = of_irq_get(np, 0);
+	of_node_put(np);
 	if (irq_num == -EPROBE_DEFER)
 		return irq_num;
 
diff --git a/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c b/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c
index 09ef73b99dd8..ba44cec5e59a 100644
--- a/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c
+++ b/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c
@@ -125,6 +125,7 @@ remove:
 
 	list_for_each_entry_safe(pos, tmp, &quirk_list, list) {
 		list_del(&pos->list);
+		of_node_put(pos->np);
 		kfree(pos);
 	}
 
@@ -174,11 +175,12 @@ static int __init rcar_gen2_regulator_quirk(void)
 		memcpy(&quirk->i2c_msg, id->data, sizeof(quirk->i2c_msg));
 
 		quirk->id = id;
-		quirk->np = np;
+		quirk->np = of_node_get(np);
 		quirk->i2c_msg.addr = addr;
 
 		ret = of_irq_parse_one(np, 0, argsa);
 		if (ret) {	/* Skip invalid entry and continue */
+			of_node_put(np);
 			kfree(quirk);
 			continue;
 		}
@@ -225,6 +227,7 @@ err_free:
 err_mem:
 	list_for_each_entry_safe(pos, tmp, &quirk_list, list) {
 		list_del(&pos->list);
+		of_node_put(pos->np);
 		kfree(pos);
 	}
 
diff --git a/arch/arm/mach-zynq/common.c b/arch/arm/mach-zynq/common.c
index e1ca6a5732d2..15e8a321a713 100644
--- a/arch/arm/mach-zynq/common.c
+++ b/arch/arm/mach-zynq/common.c
@@ -77,6 +77,7 @@ static int __init zynq_get_revision(void)
 	}
 
 	zynq_devcfg_base = of_iomap(np, 0);
+	of_node_put(np);
 	if (!zynq_devcfg_base) {
 		pr_err("%s: Unable to map I/O memory\n", __func__);
 		return -1;
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index ea81e89e7740..bcefe3f51744 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -935,6 +935,9 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	if (type == TYPE_LDST)
 		do_alignment_finish_ldst(addr, instr, regs, offset);
 
+	if (thumb_mode(regs))
+		regs->ARM_cpsr = it_advance(regs->ARM_cpsr);
+
 	return 0;
 
  bad_or_fault:
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 66bba1e2d2b1..b982bab8fff1 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -303,6 +303,13 @@ static struct mem_type mem_types[] __ro_after_init = {
 		.prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_XN,
 		.domain    = DOMAIN_KERNEL,
 	},
+	[MT_MEMORY_RO] = {
+		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
+			     L_PTE_XN | L_PTE_RDONLY,
+		.prot_l1   = PMD_TYPE_TABLE,
+		.prot_sect = PMD_TYPE_SECT,
+		.domain    = DOMAIN_KERNEL,
+	},
 	[MT_ROM] = {
 		.prot_sect = PMD_TYPE_SECT,
 		.domain    = DOMAIN_KERNEL,
@@ -496,6 +503,7 @@ static void __init build_mem_type_table(void)
 
 			/* Also setup NX memory mapping */
 			mem_types[MT_MEMORY_RW].prot_sect |= PMD_SECT_XN;
+			mem_types[MT_MEMORY_RO].prot_sect |= PMD_SECT_XN;
 		}
 		if (cpu_arch >= CPU_ARCH_ARMv7 && (cr & CR_TRE)) {
 			/*
@@ -575,6 +583,7 @@ static void __init build_mem_type_table(void)
 		mem_types[MT_ROM].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE;
 		mem_types[MT_MINICLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE;
 		mem_types[MT_CACHECLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE;
+		mem_types[MT_MEMORY_RO].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE;
 #endif
 
 		/*
@@ -594,6 +603,8 @@ static void __init build_mem_type_table(void)
 			mem_types[MT_MEMORY_RWX].prot_pte |= L_PTE_SHARED;
 			mem_types[MT_MEMORY_RW].prot_sect |= PMD_SECT_S;
 			mem_types[MT_MEMORY_RW].prot_pte |= L_PTE_SHARED;
+			mem_types[MT_MEMORY_RO].prot_sect |= PMD_SECT_S;
+			mem_types[MT_MEMORY_RO].prot_pte |= L_PTE_SHARED;
 			mem_types[MT_MEMORY_DMA_READY].prot_pte |= L_PTE_SHARED;
 			mem_types[MT_MEMORY_RWX_NONCACHED].prot_sect |= PMD_SECT_S;
 			mem_types[MT_MEMORY_RWX_NONCACHED].prot_pte |= L_PTE_SHARED;
@@ -656,6 +667,8 @@ static void __init build_mem_type_table(void)
 	mem_types[MT_MEMORY_RW].prot_sect |= ecc_mask | cp->pmd;
 	mem_types[MT_MEMORY_RW].prot_pte |= kern_pgprot;
 	mem_types[MT_MEMORY_RW_NS].prot_sect |= ecc_mask | cp->pmd;
+	mem_types[MT_MEMORY_RO].prot_sect |= ecc_mask | cp->pmd;
+	mem_types[MT_MEMORY_RO].prot_pte |= kern_pgprot;
 	mem_types[MT_MEMORY_DMA_READY].prot_pte |= kern_pgprot;
 	mem_types[MT_MEMORY_RWX_NONCACHED].prot_sect |= ecc_mask;
 	mem_types[MT_ROM].prot_sect |= cp->pmd;
@@ -1369,7 +1382,7 @@ static void __init devicemaps_init(const struct machine_desc *mdesc)
 		map.pfn = __phys_to_pfn(__atags_pointer & SECTION_MASK);
 		map.virtual = FDT_FIXED_BASE;
 		map.length = FDT_FIXED_SIZE;
-		map.type = MT_ROM;
+		map.type = MT_MEMORY_RO;
 		create_mapping(&map);
 	}
 
diff --git a/arch/arm/mm/proc-v7-bugs.c b/arch/arm/mm/proc-v7-bugs.c
index fb9f3eb6bf48..8bc7a2d6d6c7 100644
--- a/arch/arm/mm/proc-v7-bugs.c
+++ b/arch/arm/mm/proc-v7-bugs.c
@@ -108,8 +108,7 @@ static unsigned int spectre_v2_install_workaround(unsigned int method)
 #else
 static unsigned int spectre_v2_install_workaround(unsigned int method)
 {
-	pr_info("CPU%u: Spectre V2: workarounds disabled by configuration\n",
-		smp_processor_id());
+	pr_info_once("Spectre V2: workarounds disabled by configuration\n");
 
 	return SPECTRE_VULNERABLE;
 }
@@ -209,10 +208,10 @@ static int spectre_bhb_install_workaround(int method)
 			return SPECTRE_VULNERABLE;
 
 		spectre_bhb_method = method;
-	}
 
-	pr_info("CPU%u: Spectre BHB: using %s workaround\n",
-		smp_processor_id(), spectre_bhb_method_name(method));
+		pr_info("CPU%u: Spectre BHB: enabling %s workaround for all CPUs\n",
+			smp_processor_id(), spectre_bhb_method_name(method));
+	}
 
 	return SPECTRE_MITIGATED;
 }
diff --git a/arch/arm/probes/decode.h b/arch/arm/probes/decode.h
index 973173598992..facc889d05ee 100644
--- a/arch/arm/probes/decode.h
+++ b/arch/arm/probes/decode.h
@@ -14,6 +14,7 @@
 #include <linux/types.h>
 #include <linux/stddef.h>
 #include <asm/probes.h>
+#include <asm/ptrace.h>
 #include <asm/kprobes.h>
 
 void __init arm_probes_decode_init(void);
@@ -35,31 +36,6 @@ void __init find_str_pc_offset(void);
 #endif
 
 
-/*
- * Update ITSTATE after normal execution of an IT block instruction.
- *
- * The 8 IT state bits are split into two parts in CPSR:
- *	ITSTATE<1:0> are in CPSR<26:25>
- *	ITSTATE<7:2> are in CPSR<15:10>
- */
-static inline unsigned long it_advance(unsigned long cpsr)
-	{
-	if ((cpsr & 0x06000400) == 0) {
-		/* ITSTATE<2:0> == 0 means end of IT block, so clear IT state */
-		cpsr &= ~PSR_IT_MASK;
-	} else {
-		/* We need to shift left ITSTATE<4:0> */
-		const unsigned long mask = 0x06001c00;  /* Mask ITSTATE<4:0> */
-		unsigned long it = cpsr & mask;
-		it <<= 1;
-		it |= it >> (27 - 10);  /* Carry ITSTATE<2> to correct place */
-		it &= mask;
-		cpsr &= ~mask;
-		cpsr |= it;
-	}
-	return cpsr;
-}
-
 static inline void __kprobes bx_write_pc(long pcv, struct pt_regs *regs)
 {
 	long cpsr = regs->ARM_cpsr;
diff --git a/arch/arm/xen/p2m.c b/arch/arm/xen/p2m.c
index 84a1cea1f43b..309648c17f48 100644
--- a/arch/arm/xen/p2m.c
+++ b/arch/arm/xen/p2m.c
@@ -63,11 +63,12 @@ out:
 
 unsigned long __pfn_to_mfn(unsigned long pfn)
 {
-	struct rb_node *n = phys_to_mach.rb_node;
+	struct rb_node *n;
 	struct xen_p2m_entry *entry;
 	unsigned long irqflags;
 
 	read_lock_irqsave(&p2m_lock, irqflags);
+	n = phys_to_mach.rb_node;
 	while (n) {
 		entry = rb_entry(n, struct xen_p2m_entry, rbnode_phys);
 		if (entry->pfn <= pfn &&
@@ -152,10 +153,11 @@ bool __set_phys_to_machine_multi(unsigned long pfn,
 	int rc;
 	unsigned long irqflags;
 	struct xen_p2m_entry *p2m_entry;
-	struct rb_node *n = phys_to_mach.rb_node;
+	struct rb_node *n;
 
 	if (mfn == INVALID_P2M_ENTRY) {
 		write_lock_irqsave(&p2m_lock, irqflags);
+		n = phys_to_mach.rb_node;
 		while (n) {
 			p2m_entry = rb_entry(n, struct xen_p2m_entry, rbnode_phys);
 			if (p2m_entry->pfn <= pfn &&
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 972ae8d50b8c..5688854e1540 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -220,6 +220,7 @@ config ARM64
 	select THREAD_INFO_IN_TASK
 	select HAVE_ARCH_USERFAULTFD_MINOR if USERFAULTFD
 	select TRACE_IRQFLAGS_SUPPORT
+	select TRACE_IRQFLAGS_NMI_SUPPORT
 	help
 	  ARM 64-bit (AArch64) Linux support.
 
@@ -665,6 +666,40 @@ config ARM64_ERRATUM_1508412
 
 	  If unsure, say Y.
 
+config ARM64_ERRATUM_2441009
+	bool "Cortex-A510: Completion of affected memory accesses might not be guaranteed by completion of a TLBI"
+	default y
+	select ARM64_WORKAROUND_REPEAT_TLBI
+	help
+	  This option adds a workaround for ARM Cortex-A510 erratum #2441009.
+
+	  Under very rare circumstances, affected Cortex-A510 CPUs
+	  may not handle a race between a break-before-make sequence on one
+	  CPU, and another CPU accessing the same page. This could allow a
+	  store to a page that has been unmapped.
+
+	  Work around this by adding the affected CPUs to the list that needs
+	  TLB sequences to be done twice.
+
+	  If unsure, say Y.
+
+config ARM64_ERRATUM_2457168
+	bool "Cortex-A510: 2457168: workaround for AMEVCNTR01 incrementing incorrectly"
+	depends on ARM64_AMU_EXTN
+	default y
+	help
+	  This option adds the workaround for ARM Cortex-A510 erratum 2457168.
+
+	  The AMU counter AMEVCNTR01 (constant counter) should increment at the same rate
+	  as the system counter. On affected Cortex-A510 cores AMEVCNTR01 increments
+	  incorrectly giving a significantly higher output value.
+
+	  Work around this problem by returning 0 when reading the affected counter in
+	  key locations that results in disabling all users of this counter. This effect
+	  is the same to firmware disabling affected counters.
+
+	  If unsure, say Y.
+
 config CAVIUM_ERRATUM_22375
 	bool "Cavium erratum 22375, 24313"
 	default y
@@ -1608,6 +1643,8 @@ config ARM64_BTI_KERNEL
 	depends on CC_HAS_BRANCH_PROT_PAC_RET_BTI
 	# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94697
 	depends on !CC_IS_GCC || GCC_VERSION >= 100100
+	# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106671
+	depends on !CC_IS_GCC
 	# https://github.com/llvm/llvm-project/commit/a88c722e687e6780dcd6a58718350dc76fcc4cc9
 	depends on !CC_IS_CLANG || CLANG_VERSION >= 120000
 	depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_REGS)
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts
index 097a5511523a..09eee653d5ca 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts
@@ -40,7 +40,7 @@
 	leds {
 		compatible = "gpio-leds";
 
-		status {
+		led-0 {
 			label = "orangepi:green:status";
 			gpios = <&pio 7 11 GPIO_ACTIVE_HIGH>; /* PH11 */
 		};
diff --git a/arch/arm64/boot/dts/arm/juno-base.dtsi b/arch/arm64/boot/dts/arm/juno-base.dtsi
index a2635b14da30..34e5549ea748 100644
--- a/arch/arm64/boot/dts/arm/juno-base.dtsi
+++ b/arch/arm64/boot/dts/arm/juno-base.dtsi
@@ -26,7 +26,8 @@
 		compatible = "arm,mhu", "arm,primecell";
 		reg = <0x0 0x2b1f0000 0x0 0x1000>;
 		interrupts = <GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>;
+			     <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>;
 		#mbox-cells = <1>;
 		clocks = <&soc_refclk100mhz>;
 		clock-names = "apb_pclk";
diff --git a/arch/arm64/boot/dts/broadcom/bcm4908/bcm4906.dtsi b/arch/arm64/boot/dts/broadcom/bcm4908/bcm4906.dtsi
index 66023d553524..d084c33d5ca8 100644
--- a/arch/arm64/boot/dts/broadcom/bcm4908/bcm4906.dtsi
+++ b/arch/arm64/boot/dts/broadcom/bcm4908/bcm4906.dtsi
@@ -9,6 +9,14 @@
 		/delete-node/ cpu@3;
 	};
 
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>;
+	};
+
 	pmu {
 		compatible = "arm,cortex-a53-pmu";
 		interrupts = <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/arch/arm64/boot/dts/broadcom/bcm4908/bcm4908.dtsi b/arch/arm64/boot/dts/broadcom/bcm4908/bcm4908.dtsi
index e8907d3fe2d1..e510a6961cf9 100644
--- a/arch/arm64/boot/dts/broadcom/bcm4908/bcm4908.dtsi
+++ b/arch/arm64/boot/dts/broadcom/bcm4908/bcm4908.dtsi
@@ -29,6 +29,8 @@
 			device_type = "cpu";
 			compatible = "brcm,brahma-b53";
 			reg = <0x0>;
+			enable-method = "spin-table";
+			cpu-release-addr = <0x0 0xfff8>;
 			next-level-cache = <&l2>;
 		};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-evk.dts b/arch/arm64/boot/dts/freescale/imx8mp-evk.dts
index 03783ece0fcb..b354490ea775 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-evk.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-evk.dts
@@ -961,21 +961,21 @@
 
 	pinctrl_eqos: eqosgrp {
 		fsl,pins = <
-			MX8MP_IOMUXC_ENET_MDC__ENET_QOS_MDC				0x3
-			MX8MP_IOMUXC_ENET_MDIO__ENET_QOS_MDIO				0x3
-			MX8MP_IOMUXC_ENET_RD0__ENET_QOS_RGMII_RD0			0x91
-			MX8MP_IOMUXC_ENET_RD1__ENET_QOS_RGMII_RD1			0x91
-			MX8MP_IOMUXC_ENET_RD2__ENET_QOS_RGMII_RD2			0x91
-			MX8MP_IOMUXC_ENET_RD3__ENET_QOS_RGMII_RD3			0x91
-			MX8MP_IOMUXC_ENET_RXC__CCM_ENET_QOS_CLOCK_GENERATE_RX_CLK	0x91
-			MX8MP_IOMUXC_ENET_RX_CTL__ENET_QOS_RGMII_RX_CTL			0x91
-			MX8MP_IOMUXC_ENET_TD0__ENET_QOS_RGMII_TD0			0x1f
-			MX8MP_IOMUXC_ENET_TD1__ENET_QOS_RGMII_TD1			0x1f
-			MX8MP_IOMUXC_ENET_TD2__ENET_QOS_RGMII_TD2			0x1f
-			MX8MP_IOMUXC_ENET_TD3__ENET_QOS_RGMII_TD3			0x1f
-			MX8MP_IOMUXC_ENET_TX_CTL__ENET_QOS_RGMII_TX_CTL			0x1f
-			MX8MP_IOMUXC_ENET_TXC__CCM_ENET_QOS_CLOCK_GENERATE_TX_CLK	0x1f
-			MX8MP_IOMUXC_SAI2_RXC__GPIO4_IO22				0x19
+			MX8MP_IOMUXC_ENET_MDC__ENET_QOS_MDC				0x2
+			MX8MP_IOMUXC_ENET_MDIO__ENET_QOS_MDIO				0x2
+			MX8MP_IOMUXC_ENET_RD0__ENET_QOS_RGMII_RD0			0x90
+			MX8MP_IOMUXC_ENET_RD1__ENET_QOS_RGMII_RD1			0x90
+			MX8MP_IOMUXC_ENET_RD2__ENET_QOS_RGMII_RD2			0x90
+			MX8MP_IOMUXC_ENET_RD3__ENET_QOS_RGMII_RD3			0x90
+			MX8MP_IOMUXC_ENET_RXC__CCM_ENET_QOS_CLOCK_GENERATE_RX_CLK	0x90
+			MX8MP_IOMUXC_ENET_RX_CTL__ENET_QOS_RGMII_RX_CTL			0x90
+			MX8MP_IOMUXC_ENET_TD0__ENET_QOS_RGMII_TD0			0x16
+			MX8MP_IOMUXC_ENET_TD1__ENET_QOS_RGMII_TD1			0x16
+			MX8MP_IOMUXC_ENET_TD2__ENET_QOS_RGMII_TD2			0x16
+			MX8MP_IOMUXC_ENET_TD3__ENET_QOS_RGMII_TD3			0x16
+			MX8MP_IOMUXC_ENET_TX_CTL__ENET_QOS_RGMII_TX_CTL			0x16
+			MX8MP_IOMUXC_ENET_TXC__CCM_ENET_QOS_CLOCK_GENERATE_TX_CLK	0x16
+			MX8MP_IOMUXC_SAI2_RXC__GPIO4_IO22				0x10
 		>;
 	};
 
@@ -1038,7 +1038,7 @@
 
 	pinctrl_gpio_led: gpioledgrp {
 		fsl,pins = <
-			MX8MP_IOMUXC_NAND_READY_B__GPIO3_IO16	0x19
+			MX8MP_IOMUXC_NAND_READY_B__GPIO3_IO16	0x140
 		>;
 	};
 
@@ -1086,7 +1086,7 @@
 
 	pinctrl_reg_usdhc2_vmmc: regusdhc2vmmcgrp {
 		fsl,pins = <
-			MX8MP_IOMUXC_SD2_RESET_B__GPIO2_IO19	0x41
+			MX8MP_IOMUXC_SD2_RESET_B__GPIO2_IO19	0x40
 		>;
 	};
 
@@ -1178,7 +1178,7 @@
 			MX8MP_IOMUXC_SD2_DATA1__USDHC2_DATA1	0x1d0
 			MX8MP_IOMUXC_SD2_DATA2__USDHC2_DATA2	0x1d0
 			MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3	0x1d0
-			MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT	0xc1
+			MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT	0xc0
 		>;
 	};
 
@@ -1190,7 +1190,7 @@
 			MX8MP_IOMUXC_SD2_DATA1__USDHC2_DATA1	0x1d4
 			MX8MP_IOMUXC_SD2_DATA2__USDHC2_DATA2	0x1d4
 			MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3	0x1d4
-			MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT 0xc1
+			MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT 0xc0
 		>;
 	};
 
@@ -1202,7 +1202,7 @@
 			MX8MP_IOMUXC_SD2_DATA1__USDHC2_DATA1	0x1d6
 			MX8MP_IOMUXC_SD2_DATA2__USDHC2_DATA2	0x1d6
 			MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3	0x1d6
-			MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT 0xc1
+			MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT 0xc0
 		>;
 	};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts b/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts
index 984a6b9ded8d..6aa720bafe28 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts
@@ -116,48 +116,48 @@
 &iomuxc {
 	pinctrl_eqos: eqosgrp {
 		fsl,pins = <
-			MX8MP_IOMUXC_ENET_MDC__ENET_QOS_MDC			0x3
-			MX8MP_IOMUXC_ENET_MDIO__ENET_QOS_MDIO			0x3
-			MX8MP_IOMUXC_ENET_RD0__ENET_QOS_RGMII_RD0		0x91
-			MX8MP_IOMUXC_ENET_RD1__ENET_QOS_RGMII_RD1		0x91
-			MX8MP_IOMUXC_ENET_RD2__ENET_QOS_RGMII_RD2		0x91
-			MX8MP_IOMUXC_ENET_RD3__ENET_QOS_RGMII_RD3		0x91
-			MX8MP_IOMUXC_ENET_RXC__CCM_ENET_QOS_CLOCK_GENERATE_RX_CLK	0x91
-			MX8MP_IOMUXC_ENET_RX_CTL__ENET_QOS_RGMII_RX_CTL		0x91
-			MX8MP_IOMUXC_ENET_TD0__ENET_QOS_RGMII_TD0		0x1f
-			MX8MP_IOMUXC_ENET_TD1__ENET_QOS_RGMII_TD1		0x1f
-			MX8MP_IOMUXC_ENET_TD2__ENET_QOS_RGMII_TD2		0x1f
-			MX8MP_IOMUXC_ENET_TD3__ENET_QOS_RGMII_TD3		0x1f
-			MX8MP_IOMUXC_ENET_TX_CTL__ENET_QOS_RGMII_TX_CTL		0x1f
-			MX8MP_IOMUXC_ENET_TXC__CCM_ENET_QOS_CLOCK_GENERATE_TX_CLK	0x1f
+			MX8MP_IOMUXC_ENET_MDC__ENET_QOS_MDC			0x2
+			MX8MP_IOMUXC_ENET_MDIO__ENET_QOS_MDIO			0x2
+			MX8MP_IOMUXC_ENET_RD0__ENET_QOS_RGMII_RD0		0x90
+			MX8MP_IOMUXC_ENET_RD1__ENET_QOS_RGMII_RD1		0x90
+			MX8MP_IOMUXC_ENET_RD2__ENET_QOS_RGMII_RD2		0x90
+			MX8MP_IOMUXC_ENET_RD3__ENET_QOS_RGMII_RD3		0x90
+			MX8MP_IOMUXC_ENET_RXC__CCM_ENET_QOS_CLOCK_GENERATE_RX_CLK	0x90
+			MX8MP_IOMUXC_ENET_RX_CTL__ENET_QOS_RGMII_RX_CTL		0x90
+			MX8MP_IOMUXC_ENET_TD0__ENET_QOS_RGMII_TD0		0x16
+			MX8MP_IOMUXC_ENET_TD1__ENET_QOS_RGMII_TD1		0x16
+			MX8MP_IOMUXC_ENET_TD2__ENET_QOS_RGMII_TD2		0x16
+			MX8MP_IOMUXC_ENET_TD3__ENET_QOS_RGMII_TD3		0x16
+			MX8MP_IOMUXC_ENET_TX_CTL__ENET_QOS_RGMII_TX_CTL		0x16
+			MX8MP_IOMUXC_ENET_TXC__CCM_ENET_QOS_CLOCK_GENERATE_TX_CLK	0x16
 			MX8MP_IOMUXC_SAI1_MCLK__GPIO4_IO20			0x10
 		>;
 	};
 
 	pinctrl_i2c2: i2c2grp {
 		fsl,pins = <
-			MX8MP_IOMUXC_I2C2_SCL__I2C2_SCL		0x400001c3
-			MX8MP_IOMUXC_I2C2_SDA__I2C2_SDA		0x400001c3
+			MX8MP_IOMUXC_I2C2_SCL__I2C2_SCL		0x400001c2
+			MX8MP_IOMUXC_I2C2_SDA__I2C2_SDA		0x400001c2
 		>;
 	};
 
 	pinctrl_i2c2_gpio: i2c2gpiogrp {
 		fsl,pins = <
-			MX8MP_IOMUXC_I2C2_SCL__GPIO5_IO16	0x1e3
-			MX8MP_IOMUXC_I2C2_SDA__GPIO5_IO17	0x1e3
+			MX8MP_IOMUXC_I2C2_SCL__GPIO5_IO16	0x1e2
+			MX8MP_IOMUXC_I2C2_SDA__GPIO5_IO17	0x1e2
 		>;
 	};
 
 	pinctrl_reg_usdhc2_vmmc: regusdhc2vmmcgrp {
 		fsl,pins = <
-			MX8MP_IOMUXC_SD2_RESET_B__GPIO2_IO19	0x41
+			MX8MP_IOMUXC_SD2_RESET_B__GPIO2_IO19	0x40
 		>;
 	};
 
 	pinctrl_uart1: uart1grp {
 		fsl,pins = <
-			MX8MP_IOMUXC_UART1_RXD__UART1_DCE_RX	0x49
-			MX8MP_IOMUXC_UART1_TXD__UART1_DCE_TX	0x49
+			MX8MP_IOMUXC_UART1_RXD__UART1_DCE_RX	0x40
+			MX8MP_IOMUXC_UART1_TXD__UART1_DCE_TX	0x40
 		>;
 	};
 
@@ -175,7 +175,7 @@
 			MX8MP_IOMUXC_SD2_DATA1__USDHC2_DATA1	0x1d0
 			MX8MP_IOMUXC_SD2_DATA2__USDHC2_DATA2	0x1d0
 			MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3	0x1d0
-			MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT	0xc1
+			MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT	0xc0
 		>;
 	};
 
@@ -187,7 +187,7 @@
 			MX8MP_IOMUXC_SD2_DATA1__USDHC2_DATA1	0x1d4
 			MX8MP_IOMUXC_SD2_DATA2__USDHC2_DATA2	0x1d4
 			MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3	0x1d4
-			MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT	0xc1
+			MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT	0xc0
 		>;
 	};
 
@@ -199,7 +199,7 @@
 			MX8MP_IOMUXC_SD2_DATA1__USDHC2_DATA1	0x1d6
 			MX8MP_IOMUXC_SD2_DATA2__USDHC2_DATA2	0x1d6
 			MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3	0x1d6
-			MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT	0xc1
+			MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT	0xc0
 		>;
 	};
 };
diff --git a/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts b/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts
index 2f77dc40b9b8..6b99d903b479 100644
--- a/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts
+++ b/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts
@@ -49,7 +49,7 @@
 		wps {
 			label = "wps";
 			linux,code = <KEY_WPS_BUTTON>;
-			gpios = <&pio 102 GPIO_ACTIVE_HIGH>;
+			gpios = <&pio 102 GPIO_ACTIVE_LOW>;
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/mediatek/mt8192.dtsi b/arch/arm64/boot/dts/mediatek/mt8192.dtsi
index cb1e46d2c1ba..d1e63527b387 100644
--- a/arch/arm64/boot/dts/mediatek/mt8192.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8192.dtsi
@@ -39,7 +39,7 @@
 			reg = <0x000>;
 			enable-method = "psci";
 			clock-frequency = <1701000000>;
-			cpu-idle-states = <&cpuoff_l &clusteroff_l>;
+			cpu-idle-states = <&cpu_sleep_l &cluster_sleep_l>;
 			next-level-cache = <&l2_0>;
 			capacity-dmips-mhz = <530>;
 		};
@@ -50,7 +50,7 @@
 			reg = <0x100>;
 			enable-method = "psci";
 			clock-frequency = <1701000000>;
-			cpu-idle-states = <&cpuoff_l &clusteroff_l>;
+			cpu-idle-states = <&cpu_sleep_l &cluster_sleep_l>;
 			next-level-cache = <&l2_0>;
 			capacity-dmips-mhz = <530>;
 		};
@@ -61,7 +61,7 @@
 			reg = <0x200>;
 			enable-method = "psci";
 			clock-frequency = <1701000000>;
-			cpu-idle-states = <&cpuoff_l &clusteroff_l>;
+			cpu-idle-states = <&cpu_sleep_l &cluster_sleep_l>;
 			next-level-cache = <&l2_0>;
 			capacity-dmips-mhz = <530>;
 		};
@@ -72,7 +72,7 @@
 			reg = <0x300>;
 			enable-method = "psci";
 			clock-frequency = <1701000000>;
-			cpu-idle-states = <&cpuoff_l &clusteroff_l>;
+			cpu-idle-states = <&cpu_sleep_l &cluster_sleep_l>;
 			next-level-cache = <&l2_0>;
 			capacity-dmips-mhz = <530>;
 		};
@@ -83,7 +83,7 @@
 			reg = <0x400>;
 			enable-method = "psci";
 			clock-frequency = <2171000000>;
-			cpu-idle-states = <&cpuoff_b &clusteroff_b>;
+			cpu-idle-states = <&cpu_sleep_b &cluster_sleep_b>;
 			next-level-cache = <&l2_1>;
 			capacity-dmips-mhz = <1024>;
 		};
@@ -94,7 +94,7 @@
 			reg = <0x500>;
 			enable-method = "psci";
 			clock-frequency = <2171000000>;
-			cpu-idle-states = <&cpuoff_b &clusteroff_b>;
+			cpu-idle-states = <&cpu_sleep_b &cluster_sleep_b>;
 			next-level-cache = <&l2_1>;
 			capacity-dmips-mhz = <1024>;
 		};
@@ -105,7 +105,7 @@
 			reg = <0x600>;
 			enable-method = "psci";
 			clock-frequency = <2171000000>;
-			cpu-idle-states = <&cpuoff_b &clusteroff_b>;
+			cpu-idle-states = <&cpu_sleep_b &cluster_sleep_b>;
 			next-level-cache = <&l2_1>;
 			capacity-dmips-mhz = <1024>;
 		};
@@ -116,7 +116,7 @@
 			reg = <0x700>;
 			enable-method = "psci";
 			clock-frequency = <2171000000>;
-			cpu-idle-states = <&cpuoff_b &clusteroff_b>;
+			cpu-idle-states = <&cpu_sleep_b &cluster_sleep_b>;
 			next-level-cache = <&l2_1>;
 			capacity-dmips-mhz = <1024>;
 		};
@@ -168,8 +168,8 @@
 		};
 
 		idle-states {
-			entry-method = "arm,psci";
-			cpuoff_l: cpuoff_l {
+			entry-method = "psci";
+			cpu_sleep_l: cpu-sleep-l {
 				compatible = "arm,idle-state";
 				arm,psci-suspend-param = <0x00010001>;
 				local-timer-stop;
@@ -177,7 +177,7 @@
 				exit-latency-us = <140>;
 				min-residency-us = <780>;
 			};
-			cpuoff_b: cpuoff_b {
+			cpu_sleep_b: cpu-sleep-b {
 				compatible = "arm,idle-state";
 				arm,psci-suspend-param = <0x00010001>;
 				local-timer-stop;
@@ -185,7 +185,7 @@
 				exit-latency-us = <145>;
 				min-residency-us = <720>;
 			};
-			clusteroff_l: clusteroff_l {
+			cluster_sleep_l: cluster-sleep-l {
 				compatible = "arm,idle-state";
 				arm,psci-suspend-param = <0x01010002>;
 				local-timer-stop;
@@ -193,7 +193,7 @@
 				exit-latency-us = <155>;
 				min-residency-us = <860>;
 			};
-			clusteroff_b: clusteroff_b {
+			cluster_sleep_b: cluster-sleep-b {
 				compatible = "arm,idle-state";
 				arm,psci-suspend-param = <0x01010002>;
 				local-timer-stop;
diff --git a/arch/arm64/boot/dts/nvidia/tegra186.dtsi b/arch/arm64/boot/dts/nvidia/tegra186.dtsi
index 062e87e89331..5b0bc9aa1a42 100644
--- a/arch/arm64/boot/dts/nvidia/tegra186.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra186.dtsi
@@ -1583,6 +1583,7 @@
 		#address-cells = <1>;
 		#size-cells = <1>;
 		ranges = <0x0 0x0 0x30000000 0x50000>;
+		no-memory-wc;
 
 		cpu_bpmp_tx: sram@4e000 {
 			reg = <0x4e000 0x1000>;
@@ -1635,7 +1636,7 @@
 		iommus = <&smmu TEGRA186_SID_BPMP>;
 		mboxes = <&hsp_top0 TEGRA_HSP_MBOX_TYPE_DB
 				    TEGRA_HSP_DB_MASTER_BPMP>;
-		shmem = <&cpu_bpmp_tx &cpu_bpmp_rx>;
+		shmem = <&cpu_bpmp_tx>, <&cpu_bpmp_rx>;
 		#clock-cells = <1>;
 		#reset-cells = <1>;
 		#power-domain-cells = <1>;
diff --git a/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi b/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi
index c4058ee36fec..1a444705517f 100644
--- a/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi
@@ -75,7 +75,7 @@
 
 		/* SDMMC1 (SD/MMC) */
 		mmc@3400000 {
-			cd-gpios = <&gpio TEGRA194_MAIN_GPIO(A, 0) GPIO_ACTIVE_LOW>;
+			cd-gpios = <&gpio TEGRA194_MAIN_GPIO(G, 7) GPIO_ACTIVE_LOW>;
 		};
 
 		/* SDMMC4 (eMMC) */
diff --git a/arch/arm64/boot/dts/nvidia/tegra194.dtsi b/arch/arm64/boot/dts/nvidia/tegra194.dtsi
index 510d2974470c..ca71b71d801a 100644
--- a/arch/arm64/boot/dts/nvidia/tegra194.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra194.dtsi
@@ -2249,6 +2249,7 @@
 		#address-cells = <1>;
 		#size-cells = <1>;
 		ranges = <0x0 0x0 0x40000000 0x50000>;
+		no-memory-wc;
 
 		cpu_bpmp_tx: sram@4e000 {
 			reg = <0x4e000 0x1000>;
@@ -2267,7 +2268,7 @@
 		compatible = "nvidia,tegra186-bpmp";
 		mboxes = <&hsp_top0 TEGRA_HSP_MBOX_TYPE_DB
 				    TEGRA_HSP_DB_MASTER_BPMP>;
-		shmem = <&cpu_bpmp_tx &cpu_bpmp_rx>;
+		shmem = <&cpu_bpmp_tx>, <&cpu_bpmp_rx>;
 		#clock-cells = <1>;
 		#reset-cells = <1>;
 		#power-domain-cells = <1>;
diff --git a/arch/arm64/boot/dts/nvidia/tegra234.dtsi b/arch/arm64/boot/dts/nvidia/tegra234.dtsi
index f0efb3a62804..2b4784572220 100644
--- a/arch/arm64/boot/dts/nvidia/tegra234.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra234.dtsi
@@ -122,21 +122,22 @@
 		};
 	};
 
-	sysram@40000000 {
+	sram@40000000 {
 		compatible = "nvidia,tegra234-sysram", "mmio-sram";
-		reg = <0x0 0x40000000 0x0 0x50000>;
+		reg = <0x0 0x40000000 0x0 0x80000>;
 		#address-cells = <1>;
 		#size-cells = <1>;
-		ranges = <0x0 0x0 0x40000000 0x50000>;
+		ranges = <0x0 0x0 0x40000000 0x80000>;
+		no-memory-wc;
 
-		cpu_bpmp_tx: shmem@4e000 {
-			reg = <0x4e000 0x1000>;
+		cpu_bpmp_tx: sram@70000 {
+			reg = <0x70000 0x1000>;
 			label = "cpu-bpmp-tx";
 			pool;
 		};
 
-		cpu_bpmp_rx: shmem@4f000 {
-			reg = <0x4f000 0x1000>;
+		cpu_bpmp_rx: sram@71000 {
+			reg = <0x71000 0x1000>;
 			label = "cpu-bpmp-rx";
 			pool;
 		};
@@ -146,7 +147,7 @@
 		compatible = "nvidia,tegra234-bpmp", "nvidia,tegra186-bpmp";
 		mboxes = <&hsp_top0 TEGRA_HSP_MBOX_TYPE_DB
 				    TEGRA_HSP_DB_MASTER_BPMP>;
-		shmem = <&cpu_bpmp_tx &cpu_bpmp_rx>;
+		shmem = <&cpu_bpmp_tx>, <&cpu_bpmp_rx>;
 		#clock-cells = <1>;
 		#reset-cells = <1>;
 		#power-domain-cells = <1>;
diff --git a/arch/arm64/boot/dts/qcom/ipq8074.dtsi b/arch/arm64/boot/dts/qcom/ipq8074.dtsi
index fea415302408..6b9ac0550490 100644
--- a/arch/arm64/boot/dts/qcom/ipq8074.dtsi
+++ b/arch/arm64/boot/dts/qcom/ipq8074.dtsi
@@ -437,7 +437,7 @@
 			status = "disabled";
 		};
 
-		qpic_nand: nand@79b0000 {
+		qpic_nand: nand-controller@79b0000 {
 			compatible = "qcom,ipq8074-nand";
 			reg = <0x079b0000 0x10000>;
 			#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/qcom/msm8916.dtsi b/arch/arm64/boot/dts/qcom/msm8916.dtsi
index 8b2724272464..19e201f52b16 100644
--- a/arch/arm64/boot/dts/qcom/msm8916.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8916.dtsi
@@ -1747,8 +1747,8 @@
 					<&rpmpd MSM8916_VDDMX>;
 			power-domain-names = "cx", "mx";
 
-			qcom,state = <&wcnss_smp2p_out 0>;
-			qcom,state-names = "stop";
+			qcom,smem-states = <&wcnss_smp2p_out 0>;
+			qcom,smem-state-names = "stop";
 
 			pinctrl-names = "default";
 			pinctrl-0 = <&wcnss_pin_a>;
diff --git a/arch/arm64/boot/dts/qcom/msm8992-bullhead-rev-101.dts b/arch/arm64/boot/dts/qcom/msm8992-bullhead-rev-101.dts
index 1ccca83292ac..c7d191dc6d4b 100644
--- a/arch/arm64/boot/dts/qcom/msm8992-bullhead-rev-101.dts
+++ b/arch/arm64/boot/dts/qcom/msm8992-bullhead-rev-101.dts
@@ -74,7 +74,7 @@
 		vdd_l17_29-supply = <&vph_pwr>;
 		vdd_l20_21-supply = <&vph_pwr>;
 		vdd_l25-supply = <&pm8994_s5>;
-		vdd_lvs1_2 = <&pm8994_s4>;
+		vdd_lvs1_2-supply = <&pm8994_s4>;
 
 		/* S1, S2, S6 and S12 are managed by RPMPD */
 
diff --git a/arch/arm64/boot/dts/qcom/msm8992-xiaomi-libra.dts b/arch/arm64/boot/dts/qcom/msm8992-xiaomi-libra.dts
index 357d55496e75..a3d6340a0c55 100644
--- a/arch/arm64/boot/dts/qcom/msm8992-xiaomi-libra.dts
+++ b/arch/arm64/boot/dts/qcom/msm8992-xiaomi-libra.dts
@@ -142,7 +142,7 @@
 		vdd_l17_29-supply = <&vph_pwr>;
 		vdd_l20_21-supply = <&vph_pwr>;
 		vdd_l25-supply = <&pm8994_s5>;
-		vdd_lvs1_2 = <&pm8994_s4>;
+		vdd_lvs1_2-supply = <&pm8994_s4>;
 
 		/* S1, S2, S6 and S12 are managed by RPMPD */
 
diff --git a/arch/arm64/boot/dts/qcom/msm8994.dtsi b/arch/arm64/boot/dts/qcom/msm8994.dtsi
index 3c27671c8b5c..a8dc8163ee82 100644
--- a/arch/arm64/boot/dts/qcom/msm8994.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8994.dtsi
@@ -93,7 +93,7 @@
 		CPU6: cpu@102 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a57";
-			reg = <0x0 0x101>;
+			reg = <0x0 0x102>;
 			enable-method = "psci";
 			next-level-cache = <&L2_1>;
 		};
@@ -101,7 +101,7 @@
 		CPU7: cpu@103 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a57";
-			reg = <0x0 0x101>;
+			reg = <0x0 0x103>;
 			enable-method = "psci";
 			next-level-cache = <&L2_1>;
 		};
diff --git a/arch/arm64/boot/dts/qcom/qcs404.dtsi b/arch/arm64/boot/dts/qcom/qcs404.dtsi
index ca5be1647980..18cc8e3bc93a 100644
--- a/arch/arm64/boot/dts/qcom/qcs404.dtsi
+++ b/arch/arm64/boot/dts/qcom/qcs404.dtsi
@@ -548,7 +548,7 @@
 				compatible = "snps,dwc3";
 				reg = <0x07580000 0xcd00>;
 				interrupts = <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>;
-				phys = <&usb2_phy_sec>, <&usb3_phy>;
+				phys = <&usb2_phy_prim>, <&usb3_phy>;
 				phy-names = "usb2-phy", "usb3-phy";
 				snps,has-lpm-erratum;
 				snps,hird-threshold = /bits/ 8 <0x10>;
@@ -577,7 +577,7 @@
 				compatible = "snps,dwc3";
 				reg = <0x078c0000 0xcc00>;
 				interrupts = <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>;
-				phys = <&usb2_phy_prim>;
+				phys = <&usb2_phy_sec>;
 				phy-names = "usb2-phy";
 				snps,has-lpm-erratum;
 				snps,hird-threshold = /bits/ 8 <0x10>;
diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi
index 70c88c37de32..a9d36ac6cb90 100644
--- a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi
@@ -42,6 +42,7 @@
  */
 
 /delete-node/ &hyp_mem;
+/delete-node/ &ipa_fw_mem;
 /delete-node/ &xbl_mem;
 /delete-node/ &aop_mem;
 /delete-node/ &sec_apps_mem;
diff --git a/arch/arm64/boot/dts/qcom/sdm630.dtsi b/arch/arm64/boot/dts/qcom/sdm630.dtsi
index a8724fd60645..952bb133914f 100644
--- a/arch/arm64/boot/dts/qcom/sdm630.dtsi
+++ b/arch/arm64/boot/dts/qcom/sdm630.dtsi
@@ -8,6 +8,7 @@
 #include <dt-bindings/clock/qcom,gpucc-sdm660.h>
 #include <dt-bindings/clock/qcom,mmcc-sdm660.h>
 #include <dt-bindings/clock/qcom,rpmcc.h>
+#include <dt-bindings/interconnect/qcom,sdm660.h>
 #include <dt-bindings/power/qcom-rpmpd.h>
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
@@ -1041,11 +1042,13 @@
 			nvmem-cells = <&gpu_speed_bin>;
 			nvmem-cell-names = "speed_bin";
 
-			interconnects = <&gnoc 1 &bimc 5>;
+			interconnects = <&bimc MASTER_OXILI &bimc SLAVE_EBI>;
 			interconnect-names = "gfx-mem";
 
 			operating-points-v2 = <&gpu_sdm630_opp_table>;
 
+			status = "disabled";
+
 			gpu_sdm630_opp_table: opp-table {
 				compatible  = "operating-points-v2";
 				opp-775000000 {
@@ -1251,7 +1254,7 @@
 			#phy-cells = <0>;
 
 			clocks = <&gcc GCC_USB_PHY_CFG_AHB2PHY_CLK>,
-				<&gcc GCC_RX1_USB2_CLKREF_CLK>;
+				 <&gcc GCC_RX0_USB2_CLKREF_CLK>;
 			clock-names = "cfg_ahb", "ref";
 
 			resets = <&gcc GCC_QUSB2PHY_PRIM_BCR>;
diff --git a/arch/arm64/boot/dts/qcom/sdm636-sony-xperia-ganges-mermaid.dts b/arch/arm64/boot/dts/qcom/sdm636-sony-xperia-ganges-mermaid.dts
index bba1c2bce213..0afe9eee025e 100644
--- a/arch/arm64/boot/dts/qcom/sdm636-sony-xperia-ganges-mermaid.dts
+++ b/arch/arm64/boot/dts/qcom/sdm636-sony-xperia-ganges-mermaid.dts
@@ -18,7 +18,7 @@
 };
 
 &sdc2_state_on {
-	pinconf-clk {
+	clk {
 		drive-strength = <14>;
 	};
 };
diff --git a/arch/arm64/boot/dts/qcom/sdm845.dtsi b/arch/arm64/boot/dts/qcom/sdm845.dtsi
index d20eacfc1017..ea7a272d267a 100644
--- a/arch/arm64/boot/dts/qcom/sdm845.dtsi
+++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi
@@ -4147,7 +4147,7 @@
 
 			power-domains = <&dispcc MDSS_GDSC>;
 
-			clocks = <&gcc GCC_DISP_AHB_CLK>,
+			clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>,
 				 <&dispcc DISP_CC_MDSS_MDP_CLK>;
 			clock-names = "iface", "core";
 
diff --git a/arch/arm64/boot/dts/qcom/sm6125-sony-xperia-seine-pdx201.dts b/arch/arm64/boot/dts/qcom/sm6125-sony-xperia-seine-pdx201.dts
index 58b6b2742d3f..47f8e5397ebb 100644
--- a/arch/arm64/boot/dts/qcom/sm6125-sony-xperia-seine-pdx201.dts
+++ b/arch/arm64/boot/dts/qcom/sm6125-sony-xperia-seine-pdx201.dts
@@ -88,11 +88,19 @@
 	status = "okay";
 };
 
-&sdc2_state_off {
+&sdc2_off_state {
 	sd-cd {
 		pins = "gpio98";
+		drive-strength = <2>;
 		bias-disable;
+	};
+};
+
+&sdc2_on_state {
+	sd-cd {
+		pins = "gpio98";
 		drive-strength = <2>;
+		bias-pull-up;
 	};
 };
 
@@ -102,32 +110,6 @@
 
 &tlmm {
 	gpio-reserved-ranges = <22 2>, <28 6>;
-
-	sdc2_state_on: sdc2-on {
-		clk {
-			pins = "sdc2_clk";
-			bias-disable;
-			drive-strength = <16>;
-		};
-
-		cmd {
-			pins = "sdc2_cmd";
-			bias-pull-up;
-			drive-strength = <10>;
-		};
-
-		data {
-			pins = "sdc2_data";
-			bias-pull-up;
-			drive-strength = <10>;
-		};
-
-		sd-cd {
-			pins = "gpio98";
-			bias-pull-up;
-			drive-strength = <2>;
-		};
-	};
 };
 
 &usb3 {
diff --git a/arch/arm64/boot/dts/qcom/sm6125.dtsi b/arch/arm64/boot/dts/qcom/sm6125.dtsi
index 9f476e3d0720..f89af5e35112 100644
--- a/arch/arm64/boot/dts/qcom/sm6125.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm6125.dtsi
@@ -336,23 +336,43 @@
 			interrupt-controller;
 			#interrupt-cells = <2>;
 
-			sdc2_state_off: sdc2-off {
+			sdc2_off_state: sdc2-off-state {
 				clk {
 					pins = "sdc2_clk";
-					bias-disable;
 					drive-strength = <2>;
+					bias-disable;
 				};
 
 				cmd {
 					pins = "sdc2_cmd";
+					drive-strength = <2>;
 					bias-pull-up;
+				};
+
+				data {
+					pins = "sdc2_data";
 					drive-strength = <2>;
+					bias-pull-up;
+				};
+			};
+
+			sdc2_on_state: sdc2-on-state {
+				clk {
+					pins = "sdc2_clk";
+					drive-strength = <16>;
+					bias-disable;
+				};
+
+				cmd {
+					pins = "sdc2_cmd";
+					drive-strength = <10>;
+					bias-pull-up;
 				};
 
 				data {
 					pins = "sdc2_data";
+					drive-strength = <10>;
 					bias-pull-up;
-					drive-strength = <2>;
 				};
 			};
 		};
@@ -417,8 +437,8 @@
 				<&xo_board>;
 			clock-names = "iface", "core", "xo";
 
-			pinctrl-0 = <&sdc2_state_on>;
-			pinctrl-1 = <&sdc2_state_off>;
+			pinctrl-0 = <&sdc2_on_state>;
+			pinctrl-1 = <&sdc2_off_state>;
 			pinctrl-names = "default", "sleep";
 
 			bus-width = <4>;
diff --git a/arch/arm64/boot/dts/qcom/sm8250.dtsi b/arch/arm64/boot/dts/qcom/sm8250.dtsi
index 2786e2c8e565..b710bca45648 100644
--- a/arch/arm64/boot/dts/qcom/sm8250.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8250.dtsi
@@ -1472,6 +1472,8 @@
 				clock-names = "pipe0";
 
 				#phy-cells = <0>;
+
+				#clock-cells = <0>;
 				clock-output-names = "pcie_0_pipe_clk";
 			};
 		};
@@ -1578,6 +1580,8 @@
 				clock-names = "pipe0";
 
 				#phy-cells = <0>;
+
+				#clock-cells = <0>;
 				clock-output-names = "pcie_1_pipe_clk";
 			};
 		};
@@ -1684,6 +1688,8 @@
 				clock-names = "pipe0";
 
 				#phy-cells = <0>;
+
+				#clock-cells = <0>;
 				clock-output-names = "pcie_2_pipe_clk";
 			};
 		};
diff --git a/arch/arm64/boot/dts/renesas/beacon-renesom-baseboard.dtsi b/arch/arm64/boot/dts/renesas/beacon-renesom-baseboard.dtsi
index 2692cc64bff6..48e0c0494f6a 100644
--- a/arch/arm64/boot/dts/renesas/beacon-renesom-baseboard.dtsi
+++ b/arch/arm64/boot/dts/renesas/beacon-renesom-baseboard.dtsi
@@ -146,7 +146,7 @@
 		};
 	};
 
-	reg_audio: regulator_audio {
+	reg_audio: regulator-audio {
 		compatible = "regulator-fixed";
 		regulator-name = "audio-1.8V";
 		regulator-min-microvolt = <1800000>;
@@ -174,7 +174,7 @@
 		vin-supply = <&reg_lcd>;
 	};
 
-	reg_cam0: regulator_camera {
+	reg_cam0: regulator-cam0 {
 		compatible = "regulator-fixed";
 		regulator-name = "reg_cam0";
 		regulator-min-microvolt = <1800000>;
@@ -183,7 +183,7 @@
 		enable-active-high;
 	};
 
-	reg_cam1: regulator_camera {
+	reg_cam1: regulator-cam1 {
 		compatible = "regulator-fixed";
 		regulator-name = "reg_cam1";
 		regulator-min-microvolt = <1800000>;
diff --git a/arch/arm64/boot/dts/renesas/r8a774c0.dtsi b/arch/arm64/boot/dts/renesas/r8a774c0.dtsi
index d597772c4c37..9eb08be3b98e 100644
--- a/arch/arm64/boot/dts/renesas/r8a774c0.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a774c0.dtsi
@@ -1953,7 +1953,7 @@
 		cpu-thermal {
 			polling-delay-passive = <250>;
 			polling-delay = <0>;
-			thermal-sensors = <&thermal 0>;
+			thermal-sensors = <&thermal>;
 			sustainable-power = <717>;
 
 			cooling-maps {
diff --git a/arch/arm64/boot/dts/renesas/r8a77990.dtsi b/arch/arm64/boot/dts/renesas/r8a77990.dtsi
index 0ea300a8147d..9e616b0f04d4 100644
--- a/arch/arm64/boot/dts/renesas/r8a77990.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a77990.dtsi
@@ -2102,7 +2102,7 @@
 		cpu-thermal {
 			polling-delay-passive = <250>;
 			polling-delay = <0>;
-			thermal-sensors = <&thermal 0>;
+			thermal-sensors = <&thermal>;
 			sustainable-power = <717>;
 
 			cooling-maps {
diff --git a/arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi b/arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi
index be97da132258..ba75adedbf79 100644
--- a/arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi
+++ b/arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi
@@ -599,8 +599,8 @@
 			compatible = "socionext,uniphier-dwc3", "snps,dwc3";
 			status = "disabled";
 			reg = <0x65a00000 0xcd00>;
-			interrupt-names = "host", "peripheral";
-			interrupts = <0 134 4>, <0 135 4>;
+			interrupt-names = "dwc_usb3";
+			interrupts = <0 134 4>;
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinctrl_usb0>, <&pinctrl_usb2>;
 			clock-names = "ref", "bus_early", "suspend";
@@ -701,8 +701,8 @@
 			compatible = "socionext,uniphier-dwc3", "snps,dwc3";
 			status = "disabled";
 			reg = <0x65c00000 0xcd00>;
-			interrupt-names = "host", "peripheral";
-			interrupts = <0 137 4>, <0 138 4>;
+			interrupt-names = "dwc_usb3";
+			interrupts = <0 137 4>;
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinctrl_usb1>, <&pinctrl_usb3>;
 			clock-names = "ref", "bus_early", "suspend";
diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
index 55f19450091b..1a5406e599ba 100644
--- a/arch/arm64/crypto/Kconfig
+++ b/arch/arm64/crypto/Kconfig
@@ -59,6 +59,7 @@ config CRYPTO_GHASH_ARM64_CE
 	select CRYPTO_HASH
 	select CRYPTO_GF128MUL
 	select CRYPTO_LIB_AES
+	select CRYPTO_AEAD
 
 config CRYPTO_CRCT10DIF_ARM64_CE
 	tristate "CRCT10DIF digest algorithm using PMULL instructions"
diff --git a/arch/arm64/crypto/poly1305-glue.c b/arch/arm64/crypto/poly1305-glue.c
index 9c3d86e397bf..1fae18ba11ed 100644
--- a/arch/arm64/crypto/poly1305-glue.c
+++ b/arch/arm64/crypto/poly1305-glue.c
@@ -52,7 +52,7 @@ static void neon_poly1305_blocks(struct poly1305_desc_ctx *dctx, const u8 *src,
 {
 	if (unlikely(!dctx->sset)) {
 		if (!dctx->rset) {
-			poly1305_init_arch(dctx, src);
+			poly1305_init_arm64(&dctx->h, src);
 			src += POLY1305_BLOCK_SIZE;
 			len -= POLY1305_BLOCK_SIZE;
 			dctx->rset = 1;
diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
index 4ad22c3135db..5a0f792492af 100644
--- a/arch/arm64/include/asm/arch_gicv3.h
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -26,12 +26,6 @@
  * sets the GP register's most significant bits to 0 with an explicit cast.
  */
 
-static inline void gic_write_eoir(u32 irq)
-{
-	write_sysreg_s(irq, SYS_ICC_EOIR1_EL1);
-	isb();
-}
-
 static __always_inline void gic_write_dir(u32 irq)
 {
 	write_sysreg_s(irq, SYS_ICC_DIR_EL1);
diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h
index 96dc0f7da258..a971d462f531 100644
--- a/arch/arm64/include/asm/kernel-pgtable.h
+++ b/arch/arm64/include/asm/kernel-pgtable.h
@@ -103,8 +103,8 @@
 /*
  * Initial memory map attributes.
  */
-#define SWAPPER_PTE_FLAGS	(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
-#define SWAPPER_PMD_FLAGS	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
+#define SWAPPER_PTE_FLAGS	(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED | PTE_UXN)
+#define SWAPPER_PMD_FLAGS	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S | PMD_SECT_UXN)
 
 #if ARM64_KERNEL_USES_PMD_MAPS
 #define SWAPPER_MM_MMUFLAGS	(PMD_ATTRINDX(MT_NORMAL) | SWAPPER_PMD_FLAGS)
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index fc6ee6c5972d..1713630bf8f5 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -795,6 +795,10 @@ bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu);
 #define kvm_vcpu_has_pmu(vcpu)					\
 	(test_bit(KVM_ARM_VCPU_PMU_V3, (vcpu)->arch.features))
 
+#define kvm_supports_32bit_el0()				\
+	(system_supports_32bit_el0() &&				\
+	 !static_branch_unlikely(&arm64_mismatched_32bit_el0))
+
 int kvm_trng_call(struct kvm_vcpu *vcpu);
 #ifdef CONFIG_KVM
 extern phys_addr_t hyp_mem_base;
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 5e73d7f7d1e7..d9bf3d12a2b8 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -204,8 +204,9 @@ void tls_preserve_current_state(void);
 
 static inline void start_thread_common(struct pt_regs *regs, unsigned long pc)
 {
+	s32 previous_syscall = regs->syscallno;
 	memset(regs, 0, sizeof(*regs));
-	forget_syscall(regs);
+	regs->syscallno = previous_syscall;
 	regs->pc = pc;
 
 	if (system_uses_irq_prio_masking())
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index 0e86e8b9cedd..c5da9d1e954a 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -59,6 +59,7 @@ struct insn_emulation {
 static LIST_HEAD(insn_emulation);
 static int nr_insn_emulated __initdata;
 static DEFINE_RAW_SPINLOCK(insn_emulation_lock);
+static DEFINE_MUTEX(insn_emulation_mutex);
 
 static void register_emulation_hooks(struct insn_emulation_ops *ops)
 {
@@ -207,10 +208,10 @@ static int emulation_proc_handler(struct ctl_table *table, int write,
 				  loff_t *ppos)
 {
 	int ret = 0;
-	struct insn_emulation *insn = (struct insn_emulation *) table->data;
+	struct insn_emulation *insn = container_of(table->data, struct insn_emulation, current_mode);
 	enum insn_emulation_mode prev_mode = insn->current_mode;
 
-	table->data = &insn->current_mode;
+	mutex_lock(&insn_emulation_mutex);
 	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 
 	if (ret || !write || prev_mode == insn->current_mode)
@@ -223,7 +224,7 @@ static int emulation_proc_handler(struct ctl_table *table, int write,
 		update_insn_emulation_mode(insn, INSN_UNDEF);
 	}
 ret:
-	table->data = insn;
+	mutex_unlock(&insn_emulation_mutex);
 	return ret;
 }
 
@@ -247,7 +248,7 @@ static void __init register_insn_emulation_sysctl(void)
 		sysctl->maxlen = sizeof(int);
 
 		sysctl->procname = insn->ops->name;
-		sysctl->data = insn;
+		sysctl->data = &insn->current_mode;
 		sysctl->extra1 = &insn->min;
 		sysctl->extra2 = &insn->max;
 		sysctl->proc_handler = emulation_proc_handler;
diff --git a/arch/arm64/kernel/cacheinfo.c b/arch/arm64/kernel/cacheinfo.c
index 587543c6c51c..97c42be71338 100644
--- a/arch/arm64/kernel/cacheinfo.c
+++ b/arch/arm64/kernel/cacheinfo.c
@@ -45,7 +45,8 @@ static void ci_leaf_init(struct cacheinfo *this_leaf,
 
 int init_cache_level(unsigned int cpu)
 {
-	unsigned int ctype, level, leaves, fw_level;
+	unsigned int ctype, level, leaves;
+	int fw_level;
 	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
 
 	for (level = 1, leaves = 0; level <= MAX_CACHE_LEVEL; level++) {
@@ -63,6 +64,9 @@ int init_cache_level(unsigned int cpu)
 	else
 		fw_level = acpi_find_last_cache_level(cpu);
 
+	if (fw_level < 0)
+		return fw_level;
+
 	if (level < fw_level) {
 		/*
 		 * some external caches not specified in CLIDR_EL1
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index c67c19d70159..25c495f58f67 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -208,10 +208,18 @@ static const struct arm64_cpu_capabilities arm64_repeat_tlbi_list[] = {
 #ifdef CONFIG_ARM64_ERRATUM_1286807
 	{
 		ERRATA_MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 0),
+	},
+	{
 		/* Kryo4xx Gold (rcpe to rfpe) => (r0p0 to r3p0) */
 		ERRATA_MIDR_RANGE(MIDR_QCOM_KRYO_4XX_GOLD, 0xc, 0xe, 0xf, 0xe),
 	},
 #endif
+#ifdef CONFIG_ARM64_ERRATUM_2441009
+	{
+		/* Cortex-A510 r0p0 -> r1p1. Fixed in r1p2 */
+		ERRATA_MIDR_RANGE(MIDR_CORTEX_A510, 0, 0, 1, 1),
+	},
+#endif
 	{},
 };
 #endif
@@ -427,7 +435,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 #endif
 #ifdef CONFIG_ARM64_WORKAROUND_REPEAT_TLBI
 	{
-		.desc = "Qualcomm erratum 1009, or ARM erratum 1286807",
+		.desc = "Qualcomm erratum 1009, or ARM erratum 1286807, 2441009",
 		.capability = ARM64_WORKAROUND_REPEAT_TLBI,
 		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
 		.matches = cpucap_multi_entry_cap_matches,
@@ -543,6 +551,15 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		ERRATA_MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL),
 	},
 #endif
+#ifdef CONFIG_ARM64_ERRATUM_2457168
+	{
+		.desc = "ARM erratum 2457168",
+		.capability = ARM64_WORKAROUND_2457168,
+		.type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE,
+		/* Cortex-A510 r0p0-r1p1 */
+		CAP_MIDR_RANGE(MIDR_CORTEX_A510, 0, 0, 1, 1)
+	},
+#endif
 	{
 	}
 };
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 1e6f01667f03..3337658baed1 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -536,7 +536,7 @@ static const struct arm64_ftr_bits ftr_id_pfr2[] = {
 
 static const struct arm64_ftr_bits ftr_id_dfr0[] = {
 	/* [31:28] TraceFilt */
-	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_PERFMON_SHIFT, 4, 0xf),
+	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_DFR0_PERFMON_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_MPROFDBG_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_MMAPTRC_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_COPTRC_SHIFT, 4, 0),
@@ -1749,7 +1749,10 @@ static void cpu_amu_enable(struct arm64_cpu_capabilities const *cap)
 		pr_info("detected CPU%d: Activity Monitors Unit (AMU)\n",
 			smp_processor_id());
 		cpumask_set_cpu(smp_processor_id(), &amu_cpus);
-		update_freq_counters_refs();
+
+		/* 0 reference values signal broken/disabled counters */
+		if (!this_cpu_has_cap(ARM64_WORKAROUND_2457168))
+			update_freq_counters_refs();
 	}
 }
 
diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index 32f9796c4ffe..60225bc09b01 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -72,7 +72,7 @@ static __always_inline void __exit_to_kernel_mode(struct pt_regs *regs)
 	if (interrupts_enabled(regs)) {
 		if (regs->exit_rcu) {
 			trace_hardirqs_on_prepare();
-			lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+			lockdep_hardirqs_on_prepare();
 			rcu_irq_exit();
 			lockdep_hardirqs_on(CALLER_ADDR0);
 			return;
@@ -117,7 +117,7 @@ static __always_inline void enter_from_user_mode(struct pt_regs *regs)
 static __always_inline void __exit_to_user_mode(void)
 {
 	trace_hardirqs_on_prepare();
-	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+	lockdep_hardirqs_on_prepare();
 	user_enter_irqoff();
 	lockdep_hardirqs_on(CALLER_ADDR0);
 }
@@ -175,7 +175,7 @@ static void noinstr arm64_exit_nmi(struct pt_regs *regs)
 	ftrace_nmi_exit();
 	if (restore) {
 		trace_hardirqs_on_prepare();
-		lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+		lockdep_hardirqs_on_prepare();
 	}
 
 	rcu_nmi_exit();
@@ -211,7 +211,7 @@ static void noinstr arm64_exit_el1_dbg(struct pt_regs *regs)
 
 	if (restore) {
 		trace_hardirqs_on_prepare();
-		lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+		lockdep_hardirqs_on_prepare();
 	}
 
 	rcu_nmi_exit();
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 17962452e31d..ab6566bf1c33 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -285,7 +285,7 @@ SYM_FUNC_START_LOCAL(__create_page_tables)
 	subs	x1, x1, #64
 	b.ne	1b
 
-	mov	x7, SWAPPER_MM_MMUFLAGS
+	mov_q	x7, SWAPPER_MM_MMUFLAGS
 
 	/*
 	 * Create the identity mapping.
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 4dd14a6620c1..acf67ef4c505 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -308,12 +308,25 @@ core_initcall(init_amu_fie);
 
 static void cpu_read_corecnt(void *val)
 {
+	/*
+	 * A value of 0 can be returned if the current CPU does not support AMUs
+	 * or if the counter is disabled for this CPU. A return value of 0 at
+	 * counter read is properly handled as an error case by the users of the
+	 * counter.
+	 */
 	*(u64 *)val = read_corecnt();
 }
 
 static void cpu_read_constcnt(void *val)
 {
-	*(u64 *)val = read_constcnt();
+	/*
+	 * Return 0 if the current CPU is affected by erratum 2457168. A value
+	 * of 0 is also returned if the current CPU does not support AMUs or if
+	 * the counter is disabled. A return value of 0 at counter read is
+	 * properly handled as an error case by the users of the counter.
+	 */
+	*(u64 *)val = this_cpu_has_cap(ARM64_WORKAROUND_2457168) ?
+		      0UL : read_constcnt();
 }
 
 static inline
@@ -340,7 +353,22 @@ int counters_read_on_cpu(int cpu, smp_call_func_t func, u64 *val)
  */
 bool cpc_ffh_supported(void)
 {
-	return freq_counters_valid(get_cpu_with_amu_feat());
+	int cpu = get_cpu_with_amu_feat();
+
+	/*
+	 * FFH is considered supported if there is at least one present CPU that
+	 * supports AMUs. Using FFH to read core and reference counters for CPUs
+	 * that do not support AMUs, have counters disabled or that are affected
+	 * by errata, will result in a return value of 0.
+	 *
+	 * This is done to allow any enabled and valid counters to be read
+	 * through FFH, knowing that potentially returning 0 as counter value is
+	 * properly handled by the users of these counters.
+	 */
+	if ((cpu >= nr_cpu_ids) || !cpumask_test_cpu(cpu, cpu_present_mask))
+		return false;
+
+	return true;
 }
 
 int cpc_read_ffh(int cpu, struct cpc_reg *reg, u64 *val)
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index f181527f9d43..4cb265e15361 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -712,8 +712,7 @@ static bool vcpu_mode_is_bad_32bit(struct kvm_vcpu *vcpu)
 	if (likely(!vcpu_mode_is_32bit(vcpu)))
 		return false;
 
-	return !system_supports_32bit_el0() ||
-		static_branch_unlikely(&arm64_mismatched_32bit_el0);
+	return !kvm_supports_32bit_el0();
 }
 
 /**
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 5ce26bedf23c..94108e2e0917 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -242,7 +242,7 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		u64 mode = (*(u64 *)valp) & PSR_AA32_MODE_MASK;
 		switch (mode) {
 		case PSR_AA32_MODE_USR:
-			if (!system_supports_32bit_el0())
+			if (!kvm_supports_32bit_el0())
 				return -EINVAL;
 			break;
 		case PSR_AA32_MODE_FIQ:
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index a34b01cc8ab9..4db5409f40c4 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -279,5 +279,5 @@ void __noreturn hyp_panic(void)
 
 asmlinkage void kvm_unexpected_el2_exception(void)
 {
-	return __kvm_unexpected_el2_exception();
+	__kvm_unexpected_el2_exception();
 }
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index d88d3c143a73..813e6e2178c1 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -220,5 +220,5 @@ void __noreturn hyp_panic(void)
 
 asmlinkage void kvm_unexpected_el2_exception(void)
 {
-	return __kvm_unexpected_el2_exception();
+	__kvm_unexpected_el2_exception();
 }
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 7c18e429b449..c11612db4a37 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -649,7 +649,7 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	 */
 	val = ((pmcr & ~ARMV8_PMU_PMCR_MASK)
 	       | (ARMV8_PMU_PMCR_MASK & 0xdecafbad)) & (~ARMV8_PMU_PMCR_E);
-	if (!system_supports_32bit_el0())
+	if (!kvm_supports_32bit_el0())
 		val |= ARMV8_PMU_PMCR_LC;
 	__vcpu_sys_reg(vcpu, r->reg) = val;
 }
@@ -698,7 +698,7 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		val = __vcpu_sys_reg(vcpu, PMCR_EL0);
 		val &= ~ARMV8_PMU_PMCR_MASK;
 		val |= p->regval & ARMV8_PMU_PMCR_MASK;
-		if (!system_supports_32bit_el0())
+		if (!kvm_supports_32bit_el0())
 			val |= ARMV8_PMU_PMCR_LC;
 		__vcpu_sys_reg(vcpu, PMCR_EL0) = val;
 		kvm_pmu_handle_pmcr(vcpu, val);
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 95439bbe5df8..4895b4d7e150 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -788,7 +788,10 @@ emit_cond_jmp:
 		u64 imm64;
 
 		imm64 = (u64)insn1.imm << 32 | (u32)imm;
-		emit_a64_mov_i64(dst, imm64, ctx);
+		if (bpf_pseudo_func(insn))
+			emit_addr_mov_i64(dst, imm64, ctx);
+		else
+			emit_a64_mov_i64(dst, imm64, ctx);
 
 		return 1;
 	}
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index b71c6cbb2309..cfaffd3c8289 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -54,6 +54,7 @@ WORKAROUND_1418040
 WORKAROUND_1463225
 WORKAROUND_1508412
 WORKAROUND_1542419
+WORKAROUND_2457168
 WORKAROUND_CAVIUM_23154
 WORKAROUND_CAVIUM_27456
 WORKAROUND_CAVIUM_30115
diff --git a/arch/csky/kernel/probes/kprobes.c b/arch/csky/kernel/probes/kprobes.c
index 4045894d9280..584ed9f36290 100644
--- a/arch/csky/kernel/probes/kprobes.c
+++ b/arch/csky/kernel/probes/kprobes.c
@@ -124,6 +124,10 @@ void __kprobes arch_disarm_kprobe(struct kprobe *p)
 
 void __kprobes arch_remove_kprobe(struct kprobe *p)
 {
+	if (p->ainsn.api.insn) {
+		free_insn_slot(p->ainsn.api.insn, 0);
+		p->ainsn.api.insn = NULL;
+	}
 }
 
 static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
diff --git a/arch/ia64/include/asm/processor.h b/arch/ia64/include/asm/processor.h
index 2d8bcdc27d7f..05e7c9ad1a96 100644
--- a/arch/ia64/include/asm/processor.h
+++ b/arch/ia64/include/asm/processor.h
@@ -542,7 +542,7 @@ ia64_get_irr(unsigned int vector)
 {
 	unsigned int reg = vector / 64;
 	unsigned int bit = vector % 64;
-	u64 irr;
+	unsigned long irr;
 
 	switch (reg) {
 	case 0: irr = ia64_getreg(_IA64_REG_CR_IRR0); break;
diff --git a/arch/m68k/coldfire/device.c b/arch/m68k/coldfire/device.c
index 4218750414bb..7dab46728aed 100644
--- a/arch/m68k/coldfire/device.c
+++ b/arch/m68k/coldfire/device.c
@@ -581,7 +581,7 @@ static struct platform_device mcf_esdhc = {
 };
 #endif /* MCFSDHC_BASE */
 
-#if IS_ENABLED(CONFIG_CAN_FLEXCAN)
+#ifdef MCFFLEXCAN_SIZE
 
 #include <linux/can/platform/flexcan.h>
 
@@ -620,7 +620,7 @@ static struct platform_device mcf_flexcan0 = {
 	.resource = mcf5441x_flexcan0_resource,
 	.dev.platform_data = &mcf5441x_flexcan_info,
 };
-#endif /* IS_ENABLED(CONFIG_CAN_FLEXCAN) */
+#endif /* MCFFLEXCAN_SIZE */
 
 static struct platform_device *mcf_devices[] __initdata = {
 	&mcf_uart,
@@ -657,7 +657,7 @@ static struct platform_device *mcf_devices[] __initdata = {
 #ifdef MCFSDHC_BASE
 	&mcf_esdhc,
 #endif
-#if IS_ENABLED(CONFIG_CAN_FLEXCAN)
+#ifdef MCFFLEXCAN_SIZE
 	&mcf_flexcan0,
 #endif
 };
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index be5d4afcd30f..353dfeee0a6d 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -127,6 +127,16 @@ static void octeon_irq_free_cd(struct irq_domain *d, unsigned int irq)
 static int octeon_irq_force_ciu_mapping(struct irq_domain *domain,
 					int irq, int line, int bit)
 {
+	struct device_node *of_node;
+	int ret;
+
+	of_node = irq_domain_get_of_node(domain);
+	if (!of_node)
+		return -EINVAL;
+	ret = irq_alloc_desc_at(irq, of_node_to_nid(of_node));
+	if (ret < 0)
+		return ret;
+
 	return irq_domain_associate(domain, irq, line << 6 | bit);
 }
 
diff --git a/arch/mips/cavium-octeon/octeon-platform.c b/arch/mips/cavium-octeon/octeon-platform.c
index a994022e32c9..ce05c0dd3acd 100644
--- a/arch/mips/cavium-octeon/octeon-platform.c
+++ b/arch/mips/cavium-octeon/octeon-platform.c
@@ -86,11 +86,12 @@ static void octeon2_usb_clocks_start(struct device *dev)
 					 "refclk-frequency", &clock_rate);
 		if (i) {
 			dev_err(dev, "No UCTL \"refclk-frequency\"\n");
+			of_node_put(uctl_node);
 			goto exit;
 		}
 		i = of_property_read_string(uctl_node,
 					    "refclk-type", &clock_type);
-
+		of_node_put(uctl_node);
 		if (!i && strcmp("crystal", clock_type) == 0)
 			is_crystal_clock = true;
 	}
diff --git a/arch/mips/kernel/proc.c b/arch/mips/kernel/proc.c
index 4184d641f05e..33a02f3814f5 100644
--- a/arch/mips/kernel/proc.c
+++ b/arch/mips/kernel/proc.c
@@ -172,7 +172,7 @@ static void *c_start(struct seq_file *m, loff_t *pos)
 {
 	unsigned long i = *pos;
 
-	return i < NR_CPUS ? (void *) (i + 1) : NULL;
+	return i < nr_cpu_ids ? (void *) (i + 1) : NULL;
 }
 
 static void *c_next(struct seq_file *m, void *v, loff_t *pos)
diff --git a/arch/mips/kernel/vdso.c b/arch/mips/kernel/vdso.c
index 3d0cf471f2fe..b2cc2c2dd4bf 100644
--- a/arch/mips/kernel/vdso.c
+++ b/arch/mips/kernel/vdso.c
@@ -159,7 +159,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	/* Map GIC user page. */
 	if (gic_size) {
 		gic_base = (unsigned long)mips_gic_base + MIPS_GIC_USER_OFS;
-		gic_pfn = virt_to_phys((void *)gic_base) >> PAGE_SHIFT;
+		gic_pfn = PFN_DOWN(__pa(gic_base));
 
 		ret = io_remap_pfn_range(vma, base, gic_pfn, gic_size,
 					 pgprot_noncached(vma->vm_page_prot));
diff --git a/arch/mips/loongson32/ls1c/board.c b/arch/mips/loongson32/ls1c/board.c
index e9de6da0ce51..9dcfe9de55b0 100644
--- a/arch/mips/loongson32/ls1c/board.c
+++ b/arch/mips/loongson32/ls1c/board.c
@@ -15,7 +15,6 @@ static struct platform_device *ls1c_platform_devices[] __initdata = {
 static int __init ls1c_platform_init(void)
 {
 	ls1x_serial_set_uartclk(&ls1x_uart_pdev);
-	ls1x_rtc_set_extclk(&ls1x_rtc_pdev);
 
 	return platform_add_devices(ls1c_platform_devices,
 				   ARRAY_SIZE(ls1c_platform_devices));
diff --git a/arch/mips/mm/physaddr.c b/arch/mips/mm/physaddr.c
index a1ced5e44951..f9b8c85e9843 100644
--- a/arch/mips/mm/physaddr.c
+++ b/arch/mips/mm/physaddr.c
@@ -5,6 +5,7 @@
 #include <linux/mmdebug.h>
 #include <linux/mm.h>
 
+#include <asm/addrspace.h>
 #include <asm/sections.h>
 #include <asm/io.h>
 #include <asm/page.h>
@@ -12,15 +13,6 @@
 
 static inline bool __debug_virt_addr_valid(unsigned long x)
 {
-	/* high_memory does not get immediately defined, and there
-	 * are early callers of __pa() against PAGE_OFFSET
-	 */
-	if (!high_memory && x >= PAGE_OFFSET)
-		return true;
-
-	if (high_memory && x >= PAGE_OFFSET && x < (unsigned long)high_memory)
-		return true;
-
 	/*
 	 * MAX_DMA_ADDRESS is a virtual address that may not correspond to an
 	 * actual physical address. Enough code relies on
@@ -30,7 +22,9 @@ static inline bool __debug_virt_addr_valid(unsigned long x)
 	if (x == MAX_DMA_ADDRESS)
 		return true;
 
-	return false;
+	return x >= PAGE_OFFSET && (KSEGX(x) < KSEG2 ||
+	       IS_ENABLED(CONFIG_EVA) ||
+	       !IS_ENABLED(CONFIG_HIGHMEM));
 }
 
 phys_addr_t __virt_to_phys(volatile const void *x)
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index 046d51a454af..3471a089bc05 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -634,7 +634,7 @@ static __maybe_unused void build_convert_pte_to_entrylo(u32 **p,
 		return;
 	}
 
-	if (cpu_has_rixi && !!_PAGE_NO_EXEC) {
+	if (cpu_has_rixi && _PAGE_NO_EXEC != 0) {
 		if (fill_includes_sw_bits) {
 			UASM_i_ROTR(p, reg, reg, ilog2(_PAGE_GLOBAL));
 		} else {
@@ -2573,7 +2573,7 @@ static void check_pabits(void)
 	unsigned long entry;
 	unsigned pabits, fillbits;
 
-	if (!cpu_has_rixi || !_PAGE_NO_EXEC) {
+	if (!cpu_has_rixi || _PAGE_NO_EXEC == 0) {
 		/*
 		 * We'll only be making use of the fact that we can rotate bits
 		 * into the fill if the CPU supports RIXI, so don't bother
diff --git a/arch/nios2/include/asm/entry.h b/arch/nios2/include/asm/entry.h
index cf37f55efbc2..bafb7b2ca59f 100644
--- a/arch/nios2/include/asm/entry.h
+++ b/arch/nios2/include/asm/entry.h
@@ -50,7 +50,8 @@
 	stw	r13, PT_R13(sp)
 	stw	r14, PT_R14(sp)
 	stw	r15, PT_R15(sp)
-	stw	r2, PT_ORIG_R2(sp)
+	movi	r24, -1
+	stw	r24, PT_ORIG_R2(sp)
 	stw	r7, PT_ORIG_R7(sp)
 
 	stw	ra, PT_RA(sp)
diff --git a/arch/nios2/include/asm/ptrace.h b/arch/nios2/include/asm/ptrace.h
index 642462144872..9da34c3022a2 100644
--- a/arch/nios2/include/asm/ptrace.h
+++ b/arch/nios2/include/asm/ptrace.h
@@ -74,6 +74,8 @@ extern void show_regs(struct pt_regs *);
 	((struct pt_regs *)((unsigned long)current_thread_info() + THREAD_SIZE)\
 		- 1)
 
+#define force_successful_syscall_return() (current_pt_regs()->orig_r2 = -1)
+
 int do_syscall_trace_enter(void);
 void do_syscall_trace_exit(void);
 #endif /* __ASSEMBLY__ */
diff --git a/arch/nios2/kernel/entry.S b/arch/nios2/kernel/entry.S
index 0794cd7803df..99f0a65e6234 100644
--- a/arch/nios2/kernel/entry.S
+++ b/arch/nios2/kernel/entry.S
@@ -185,6 +185,7 @@ ENTRY(handle_system_call)
 	ldw	r5, PT_R5(sp)
 
 local_restart:
+	stw	r2, PT_ORIG_R2(sp)
 	/* Check that the requested system call is within limits */
 	movui	r1, __NR_syscalls
 	bgeu	r2, r1, ret_invsyscall
@@ -192,7 +193,6 @@ local_restart:
 	movhi	r11, %hiadj(sys_call_table)
 	add	r1, r1, r11
 	ldw	r1, %lo(sys_call_table)(r1)
-	beq	r1, r0, ret_invsyscall
 
 	/* Check if we are being traced */
 	GET_THREAD_INFO r11
@@ -213,6 +213,9 @@ local_restart:
 translate_rc_and_ret:
 	movi	r1, 0
 	bge	r2, zero, 3f
+	ldw	r1, PT_ORIG_R2(sp)
+	addi	r1, r1, 1
+	beq	r1, zero, 3f
 	sub	r2, zero, r2
 	movi	r1, 1
 3:
@@ -255,9 +258,9 @@ traced_system_call:
 	ldw	r6, PT_R6(sp)
 	ldw	r7, PT_R7(sp)
 
-	/* Fetch the syscall function, we don't need to check the boundaries
-	 * since this is already done.
-	 */
+	/* Fetch the syscall function. */
+	movui	r1, __NR_syscalls
+	bgeu	r2, r1, traced_invsyscall
 	slli	r1, r2, 2
 	movhi	r11,%hiadj(sys_call_table)
 	add	r1, r1, r11
@@ -276,6 +279,9 @@ traced_system_call:
 translate_rc_and_ret2:
 	movi	r1, 0
 	bge	r2, zero, 4f
+	ldw	r1, PT_ORIG_R2(sp)
+	addi	r1, r1, 1
+	beq	r1, zero, 4f
 	sub	r2, zero, r2
 	movi	r1, 1
 4:
@@ -287,6 +293,11 @@ end_translate_rc_and_ret2:
 	RESTORE_SWITCH_STACK
 	br	ret_from_exception
 
+	/* If the syscall number was invalid return ENOSYS */
+traced_invsyscall:
+	movi	r2, -ENOSYS
+	br	translate_rc_and_ret2
+
 Luser_return:
 	GET_THREAD_INFO	r11			/* get thread_info pointer */
 	ldw	r10, TI_FLAGS(r11)		/* get thread_info->flags */
@@ -336,9 +347,6 @@ external_interrupt:
 	/* skip if no interrupt is pending */
 	beq	r12, r0, ret_from_interrupt
 
-	movi	r24, -1
-	stw	r24, PT_ORIG_R2(sp)
-
 	/*
 	 * Process an external hardware interrupt.
 	 */
diff --git a/arch/nios2/kernel/signal.c b/arch/nios2/kernel/signal.c
index 386e46443b60..68d626c4f1ba 100644
--- a/arch/nios2/kernel/signal.c
+++ b/arch/nios2/kernel/signal.c
@@ -242,7 +242,7 @@ static int do_signal(struct pt_regs *regs)
 	/*
 	 * If we were from a system call, check for system call restarting...
 	 */
-	if (regs->orig_r2 >= 0) {
+	if (regs->orig_r2 >= 0 && regs->r1) {
 		continue_addr = regs->ea;
 		restart_addr = continue_addr - 4;
 		retval = regs->r2;
@@ -264,6 +264,7 @@ static int do_signal(struct pt_regs *regs)
 			regs->ea = restart_addr;
 			break;
 		}
+		regs->orig_r2 = -1;
 	}
 
 	if (get_signal(&ksig)) {
diff --git a/arch/nios2/kernel/syscall_table.c b/arch/nios2/kernel/syscall_table.c
index 6176d63023c1..c2875a6dd5a4 100644
--- a/arch/nios2/kernel/syscall_table.c
+++ b/arch/nios2/kernel/syscall_table.c
@@ -13,5 +13,6 @@
 #define __SYSCALL(nr, call) [nr] = (call),
 
 void *sys_call_table[__NR_syscalls] = {
+	[0 ... __NR_syscalls-1] = sys_ni_syscall,
 #include <asm/unistd.h>
 };
diff --git a/arch/openrisc/include/asm/io.h b/arch/openrisc/include/asm/io.h
index c298061c70a7..8aa3e78181e9 100644
--- a/arch/openrisc/include/asm/io.h
+++ b/arch/openrisc/include/asm/io.h
@@ -31,7 +31,7 @@
 void __iomem *ioremap(phys_addr_t offset, unsigned long size);
 
 #define iounmap iounmap
-extern void iounmap(void __iomem *addr);
+extern void iounmap(volatile void __iomem *addr);
 
 #include <asm-generic/io.h>
 
diff --git a/arch/openrisc/mm/ioremap.c b/arch/openrisc/mm/ioremap.c
index daae13a76743..8ec0dafecf25 100644
--- a/arch/openrisc/mm/ioremap.c
+++ b/arch/openrisc/mm/ioremap.c
@@ -77,7 +77,7 @@ void __iomem *__ref ioremap(phys_addr_t addr, unsigned long size)
 }
 EXPORT_SYMBOL(ioremap);
 
-void iounmap(void __iomem *addr)
+void iounmap(volatile void __iomem *addr)
 {
 	/* If the page is from the fixmap pool then we just clear out
 	 * the fixmap mapping.
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 5dccf01a9e17..117b0f882750 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -142,10 +142,10 @@ menu "Processor type and features"
 
 choice
 	prompt "Processor type"
-	default PA7000
+	default PA7000 if "$(ARCH)" = "parisc"
 
 config PA7000
-	bool "PA7000/PA7100"
+	bool "PA7000/PA7100" if "$(ARCH)" = "parisc"
 	help
 	  This is the processor type of your CPU.  This information is
 	  used for optimizing purposes.  In order to compile a kernel
@@ -156,21 +156,21 @@ config PA7000
 	  which is required on some machines.
 
 config PA7100LC
-	bool "PA7100LC"
+	bool "PA7100LC" if "$(ARCH)" = "parisc"
 	help
 	  Select this option for the PCX-L processor, as used in the
 	  712, 715/64, 715/80, 715/100, 715/100XC, 725/100, 743, 748,
 	  D200, D210, D300, D310 and E-class
 
 config PA7200
-	bool "PA7200"
+	bool "PA7200" if "$(ARCH)" = "parisc"
 	help
 	  Select this option for the PCX-T' processor, as used in the
 	  C100, C110, J100, J110, J210XC, D250, D260, D350, D360,
 	  K100, K200, K210, K220, K400, K410 and K420
 
 config PA7300LC
-	bool "PA7300LC"
+	bool "PA7300LC" if "$(ARCH)" = "parisc"
 	help
 	  Select this option for the PCX-L2 processor, as used in the
 	  744, A180, B132L, B160L, B180L, C132L, C160L, C180L,
@@ -220,7 +220,8 @@ config MLONGCALLS
 	  Enabling this option will probably slow down your kernel.
 
 config 64BIT
-	bool "64-bit kernel"
+	def_bool y if "$(ARCH)" = "parisc64"
+	bool "64-bit kernel" if "$(ARCH)" = "parisc"
 	depends on PA8X00
 	help
 	  Enable this if you want to support 64bit kernel on PA-RISC platform.
diff --git a/arch/parisc/include/asm/bitops.h b/arch/parisc/include/asm/bitops.h
index 5779d463b341..aa4e883431c1 100644
--- a/arch/parisc/include/asm/bitops.h
+++ b/arch/parisc/include/asm/bitops.h
@@ -12,14 +12,6 @@
 #include <asm/barrier.h>
 #include <linux/atomic.h>
 
-/* compiler build environment sanity checks: */
-#if !defined(CONFIG_64BIT) && defined(__LP64__)
-#error "Please use 'ARCH=parisc' to build the 32-bit kernel."
-#endif
-#if defined(CONFIG_64BIT) && !defined(__LP64__)
-#error "Please use 'ARCH=parisc64' to build the 64-bit kernel."
-#endif
-
 /* See http://marc.theaimsgroup.com/?t=108826637900003 for discussion
  * on use of volatile and __*_bit() (set/clear/change):
  *	*_bit() want use of volatile.
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index 4ed4942d8312..394e6e14e5c4 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -46,9 +46,6 @@ void flush_icache_page_asm(unsigned long phys_addr, unsigned long vaddr);
  */
 DEFINE_SPINLOCK(pa_tlb_flush_lock);
 
-/* Swapper page setup lock. */
-DEFINE_SPINLOCK(pa_swapper_pg_lock);
-
 #if defined(CONFIG_64BIT) && defined(CONFIG_SMP)
 int pa_serialize_tlb_flushes __ro_after_init;
 #endif
diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c
index 776d624a7207..d126e78e101a 100644
--- a/arch/parisc/kernel/drivers.c
+++ b/arch/parisc/kernel/drivers.c
@@ -520,7 +520,6 @@ alloc_pa_dev(unsigned long hpa, struct hardware_path *mod_path)
 	dev->id.hversion_rev = iodc_data[1] & 0x0f;
 	dev->id.sversion = ((iodc_data[4] & 0x0f) << 16) |
 			(iodc_data[5] << 8) | iodc_data[6];
-	dev->hpa.name = parisc_pathname(dev);
 	dev->hpa.start = hpa;
 	/* This is awkward.  The STI spec says that gfx devices may occupy
 	 * 32MB or 64MB.  Unfortunately, we don't know how to tell whether
@@ -534,10 +533,10 @@ alloc_pa_dev(unsigned long hpa, struct hardware_path *mod_path)
 		dev->hpa.end = hpa + 0xfff;
 	}
 	dev->hpa.flags = IORESOURCE_MEM;
-	name = parisc_hardware_description(&dev->id);
-	if (name) {
-		strlcpy(dev->name, name, sizeof(dev->name));
-	}
+	dev->hpa.name = dev->name;
+	name = parisc_hardware_description(&dev->id) ? : "unknown";
+	snprintf(dev->name, sizeof(dev->name), "%s [%s]",
+		name, parisc_pathname(dev));
 
 	/* Silently fail things like mouse ports which are subsumed within
 	 * the keyboard controller
diff --git a/arch/parisc/kernel/head.S b/arch/parisc/kernel/head.S
index aa93d775c34d..598d0938449d 100644
--- a/arch/parisc/kernel/head.S
+++ b/arch/parisc/kernel/head.S
@@ -22,7 +22,7 @@
 #include <linux/init.h>
 #include <linux/pgtable.h>
 
-	.level	PA_ASM_LEVEL
+	.level	1.1
 
 	__INITDATA
 ENTRY(boot_args)
@@ -69,6 +69,47 @@ $bss_loop:
 	stw,ma          %arg2,4(%r1)
 	stw,ma          %arg3,4(%r1)
 
+#if !defined(CONFIG_64BIT) && defined(CONFIG_PA20)
+	/* This 32-bit kernel was compiled for PA2.0 CPUs. Check current CPU
+	 * and halt kernel if we detect a PA1.x CPU. */
+	ldi		32,%r10
+	mtctl		%r10,%cr11
+	.level 2.0
+	mfctl,w		%cr11,%r10
+	.level 1.1
+	comib,<>,n	0,%r10,$cpu_ok
+
+	load32		PA(msg1),%arg0
+	ldi		msg1_end-msg1,%arg1
+$iodc_panic:
+	copy		%arg0, %r10
+	copy		%arg1, %r11
+	load32		PA(init_stack),%sp
+#define MEM_CONS 0x3A0
+	ldw		MEM_CONS+32(%r0),%arg0	// HPA
+	ldi		ENTRY_IO_COUT,%arg1
+	ldw		MEM_CONS+36(%r0),%arg2	// SPA
+	ldw		MEM_CONS+8(%r0),%arg3	// layers
+	load32		PA(__bss_start),%r1
+	stw		%r1,-52(%sp)		// arg4
+	stw		%r0,-56(%sp)		// arg5
+	stw		%r10,-60(%sp)		// arg6 = ptr to text
+	stw		%r11,-64(%sp)		// arg7 = len
+	stw		%r0,-68(%sp)		// arg8
+	load32		PA(.iodc_panic_ret), %rp
+	ldw		MEM_CONS+40(%r0),%r1	// ENTRY_IODC
+	bv,n		(%r1)
+.iodc_panic_ret:
+	b .				/* wait endless with ... */
+	or		%r10,%r10,%r10	/* qemu idle sleep */
+msg1:	.ascii "Can't boot kernel which was built for PA8x00 CPUs on this machine.\r\n"
+msg1_end:
+
+$cpu_ok:
+#endif
+
+	.level	PA_ASM_LEVEL
+
 	/* Initialize startup VM. Just map first 16/32 MB of memory */
 	load32		PA(swapper_pg_dir),%r4
 	mtctl		%r4,%cr24	/* Initialize kernel root pointer */
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index bf751e0732b7..c23f4fa17005 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -413,7 +413,7 @@
 412	32	utimensat_time64		sys_utimensat			sys_utimensat
 413	32	pselect6_time64			sys_pselect6			compat_sys_pselect6_time64
 414	32	ppoll_time64			sys_ppoll			compat_sys_ppoll_time64
-416	32	io_pgetevents_time64		sys_io_pgetevents		sys_io_pgetevents
+416	32	io_pgetevents_time64		sys_io_pgetevents		compat_sys_io_pgetevents_time64
 417	32	recvmmsg_time64			sys_recvmmsg			compat_sys_recvmmsg_time64
 418	32	mq_timedsend_time64		sys_mq_timedsend		sys_mq_timedsend
 419	32	mq_timedreceive_time64		sys_mq_timedreceive		sys_mq_timedreceive
diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c
index 286cec4d86d7..cc6ed7496050 100644
--- a/arch/parisc/kernel/unaligned.c
+++ b/arch/parisc/kernel/unaligned.c
@@ -107,7 +107,7 @@
 #define R1(i) (((i)>>21)&0x1f)
 #define R2(i) (((i)>>16)&0x1f)
 #define R3(i) ((i)&0x1f)
-#define FR3(i) ((((i)<<1)&0x1f)|(((i)>>6)&1))
+#define FR3(i) ((((i)&0x1f)<<1)|(((i)>>6)&1))
 #define IM(i,n) (((i)>>1&((1<<(n-1))-1))|((i)&1?((0-1L)<<(n-1)):0))
 #define IM5_2(i) IM((i)>>16,5)
 #define IM5_3(i) IM((i),5)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 1298dea53506..8629bd1fc9f4 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -353,6 +353,10 @@ config ARCH_SUSPEND_NONZERO_CPU
 	def_bool y
 	depends on PPC_POWERNV || PPC_PSERIES
 
+config ARCH_HAS_ADD_PAGES
+	def_bool y
+	depends on ARCH_ENABLE_MEMORY_HOTPLUG
+
 config PPC_DCR_NATIVE
 	bool
 
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index f8abfcdc23b4..210da66b3cdf 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -17,23 +17,6 @@ HAS_BIARCH	:= $(call cc-option-yn, -m32)
 # Set default 32 bits cross compilers for vdso and boot wrapper
 CROSS32_COMPILE ?=
 
-ifeq ($(HAS_BIARCH),y)
-ifeq ($(CROSS32_COMPILE),)
-ifdef CONFIG_PPC32
-# These options will be overridden by any -mcpu option that the CPU
-# or platform code sets later on the command line, but they are needed
-# to set a sane 32-bit cpu target for the 64-bit cross compiler which
-# may default to the wrong ISA.
-KBUILD_CFLAGS		+= -mcpu=powerpc
-KBUILD_AFLAGS		+= -mcpu=powerpc
-endif
-endif
-endif
-
-ifdef CONFIG_PPC_BOOK3S_32
-KBUILD_CFLAGS		+= -mcpu=powerpc
-endif
-
 # If we're on a ppc/ppc64/ppc64le machine use that defconfig, otherwise just use
 # ppc64_defconfig because we have nothing better to go on.
 uname := $(shell uname -m)
@@ -185,6 +168,7 @@ endif
 endif
 
 CFLAGS-$(CONFIG_TARGET_CPU_BOOL) += $(call cc-option,-mcpu=$(CONFIG_TARGET_CPU))
+AFLAGS-$(CONFIG_TARGET_CPU_BOOL) += $(call cc-option,-mcpu=$(CONFIG_TARGET_CPU))
 
 # Altivec option not allowed with e500mc64 in GCC.
 ifdef CONFIG_ALTIVEC
@@ -195,14 +179,6 @@ endif
 CFLAGS-$(CONFIG_E5500_CPU) += $(E5500_CPU)
 CFLAGS-$(CONFIG_E6500_CPU) += $(call cc-option,-mcpu=e6500,$(E5500_CPU))
 
-ifdef CONFIG_PPC32
-ifdef CONFIG_PPC_E500MC
-CFLAGS-y += $(call cc-option,-mcpu=e500mc,-mcpu=powerpc)
-else
-CFLAGS-$(CONFIG_E500) += $(call cc-option,-mcpu=8540 -msoft-float,-mcpu=powerpc)
-endif
-endif
-
 asinstr := $(call as-instr,lis 9$(comma)foo@high,-DHAVE_AS_ATHIGH=1)
 
 KBUILD_CPPFLAGS	+= -I $(srctree)/arch/$(ARCH) $(asinstr)
diff --git a/arch/powerpc/boot/crt0.S b/arch/powerpc/boot/crt0.S
index 1d83966f5ef6..e8f10a599659 100644
--- a/arch/powerpc/boot/crt0.S
+++ b/arch/powerpc/boot/crt0.S
@@ -226,16 +226,19 @@ p_base:	mflr	r10		/* r10 now points to runtime addr of p_base */
 #ifdef __powerpc64__
 
 #define PROM_FRAME_SIZE 512
-#define SAVE_GPR(n, base)       std     n,8*(n)(base)
-#define REST_GPR(n, base)       ld      n,8*(n)(base)
-#define SAVE_2GPRS(n, base)     SAVE_GPR(n, base); SAVE_GPR(n+1, base)
-#define SAVE_4GPRS(n, base)     SAVE_2GPRS(n, base); SAVE_2GPRS(n+2, base)
-#define SAVE_8GPRS(n, base)     SAVE_4GPRS(n, base); SAVE_4GPRS(n+4, base)
-#define SAVE_10GPRS(n, base)    SAVE_8GPRS(n, base); SAVE_2GPRS(n+8, base)
-#define REST_2GPRS(n, base)     REST_GPR(n, base); REST_GPR(n+1, base)
-#define REST_4GPRS(n, base)     REST_2GPRS(n, base); REST_2GPRS(n+2, base)
-#define REST_8GPRS(n, base)     REST_4GPRS(n, base); REST_4GPRS(n+4, base)
-#define REST_10GPRS(n, base)    REST_8GPRS(n, base); REST_2GPRS(n+8, base)
+
+.macro OP_REGS op, width, start, end, base, offset
+	.Lreg=\start
+	.rept (\end - \start + 1)
+	\op	.Lreg,\offset+\width*.Lreg(\base)
+	.Lreg=.Lreg+1
+	.endr
+.endm
+
+#define SAVE_GPRS(start, end, base)	OP_REGS std, 8, start, end, base, 0
+#define REST_GPRS(start, end, base)	OP_REGS ld, 8, start, end, base, 0
+#define SAVE_GPR(n, base)		SAVE_GPRS(n, n, base)
+#define REST_GPR(n, base)		REST_GPRS(n, n, base)
 
 /* prom handles the jump into and return from firmware.  The prom args pointer
    is loaded in r3. */
@@ -246,9 +249,7 @@ prom:
 	stdu	r1,-PROM_FRAME_SIZE(r1) /* Save SP and create stack space */
 
 	SAVE_GPR(2, r1)
-	SAVE_GPR(13, r1)
-	SAVE_8GPRS(14, r1)
-	SAVE_10GPRS(22, r1)
+	SAVE_GPRS(13, 31, r1)
 	mfcr    r10
 	std     r10,8*32(r1)
 	mfmsr   r10
@@ -283,9 +284,7 @@ prom:
 
 	/* Restore other registers */
 	REST_GPR(2, r1)
-	REST_GPR(13, r1)
-	REST_8GPRS(14, r1)
-	REST_10GPRS(22, r1)
+	REST_GPRS(13, 31, r1)
 	ld      r10,8*32(r1)
 	mtcr	r10
 
diff --git a/arch/powerpc/crypto/md5-asm.S b/arch/powerpc/crypto/md5-asm.S
index 948d100a2934..fa6bc440cf4a 100644
--- a/arch/powerpc/crypto/md5-asm.S
+++ b/arch/powerpc/crypto/md5-asm.S
@@ -38,15 +38,11 @@
 
 #define INITIALIZE \
 	PPC_STLU r1,-INT_FRAME_SIZE(r1); \
-	SAVE_8GPRS(14, r1);		/* push registers onto stack	*/ \
-	SAVE_4GPRS(22, r1);						   \
-	SAVE_GPR(26, r1)
+	SAVE_GPRS(14, 26, r1)		/* push registers onto stack	*/
 
 #define FINALIZE \
-	REST_8GPRS(14, r1);		/* pop registers from stack	*/ \
-	REST_4GPRS(22, r1);						   \
-	REST_GPR(26, r1);						   \
-	addi	r1,r1,INT_FRAME_SIZE;
+	REST_GPRS(14, 26, r1);		/* pop registers from stack	*/ \
+	addi	r1,r1,INT_FRAME_SIZE
 
 #ifdef __BIG_ENDIAN__
 #define LOAD_DATA(reg, off) \
diff --git a/arch/powerpc/crypto/sha1-powerpc-asm.S b/arch/powerpc/crypto/sha1-powerpc-asm.S
index 23e248beff71..f0d5ed557ab1 100644
--- a/arch/powerpc/crypto/sha1-powerpc-asm.S
+++ b/arch/powerpc/crypto/sha1-powerpc-asm.S
@@ -125,8 +125,7 @@
 
 _GLOBAL(powerpc_sha_transform)
 	PPC_STLU r1,-INT_FRAME_SIZE(r1)
-	SAVE_8GPRS(14, r1)
-	SAVE_10GPRS(22, r1)
+	SAVE_GPRS(14, 31, r1)
 
 	/* Load up A - E */
 	lwz	RA(0),0(r3)	/* A */
@@ -184,7 +183,6 @@ _GLOBAL(powerpc_sha_transform)
 	stw	RD(0),12(r3)
 	stw	RE(0),16(r3)
 
-	REST_8GPRS(14, r1)
-	REST_10GPRS(22, r1)
+	REST_GPRS(14, 31, r1)
 	addi	r1,r1,INT_FRAME_SIZE
 	blr
diff --git a/arch/powerpc/include/asm/archrandom.h b/arch/powerpc/include/asm/archrandom.h
index 9a53e29680f4..258174304904 100644
--- a/arch/powerpc/include/asm/archrandom.h
+++ b/arch/powerpc/include/asm/archrandom.h
@@ -38,12 +38,7 @@ static inline bool __must_check arch_get_random_seed_int(unsigned int *v)
 #endif /* CONFIG_ARCH_RANDOM */
 
 #ifdef CONFIG_PPC_POWERNV
-int powernv_hwrng_present(void);
 int powernv_get_random_long(unsigned long *v);
-int powernv_get_random_real_mode(unsigned long *v);
-#else
-static inline int powernv_hwrng_present(void) { return 0; }
-static inline int powernv_get_random_real_mode(unsigned long *v) { return 0; }
 #endif
 
 #endif /* _ASM_POWERPC_ARCHRANDOM_H */
diff --git a/arch/powerpc/include/asm/bpf_perf_event.h b/arch/powerpc/include/asm/bpf_perf_event.h
new file mode 100644
index 000000000000..e8a7b4ffb58c
--- /dev/null
+++ b/arch/powerpc/include/asm/bpf_perf_event.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BPF_PERF_EVENT_H
+#define _ASM_POWERPC_BPF_PERF_EVENT_H
+
+#include <asm/ptrace.h>
+
+typedef struct user_pt_regs bpf_user_pt_regs_t;
+
+#endif /* _ASM_POWERPC_BPF_PERF_EVENT_H */
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 1c538a9a11e0..f21e6bde17a1 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -17,29 +17,40 @@
 #define SZL			(BITS_PER_LONG/8)
 
 /*
+ * This expands to a sequence of operations with reg incrementing from
+ * start to end inclusive, of this form:
+ *
+ *   op  reg, (offset + (width * reg))(base)
+ *
+ * Note that offset is not the offset of the first operation unless start
+ * is zero (or width is zero).
+ */
+.macro OP_REGS op, width, start, end, base, offset
+	.Lreg=\start
+	.rept (\end - \start + 1)
+	\op	.Lreg, \offset + \width * .Lreg(\base)
+	.Lreg=.Lreg+1
+	.endr
+.endm
+
+/*
  * Macros for storing registers into and loading registers from
  * exception frames.
  */
 #ifdef __powerpc64__
-#define SAVE_GPR(n, base)	std	n,GPR0+8*(n)(base)
-#define REST_GPR(n, base)	ld	n,GPR0+8*(n)(base)
-#define SAVE_NVGPRS(base)	SAVE_8GPRS(14, base); SAVE_10GPRS(22, base)
-#define REST_NVGPRS(base)	REST_8GPRS(14, base); REST_10GPRS(22, base)
+#define SAVE_GPRS(start, end, base)	OP_REGS std, 8, start, end, base, GPR0
+#define REST_GPRS(start, end, base)	OP_REGS ld, 8, start, end, base, GPR0
+#define SAVE_NVGPRS(base)		SAVE_GPRS(14, 31, base)
+#define REST_NVGPRS(base)		REST_GPRS(14, 31, base)
 #else
-#define SAVE_GPR(n, base)	stw	n,GPR0+4*(n)(base)
-#define REST_GPR(n, base)	lwz	n,GPR0+4*(n)(base)
-#define SAVE_NVGPRS(base)	stmw	13, GPR0+4*13(base)
-#define REST_NVGPRS(base)	lmw	13, GPR0+4*13(base)
+#define SAVE_GPRS(start, end, base)	OP_REGS stw, 4, start, end, base, GPR0
+#define REST_GPRS(start, end, base)	OP_REGS lwz, 4, start, end, base, GPR0
+#define SAVE_NVGPRS(base)		SAVE_GPRS(13, 31, base)
+#define REST_NVGPRS(base)		REST_GPRS(13, 31, base)
 #endif
 
-#define SAVE_2GPRS(n, base)	SAVE_GPR(n, base); SAVE_GPR(n+1, base)
-#define SAVE_4GPRS(n, base)	SAVE_2GPRS(n, base); SAVE_2GPRS(n+2, base)
-#define SAVE_8GPRS(n, base)	SAVE_4GPRS(n, base); SAVE_4GPRS(n+4, base)
-#define SAVE_10GPRS(n, base)	SAVE_8GPRS(n, base); SAVE_2GPRS(n+8, base)
-#define REST_2GPRS(n, base)	REST_GPR(n, base); REST_GPR(n+1, base)
-#define REST_4GPRS(n, base)	REST_2GPRS(n, base); REST_2GPRS(n+2, base)
-#define REST_8GPRS(n, base)	REST_4GPRS(n, base); REST_4GPRS(n+4, base)
-#define REST_10GPRS(n, base)	REST_8GPRS(n, base); REST_2GPRS(n+8, base)
+#define SAVE_GPR(n, base)		SAVE_GPRS(n, n, base)
+#define REST_GPR(n, base)		REST_GPRS(n, n, base)
 
 #define SAVE_FPR(n, base)	stfd	n,8*TS_FPRWIDTH*(n)(base)
 #define SAVE_2FPRS(n, base)	SAVE_FPR(n, base); SAVE_FPR(n+1, base)
diff --git a/arch/powerpc/include/asm/simple_spinlock.h b/arch/powerpc/include/asm/simple_spinlock.h
index 8985791a2ba5..3c037a12c84d 100644
--- a/arch/powerpc/include/asm/simple_spinlock.h
+++ b/arch/powerpc/include/asm/simple_spinlock.h
@@ -48,10 +48,11 @@ static inline int arch_spin_is_locked(arch_spinlock_t *lock)
 static inline unsigned long __arch_spin_trylock(arch_spinlock_t *lock)
 {
 	unsigned long tmp, token;
+	unsigned int eh = IS_ENABLED(CONFIG_PPC64);
 
 	token = LOCK_TOKEN;
 	__asm__ __volatile__(
-"1:	lwarx		%0,0,%2,1\n\
+"1:	lwarx		%0,0,%2,%[eh]\n\
 	cmpwi		0,%0,0\n\
 	bne-		2f\n\
 	stwcx.		%1,0,%2\n\
@@ -59,7 +60,7 @@ static inline unsigned long __arch_spin_trylock(arch_spinlock_t *lock)
 	PPC_ACQUIRE_BARRIER
 "2:"
 	: "=&r" (tmp)
-	: "r" (token), "r" (&lock->slock)
+	: "r" (token), "r" (&lock->slock), [eh] "n" (eh)
 	: "cr0", "memory");
 
 	return tmp;
@@ -177,9 +178,10 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 static inline long __arch_read_trylock(arch_rwlock_t *rw)
 {
 	long tmp;
+	unsigned int eh = IS_ENABLED(CONFIG_PPC64);
 
 	__asm__ __volatile__(
-"1:	lwarx		%0,0,%1,1\n"
+"1:	lwarx		%0,0,%1,%[eh]\n"
 	__DO_SIGN_EXTEND
 "	addic.		%0,%0,1\n\
 	ble-		2f\n"
@@ -187,7 +189,7 @@ static inline long __arch_read_trylock(arch_rwlock_t *rw)
 	bne-		1b\n"
 	PPC_ACQUIRE_BARRIER
 "2:"	: "=&r" (tmp)
-	: "r" (&rw->lock)
+	: "r" (&rw->lock), [eh] "n" (eh)
 	: "cr0", "xer", "memory");
 
 	return tmp;
@@ -200,17 +202,18 @@ static inline long __arch_read_trylock(arch_rwlock_t *rw)
 static inline long __arch_write_trylock(arch_rwlock_t *rw)
 {
 	long tmp, token;
+	unsigned int eh = IS_ENABLED(CONFIG_PPC64);
 
 	token = WRLOCK_TOKEN;
 	__asm__ __volatile__(
-"1:	lwarx		%0,0,%2,1\n\
+"1:	lwarx		%0,0,%2,%[eh]\n\
 	cmpwi		0,%0,0\n\
 	bne-		2f\n"
 "	stwcx.		%1,0,%2\n\
 	bne-		1b\n"
 	PPC_ACQUIRE_BARRIER
 "2:"	: "=&r" (tmp)
-	: "r" (token), "r" (&rw->lock)
+	: "r" (token), "r" (&rw->lock), [eh] "n" (eh)
 	: "cr0", "memory");
 
 	return tmp;
diff --git a/arch/powerpc/include/uapi/asm/bpf_perf_event.h b/arch/powerpc/include/uapi/asm/bpf_perf_event.h
deleted file mode 100644
index 5e1e648aeec4..000000000000
--- a/arch/powerpc/include/uapi/asm/bpf_perf_event.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__
-#define _UAPI__ASM_BPF_PERF_EVENT_H__
-
-#include <asm/ptrace.h>
-
-typedef struct user_pt_regs bpf_user_pt_regs_t;
-
-#endif /* _UAPI__ASM_BPF_PERF_EVENT_H__ */
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 36cf82e76e96..364eb06082d1 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -20,6 +20,7 @@ CFLAGS_prom.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
 CFLAGS_prom_init.o += -fno-stack-protector
 CFLAGS_prom_init.o += -DDISABLE_BRANCH_PROFILING
 CFLAGS_prom_init.o += -ffreestanding
+CFLAGS_prom_init.o += $(call cc-option, -ftrivial-auto-var-init=uninitialized)
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not trace early boot code
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 61fdd53cdd9a..c62dd9815965 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -90,8 +90,7 @@ transfer_to_syscall:
 	stw	r12,8(r1)
 	stw	r2,_TRAP(r1)
 	SAVE_GPR(0, r1)
-	SAVE_4GPRS(3, r1)
-	SAVE_2GPRS(7, r1)
+	SAVE_GPRS(3, 8, r1)
 	addi	r2,r10,-THREAD
 	SAVE_NVGPRS(r1)
 
@@ -139,7 +138,7 @@ syscall_exit_finish:
 	mtxer	r5
 	lwz	r0,GPR0(r1)
 	lwz	r3,GPR3(r1)
-	REST_8GPRS(4,r1)
+	REST_GPRS(4, 11, r1)
 	lwz	r12,GPR12(r1)
 	b	1b
 
@@ -232,9 +231,9 @@ fast_exception_return:
 	beq	3f			/* if not, we've got problems */
 #endif
 
-2:	REST_4GPRS(3, r11)
+2:	REST_GPRS(3, 6, r11)
 	lwz	r10,_CCR(r11)
-	REST_2GPRS(1, r11)
+	REST_GPRS(1, 2, r11)
 	mtcr	r10
 	lwz	r10,_LINK(r11)
 	mtlr	r10
@@ -298,16 +297,14 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 	 * the reliable stack unwinder later on. Clear it.
 	 */
 	stw	r0,8(r1)
-	REST_4GPRS(7, r1)
-	REST_2GPRS(11, r1)
+	REST_GPRS(7, 12, r1)
 
 	mtcr	r3
 	mtlr	r4
 	mtctr	r5
 	mtspr	SPRN_XER,r6
 
-	REST_4GPRS(2, r1)
-	REST_GPR(6, r1)
+	REST_GPRS(2, 6, r1)
 	REST_GPR(0, r1)
 	REST_GPR(1, r1)
 	rfi
@@ -341,8 +338,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 	lwz	r6,_CCR(r1)
 	li	r0,0
 
-	REST_4GPRS(7, r1)
-	REST_2GPRS(11, r1)
+	REST_GPRS(7, 12, r1)
 
 	mtlr	r3
 	mtctr	r4
@@ -354,7 +350,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 	 */
 	stw	r0,8(r1)
 
-	REST_4GPRS(2, r1)
+	REST_GPRS(2, 5, r1)
 
 	bne-	cr1,1f /* emulate stack store */
 	mtcr	r6
@@ -430,8 +426,7 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return)
 	bne	interrupt_return;					\
 	lwz	r0,GPR0(r1);						\
 	lwz	r2,GPR2(r1);						\
-	REST_4GPRS(3, r1);						\
-	REST_2GPRS(7, r1);						\
+	REST_GPRS(3, 8, r1);						\
 	lwz	r10,_XER(r1);						\
 	lwz	r11,_CTR(r1);						\
 	mtspr	SPRN_XER,r10;						\
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 711c66b76df1..67dc4e3179a0 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -198,8 +198,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
 
 	stdcx.	r0,0,r1		/* to clear the reservation */
 
-	REST_4GPRS(2, r1)
-	REST_4GPRS(6, r1)
+	REST_GPRS(2, 9, r1)
 
 	ld	r10,_CTR(r1)
 	ld	r11,_XER(r1)
@@ -375,9 +374,7 @@ ret_from_mc_except:
 exc_##n##_common:							    \
 	std	r0,GPR0(r1);		/* save r0 in stackframe */	    \
 	std	r2,GPR2(r1);		/* save r2 in stackframe */	    \
-	SAVE_4GPRS(3, r1);		/* save r3 - r6 in stackframe */    \
-	SAVE_2GPRS(7, r1);		/* save r7, r8 in stackframe */	    \
-	std	r9,GPR9(r1);		/* save r9 in stackframe */	    \
+	SAVE_GPRS(3, 9, r1);		/* save r3 - r9 in stackframe */    \
 	std	r10,_NIP(r1);		/* save SRR0 to stackframe */	    \
 	std	r11,_MSR(r1);		/* save SRR1 to stackframe */	    \
 	beq	2f;			/* if from kernel mode */	    \
@@ -1061,9 +1058,7 @@ bad_stack_book3e:
 	std	r11,_ESR(r1)
 	std	r0,GPR0(r1);		/* save r0 in stackframe */	    \
 	std	r2,GPR2(r1);		/* save r2 in stackframe */	    \
-	SAVE_4GPRS(3, r1);		/* save r3 - r6 in stackframe */    \
-	SAVE_2GPRS(7, r1);		/* save r7, r8 in stackframe */	    \
-	std	r9,GPR9(r1);		/* save r9 in stackframe */	    \
+	SAVE_GPRS(3, 9, r1);		/* save r3 - r9 in stackframe */    \
 	ld	r3,PACA_EXGEN+EX_R10(r13);/* get back r10 */		    \
 	ld	r4,PACA_EXGEN+EX_R11(r13);/* get back r11 */		    \
 	mfspr	r5,SPRN_SPRG_GEN_SCRATCH;/* get back r13 XXX can be wrong */ \
@@ -1077,8 +1072,7 @@ bad_stack_book3e:
 	std	r10,_LINK(r1)
 	std	r11,_CTR(r1)
 	std	r12,_XER(r1)
-	SAVE_10GPRS(14,r1)
-	SAVE_8GPRS(24,r1)
+	SAVE_GPRS(14, 31, r1)
 	lhz	r12,PACA_TRAP_SAVE(r13)
 	std	r12,_TRAP(r1)
 	addi	r11,r1,INT_FRAME_SIZE
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index eaf1f72131a1..277eccf0f086 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -574,8 +574,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 	ld	r10,IAREA+EX_CTR(r13)
 	std	r10,_CTR(r1)
 	std	r2,GPR2(r1)		/* save r2 in stackframe	*/
-	SAVE_4GPRS(3, r1)		/* save r3 - r6 in stackframe   */
-	SAVE_2GPRS(7, r1)		/* save r7, r8 in stackframe	*/
+	SAVE_GPRS(3, 8, r1)		/* save r3 - r8 in stackframe   */
 	mflr	r9			/* Get LR, later save to stack	*/
 	ld	r2,PACATOC(r13)		/* get kernel TOC into r2	*/
 	std	r9,_LINK(r1)
@@ -693,8 +692,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 	mtlr	r9
 	ld	r9,_CCR(r1)
 	mtcr	r9
-	REST_8GPRS(2, r1)
-	REST_4GPRS(10, r1)
+	REST_GPRS(2, 13, r1)
 	REST_GPR(0, r1)
 	/* restore original r1. */
 	ld	r1,GPR1(r1)
diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h
index 349c4a820231..261c79bdbe53 100644
--- a/arch/powerpc/kernel/head_32.h
+++ b/arch/powerpc/kernel/head_32.h
@@ -115,8 +115,7 @@ _ASM_NOKPROBE_SYMBOL(\name\()_virt)
 	stw	r10,8(r1)
 	li	r10, \trapno
 	stw	r10,_TRAP(r1)
-	SAVE_4GPRS(3, r1)
-	SAVE_2GPRS(7, r1)
+	SAVE_GPRS(3, 8, r1)
 	SAVE_NVGPRS(r1)
 	stw	r2,GPR2(r1)
 	stw	r12,_NIP(r1)
diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S
index 2e2a8211b17b..68e5c0a7e99d 100644
--- a/arch/powerpc/kernel/head_book3s_32.S
+++ b/arch/powerpc/kernel/head_book3s_32.S
@@ -421,14 +421,14 @@ InstructionTLBMiss:
  */
 	/* Get PTE (linux-style) and check access */
 	mfspr	r3,SPRN_IMISS
-#if defined(CONFIG_MODULES) || defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
+#ifdef CONFIG_MODULES
 	lis	r1, TASK_SIZE@h		/* check if kernel address */
 	cmplw	0,r1,r3
 #endif
 	mfspr	r2, SPRN_SDR1
 	li	r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC | _PAGE_USER
 	rlwinm	r2, r2, 28, 0xfffff000
-#if defined(CONFIG_MODULES) || defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
+#ifdef CONFIG_MODULES
 	bgt-	112f
 	lis	r2, (swapper_pg_dir - PAGE_OFFSET)@ha	/* if kernel address, use */
 	li	r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index ef8d1b1c234e..bb6d5d0fc4ac 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -87,8 +87,7 @@ END_BTB_FLUSH_SECTION
 	stw	r10, 8(r1)
 	li	r10, \trapno
 	stw	r10,_TRAP(r1)
-	SAVE_4GPRS(3, r1)
-	SAVE_2GPRS(7, r1)
+	SAVE_GPRS(3, 8, r1)
 	SAVE_NVGPRS(r1)
 	stw	r2,GPR2(r1)
 	stw	r12,_NIP(r1)
diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S
index 4c6d1a8dcefe..ff8c8c03f41a 100644
--- a/arch/powerpc/kernel/interrupt_64.S
+++ b/arch/powerpc/kernel/interrupt_64.S
@@ -166,10 +166,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	 * The value of AMR only matters while we're in the kernel.
 	 */
 	mtcr	r2
-	ld	r2,GPR2(r1)
-	ld	r3,GPR3(r1)
-	ld	r13,GPR13(r1)
-	ld	r1,GPR1(r1)
+	REST_GPRS(2, 3, r1)
+	REST_GPR(13, r1)
+	REST_GPR(1, r1)
 	RFSCV_TO_USER
 	b	.	/* prevent speculative execution */
 
@@ -187,9 +186,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	mtctr	r3
 	mtlr	r4
 	mtspr	SPRN_XER,r5
-	REST_10GPRS(2, r1)
-	REST_2GPRS(12, r1)
-	ld	r1,GPR1(r1)
+	REST_GPRS(2, 13, r1)
+	REST_GPR(1, r1)
 	RFI_TO_USER
 .Lsyscall_vectored_\name\()_rst_end:
 
@@ -378,10 +376,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	 * The value of AMR only matters while we're in the kernel.
 	 */
 	mtcr	r2
-	ld	r2,GPR2(r1)
-	ld	r3,GPR3(r1)
-	ld	r13,GPR13(r1)
-	ld	r1,GPR1(r1)
+	REST_GPRS(2, 3, r1)
+	REST_GPR(13, r1)
+	REST_GPR(1, r1)
 	RFI_TO_USER
 	b	.	/* prevent speculative execution */
 
@@ -392,8 +389,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	mtctr	r3
 	mtspr	SPRN_XER,r4
 	ld	r0,GPR0(r1)
-	REST_8GPRS(4, r1)
-	ld	r12,GPR12(r1)
+	REST_GPRS(4, 12, r1)
 	b	.Lsyscall_restore_regs_cont
 .Lsyscall_rst_end:
 
@@ -522,17 +518,14 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 	ld	r6,_XER(r1)
 	li	r0,0
 
-	REST_4GPRS(7, r1)
-	REST_2GPRS(11, r1)
-	REST_GPR(13, r1)
+	REST_GPRS(7, 13, r1)
 
 	mtcr	r3
 	mtlr	r4
 	mtctr	r5
 	mtspr	SPRN_XER,r6
 
-	REST_4GPRS(2, r1)
-	REST_GPR(6, r1)
+	REST_GPRS(2, 6, r1)
 	REST_GPR(0, r1)
 	REST_GPR(1, r1)
 	.ifc \srr,srr
@@ -629,8 +622,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 	ld	r6,_CCR(r1)
 	li	r0,0
 
-	REST_4GPRS(7, r1)
-	REST_2GPRS(11, r1)
+	REST_GPRS(7, 12, r1)
 
 	mtlr	r3
 	mtctr	r4
@@ -642,7 +634,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 	 */
 	std	r0,STACK_FRAME_OVERHEAD-16(r1)
 
-	REST_4GPRS(2, r1)
+	REST_GPRS(2, 5, r1)
 
 	bne-	cr1,1f /* emulate stack store */
 	mtcr	r6
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 07093b7cdcb9..a67fd54ccc57 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -776,6 +776,11 @@ bool iommu_table_in_use(struct iommu_table *tbl)
 	/* ignore reserved bit0 */
 	if (tbl->it_offset == 0)
 		start = 1;
+
+	/* Simple case with no reserved MMIO32 region */
+	if (!tbl->it_reserved_start && !tbl->it_reserved_end)
+		return find_next_bit(tbl->it_map, tbl->it_size, start) != tbl->it_size;
+
 	end = tbl->it_reserved_start - tbl->it_offset;
 	if (find_next_bit(tbl->it_map, end, start) != end)
 		return true;
diff --git a/arch/powerpc/kernel/optprobes_head.S b/arch/powerpc/kernel/optprobes_head.S
index 19ea3312403c..5c7f0b4b784b 100644
--- a/arch/powerpc/kernel/optprobes_head.S
+++ b/arch/powerpc/kernel/optprobes_head.S
@@ -10,8 +10,8 @@
 #include <asm/asm-offsets.h>
 
 #ifdef CONFIG_PPC64
-#define SAVE_30GPRS(base) SAVE_10GPRS(2,base); SAVE_10GPRS(12,base); SAVE_10GPRS(22,base)
-#define REST_30GPRS(base) REST_10GPRS(2,base); REST_10GPRS(12,base); REST_10GPRS(22,base)
+#define SAVE_30GPRS(base) SAVE_GPRS(2, 31, base)
+#define REST_30GPRS(base) REST_GPRS(2, 31, base)
 #define TEMPLATE_FOR_IMM_LOAD_INSNS	nop; nop; nop; nop; nop
 #else
 #define SAVE_30GPRS(base) stmw	r2, GPR2(base)
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index c3573430919d..1aabb82b5f37 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -67,23 +67,35 @@ void set_pci_dma_ops(const struct dma_map_ops *dma_ops)
 	pci_dma_ops = dma_ops;
 }
 
-/*
- * This function should run under locking protection, specifically
- * hose_spinlock.
- */
 static int get_phb_number(struct device_node *dn)
 {
 	int ret, phb_id = -1;
-	u32 prop_32;
 	u64 prop;
 
 	/*
 	 * Try fixed PHB numbering first, by checking archs and reading
-	 * the respective device-tree properties. Firstly, try powernv by
-	 * reading "ibm,opal-phbid", only present in OPAL environment.
+	 * the respective device-tree properties. Firstly, try reading
+	 * standard "linux,pci-domain", then try reading "ibm,opal-phbid"
+	 * (only present in powernv OPAL environment), then try device-tree
+	 * alias and as the last try to use lower bits of "reg" property.
 	 */
-	ret = of_property_read_u64(dn, "ibm,opal-phbid", &prop);
+	ret = of_get_pci_domain_nr(dn);
+	if (ret >= 0) {
+		prop = ret;
+		ret = 0;
+	}
+	if (ret)
+		ret = of_property_read_u64(dn, "ibm,opal-phbid", &prop);
+
 	if (ret) {
+		ret = of_alias_get_id(dn, "pci");
+		if (ret >= 0) {
+			prop = ret;
+			ret = 0;
+		}
+	}
+	if (ret) {
+		u32 prop_32;
 		ret = of_property_read_u32_index(dn, "reg", 1, &prop_32);
 		prop = prop_32;
 	}
@@ -91,18 +103,20 @@ static int get_phb_number(struct device_node *dn)
 	if (!ret)
 		phb_id = (int)(prop & (MAX_PHBS - 1));
 
+	spin_lock(&hose_spinlock);
+
 	/* We need to be sure to not use the same PHB number twice. */
 	if ((phb_id >= 0) && !test_and_set_bit(phb_id, phb_bitmap))
-		return phb_id;
+		goto out_unlock;
 
-	/*
-	 * If not pseries nor powernv, or if fixed PHB numbering tried to add
-	 * the same PHB number twice, then fallback to dynamic PHB numbering.
-	 */
+	/* If everything fails then fallback to dynamic PHB numbering. */
 	phb_id = find_first_zero_bit(phb_bitmap, MAX_PHBS);
 	BUG_ON(phb_id >= MAX_PHBS);
 	set_bit(phb_id, phb_bitmap);
 
+out_unlock:
+	spin_unlock(&hose_spinlock);
+
 	return phb_id;
 }
 
@@ -113,10 +127,13 @@ struct pci_controller *pcibios_alloc_controller(struct device_node *dev)
 	phb = zalloc_maybe_bootmem(sizeof(struct pci_controller), GFP_KERNEL);
 	if (phb == NULL)
 		return NULL;
-	spin_lock(&hose_spinlock);
+
 	phb->global_number = get_phb_number(dev);
+
+	spin_lock(&hose_spinlock);
 	list_add_tail(&phb->list_node, &hose_list);
 	spin_unlock(&hose_spinlock);
+
 	phb->dn = dev;
 	phb->is_dynamic = slab_is_available();
 #ifdef CONFIG_PPC64
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 2e67588f6f6e..86ffbabd26c6 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -751,6 +751,13 @@ void __init early_init_devtree(void *params)
 	of_scan_flat_dt(early_init_dt_scan_root, NULL);
 	of_scan_flat_dt(early_init_dt_scan_memory_ppc, NULL);
 
+	/*
+	 * As generic code authors expect to be able to use static keys
+	 * in early_param() handlers, we initialize the static keys just
+	 * before parsing early params (it's fine to call jump_label_init()
+	 * more than once).
+	 */
+	jump_label_init();
 	parse_early_param();
 
 	/* make sure we've parsed cmdline for mem= before this */
diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh
index b183ab9c5107..dfa5f729f774 100644
--- a/arch/powerpc/kernel/prom_init_check.sh
+++ b/arch/powerpc/kernel/prom_init_check.sh
@@ -13,7 +13,7 @@
 # If you really need to reference something from prom_init.o add
 # it to the list below:
 
-grep "^CONFIG_KASAN=y$" .config >/dev/null
+grep "^CONFIG_KASAN=y$" ${KCONFIG_CONFIG} >/dev/null
 if [ $? -eq 0 ]
 then
 	MEM_FUNCS="__memcpy __memset"
diff --git a/arch/powerpc/kernel/systbl.S b/arch/powerpc/kernel/systbl.S
index cb3358886203..6c1db3b6de2d 100644
--- a/arch/powerpc/kernel/systbl.S
+++ b/arch/powerpc/kernel/systbl.S
@@ -18,6 +18,7 @@
 	.p2align	3
 #define __SYSCALL(nr, entry)	.8byte entry
 #else
+	.p2align	2
 #define __SYSCALL(nr, entry)	.long entry
 #endif
 
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index 2b91f233b05d..5a0f023a26e9 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -226,11 +226,8 @@ _GLOBAL(tm_reclaim)
 
 	/* Sync the userland GPRs 2-12, 14-31 to thread->regs: */
 	SAVE_GPR(0, r7)				/* user r0 */
-	SAVE_GPR(2, r7)				/* user r2 */
-	SAVE_4GPRS(3, r7)			/* user r3-r6 */
-	SAVE_GPR(8, r7)				/* user r8 */
-	SAVE_GPR(9, r7)				/* user r9 */
-	SAVE_GPR(10, r7)			/* user r10 */
+	SAVE_GPRS(2, 6, r7)			/* user r2-r6 */
+	SAVE_GPRS(8, 10, r7)			/* user r8-r10 */
 	ld	r3, GPR1(r1)			/* user r1 */
 	ld	r4, GPR7(r1)			/* user r7 */
 	ld	r5, GPR11(r1)			/* user r11 */
@@ -445,12 +442,9 @@ restore_gprs:
 	ld	r6, THREAD_TM_PPR(r3)
 
 	REST_GPR(0, r7)				/* GPR0 */
-	REST_2GPRS(2, r7)			/* GPR2-3 */
-	REST_GPR(4, r7)				/* GPR4 */
-	REST_4GPRS(8, r7)			/* GPR8-11 */
-	REST_2GPRS(12, r7)			/* GPR12-13 */
-
-	REST_NVGPRS(r7)				/* GPR14-31 */
+	REST_GPRS(2, 4, r7)			/* GPR2-4 */
+	REST_GPRS(8, 12, r7)			/* GPR8-12 */
+	REST_GPRS(14, 31, r7)			/* GPR14-31 */
 
 	/* Load up PPR and DSCR here so we don't run with user values for long */
 	mtspr	SPRN_DSCR, r5
@@ -486,18 +480,24 @@ restore_gprs:
 	REST_GPR(6, r7)
 
 	/*
-	 * Store r1 and r5 on the stack so that we can access them after we
-	 * clear MSR RI.
+	 * Store user r1 and r5 and r13 on the stack (in the unused save
+	 * areas / compiler reserved areas), so that we can access them after
+	 * we clear MSR RI.
 	 */
 
 	REST_GPR(5, r7)
 	std	r5, -8(r1)
-	ld	r5, GPR1(r7)
+	ld	r5, GPR13(r7)
 	std	r5, -16(r1)
+	ld	r5, GPR1(r7)
+	std	r5, -24(r1)
 
 	REST_GPR(7, r7)
 
-	/* Clear MSR RI since we are about to use SCRATCH0. EE is already off */
+	/* Stash the stack pointer away for use after recheckpoint */
+	std	r1, PACAR1(r13)
+
+	/* Clear MSR RI since we are about to clobber r13. EE is already off */
 	li	r5, 0
 	mtmsrd	r5, 1
 
@@ -508,9 +508,9 @@ restore_gprs:
 	 * until we turn MSR RI back on.
 	 */
 
-	SET_SCRATCH0(r1)
 	ld	r5, -8(r1)
-	ld	r1, -16(r1)
+	ld	r13, -16(r1)
+	ld	r1, -24(r1)
 
 	/* Commit register state as checkpointed state: */
 	TRECHKPT
@@ -526,9 +526,9 @@ restore_gprs:
 	 */
 
 	GET_PACA(r13)
-	GET_SCRATCH0(r1)
+	ld	r1, PACAR1(r13)
 
-	/* R1 is restored, so we are recoverable again.  EE is still off */
+	/* R13, R1 is restored, so we are recoverable again.  EE is still off */
 	li	r4, MSR_RI
 	mtmsrd	r4, 1
 
diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
index f9fd5f743eba..d636fc755f60 100644
--- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
+++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
@@ -41,15 +41,14 @@ _GLOBAL(ftrace_regs_caller)
 
 	/* Save all gprs to pt_regs */
 	SAVE_GPR(0, r1)
-	SAVE_10GPRS(2, r1)
+	SAVE_GPRS(2, 11, r1)
 
 	/* Ok to continue? */
 	lbz	r3, PACA_FTRACE_ENABLED(r13)
 	cmpdi	r3, 0
 	beq	ftrace_no_trace
 
-	SAVE_10GPRS(12, r1)
-	SAVE_10GPRS(22, r1)
+	SAVE_GPRS(12, 31, r1)
 
 	/* Save previous stack pointer (r1) */
 	addi	r8, r1, SWITCH_FRAME_SIZE
@@ -108,10 +107,8 @@ ftrace_regs_call:
 #endif
 
 	/* Restore gprs */
-	REST_GPR(0,r1)
-	REST_10GPRS(2,r1)
-	REST_10GPRS(12,r1)
-	REST_10GPRS(22,r1)
+	REST_GPR(0, r1)
+	REST_GPRS(2, 31, r1)
 
 	/* Restore possibly modified LR */
 	ld	r0, _LINK(r1)
@@ -157,7 +154,7 @@ _GLOBAL(ftrace_caller)
 	stdu	r1, -SWITCH_FRAME_SIZE(r1)
 
 	/* Save all gprs to pt_regs */
-	SAVE_8GPRS(3, r1)
+	SAVE_GPRS(3, 10, r1)
 
 	lbz	r3, PACA_FTRACE_ENABLED(r13)
 	cmpdi	r3, 0
@@ -194,7 +191,7 @@ ftrace_call:
 	mtctr	r3
 
 	/* Restore gprs */
-	REST_8GPRS(3,r1)
+	REST_GPRS(3, 10, r1)
 
 	/* Restore callee's TOC */
 	ld	r2, 24(r1)
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 70b7a8f97153..b148629b7f03 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -20,7 +20,7 @@
 #include <asm/interrupt.h>
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
-#include <asm/archrandom.h>
+#include <asm/machdep.h>
 #include <asm/xics.h>
 #include <asm/xive.h>
 #include <asm/dbell.h>
@@ -177,13 +177,14 @@ EXPORT_SYMBOL_GPL(kvmppc_hcall_impl_hv_realmode);
 
 int kvmppc_hwrng_present(void)
 {
-	return powernv_hwrng_present();
+	return ppc_md.get_random_seed != NULL;
 }
 EXPORT_SYMBOL_GPL(kvmppc_hwrng_present);
 
 long kvmppc_rm_h_random(struct kvm_vcpu *vcpu)
 {
-	if (powernv_get_random_real_mode(&vcpu->arch.regs.gpr[4]))
+	if (ppc_md.get_random_seed &&
+	    ppc_md.get_random_seed(&vcpu->arch.regs.gpr[4]))
 		return H_SUCCESS;
 
 	return H_HARDWARE;
diff --git a/arch/powerpc/kvm/book3s_hv_p9_entry.c b/arch/powerpc/kvm/book3s_hv_p9_entry.c
index 961b3d70483c..a0e0c28408c0 100644
--- a/arch/powerpc/kvm/book3s_hv_p9_entry.c
+++ b/arch/powerpc/kvm/book3s_hv_p9_entry.c
@@ -7,15 +7,6 @@
 #include <asm/ppc-opcode.h>
 
 #ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
-static void __start_timing(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator *next)
-{
-	struct kvmppc_vcore *vc = vcpu->arch.vcore;
-	u64 tb = mftb() - vc->tb_offset_applied;
-
-	vcpu->arch.cur_activity = next;
-	vcpu->arch.cur_tb_start = tb;
-}
-
 static void __accumulate_time(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator *next)
 {
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
@@ -47,8 +38,8 @@ static void __accumulate_time(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator
 	curr->seqcount = seq + 2;
 }
 
-#define start_timing(vcpu, next) __start_timing(vcpu, next)
-#define end_timing(vcpu) __start_timing(vcpu, NULL)
+#define start_timing(vcpu, next) __accumulate_time(vcpu, next)
+#define end_timing(vcpu) __accumulate_time(vcpu, NULL)
 #define accumulate_time(vcpu, next) __accumulate_time(vcpu, next)
 #else
 #define start_timing(vcpu, next) do {} while (0)
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 32a4b4d412b9..81fc1e0ebe9a 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -2711,8 +2711,7 @@ kvmppc_bad_host_intr:
 	std	r0, GPR0(r1)
 	std	r9, GPR1(r1)
 	std	r2, GPR2(r1)
-	SAVE_4GPRS(3, r1)
-	SAVE_2GPRS(7, r1)
+	SAVE_GPRS(3, 8, r1)
 	srdi	r0, r12, 32
 	clrldi	r12, r12, 32
 	std	r0, _CCR(r1)
@@ -2735,7 +2734,7 @@ kvmppc_bad_host_intr:
 	ld	r9, HSTATE_SCRATCH2(r13)
 	ld	r12, HSTATE_SCRATCH0(r13)
 	GET_SCRATCH0(r0)
-	SAVE_4GPRS(9, r1)
+	SAVE_GPRS(9, 12, r1)
 	std	r0, GPR13(r1)
 	SAVE_NVGPRS(r1)
 	ld	r5, HSTATE_CFAR(r13)
diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index 3fbe710ff839..3d4ee75b0fb7 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -251,7 +251,7 @@ int kvmppc_uvmem_slot_init(struct kvm *kvm, const struct kvm_memory_slot *slot)
 	p = kzalloc(sizeof(*p), GFP_KERNEL);
 	if (!p)
 		return -ENOMEM;
-	p->pfns = vzalloc(array_size(slot->npages, sizeof(*p->pfns)));
+	p->pfns = vcalloc(slot->npages, sizeof(*p->pfns));
 	if (!p->pfns) {
 		kfree(p);
 		return -ENOMEM;
diff --git a/arch/powerpc/lib/test_emulate_step_exec_instr.S b/arch/powerpc/lib/test_emulate_step_exec_instr.S
index 9ef941d958d8..5473f9d03df3 100644
--- a/arch/powerpc/lib/test_emulate_step_exec_instr.S
+++ b/arch/powerpc/lib/test_emulate_step_exec_instr.S
@@ -37,7 +37,7 @@ _GLOBAL(exec_instr)
 	 * The stack pointer (GPR1) and the thread pointer (GPR13) are not
 	 * saved as these should not be modified anyway.
 	 */
-	SAVE_2GPRS(2, r1)
+	SAVE_GPRS(2, 3, r1)
 	SAVE_NVGPRS(r1)
 
 	/*
@@ -75,8 +75,7 @@ _GLOBAL(exec_instr)
 
 	/* Load GPRs from pt_regs */
 	REST_GPR(0, r31)
-	REST_10GPRS(2, r31)
-	REST_GPR(12, r31)
+	REST_GPRS(2, 12, r31)
 	REST_NVGPRS(r31)
 
 	/* Placeholder for the test instruction */
@@ -99,8 +98,7 @@ _GLOBAL(exec_instr)
 	subi	r3, r3, GPR0
 	SAVE_GPR(0, r3)
 	SAVE_GPR(2, r3)
-	SAVE_8GPRS(4, r3)
-	SAVE_GPR(12, r3)
+	SAVE_GPRS(4, 12, r3)
 	SAVE_NVGPRS(r3)
 
 	/* Save resulting LR to pt_regs */
diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c
index 203735caf691..bfca0afe9112 100644
--- a/arch/powerpc/mm/book3s32/mmu.c
+++ b/arch/powerpc/mm/book3s32/mmu.c
@@ -160,7 +160,10 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
 {
 	unsigned long done;
 	unsigned long border = (unsigned long)__init_begin - PAGE_OFFSET;
+	unsigned long size;
 
+	size = roundup_pow_of_two((unsigned long)_einittext - PAGE_OFFSET);
+	setibat(0, PAGE_OFFSET, 0, size, PAGE_KERNEL_X);
 
 	if (debug_pagealloc_enabled_or_kfence() || __map_without_bats) {
 		pr_debug_once("Read-Write memory mapped without BATs\n");
@@ -246,10 +249,9 @@ void mmu_mark_rodata_ro(void)
 }
 
 /*
- * Set up one of the I/D BAT (block address translation) register pairs.
+ * Set up one of the D BAT (block address translation) register pairs.
  * The parameters are not checked; in particular size must be a power
  * of 2 between 128k and 256M.
- * On 603+, only set IBAT when _PAGE_EXEC is set
  */
 void __init setbat(int index, unsigned long virt, phys_addr_t phys,
 		   unsigned int size, pgprot_t prot)
@@ -285,10 +287,6 @@ void __init setbat(int index, unsigned long virt, phys_addr_t phys,
 		/* G bit must be zero in IBATs */
 		flags &= ~_PAGE_EXEC;
 	}
-	if (flags & _PAGE_EXEC)
-		bat[0] = bat[1];
-	else
-		bat[0].batu = bat[0].batl = 0;
 
 	bat_addrs[index].start = virt;
 	bat_addrs[index].limit = virt + ((bl + 1) << 17) - 1;
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 543a044560e9..6902f453c745 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -104,6 +104,37 @@ void __ref arch_remove_linear_mapping(u64 start, u64 size)
 	vm_unmap_aliases();
 }
 
+/*
+ * After memory hotplug the variables max_pfn, max_low_pfn and high_memory need
+ * updating.
+ */
+static void update_end_of_memory_vars(u64 start, u64 size)
+{
+	unsigned long end_pfn = PFN_UP(start + size);
+
+	if (end_pfn > max_pfn) {
+		max_pfn = end_pfn;
+		max_low_pfn = end_pfn;
+		high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1;
+	}
+}
+
+int __ref add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
+		    struct mhp_params *params)
+{
+	int ret;
+
+	ret = __add_pages(nid, start_pfn, nr_pages, params);
+	if (ret)
+		return ret;
+
+	/* update max_pfn, max_low_pfn and high_memory */
+	update_end_of_memory_vars(start_pfn << PAGE_SHIFT,
+				  nr_pages << PAGE_SHIFT);
+
+	return ret;
+}
+
 int __ref arch_add_memory(int nid, u64 start, u64 size,
 			  struct mhp_params *params)
 {
@@ -114,7 +145,7 @@ int __ref arch_add_memory(int nid, u64 start, u64 size,
 	rc = arch_create_linear_mapping(nid, start, size, params);
 	if (rc)
 		return rc;
-	rc = __add_pages(nid, start_pfn, nr_pages, params);
+	rc = add_pages(nid, start_pfn, nr_pages, params);
 	if (rc)
 		arch_remove_linear_mapping(start, size);
 	return rc;
diff --git a/arch/powerpc/mm/nohash/8xx.c b/arch/powerpc/mm/nohash/8xx.c
index 0df9fe29dd56..5348e1f9eb94 100644
--- a/arch/powerpc/mm/nohash/8xx.c
+++ b/arch/powerpc/mm/nohash/8xx.c
@@ -183,8 +183,8 @@ void mmu_mark_initmem_nx(void)
 	unsigned long boundary = strict_kernel_rwx_enabled() ? sinittext : etext8;
 	unsigned long einittext8 = ALIGN(__pa(_einittext), SZ_8M);
 
-	mmu_mapin_ram_chunk(0, boundary, PAGE_KERNEL_TEXT, false);
-	mmu_mapin_ram_chunk(boundary, einittext8, PAGE_KERNEL, false);
+	if (!debug_pagealloc_enabled_or_kfence())
+		mmu_mapin_ram_chunk(boundary, einittext8, PAGE_KERNEL, false);
 
 	mmu_pin_tlb(block_mapped_ram, false);
 }
diff --git a/arch/powerpc/mm/nohash/book3e_pgtable.c b/arch/powerpc/mm/nohash/book3e_pgtable.c
index 77884e24281d..3d845e001c87 100644
--- a/arch/powerpc/mm/nohash/book3e_pgtable.c
+++ b/arch/powerpc/mm/nohash/book3e_pgtable.c
@@ -95,8 +95,8 @@ int __ref map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t prot)
 		pgdp = pgd_offset_k(ea);
 		p4dp = p4d_offset(pgdp, ea);
 		if (p4d_none(*p4dp)) {
-			pmdp = early_alloc_pgtable(PMD_TABLE_SIZE);
-			p4d_populate(&init_mm, p4dp, pmdp);
+			pudp = early_alloc_pgtable(PUD_TABLE_SIZE);
+			p4d_populate(&init_mm, p4dp, pudp);
 		}
 		pudp = pud_offset(p4dp, ea);
 		if (pud_none(*pudp)) {
@@ -105,7 +105,7 @@ int __ref map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t prot)
 		}
 		pmdp = pmd_offset(pudp, ea);
 		if (!pmd_present(*pmdp)) {
-			ptep = early_alloc_pgtable(PAGE_SIZE);
+			ptep = early_alloc_pgtable(PTE_TABLE_SIZE);
 			pmd_populate_kernel(&init_mm, pmdp, ptep);
 		}
 		ptep = pte_offset_kernel(pmdp, ea);
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index f28859771440..502e3d3d1dbf 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -138,9 +138,9 @@ void mark_initmem_nx(void)
 	unsigned long numpages = PFN_UP((unsigned long)_einittext) -
 				 PFN_DOWN((unsigned long)_sinittext);
 
-	if (v_block_mapped((unsigned long)_sinittext)) {
-		mmu_mark_initmem_nx();
-	} else {
+	mmu_mark_initmem_nx();
+
+	if (!v_block_mapped((unsigned long)_sinittext)) {
 		set_memory_nx((unsigned long)_sinittext, numpages);
 		set_memory_rw((unsigned long)_sinittext, numpages);
 	}
diff --git a/arch/powerpc/mm/ptdump/shared.c b/arch/powerpc/mm/ptdump/shared.c
index 03607ab90c66..f884760ca5cf 100644
--- a/arch/powerpc/mm/ptdump/shared.c
+++ b/arch/powerpc/mm/ptdump/shared.c
@@ -17,9 +17,9 @@ static const struct flag_info flag_array[] = {
 		.clear	= "    ",
 	}, {
 		.mask	= _PAGE_RW,
-		.val	= _PAGE_RW,
-		.set	= "rw",
-		.clear	= "r ",
+		.val	= 0,
+		.set	= "r ",
+		.clear	= "rw",
 	}, {
 		.mask	= _PAGE_EXEC,
 		.val	= _PAGE_EXEC,
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index e78de7050947..1078784b74c9 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -1320,27 +1320,22 @@ static void power_pmu_disable(struct pmu *pmu)
 		 * a PMI happens during interrupt replay and perf counter
 		 * values are cleared by PMU callbacks before replay.
 		 *
-		 * If any PMC corresponding to the active PMU events are
-		 * overflown, disable the interrupt by clearing the paca
-		 * bit for PMI since we are disabling the PMU now.
-		 * Otherwise provide a warning if there is PMI pending, but
-		 * no counter is found overflown.
+		 * Disable the interrupt by clearing the paca bit for PMI
+		 * since we are disabling the PMU now. Otherwise provide a
+		 * warning if there is PMI pending, but no counter is found
+		 * overflown.
+		 *
+		 * Since power_pmu_disable runs under local_irq_save, it
+		 * could happen that code hits a PMC overflow without PMI
+		 * pending in paca. Hence only clear PMI pending if it was
+		 * set.
+		 *
+		 * If a PMI is pending, then MSR[EE] must be disabled (because
+		 * the masked PMI handler disabling EE). So it is safe to
+		 * call clear_pmi_irq_pending().
 		 */
-		if (any_pmc_overflown(cpuhw)) {
-			/*
-			 * Since power_pmu_disable runs under local_irq_save, it
-			 * could happen that code hits a PMC overflow without PMI
-			 * pending in paca. Hence only clear PMI pending if it was
-			 * set.
-			 *
-			 * If a PMI is pending, then MSR[EE] must be disabled (because
-			 * the masked PMI handler disabling EE). So it is safe to
-			 * call clear_pmi_irq_pending().
-			 */
-			if (pmi_irq_pending())
-				clear_pmi_irq_pending();
-		} else
-			WARN_ON(pmi_irq_pending());
+		if (pmi_irq_pending())
+			clear_pmi_irq_pending();
 
 		val = mmcra = cpuhw->mmcr.mmcra;
 
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 87a95cbff2f3..1b1e67ff9d21 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -137,9 +137,9 @@ config GENERIC_CPU
 	depends on PPC64 && CPU_LITTLE_ENDIAN
 	select ARCH_HAS_FAST_MULTIPLIER
 
-config GENERIC_CPU
+config POWERPC_CPU
 	bool "Generic 32 bits powerpc"
-	depends on PPC32 && !PPC_8xx
+	depends on PPC32 && !PPC_8xx && !PPC_85xx
 
 config CELL_CPU
 	bool "Cell Broadband Engine"
@@ -170,11 +170,11 @@ config POWER9_CPU
 
 config E5500_CPU
 	bool "Freescale e5500"
-	depends on E500
+	depends on PPC64 && E500
 
 config E6500_CPU
 	bool "Freescale e6500"
-	depends on E500
+	depends on PPC64 && E500
 
 config 860_CPU
 	bool "8xx family"
@@ -193,11 +193,23 @@ config G4_CPU
 	depends on PPC_BOOK3S_32
 	select ALTIVEC
 
+config E500_CPU
+	bool "e500 (8540)"
+	depends on PPC_85xx && !PPC_E500MC
+
+config E500MC_CPU
+	bool "e500mc"
+	depends on PPC_85xx && PPC_E500MC
+
+config TOOLCHAIN_DEFAULT_CPU
+	bool "Rely on the toolchain's implicit default CPU"
+	depends on PPC32
+
 endchoice
 
 config TARGET_CPU_BOOL
 	bool
-	default !GENERIC_CPU
+	default !GENERIC_CPU && !TOOLCHAIN_DEFAULT_CPU
 
 config TARGET_CPU
 	string
@@ -212,6 +224,9 @@ config TARGET_CPU
 	default "e300c2" if E300C2_CPU
 	default "e300c3" if E300C3_CPU
 	default "G4" if G4_CPU
+	default "8540" if E500_CPU
+	default "e500mc" if E500MC_CPU
+	default "powerpc" if POWERPC_CPU
 
 config PPC_BOOK3S
 	def_bool y
diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c
index 82335e364c44..f630693c8de7 100644
--- a/arch/powerpc/platforms/cell/axon_msi.c
+++ b/arch/powerpc/platforms/cell/axon_msi.c
@@ -226,6 +226,7 @@ static int setup_msi_msg_address(struct pci_dev *dev, struct msi_msg *msg)
 	if (!prop) {
 		dev_dbg(&dev->dev,
 			"axon_msi: no msi-address-(32|64) properties found\n");
+		of_node_put(dn);
 		return -ENOENT;
 	}
 
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index bed05b644c2c..ed37a93bf858 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -659,6 +659,7 @@ spufs_init_isolated_loader(void)
 		return;
 
 	loader = of_get_property(dn, "loader", &size);
+	of_node_put(dn);
 	if (!loader)
 		return;
 
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 3dd35c327d1c..624822a81019 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1618,6 +1618,7 @@ found:
 	tbl->it_ops = &pnv_ioda1_iommu_ops;
 	pe->table_group.tce32_start = tbl->it_offset << tbl->it_page_shift;
 	pe->table_group.tce32_size = tbl->it_size << tbl->it_page_shift;
+	tbl->it_index = (phb->hose->global_number << 16) | pe->pe_number;
 	if (!iommu_init_table(tbl, phb->hose->node, 0, 0))
 		panic("Failed to initialize iommu table");
 
@@ -1788,6 +1789,7 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe)
 		res_end = min(window_size, SZ_4G) >> tbl->it_page_shift;
 	}
 
+	tbl->it_index = (pe->phb->hose->global_number << 16) | pe->pe_number;
 	if (iommu_init_table(tbl, pe->phb->hose->node, res_start, res_end))
 		rc = pnv_pci_ioda2_set_window(&pe->table_group, 0, tbl);
 	else
diff --git a/arch/powerpc/platforms/powernv/rng.c b/arch/powerpc/platforms/powernv/rng.c
index 2b5a1a41234c..5f81ff9b5265 100644
--- a/arch/powerpc/platforms/powernv/rng.c
+++ b/arch/powerpc/platforms/powernv/rng.c
@@ -29,15 +29,6 @@ struct powernv_rng {
 
 static DEFINE_PER_CPU(struct powernv_rng *, powernv_rng);
 
-int powernv_hwrng_present(void)
-{
-	struct powernv_rng *rng;
-
-	rng = get_cpu_var(powernv_rng);
-	put_cpu_var(rng);
-	return rng != NULL;
-}
-
 static unsigned long rng_whiten(struct powernv_rng *rng, unsigned long val)
 {
 	unsigned long parity;
@@ -58,17 +49,6 @@ static unsigned long rng_whiten(struct powernv_rng *rng, unsigned long val)
 	return val;
 }
 
-int powernv_get_random_real_mode(unsigned long *v)
-{
-	struct powernv_rng *rng;
-
-	rng = raw_cpu_read(powernv_rng);
-
-	*v = rng_whiten(rng, __raw_rm_readq(rng->regs_real));
-
-	return 1;
-}
-
 static int powernv_get_random_darn(unsigned long *v)
 {
 	unsigned long val;
@@ -105,12 +85,14 @@ int powernv_get_random_long(unsigned long *v)
 {
 	struct powernv_rng *rng;
 
-	rng = get_cpu_var(powernv_rng);
-
-	*v = rng_whiten(rng, in_be64(rng->regs));
-
-	put_cpu_var(rng);
-
+	if (mfmsr() & MSR_DR) {
+		rng = get_cpu_var(powernv_rng);
+		*v = rng_whiten(rng, in_be64(rng->regs));
+		put_cpu_var(rng);
+	} else {
+		rng = raw_cpu_read(powernv_rng);
+		*v = rng_whiten(rng, __raw_rm_readq(rng->regs_real));
+	}
 	return 1;
 }
 EXPORT_SYMBOL_GPL(powernv_get_random_long);
@@ -176,12 +158,8 @@ static int __init pnv_get_random_long_early(unsigned long *v)
 		    NULL) != pnv_get_random_long_early)
 		return 0;
 
-	for_each_compatible_node(dn, NULL, "ibm,power-rng") {
-		if (rng_create(dn))
-			continue;
-		/* Create devices for hwrng driver */
-		of_platform_device_create(dn, NULL, NULL);
-	}
+	for_each_compatible_node(dn, NULL, "ibm,power-rng")
+		rng_create(dn);
 
 	if (!ppc_md.get_random_seed)
 		return 0;
@@ -205,10 +183,18 @@ void __init pnv_rng_init(void)
 
 static int __init pnv_rng_late_init(void)
 {
+	struct device_node *dn;
 	unsigned long v;
+
 	/* In case it wasn't called during init for some other reason. */
 	if (ppc_md.get_random_seed == pnv_get_random_long_early)
 		pnv_get_random_long_early(&v);
+
+	if (ppc_md.get_random_seed == powernv_get_random_long) {
+		for_each_compatible_node(dn, NULL, "ibm,power-rng")
+			of_platform_device_create(dn, NULL, NULL);
+	}
+
 	return 0;
 }
 machine_subsys_initcall(powernv, pnv_rng_late_init);
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index b8f76f3fd994..a14a88e5025e 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -520,6 +520,7 @@ int fsl_add_bridge(struct platform_device *pdev, int is_primary)
 	struct resource rsrc;
 	const int *bus_range;
 	u8 hdr_type, progif;
+	u32 class_code;
 	struct device_node *dev;
 	struct ccsr_pci __iomem *pci;
 	u16 temp;
@@ -593,6 +594,13 @@ int fsl_add_bridge(struct platform_device *pdev, int is_primary)
 			PPC_INDIRECT_TYPE_SURPRESS_PRIMARY_BUS;
 		if (fsl_pcie_check_link(hose))
 			hose->indirect_type |= PPC_INDIRECT_TYPE_NO_PCIE_LINK;
+		/* Fix Class Code to PCI_CLASS_BRIDGE_PCI_NORMAL for pre-3.0 controller */
+		if (in_be32(&pci->block_rev1) < PCIE_IP_REV_3_0) {
+			early_read_config_dword(hose, 0, 0, PCIE_FSL_CSR_CLASSCODE, &class_code);
+			class_code &= 0xff;
+			class_code |= PCI_CLASS_BRIDGE_PCI_NORMAL << 8;
+			early_write_config_dword(hose, 0, 0, PCIE_FSL_CSR_CLASSCODE, class_code);
+		}
 	} else {
 		/*
 		 * Set PBFR(PCI Bus Function Register)[10] = 1 to
diff --git a/arch/powerpc/sysdev/fsl_pci.h b/arch/powerpc/sysdev/fsl_pci.h
index 1d7a41205695..5ffaa60f1fa0 100644
--- a/arch/powerpc/sysdev/fsl_pci.h
+++ b/arch/powerpc/sysdev/fsl_pci.h
@@ -18,6 +18,7 @@ struct platform_device;
 
 #define PCIE_LTSSM	0x0404		/* PCIE Link Training and Status */
 #define PCIE_LTSSM_L0	0x16		/* L0 state */
+#define PCIE_FSL_CSR_CLASSCODE	0x474	/* FSL GPEX CSR */
 #define PCIE_IP_REV_2_2		0x02080202 /* PCIE IP block version Rev2.2 */
 #define PCIE_IP_REV_3_0		0x02080300 /* PCIE IP block version Rev3.0 */
 #define PIWAR_EN		0x80000000	/* Enable */
diff --git a/arch/powerpc/sysdev/xive/spapr.c b/arch/powerpc/sysdev/xive/spapr.c
index a82f32fbe772..2bf78a30238b 100644
--- a/arch/powerpc/sysdev/xive/spapr.c
+++ b/arch/powerpc/sysdev/xive/spapr.c
@@ -13,6 +13,7 @@
 #include <linux/of.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/bitmap.h>
 #include <linux/cpumask.h>
 #include <linux/mm.h>
 #include <linux/delay.h>
@@ -55,7 +56,7 @@ static int xive_irq_bitmap_add(int base, int count)
 	spin_lock_init(&xibm->lock);
 	xibm->base = base;
 	xibm->count = count;
-	xibm->bitmap = kzalloc(xibm->count, GFP_KERNEL);
+	xibm->bitmap = bitmap_zalloc(xibm->count, GFP_KERNEL);
 	if (!xibm->bitmap) {
 		kfree(xibm);
 		return -ENOMEM;
@@ -73,7 +74,7 @@ static void xive_irq_bitmap_remove_all(void)
 
 	list_for_each_entry_safe(xibm, tmp, &xive_irq_bitmaps, list) {
 		list_del(&xibm->list);
-		kfree(xibm->bitmap);
+		bitmap_free(xibm->bitmap);
 		kfree(xibm);
 	}
 }
@@ -715,6 +716,7 @@ static bool xive_get_max_prio(u8 *max_prio)
 	}
 
 	reg = of_get_property(rootdn, "ibm,plat-res-int-priorities", &len);
+	of_node_put(rootdn);
 	if (!reg) {
 		pr_err("Failed to read 'ibm,plat-res-int-priorities' property\n");
 		return false;
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index e03f45f7711a..583e1ff0c0bf 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -75,6 +75,7 @@ ifeq ($(CONFIG_PERF_EVENTS),y)
 endif
 
 KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-relax)
+KBUILD_AFLAGS_MODULE += $(call as-option,-Wa$(comma)-mno-relax)
 
 # GCC versions that support the "-mstrict-align" option default to allowing
 # unaligned accesses.  While unaligned accesses are explicitly allowed in the
diff --git a/arch/riscv/boot/dts/canaan/k210.dtsi b/arch/riscv/boot/dts/canaan/k210.dtsi
index 780416d489aa..fa9162e3afa3 100644
--- a/arch/riscv/boot/dts/canaan/k210.dtsi
+++ b/arch/riscv/boot/dts/canaan/k210.dtsi
@@ -65,6 +65,18 @@
 				compatible = "riscv,cpu-intc";
 			};
 		};
+
+		cpu-map {
+			cluster0 {
+				core0 {
+					cpu = <&cpu0>;
+				};
+
+				core1 {
+					cpu = <&cpu1>;
+				};
+			};
+		};
 	};
 
 	sram: memory@80000000 {
diff --git a/arch/riscv/boot/dts/sifive/fu740-c000.dtsi b/arch/riscv/boot/dts/sifive/fu740-c000.dtsi
index abbb960f90a0..454079a69ab4 100644
--- a/arch/riscv/boot/dts/sifive/fu740-c000.dtsi
+++ b/arch/riscv/boot/dts/sifive/fu740-c000.dtsi
@@ -134,6 +134,30 @@
 				interrupt-controller;
 			};
 		};
+
+		cpu-map {
+			cluster0 {
+				core0 {
+					cpu = <&cpu0>;
+				};
+
+				core1 {
+					cpu = <&cpu1>;
+				};
+
+				core2 {
+					cpu = <&cpu2>;
+				};
+
+				core3 {
+					cpu = <&cpu3>;
+				};
+
+				core4 {
+					cpu = <&cpu4>;
+				};
+			};
+		};
 	};
 	soc {
 		#address-cells = <2>;
diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig
index 4ebc80315f01..f2a2f9c9ed49 100644
--- a/arch/riscv/configs/defconfig
+++ b/arch/riscv/configs/defconfig
@@ -72,9 +72,11 @@ CONFIG_GPIOLIB=y
 CONFIG_GPIO_SIFIVE=y
 # CONFIG_PTP_1588_CLOCK is not set
 CONFIG_POWER_RESET=y
-CONFIG_DRM=y
-CONFIG_DRM_RADEON=y
-CONFIG_DRM_VIRTIO_GPU=y
+CONFIG_DRM=m
+CONFIG_DRM_RADEON=m
+CONFIG_DRM_NOUVEAU=m
+CONFIG_DRM_VIRTIO_GPU=m
+CONFIG_FB=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_USB=y
 CONFIG_USB_XHCI_HCD=y
diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig
index 434ef5b64599..cdd113e7a291 100644
--- a/arch/riscv/configs/rv32_defconfig
+++ b/arch/riscv/configs/rv32_defconfig
@@ -71,6 +71,7 @@ CONFIG_POWER_RESET=y
 CONFIG_DRM=y
 CONFIG_DRM_RADEON=y
 CONFIG_DRM_VIRTIO_GPU=y
+CONFIG_FB=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_USB=y
 CONFIG_USB_XHCI_HCD=y
diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h
index 74d888c8d631..e3866ffa06c5 100644
--- a/arch/riscv/include/asm/thread_info.h
+++ b/arch/riscv/include/asm/thread_info.h
@@ -42,6 +42,8 @@
 
 #ifndef __ASSEMBLY__
 
+extern long shadow_stack[SHADOW_OVERFLOW_STACK_SIZE / sizeof(long)];
+
 #include <asm/processor.h>
 #include <asm/csr.h>
 
diff --git a/arch/riscv/kernel/crash_save_regs.S b/arch/riscv/kernel/crash_save_regs.S
index 7832fb763aba..b2a1908c0463 100644
--- a/arch/riscv/kernel/crash_save_regs.S
+++ b/arch/riscv/kernel/crash_save_regs.S
@@ -44,7 +44,7 @@ SYM_CODE_START(riscv_crash_save_regs)
 	REG_S t6,  PT_T6(a0)	/* x31 */
 
 	csrr t1, CSR_STATUS
-	csrr t2, CSR_EPC
+	auipc t2, 0x0
 	csrr t3, CSR_TVAL
 	csrr t4, CSR_CAUSE
 
diff --git a/arch/riscv/kernel/machine_kexec.c b/arch/riscv/kernel/machine_kexec.c
index df8e24559035..ee79e6839b86 100644
--- a/arch/riscv/kernel/machine_kexec.c
+++ b/arch/riscv/kernel/machine_kexec.c
@@ -138,19 +138,37 @@ void machine_shutdown(void)
 #endif
 }
 
+/* Override the weak function in kernel/panic.c */
+void crash_smp_send_stop(void)
+{
+	static int cpus_stopped;
+
+	/*
+	 * This function can be called twice in panic path, but obviously
+	 * we execute this only once.
+	 */
+	if (cpus_stopped)
+		return;
+
+	smp_send_stop();
+	cpus_stopped = 1;
+}
+
 /*
  * machine_crash_shutdown - Prepare to kexec after a kernel crash
  *
  * This function is called by crash_kexec just before machine_kexec
- * below and its goal is similar to machine_shutdown, but in case of
- * a kernel crash. Since we don't handle such cases yet, this function
- * is empty.
+ * and its goal is to shutdown non-crashing cpus and save registers.
  */
 void
 machine_crash_shutdown(struct pt_regs *regs)
 {
+	local_irq_disable();
+
+	/* shutdown non-crashing cpus */
+	crash_smp_send_stop();
+
 	crash_save_cpu(regs, smp_processor_id());
-	machine_shutdown();
 	pr_info("Starting crashdump kernel...\n");
 }
 
@@ -171,7 +189,7 @@ machine_kexec(struct kimage *image)
 	struct kimage_arch *internal = &image->arch;
 	unsigned long jump_addr = (unsigned long) image->start;
 	unsigned long first_ind_entry = (unsigned long) &image->head;
-	unsigned long this_cpu_id = smp_processor_id();
+	unsigned long this_cpu_id = __smp_processor_id();
 	unsigned long this_hart_id = cpuid_to_hartid_map(this_cpu_id);
 	unsigned long fdt_addr = internal->fdt_addr;
 	void *control_code_buffer = page_address(image->control_code_page);
diff --git a/arch/riscv/kernel/probes/uprobes.c b/arch/riscv/kernel/probes/uprobes.c
index 7a057b5f0adc..c976a21cd4bd 100644
--- a/arch/riscv/kernel/probes/uprobes.c
+++ b/arch/riscv/kernel/probes/uprobes.c
@@ -59,8 +59,6 @@ int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 
 	instruction_pointer_set(regs, utask->xol_vaddr);
 
-	regs->status &= ~SR_SPIE;
-
 	return 0;
 }
 
@@ -72,8 +70,6 @@ int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 
 	instruction_pointer_set(regs, utask->vaddr + auprobe->insn_size);
 
-	regs->status |= SR_SPIE;
-
 	return 0;
 }
 
@@ -111,8 +107,6 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 	 * address.
 	 */
 	instruction_pointer_set(regs, utask->vaddr);
-
-	regs->status &= ~SR_SPIE;
 }
 
 bool arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check ctx,
diff --git a/arch/riscv/kernel/reset.c b/arch/riscv/kernel/reset.c
index ee5878d968cc..9c842c41684a 100644
--- a/arch/riscv/kernel/reset.c
+++ b/arch/riscv/kernel/reset.c
@@ -12,7 +12,7 @@ static void default_power_off(void)
 		wait_for_interrupt();
 }
 
-void (*pm_power_off)(void) = default_power_off;
+void (*pm_power_off)(void) = NULL;
 EXPORT_SYMBOL(pm_power_off);
 
 void machine_restart(char *cmd)
@@ -23,10 +23,16 @@ void machine_restart(char *cmd)
 
 void machine_halt(void)
 {
-	pm_power_off();
+	if (pm_power_off != NULL)
+		pm_power_off();
+	else
+		default_power_off();
 }
 
 void machine_power_off(void)
 {
-	pm_power_off();
+	if (pm_power_off != NULL)
+		pm_power_off();
+	else
+		default_power_off();
 }
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index 12f8a7fce78b..8a7880b9c433 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -18,9 +18,8 @@ static long riscv_sys_mmap(unsigned long addr, unsigned long len,
 	if (unlikely(offset & (~PAGE_MASK >> page_shift_offset)))
 		return -EINVAL;
 
-	if ((prot & PROT_WRITE) && (prot & PROT_EXEC))
-		if (unlikely(!(prot & PROT_READ)))
-			return -EINVAL;
+	if (unlikely((prot & PROT_WRITE) && !(prot & PROT_READ)))
+		return -EINVAL;
 
 	return ksys_mmap_pgoff(addr, len, prot, flags, fd,
 			       offset >> (PAGE_SHIFT - page_shift_offset));
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 0daaa3e4630d..8c58aa5d2b36 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -16,12 +16,14 @@
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/irq.h>
+#include <linux/kexec.h>
 
 #include <asm/asm-prototypes.h>
 #include <asm/bug.h>
+#include <asm/csr.h>
 #include <asm/processor.h>
 #include <asm/ptrace.h>
-#include <asm/csr.h>
+#include <asm/thread_info.h>
 
 int show_unhandled_signals = 1;
 
@@ -44,6 +46,9 @@ void die(struct pt_regs *regs, const char *str)
 
 	ret = notify_die(DIE_OOPS, str, regs, 0, regs->cause, SIGSEGV);
 
+	if (regs && kexec_should_crash(current))
+		crash_kexec(regs);
+
 	bust_spinlocks(0);
 	add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
 	spin_unlock_irq(&die_lock);
diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S
index 63bc691cff91..2c7c1c5026af 100644
--- a/arch/riscv/lib/uaccess.S
+++ b/arch/riscv/lib/uaccess.S
@@ -173,6 +173,13 @@ ENTRY(__asm_copy_from_user)
 	csrc CSR_STATUS, t6
 	li	a0, 0
 	ret
+
+	/* Exception fixup code */
+10:
+	/* Disable access to user memory */
+	csrc CSR_STATUS, t6
+	mv a0, t5
+	ret
 ENDPROC(__asm_copy_to_user)
 ENDPROC(__asm_copy_from_user)
 EXPORT_SYMBOL(__asm_copy_to_user)
@@ -218,19 +225,12 @@ ENTRY(__clear_user)
 	addi a0, a0, 1
 	bltu a0, a3, 5b
 	j 3b
-ENDPROC(__clear_user)
-EXPORT_SYMBOL(__clear_user)
 
-	.section .fixup,"ax"
-	.balign 4
-	/* Fixup code for __copy_user(10) and __clear_user(11) */
-10:
-	/* Disable access to user memory */
-	csrs CSR_STATUS, t6
-	mv a0, t5
-	ret
+	/* Exception fixup code */
 11:
-	csrs CSR_STATUS, t6
+	/* Disable access to user memory */
+	csrc CSR_STATUS, t6
 	mv a0, a1
 	ret
-	.previous
+ENDPROC(__clear_user)
+EXPORT_SYMBOL(__clear_user)
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 7f130ac3b9f9..a37a08ceeded 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -100,6 +100,10 @@ static void __init print_vm_layout(void)
 		  (unsigned long)VMEMMAP_END);
 	print_mlm("vmalloc", (unsigned long)VMALLOC_START,
 		  (unsigned long)VMALLOC_END);
+#ifdef CONFIG_64BIT
+	print_mlm("modules", (unsigned long)MODULES_VADDR,
+		  (unsigned long)MODULES_END);
+#endif
 	print_mlm("lowmem", (unsigned long)PAGE_OFFSET,
 		  (unsigned long)high_memory);
 #ifdef CONFIG_64BIT
@@ -265,6 +269,7 @@ pgd_t early_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE);
 static pmd_t __maybe_unused early_dtb_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE);
 
 #ifdef CONFIG_XIP_KERNEL
+#define riscv_pfn_base         (*(unsigned long  *)XIP_FIXUP(&riscv_pfn_base))
 #define trampoline_pg_dir      ((pgd_t *)XIP_FIXUP(trampoline_pg_dir))
 #define fixmap_pte             ((pte_t *)XIP_FIXUP(fixmap_pte))
 #define early_pg_dir           ((pgd_t *)XIP_FIXUP(early_pg_dir))
diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c
index 5e49e4b4a4cc..86c56616e5de 100644
--- a/arch/riscv/mm/pageattr.c
+++ b/arch/riscv/mm/pageattr.c
@@ -118,10 +118,10 @@ static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask,
 	if (!numpages)
 		return 0;
 
-	mmap_read_lock(&init_mm);
+	mmap_write_lock(&init_mm);
 	ret =  walk_page_range_novma(&init_mm, start, end, &pageattr_ops, NULL,
 				     &masks);
-	mmap_read_unlock(&init_mm);
+	mmap_write_unlock(&init_mm);
 
 	flush_tlb_kernel_range(start, end);
 
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 797041b5109a..e402fa964f23 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -516,7 +516,6 @@ config KEXEC
 config KEXEC_FILE
 	bool "kexec file based system call"
 	select KEXEC_CORE
-	select BUILD_BIN2C
 	depends on CRYPTO
 	depends on CRYPTO_SHA256
 	depends on CRYPTO_SHA256_S390
diff --git a/arch/s390/boot/compressed/decompressor.h b/arch/s390/boot/compressed/decompressor.h
index a59f75c5b049..f75cc31a77dd 100644
--- a/arch/s390/boot/compressed/decompressor.h
+++ b/arch/s390/boot/compressed/decompressor.h
@@ -24,6 +24,7 @@ struct vmlinux_info {
 	unsigned long dynsym_start;
 	unsigned long rela_dyn_start;
 	unsigned long rela_dyn_end;
+	unsigned long amode31_size;
 };
 
 /* Symbols defined by linker scripts */
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index b13352dd1e1c..1aa11a8f57dd 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -15,6 +15,7 @@
 #include "uv.h"
 
 unsigned long __bootdata_preserved(__kaslr_offset);
+unsigned long __bootdata(__amode31_base);
 unsigned long __bootdata_preserved(VMALLOC_START);
 unsigned long __bootdata_preserved(VMALLOC_END);
 struct page *__bootdata_preserved(vmemmap);
@@ -233,6 +234,12 @@ static void offset_vmlinux_info(unsigned long offset)
 	vmlinux.dynsym_start += offset;
 }
 
+static unsigned long reserve_amode31(unsigned long safe_addr)
+{
+	__amode31_base = PAGE_ALIGN(safe_addr);
+	return safe_addr + vmlinux.amode31_size;
+}
+
 void startup_kernel(void)
 {
 	unsigned long random_lma;
@@ -247,6 +254,7 @@ void startup_kernel(void)
 	setup_lpp();
 	store_ipl_parmblock();
 	safe_addr = mem_safe_offset();
+	safe_addr = reserve_amode31(safe_addr);
 	safe_addr = read_ipl_report(safe_addr);
 	uv_query_info();
 	rescue_initrd(safe_addr);
diff --git a/arch/s390/crypto/arch_random.c b/arch/s390/crypto/arch_random.c
index 56007c763902..1f2d40993c4d 100644
--- a/arch/s390/crypto/arch_random.c
+++ b/arch/s390/crypto/arch_random.c
@@ -4,232 +4,15 @@
  *
  * Copyright IBM Corp. 2017, 2020
  * Author(s): Harald Freudenberger
- *
- * The s390_arch_random_generate() function may be called from random.c
- * in interrupt context. So this implementation does the best to be very
- * fast. There is a buffer of random data which is asynchronously checked
- * and filled by a workqueue thread.
- * If there are enough bytes in the buffer the s390_arch_random_generate()
- * just delivers these bytes. Otherwise false is returned until the
- * worker thread refills the buffer.
- * The worker fills the rng buffer by pulling fresh entropy from the
- * high quality (but slow) true hardware random generator. This entropy
- * is then spread over the buffer with an pseudo random generator PRNG.
- * As the arch_get_random_seed_long() fetches 8 bytes and the calling
- * function add_interrupt_randomness() counts this as 1 bit entropy the
- * distribution needs to make sure there is in fact 1 bit entropy contained
- * in 8 bytes of the buffer. The current values pull 32 byte entropy
- * and scatter this into a 2048 byte buffer. So 8 byte in the buffer
- * will contain 1 bit of entropy.
- * The worker thread is rescheduled based on the charge level of the
- * buffer but at least with 500 ms delay to avoid too much CPU consumption.
- * So the max. amount of rng data delivered via arch_get_random_seed is
- * limited to 4k bytes per second.
  */
 
 #include <linux/kernel.h>
 #include <linux/atomic.h>
 #include <linux/random.h>
-#include <linux/slab.h>
 #include <linux/static_key.h>
-#include <linux/workqueue.h>
-#include <linux/moduleparam.h>
 #include <asm/cpacf.h>
 
 DEFINE_STATIC_KEY_FALSE(s390_arch_random_available);
 
 atomic64_t s390_arch_random_counter = ATOMIC64_INIT(0);
 EXPORT_SYMBOL(s390_arch_random_counter);
-
-#define ARCH_REFILL_TICKS (HZ/2)
-#define ARCH_PRNG_SEED_SIZE 32
-#define ARCH_RNG_BUF_SIZE 2048
-
-static DEFINE_SPINLOCK(arch_rng_lock);
-static u8 *arch_rng_buf;
-static unsigned int arch_rng_buf_idx;
-
-static void arch_rng_refill_buffer(struct work_struct *);
-static DECLARE_DELAYED_WORK(arch_rng_work, arch_rng_refill_buffer);
-
-bool s390_arch_random_generate(u8 *buf, unsigned int nbytes)
-{
-	/* max hunk is ARCH_RNG_BUF_SIZE */
-	if (nbytes > ARCH_RNG_BUF_SIZE)
-		return false;
-
-	/* lock rng buffer */
-	if (!spin_trylock(&arch_rng_lock))
-		return false;
-
-	/* try to resolve the requested amount of bytes from the buffer */
-	arch_rng_buf_idx -= nbytes;
-	if (arch_rng_buf_idx < ARCH_RNG_BUF_SIZE) {
-		memcpy(buf, arch_rng_buf + arch_rng_buf_idx, nbytes);
-		atomic64_add(nbytes, &s390_arch_random_counter);
-		spin_unlock(&arch_rng_lock);
-		return true;
-	}
-
-	/* not enough bytes in rng buffer, refill is done asynchronously */
-	spin_unlock(&arch_rng_lock);
-
-	return false;
-}
-EXPORT_SYMBOL(s390_arch_random_generate);
-
-static void arch_rng_refill_buffer(struct work_struct *unused)
-{
-	unsigned int delay = ARCH_REFILL_TICKS;
-
-	spin_lock(&arch_rng_lock);
-	if (arch_rng_buf_idx > ARCH_RNG_BUF_SIZE) {
-		/* buffer is exhausted and needs refill */
-		u8 seed[ARCH_PRNG_SEED_SIZE];
-		u8 prng_wa[240];
-		/* fetch ARCH_PRNG_SEED_SIZE bytes of entropy */
-		cpacf_trng(NULL, 0, seed, sizeof(seed));
-		/* blow this entropy up to ARCH_RNG_BUF_SIZE with PRNG */
-		memset(prng_wa, 0, sizeof(prng_wa));
-		cpacf_prno(CPACF_PRNO_SHA512_DRNG_SEED,
-			   &prng_wa, NULL, 0, seed, sizeof(seed));
-		cpacf_prno(CPACF_PRNO_SHA512_DRNG_GEN,
-			   &prng_wa, arch_rng_buf, ARCH_RNG_BUF_SIZE, NULL, 0);
-		arch_rng_buf_idx = ARCH_RNG_BUF_SIZE;
-	}
-	delay += (ARCH_REFILL_TICKS * arch_rng_buf_idx) / ARCH_RNG_BUF_SIZE;
-	spin_unlock(&arch_rng_lock);
-
-	/* kick next check */
-	queue_delayed_work(system_long_wq, &arch_rng_work, delay);
-}
-
-/*
- * Here follows the implementation of s390_arch_get_random_long().
- *
- * The random longs to be pulled by arch_get_random_long() are
- * prepared in an 4K buffer which is filled from the NIST 800-90
- * compliant s390 drbg. By default the random long buffer is refilled
- * 256 times before the drbg itself needs a reseed. The reseed of the
- * drbg is done with 32 bytes fetched from the high quality (but slow)
- * trng which is assumed to deliver 100% entropy. So the 32 * 8 = 256
- * bits of entropy are spread over 256 * 4KB = 1MB serving 131072
- * arch_get_random_long() invocations before reseeded.
- *
- * How often the 4K random long buffer is refilled with the drbg
- * before the drbg is reseeded can be adjusted. There is a module
- * parameter 's390_arch_rnd_long_drbg_reseed' accessible via
- *   /sys/module/arch_random/parameters/rndlong_drbg_reseed
- * or as kernel command line parameter
- *   arch_random.rndlong_drbg_reseed=<value>
- * This parameter tells how often the drbg fills the 4K buffer before
- * it is re-seeded by fresh entropy from the trng.
- * A value of 16 results in reseeding the drbg at every 16 * 4 KB = 64
- * KB with 32 bytes of fresh entropy pulled from the trng. So a value
- * of 16 would result in 256 bits entropy per 64 KB.
- * A value of 256 results in 1MB of drbg output before a reseed of the
- * drbg is done. So this would spread the 256 bits of entropy among 1MB.
- * Setting this parameter to 0 forces the reseed to take place every
- * time the 4K buffer is depleted, so the entropy rises to 256 bits
- * entropy per 4K or 0.5 bit entropy per arch_get_random_long().  With
- * setting this parameter to negative values all this effort is
- * disabled, arch_get_random long() returns false and thus indicating
- * that the arch_get_random_long() feature is disabled at all.
- */
-
-static unsigned long rndlong_buf[512];
-static DEFINE_SPINLOCK(rndlong_lock);
-static int rndlong_buf_index;
-
-static int rndlong_drbg_reseed = 256;
-module_param_named(rndlong_drbg_reseed, rndlong_drbg_reseed, int, 0600);
-MODULE_PARM_DESC(rndlong_drbg_reseed, "s390 arch_get_random_long() drbg reseed");
-
-static inline void refill_rndlong_buf(void)
-{
-	static u8 prng_ws[240];
-	static int drbg_counter;
-
-	if (--drbg_counter < 0) {
-		/* need to re-seed the drbg */
-		u8 seed[32];
-
-		/* fetch seed from trng */
-		cpacf_trng(NULL, 0, seed, sizeof(seed));
-		/* seed drbg */
-		memset(prng_ws, 0, sizeof(prng_ws));
-		cpacf_prno(CPACF_PRNO_SHA512_DRNG_SEED,
-			   &prng_ws, NULL, 0, seed, sizeof(seed));
-		/* re-init counter for drbg */
-		drbg_counter = rndlong_drbg_reseed;
-	}
-
-	/* fill the arch_get_random_long buffer from drbg */
-	cpacf_prno(CPACF_PRNO_SHA512_DRNG_GEN, &prng_ws,
-		   (u8 *) rndlong_buf, sizeof(rndlong_buf),
-		   NULL, 0);
-}
-
-bool s390_arch_get_random_long(unsigned long *v)
-{
-	bool rc = false;
-	unsigned long flags;
-
-	/* arch_get_random_long() disabled ? */
-	if (rndlong_drbg_reseed < 0)
-		return false;
-
-	/* try to lock the random long lock */
-	if (!spin_trylock_irqsave(&rndlong_lock, flags))
-		return false;
-
-	if (--rndlong_buf_index >= 0) {
-		/* deliver next long value from the buffer */
-		*v = rndlong_buf[rndlong_buf_index];
-		rc = true;
-		goto out;
-	}
-
-	/* buffer is depleted and needs refill */
-	if (in_interrupt()) {
-		/* delay refill in interrupt context to next caller */
-		rndlong_buf_index = 0;
-		goto out;
-	}
-
-	/* refill random long buffer */
-	refill_rndlong_buf();
-	rndlong_buf_index = ARRAY_SIZE(rndlong_buf);
-
-	/* and provide one random long */
-	*v = rndlong_buf[--rndlong_buf_index];
-	rc = true;
-
-out:
-	spin_unlock_irqrestore(&rndlong_lock, flags);
-	return rc;
-}
-EXPORT_SYMBOL(s390_arch_get_random_long);
-
-static int __init s390_arch_random_init(void)
-{
-	/* all the needed PRNO subfunctions available ? */
-	if (cpacf_query_func(CPACF_PRNO, CPACF_PRNO_TRNG) &&
-	    cpacf_query_func(CPACF_PRNO, CPACF_PRNO_SHA512_DRNG_GEN)) {
-
-		/* alloc arch random working buffer */
-		arch_rng_buf = kmalloc(ARCH_RNG_BUF_SIZE, GFP_KERNEL);
-		if (!arch_rng_buf)
-			return -ENOMEM;
-
-		/* kick worker queue job to fill the random buffer */
-		queue_delayed_work(system_long_wq,
-				   &arch_rng_work, ARCH_REFILL_TICKS);
-
-		/* enable arch random to the outside world */
-		static_branch_enable(&s390_arch_random_available);
-	}
-
-	return 0;
-}
-arch_initcall(s390_arch_random_init);
diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c
index f0bc4dc3e9bf..6511d15ace45 100644
--- a/arch/s390/hypfs/hypfs_diag.c
+++ b/arch/s390/hypfs/hypfs_diag.c
@@ -437,7 +437,7 @@ __init int hypfs_diag_init(void)
 	int rc;
 
 	if (diag204_probe()) {
-		pr_err("The hardware system does not support hypfs\n");
+		pr_info("The hardware system does not support hypfs\n");
 		return -ENODATA;
 	}
 
diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c
index 5c97f48cea91..ee919bfc8186 100644
--- a/arch/s390/hypfs/inode.c
+++ b/arch/s390/hypfs/inode.c
@@ -496,9 +496,9 @@ fail_hypfs_sprp_exit:
 	hypfs_vm_exit();
 fail_hypfs_diag_exit:
 	hypfs_diag_exit();
+	pr_err("Initialization of hypfs failed with rc=%i\n", rc);
 fail_dbfs_exit:
 	hypfs_dbfs_exit();
-	pr_err("Initialization of hypfs failed with rc=%i\n", rc);
 	return rc;
 }
 device_initcall(hypfs_init)
diff --git a/arch/s390/include/asm/archrandom.h b/arch/s390/include/asm/archrandom.h
index 5dc712fde3c7..4120c428dc37 100644
--- a/arch/s390/include/asm/archrandom.h
+++ b/arch/s390/include/asm/archrandom.h
@@ -2,7 +2,7 @@
 /*
  * Kernel interface for the s390 arch_random_* functions
  *
- * Copyright IBM Corp. 2017, 2020
+ * Copyright IBM Corp. 2017, 2022
  *
  * Author: Harald Freudenberger <freude@de.ibm.com>
  *
@@ -14,18 +14,15 @@
 #ifdef CONFIG_ARCH_RANDOM
 
 #include <linux/static_key.h>
+#include <linux/preempt.h>
 #include <linux/atomic.h>
+#include <asm/cpacf.h>
 
 DECLARE_STATIC_KEY_FALSE(s390_arch_random_available);
 extern atomic64_t s390_arch_random_counter;
 
-bool s390_arch_get_random_long(unsigned long *v);
-bool s390_arch_random_generate(u8 *buf, unsigned int nbytes);
-
 static inline bool __must_check arch_get_random_long(unsigned long *v)
 {
-	if (static_branch_likely(&s390_arch_random_available))
-		return s390_arch_get_random_long(v);
 	return false;
 }
 
@@ -36,16 +33,22 @@ static inline bool __must_check arch_get_random_int(unsigned int *v)
 
 static inline bool __must_check arch_get_random_seed_long(unsigned long *v)
 {
-	if (static_branch_likely(&s390_arch_random_available)) {
-		return s390_arch_random_generate((u8 *)v, sizeof(*v));
+	if (static_branch_likely(&s390_arch_random_available) &&
+	    in_task()) {
+		cpacf_trng(NULL, 0, (u8 *)v, sizeof(*v));
+		atomic64_add(sizeof(*v), &s390_arch_random_counter);
+		return true;
 	}
 	return false;
 }
 
 static inline bool __must_check arch_get_random_seed_int(unsigned int *v)
 {
-	if (static_branch_likely(&s390_arch_random_available)) {
-		return s390_arch_random_generate((u8 *)v, sizeof(*v));
+	if (static_branch_likely(&s390_arch_random_available) &&
+	    in_task()) {
+		cpacf_trng(NULL, 0, (u8 *)v, sizeof(*v));
+		atomic64_add(sizeof(*v), &s390_arch_random_counter);
+		return true;
 	}
 	return false;
 }
diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h
index 04dc65f8901d..80b93c06a2bb 100644
--- a/arch/s390/include/asm/ctl_reg.h
+++ b/arch/s390/include/asm/ctl_reg.h
@@ -72,8 +72,17 @@ static __always_inline void __ctl_clear_bit(unsigned int cr, unsigned int bit)
 	__ctl_load(reg, cr, cr);
 }
 
-void smp_ctl_set_bit(int cr, int bit);
-void smp_ctl_clear_bit(int cr, int bit);
+void smp_ctl_set_clear_bit(int cr, int bit, bool set);
+
+static inline void ctl_set_bit(int cr, int bit)
+{
+	smp_ctl_set_clear_bit(cr, bit, true);
+}
+
+static inline void ctl_clear_bit(int cr, int bit)
+{
+	smp_ctl_set_clear_bit(cr, bit, false);
+}
 
 union ctlreg0 {
 	unsigned long val;
@@ -128,8 +137,5 @@ union ctlreg15 {
 	};
 };
 
-#define ctl_set_bit(cr, bit) smp_ctl_set_bit(cr, bit)
-#define ctl_clear_bit(cr, bit) smp_ctl_clear_bit(cr, bit)
-
 #endif /* __ASSEMBLY__ */
 #endif /* __ASM_CTL_REG_H */
diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h
index 40264f60b0da..f4073106e1f3 100644
--- a/arch/s390/include/asm/gmap.h
+++ b/arch/s390/include/asm/gmap.h
@@ -148,4 +148,6 @@ void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long dirty_bitmap[4],
 			     unsigned long gaddr, unsigned long vmaddr);
 int gmap_mark_unmergeable(void);
 void s390_reset_acc(struct mm_struct *mm);
+void s390_unlist_old_asce(struct gmap *gmap);
+int s390_replace_asce(struct gmap *gmap);
 #endif /* _ASM_S390_GMAP_H */
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index 60f9241e5e4a..d3642fb634bd 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -28,9 +28,11 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 static inline int prepare_hugepage_range(struct file *file,
 			unsigned long addr, unsigned long len)
 {
-	if (len & ~HPAGE_MASK)
+	struct hstate *h = hstate_file(file);
+
+	if (len & ~huge_page_mask(h))
 		return -EINVAL;
-	if (addr & ~HPAGE_MASK)
+	if (addr & ~huge_page_mask(h))
 		return -EINVAL;
 	return 0;
 }
diff --git a/arch/s390/include/asm/os_info.h b/arch/s390/include/asm/os_info.h
index 3c89279d2a4b..147a8d547ef9 100644
--- a/arch/s390/include/asm/os_info.h
+++ b/arch/s390/include/asm/os_info.h
@@ -39,7 +39,7 @@ u32 os_info_csum(struct os_info *os_info);
 
 #ifdef CONFIG_CRASH_DUMP
 void *os_info_old_entry(int nr, unsigned long *size);
-int copy_oldmem_kernel(void *dst, void *src, size_t count);
+int copy_oldmem_kernel(void *dst, unsigned long src, size_t count);
 #else
 static inline void *os_info_old_entry(int nr, unsigned long *size)
 {
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 879b8e3f609c..d7ca76bb2720 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -318,14 +318,21 @@ extern void (*s390_base_pgm_handler_fn)(void);
 
 #define ARCH_LOW_ADDRESS_LIMIT	0x7fffffffUL
 
-extern int memcpy_real(void *, void *, size_t);
+extern int memcpy_real(void *, unsigned long, size_t);
 extern void memcpy_absolute(void *, void *, size_t);
 
-#define mem_assign_absolute(dest, val) do {			\
-	__typeof__(dest) __tmp = (val);				\
-								\
-	BUILD_BUG_ON(sizeof(__tmp) != sizeof(val));		\
-	memcpy_absolute(&(dest), &__tmp, sizeof(__tmp));	\
+#define put_abs_lowcore(member, x) do {					\
+	unsigned long __abs_address = offsetof(struct lowcore, member);	\
+	__typeof__(((struct lowcore *)0)->member) __tmp = (x);		\
+									\
+	memcpy_absolute(__va(__abs_address), &__tmp, sizeof(__tmp));	\
+} while (0)
+
+#define get_abs_lowcore(x, member) do {					\
+	unsigned long __abs_address = offsetof(struct lowcore, member);	\
+	__typeof__(((struct lowcore *)0)->member) *__ptr = &(x);	\
+									\
+	memcpy_absolute(__ptr, __va(__abs_address), sizeof(*__ptr));	\
 } while (0)
 
 extern int s390_isolate_bp(void);
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index ce550d06abc3..3379694e9a42 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -245,7 +245,7 @@ static inline unsigned long __must_check clear_user(void __user *to, unsigned lo
 	return __clear_user(to, n);
 }
 
-int copy_to_user_real(void __user *dest, void *src, unsigned long count);
+int copy_to_user_real(void __user *dest, unsigned long src, unsigned long count);
 void *s390_kernel_write(void *dst, const void *src, size_t size);
 
 #define HAVE_GET_KERNEL_NOFAULT
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index b57da9338588..9242d7ad71e7 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -128,6 +128,8 @@ int main(void)
 	OFFSET(__LC_BR_R1, lowcore, br_r1_trampoline);
 	/* software defined ABI-relevant lowcore locations 0xe00 - 0xe20 */
 	OFFSET(__LC_DUMP_REIPL, lowcore, ipib);
+	OFFSET(__LC_VMCORE_INFO, lowcore, vmcore_info);
+	OFFSET(__LC_OS_INFO, lowcore, os_info);
 	/* hardware defined lowcore locations 0x1000 - 0x18ff */
 	OFFSET(__LC_MCESAD, lowcore, mcesad);
 	OFFSET(__LC_EXT_PARAMS2, lowcore, ext_params2);
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index 785d54c9350c..f17ad2daab07 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -132,28 +132,27 @@ static inline void *load_real_addr(void *addr)
 /*
  * Copy memory of the old, dumped system to a kernel space virtual address
  */
-int copy_oldmem_kernel(void *dst, void *src, size_t count)
+int copy_oldmem_kernel(void *dst, unsigned long src, size_t count)
 {
-	unsigned long from, len;
+	unsigned long len;
 	void *ra;
 	int rc;
 
 	while (count) {
-		from = __pa(src);
-		if (!oldmem_data.start && from < sclp.hsa_size) {
+		if (!oldmem_data.start && src < sclp.hsa_size) {
 			/* Copy from zfcp/nvme dump HSA area */
-			len = min(count, sclp.hsa_size - from);
-			rc = memcpy_hsa_kernel(dst, from, len);
+			len = min(count, sclp.hsa_size - src);
+			rc = memcpy_hsa_kernel(dst, src, len);
 			if (rc)
 				return rc;
 		} else {
 			/* Check for swapped kdump oldmem areas */
-			if (oldmem_data.start && from - oldmem_data.start < oldmem_data.size) {
-				from -= oldmem_data.start;
-				len = min(count, oldmem_data.size - from);
-			} else if (oldmem_data.start && from < oldmem_data.size) {
-				len = min(count, oldmem_data.size - from);
-				from += oldmem_data.start;
+			if (oldmem_data.start && src - oldmem_data.start < oldmem_data.size) {
+				src -= oldmem_data.start;
+				len = min(count, oldmem_data.size - src);
+			} else if (oldmem_data.start && src < oldmem_data.size) {
+				len = min(count, oldmem_data.size - src);
+				src += oldmem_data.start;
 			} else {
 				len = count;
 			}
@@ -163,7 +162,7 @@ int copy_oldmem_kernel(void *dst, void *src, size_t count)
 			} else {
 				ra = dst;
 			}
-			if (memcpy_real(ra, (void *) from, len))
+			if (memcpy_real(ra, src, len))
 				return -EFAULT;
 		}
 		dst += len;
@@ -176,31 +175,30 @@ int copy_oldmem_kernel(void *dst, void *src, size_t count)
 /*
  * Copy memory of the old, dumped system to a user space virtual address
  */
-static int copy_oldmem_user(void __user *dst, void *src, size_t count)
+static int copy_oldmem_user(void __user *dst, unsigned long src, size_t count)
 {
-	unsigned long from, len;
+	unsigned long len;
 	int rc;
 
 	while (count) {
-		from = __pa(src);
-		if (!oldmem_data.start && from < sclp.hsa_size) {
+		if (!oldmem_data.start && src < sclp.hsa_size) {
 			/* Copy from zfcp/nvme dump HSA area */
-			len = min(count, sclp.hsa_size - from);
-			rc = memcpy_hsa_user(dst, from, len);
+			len = min(count, sclp.hsa_size - src);
+			rc = memcpy_hsa_user(dst, src, len);
 			if (rc)
 				return rc;
 		} else {
 			/* Check for swapped kdump oldmem areas */
-			if (oldmem_data.start && from - oldmem_data.start < oldmem_data.size) {
-				from -= oldmem_data.start;
-				len = min(count, oldmem_data.size - from);
-			} else if (oldmem_data.start && from < oldmem_data.size) {
-				len = min(count, oldmem_data.size - from);
-				from += oldmem_data.start;
+			if (oldmem_data.start && src - oldmem_data.start < oldmem_data.size) {
+				src -= oldmem_data.start;
+				len = min(count, oldmem_data.size - src);
+			} else if (oldmem_data.start && src < oldmem_data.size) {
+				len = min(count, oldmem_data.size - src);
+				src += oldmem_data.start;
 			} else {
 				len = count;
 			}
-			rc = copy_to_user_real(dst, (void *) from, count);
+			rc = copy_to_user_real(dst, src, len);
 			if (rc)
 				return rc;
 		}
@@ -217,12 +215,12 @@ static int copy_oldmem_user(void __user *dst, void *src, size_t count)
 ssize_t copy_oldmem_page(unsigned long pfn, char *buf, size_t csize,
 			 unsigned long offset, int userbuf)
 {
-	void *src;
+	unsigned long src;
 	int rc;
 
 	if (!csize)
 		return 0;
-	src = (void *) (pfn << PAGE_SHIFT) + offset;
+	src = pfn_to_phys(pfn) + offset;
 	if (userbuf)
 		rc = copy_oldmem_user((void __force __user *) buf, src, csize);
 	else
@@ -429,10 +427,10 @@ static void *nt_prpsinfo(void *ptr)
 static void *get_vmcoreinfo_old(unsigned long *size)
 {
 	char nt_name[11], *vmcoreinfo;
+	unsigned long addr;
 	Elf64_Nhdr note;
-	void *addr;
 
-	if (copy_oldmem_kernel(&addr, &S390_lowcore.vmcore_info, sizeof(addr)))
+	if (copy_oldmem_kernel(&addr, __LC_VMCORE_INFO, sizeof(addr)))
 		return NULL;
 	memset(nt_name, 0, sizeof(nt_name));
 	if (copy_oldmem_kernel(&note, addr, sizeof(note)))
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index 7f2696e8d511..6083090be1f4 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -70,5 +70,6 @@ extern struct exception_table_entry _stop_amode31_ex_table[];
 #define __amode31_data __section(".amode31.data")
 #define __amode31_ref __section(".amode31.refs")
 extern long _start_amode31_refs[], _end_amode31_refs[];
+extern unsigned long __amode31_base;
 
 #endif /* _ENTRY_H */
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index 5ad1dde23dc5..ba2988783d66 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -1646,8 +1646,8 @@ static void dump_reipl_run(struct shutdown_trigger *trigger)
 
 	csum = (__force unsigned int)
 	       csum_partial(reipl_block_actual, reipl_block_actual->hdr.len, 0);
-	mem_assign_absolute(S390_lowcore.ipib, ipib);
-	mem_assign_absolute(S390_lowcore.ipib_checksum, csum);
+	put_abs_lowcore(ipib, ipib);
+	put_abs_lowcore(ipib_checksum, csum);
 	dump_run(trigger);
 }
 
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index 0505e55a6297..4b95684fbe46 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -227,7 +227,7 @@ void arch_crash_save_vmcoreinfo(void)
 	vmcoreinfo_append_str("SAMODE31=%lx\n", __samode31);
 	vmcoreinfo_append_str("EAMODE31=%lx\n", __eamode31);
 	vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
-	mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note());
+	put_abs_lowcore(vmcore_info, paddr_vmcoreinfo_note());
 }
 
 void machine_shutdown(void)
diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c
index a81d6c43b9b6..3459362c54ac 100644
--- a/arch/s390/kernel/machine_kexec_file.c
+++ b/arch/s390/kernel/machine_kexec_file.c
@@ -29,6 +29,7 @@ int s390_verify_sig(const char *kernel, unsigned long kernel_len)
 	const unsigned long marker_len = sizeof(MODULE_SIG_STRING) - 1;
 	struct module_signature *ms;
 	unsigned long sig_len;
+	int ret;
 
 	/* Skip signature verification when not secure IPLed. */
 	if (!ipl_secure_flag)
@@ -63,11 +64,18 @@ int s390_verify_sig(const char *kernel, unsigned long kernel_len)
 		return -EBADMSG;
 	}
 
-	return verify_pkcs7_signature(kernel, kernel_len,
-				      kernel + kernel_len, sig_len,
-				      VERIFY_USE_PLATFORM_KEYRING,
-				      VERIFYING_MODULE_SIGNATURE,
-				      NULL, NULL);
+	ret = verify_pkcs7_signature(kernel, kernel_len,
+				     kernel + kernel_len, sig_len,
+				     VERIFY_USE_SECONDARY_KEYRING,
+				     VERIFYING_MODULE_SIGNATURE,
+				     NULL, NULL);
+	if (ret == -ENOKEY && IS_ENABLED(CONFIG_INTEGRITY_PLATFORM_KEYRING))
+		ret = verify_pkcs7_signature(kernel, kernel_len,
+					     kernel + kernel_len, sig_len,
+					     VERIFY_USE_PLATFORM_KEYRING,
+					     VERIFYING_MODULE_SIGNATURE,
+					     NULL, NULL);
+	return ret;
 }
 #endif /* CONFIG_KEXEC_SIG */
 
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index a50f2ff1b00e..383b4799b6dd 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -62,7 +62,7 @@ static inline unsigned long nmi_get_mcesa_size(void)
  * The structure is required for machine check happening early in
  * the boot process.
  */
-static struct mcesa boot_mcesa __initdata __aligned(MCESA_MAX_SIZE);
+static struct mcesa boot_mcesa __aligned(MCESA_MAX_SIZE);
 
 void __init nmi_alloc_boot_cpu(struct lowcore *lc)
 {
diff --git a/arch/s390/kernel/os_info.c b/arch/s390/kernel/os_info.c
index 4bef35b79b93..1acc2e05d70f 100644
--- a/arch/s390/kernel/os_info.c
+++ b/arch/s390/kernel/os_info.c
@@ -15,6 +15,7 @@
 #include <asm/checksum.h>
 #include <asm/lowcore.h>
 #include <asm/os_info.h>
+#include <asm/asm-offsets.h>
 
 /*
  * OS info structure has to be page aligned
@@ -45,7 +46,7 @@ void os_info_crashkernel_add(unsigned long base, unsigned long size)
  */
 void os_info_entry_add(int nr, void *ptr, u64 size)
 {
-	os_info.entry[nr].addr = (u64)(unsigned long)ptr;
+	os_info.entry[nr].addr = __pa(ptr);
 	os_info.entry[nr].size = size;
 	os_info.entry[nr].csum = (__force u32)csum_partial(ptr, size, 0);
 	os_info.csum = os_info_csum(&os_info);
@@ -62,7 +63,7 @@ void __init os_info_init(void)
 	os_info.version_minor = OS_INFO_VERSION_MINOR;
 	os_info.magic = OS_INFO_MAGIC;
 	os_info.csum = os_info_csum(&os_info);
-	mem_assign_absolute(S390_lowcore.os_info, (unsigned long) ptr);
+	put_abs_lowcore(os_info, __pa(ptr));
 }
 
 #ifdef CONFIG_CRASH_DUMP
@@ -90,7 +91,7 @@ static void os_info_old_alloc(int nr, int align)
 		goto fail;
 	}
 	buf_align = PTR_ALIGN(buf, align);
-	if (copy_oldmem_kernel(buf_align, (void *) addr, size)) {
+	if (copy_oldmem_kernel(buf_align, addr, size)) {
 		msg = "copy failed";
 		goto fail_free;
 	}
@@ -123,15 +124,14 @@ static void os_info_old_init(void)
 		return;
 	if (!oldmem_data.start)
 		goto fail;
-	if (copy_oldmem_kernel(&addr, &S390_lowcore.os_info, sizeof(addr)))
+	if (copy_oldmem_kernel(&addr, __LC_OS_INFO, sizeof(addr)))
 		goto fail;
 	if (addr == 0 || addr % PAGE_SIZE)
 		goto fail;
 	os_info_old = kzalloc(sizeof(*os_info_old), GFP_KERNEL);
 	if (!os_info_old)
 		goto fail;
-	if (copy_oldmem_kernel(os_info_old, (void *) addr,
-			       sizeof(*os_info_old)))
+	if (copy_oldmem_kernel(os_info_old, addr, sizeof(*os_info_old)))
 		goto fail_free;
 	if (os_info_old->magic != OS_INFO_MAGIC)
 		goto fail_free;
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 350e94d0cac2..d015cb1027fa 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -91,6 +91,18 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 
 	memcpy(dst, src, arch_task_struct_size);
 	dst->thread.fpu.regs = dst->thread.fpu.fprs;
+
+	/*
+	 * Don't transfer over the runtime instrumentation or the guarded
+	 * storage control block pointers. These fields are cleared here instead
+	 * of in copy_thread() to avoid premature freeing of associated memory
+	 * on fork() failure. Wait to clear the RI flag because ->stack still
+	 * refers to the source thread.
+	 */
+	dst->thread.ri_cb = NULL;
+	dst->thread.gs_cb = NULL;
+	dst->thread.gs_bc_cb = NULL;
+
 	return 0;
 }
 
@@ -149,13 +161,11 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp,
 	frame->childregs.flags = 0;
 	if (new_stackp)
 		frame->childregs.gprs[15] = new_stackp;
-
-	/* Don't copy runtime instrumentation info */
-	p->thread.ri_cb = NULL;
+	/*
+	 * Clear the runtime instrumentation flag after the above childregs
+	 * copy. The CB pointer was already cleared in arch_dup_task_struct().
+	 */
 	frame->childregs.psw.mask &= ~PSW_MASK_RI;
-	/* Don't copy guarded storage control block */
-	p->thread.gs_cb = NULL;
-	p->thread.gs_bc_cb = NULL;
 
 	/* Set a new TLS ?  */
 	if (clone_flags & CLONE_SETTLS) {
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index ee67215a678a..4dfe37b06889 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -95,10 +95,10 @@ EXPORT_SYMBOL(console_irq);
  * relocated above 2 GB, because it has to use 31 bit addresses.
  * Such code and data is part of the .amode31 section.
  */
-unsigned long __amode31_ref __samode31 = __pa(&_samode31);
-unsigned long __amode31_ref __eamode31 = __pa(&_eamode31);
-unsigned long __amode31_ref __stext_amode31 = __pa(&_stext_amode31);
-unsigned long __amode31_ref __etext_amode31 = __pa(&_etext_amode31);
+unsigned long __amode31_ref __samode31 = (unsigned long)&_samode31;
+unsigned long __amode31_ref __eamode31 = (unsigned long)&_eamode31;
+unsigned long __amode31_ref __stext_amode31 = (unsigned long)&_stext_amode31;
+unsigned long __amode31_ref __etext_amode31 = (unsigned long)&_etext_amode31;
 struct exception_table_entry __amode31_ref *__start_amode31_ex_table = _start_amode31_ex_table;
 struct exception_table_entry __amode31_ref *__stop_amode31_ex_table = _stop_amode31_ex_table;
 
@@ -149,6 +149,7 @@ struct mem_detect_info __bootdata(mem_detect);
 struct initrd_data __bootdata(initrd_data);
 
 unsigned long __bootdata_preserved(__kaslr_offset);
+unsigned long __bootdata(__amode31_base);
 unsigned int __bootdata_preserved(zlib_dfltcc_support);
 EXPORT_SYMBOL(zlib_dfltcc_support);
 u64 __bootdata_preserved(stfle_fac_list[16]);
@@ -478,11 +479,12 @@ static void __init setup_lowcore_dat_off(void)
 	lc->mcck_stack = mcck_stack + STACK_INIT_OFFSET;
 
 	/* Setup absolute zero lowcore */
-	mem_assign_absolute(S390_lowcore.restart_stack, lc->restart_stack);
-	mem_assign_absolute(S390_lowcore.restart_fn, lc->restart_fn);
-	mem_assign_absolute(S390_lowcore.restart_data, lc->restart_data);
-	mem_assign_absolute(S390_lowcore.restart_source, lc->restart_source);
-	mem_assign_absolute(S390_lowcore.restart_psw, lc->restart_psw);
+	put_abs_lowcore(restart_stack, lc->restart_stack);
+	put_abs_lowcore(restart_fn, lc->restart_fn);
+	put_abs_lowcore(restart_data, lc->restart_data);
+	put_abs_lowcore(restart_source, lc->restart_source);
+	put_abs_lowcore(restart_psw, lc->restart_psw);
+	put_abs_lowcore(mcesad, lc->mcesad);
 
 	lc->spinlock_lockval = arch_spin_lockval(0);
 	lc->spinlock_index = 0;
@@ -499,6 +501,7 @@ static void __init setup_lowcore_dat_off(void)
 static void __init setup_lowcore_dat_on(void)
 {
 	struct lowcore *lc = lowcore_ptr[0];
+	int cr;
 
 	__ctl_clear_bit(0, 28);
 	S390_lowcore.external_new_psw.mask |= PSW_MASK_DAT;
@@ -507,10 +510,10 @@ static void __init setup_lowcore_dat_on(void)
 	S390_lowcore.io_new_psw.mask |= PSW_MASK_DAT;
 	__ctl_store(S390_lowcore.cregs_save_area, 0, 15);
 	__ctl_set_bit(0, 28);
-	mem_assign_absolute(S390_lowcore.restart_flags, RESTART_FLAG_CTLREGS);
-	mem_assign_absolute(S390_lowcore.program_new_psw, lc->program_new_psw);
-	memcpy_absolute(&S390_lowcore.cregs_save_area, lc->cregs_save_area,
-			sizeof(S390_lowcore.cregs_save_area));
+	put_abs_lowcore(restart_flags, RESTART_FLAG_CTLREGS);
+	put_abs_lowcore(program_new_psw, lc->program_new_psw);
+	for (cr = 0; cr < ARRAY_SIZE(lc->cregs_save_area); cr++)
+		put_abs_lowcore(cregs_save_area[cr], lc->cregs_save_area[cr]);
 }
 
 static struct resource code_resource = {
@@ -796,12 +799,12 @@ static void __init check_initrd(void)
  */
 static void __init reserve_kernel(void)
 {
-	unsigned long start_pfn = PFN_UP(__pa(_end));
-
 	memblock_reserve(0, STARTUP_NORMAL_OFFSET);
-	memblock_reserve((unsigned long)sclp_early_sccb, EXT_SCCB_READ_SCP);
-	memblock_reserve((unsigned long)_stext, PFN_PHYS(start_pfn)
-			 - (unsigned long)_stext);
+	memblock_reserve(OLDMEM_BASE, sizeof(unsigned long));
+	memblock_reserve(OLDMEM_SIZE, sizeof(unsigned long));
+	memblock_reserve(__amode31_base, __eamode31 - __samode31);
+	memblock_reserve(__pa(sclp_early_sccb), EXT_SCCB_READ_SCP);
+	memblock_reserve(__pa(_stext), _end - _stext);
 }
 
 static void __init setup_memory(void)
@@ -820,20 +823,14 @@ static void __init setup_memory(void)
 
 static void __init relocate_amode31_section(void)
 {
-	unsigned long amode31_addr, amode31_size;
-	long amode31_offset;
+	unsigned long amode31_size = __eamode31 - __samode31;
+	long amode31_offset = __amode31_base - __samode31;
 	long *ptr;
 
-	/* Allocate a new AMODE31 capable memory region */
-	amode31_size = __eamode31 - __samode31;
 	pr_info("Relocating AMODE31 section of size 0x%08lx\n", amode31_size);
-	amode31_addr = (unsigned long)memblock_alloc_low(amode31_size, PAGE_SIZE);
-	if (!amode31_addr)
-		panic("Failed to allocate memory for AMODE31 section\n");
-	amode31_offset = amode31_addr - __samode31;
 
 	/* Move original AMODE31 section to the new one */
-	memmove((void *)amode31_addr, (void *)__samode31, amode31_size);
+	memmove((void *)__amode31_base, (void *)__samode31, amode31_size);
 	/* Zero out the old AMODE31 section to catch invalid accesses within it */
 	memset((void *)__samode31, 0, amode31_size);
 
@@ -880,6 +877,11 @@ static void __init setup_randomness(void)
 	if (stsi(vmms, 3, 2, 2) == 0 && vmms->count)
 		add_device_randomness(&vmms->vm, sizeof(vmms->vm[0]) * vmms->count);
 	memblock_free((unsigned long) vmms, PAGE_SIZE);
+
+#ifdef CONFIG_ARCH_RANDOM
+	if (cpacf_query_func(CPACF_PRNO, CPACF_PRNO_TRNG))
+		static_branch_enable(&s390_arch_random_available);
+#endif
 }
 
 /*
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 1a04e5bdf655..35af70ed58fc 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -328,10 +328,17 @@ static void pcpu_delegate(struct pcpu *pcpu,
 	/* Stop target cpu (if func returns this stops the current cpu). */
 	pcpu_sigp_retry(pcpu, SIGP_STOP, 0);
 	/* Restart func on the target cpu and stop the current cpu. */
-	mem_assign_absolute(lc->restart_stack, stack);
-	mem_assign_absolute(lc->restart_fn, (unsigned long) func);
-	mem_assign_absolute(lc->restart_data, (unsigned long) data);
-	mem_assign_absolute(lc->restart_source, source_cpu);
+	if (lc) {
+		lc->restart_stack = stack;
+		lc->restart_fn = (unsigned long)func;
+		lc->restart_data = (unsigned long)data;
+		lc->restart_source = source_cpu;
+	} else {
+		put_abs_lowcore(restart_stack, stack);
+		put_abs_lowcore(restart_fn, (unsigned long)func);
+		put_abs_lowcore(restart_data, (unsigned long)data);
+		put_abs_lowcore(restart_source, source_cpu);
+	}
 	__bpon();
 	asm volatile(
 		"0:	sigp	0,%0,%2	# sigp restart to target cpu\n"
@@ -572,39 +579,27 @@ static void smp_ctl_bit_callback(void *info)
 }
 
 static DEFINE_SPINLOCK(ctl_lock);
-static unsigned long ctlreg;
 
-/*
- * Set a bit in a control register of all cpus
- */
-void smp_ctl_set_bit(int cr, int bit)
+void smp_ctl_set_clear_bit(int cr, int bit, bool set)
 {
-	struct ec_creg_mask_parms parms = { 1UL << bit, -1UL, cr };
-
-	spin_lock(&ctl_lock);
-	memcpy_absolute(&ctlreg, &S390_lowcore.cregs_save_area[cr], sizeof(ctlreg));
-	__set_bit(bit, &ctlreg);
-	memcpy_absolute(&S390_lowcore.cregs_save_area[cr], &ctlreg, sizeof(ctlreg));
-	spin_unlock(&ctl_lock);
-	on_each_cpu(smp_ctl_bit_callback, &parms, 1);
-}
-EXPORT_SYMBOL(smp_ctl_set_bit);
-
-/*
- * Clear a bit in a control register of all cpus
- */
-void smp_ctl_clear_bit(int cr, int bit)
-{
-	struct ec_creg_mask_parms parms = { 0, ~(1UL << bit), cr };
+	struct ec_creg_mask_parms parms = { .cr = cr, };
+	u64 ctlreg;
 
+	if (set) {
+		parms.orval = 1UL << bit;
+		parms.andval = -1UL;
+	} else {
+		parms.orval = 0;
+		parms.andval = ~(1UL << bit);
+	}
 	spin_lock(&ctl_lock);
-	memcpy_absolute(&ctlreg, &S390_lowcore.cregs_save_area[cr], sizeof(ctlreg));
-	__clear_bit(bit, &ctlreg);
-	memcpy_absolute(&S390_lowcore.cregs_save_area[cr], &ctlreg, sizeof(ctlreg));
+	get_abs_lowcore(ctlreg, cregs_save_area[cr]);
+	ctlreg = (ctlreg & parms.andval) | parms.orval;
+	put_abs_lowcore(cregs_save_area[cr], ctlreg);
 	spin_unlock(&ctl_lock);
 	on_each_cpu(smp_ctl_bit_callback, &parms, 1);
 }
-EXPORT_SYMBOL(smp_ctl_clear_bit);
+EXPORT_SYMBOL(smp_ctl_set_clear_bit);
 
 #ifdef CONFIG_CRASH_DUMP
 
@@ -675,7 +670,7 @@ static __init void smp_save_cpu_regs(struct save_area *sa, u16 addr,
 	void *regs = (void *) page;
 
 	if (is_boot_cpu)
-		copy_oldmem_kernel(regs, (void *) __LC_FPREGS_SAVE_AREA, 512);
+		copy_oldmem_kernel(regs, __LC_FPREGS_SAVE_AREA, 512);
 	else
 		__pcpu_sigp_relax(addr, SIGP_STORE_STATUS_AT_ADDRESS, page);
 	save_area_add_regs(sa, regs);
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 63bdb9e1bfc1..b508ccad4856 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -132,6 +132,7 @@ SECTIONS
 	/*
 	 * Table with the patch locations to undo expolines
 	*/
+	. = ALIGN(4);
 	.nospec_call_table : {
 		__nospec_call_start = . ;
 		*(.s390_indirect*)
@@ -212,6 +213,7 @@ SECTIONS
 		QUAD(__dynsym_start)				/* dynsym_start */
 		QUAD(__rela_dyn_start)				/* rela_dyn_start */
 		QUAD(__rela_dyn_end)				/* rela_dyn_end */
+		QUAD(_eamode31 - _samode31)			/* amode31_size */
 	} :NONE
 
 	/* Debugging sections.	*/
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 2bd8f854f1b4..8ca301f49b30 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -523,12 +523,27 @@ static int handle_pv_uvc(struct kvm_vcpu *vcpu)
 
 static int handle_pv_notification(struct kvm_vcpu *vcpu)
 {
+	int ret;
+
 	if (vcpu->arch.sie_block->ipa == 0xb210)
 		return handle_pv_spx(vcpu);
 	if (vcpu->arch.sie_block->ipa == 0xb220)
 		return handle_pv_sclp(vcpu);
 	if (vcpu->arch.sie_block->ipa == 0xb9a4)
 		return handle_pv_uvc(vcpu);
+	if (vcpu->arch.sie_block->ipa >> 8 == 0xae) {
+		/*
+		 * Besides external call, other SIGP orders also cause a
+		 * 108 (pv notify) intercept. In contrast to external call,
+		 * these orders need to be emulated and hence the appropriate
+		 * place to handle them is in handle_instruction().
+		 * So first try kvm_s390_handle_sigp_pei() and if that isn't
+		 * successful, go on with handle_instruction().
+		 */
+		ret = kvm_s390_handle_sigp_pei(vcpu);
+		if (!ret)
+			return ret;
+	}
 
 	return handle_instruction(vcpu);
 }
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 402597f9d050..b456aa196c04 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -3913,14 +3913,12 @@ retry:
 	return 0;
 }
 
-void kvm_s390_set_tod_clock(struct kvm *kvm,
-			    const struct kvm_s390_vm_tod_clock *gtod)
+static void __kvm_s390_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod)
 {
 	struct kvm_vcpu *vcpu;
 	union tod_clock clk;
 	int i;
 
-	mutex_lock(&kvm->lock);
 	preempt_disable();
 
 	store_tod_clock_ext(&clk);
@@ -3941,7 +3939,22 @@ void kvm_s390_set_tod_clock(struct kvm *kvm,
 
 	kvm_s390_vcpu_unblock_all(kvm);
 	preempt_enable();
+}
+
+void kvm_s390_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod)
+{
+	mutex_lock(&kvm->lock);
+	__kvm_s390_set_tod_clock(kvm, gtod);
+	mutex_unlock(&kvm->lock);
+}
+
+int kvm_s390_try_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod)
+{
+	if (!mutex_trylock(&kvm->lock))
+		return 0;
+	__kvm_s390_set_tod_clock(kvm, gtod);
 	mutex_unlock(&kvm->lock);
+	return 1;
 }
 
 /**
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 1539dd981104..f8803bf0ff17 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -326,8 +326,8 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu);
 int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu);
 
 /* implemented in kvm-s390.c */
-void kvm_s390_set_tod_clock(struct kvm *kvm,
-			    const struct kvm_s390_vm_tod_clock *gtod);
+void kvm_s390_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod);
+int kvm_s390_try_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod);
 long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable);
 int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr);
 int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 417154b314a6..6a765fe22eaf 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -102,7 +102,20 @@ static int handle_set_clock(struct kvm_vcpu *vcpu)
 		return kvm_s390_inject_prog_cond(vcpu, rc);
 
 	VCPU_EVENT(vcpu, 3, "SCK: setting guest TOD to 0x%llx", gtod.tod);
-	kvm_s390_set_tod_clock(vcpu->kvm, &gtod);
+	/*
+	 * To set the TOD clock the kvm lock must be taken, but the vcpu lock
+	 * is already held in handle_set_clock. The usual lock order is the
+	 * opposite.  As SCK is deprecated and should not be used in several
+	 * cases, for example when the multiple epoch facility or TOD clock
+	 * steering facility is installed (see Principles of Operation),  a
+	 * slow path can be used.  If the lock can not be taken via try_lock,
+	 * the instruction will be retried via -EAGAIN at a later point in
+	 * time.
+	 */
+	if (!kvm_s390_try_set_tod_clock(vcpu->kvm, &gtod)) {
+		kvm_s390_retry_instr(vcpu);
+		return -EAGAIN;
+	}
 
 	kvm_s390_set_psw_cc(vcpu, 0);
 	return 0;
diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c
index 00d272d134c2..b906658ffc2e 100644
--- a/arch/s390/kvm/pv.c
+++ b/arch/s390/kvm/pv.c
@@ -168,10 +168,13 @@ int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc)
 	atomic_set(&kvm->mm->context.is_protected, 0);
 	KVM_UV_EVENT(kvm, 3, "PROTVIRT DESTROY VM: rc %x rrc %x", *rc, *rrc);
 	WARN_ONCE(cc, "protvirt destroy vm failed rc %x rrc %x", *rc, *rrc);
-	/* Inteded memory leak on "impossible" error */
-	if (!cc)
+	/* Intended memory leak on "impossible" error */
+	if (!cc) {
 		kvm_s390_pv_dealloc_vm(kvm);
-	return cc ? -EIO : 0;
+		return 0;
+	}
+	s390_replace_asce(kvm->arch.gmap);
+	return -EIO;
 }
 
 int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc)
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index 3dc921e853b6..52800279686c 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -492,9 +492,9 @@ int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu)
 	struct kvm_vcpu *dest_vcpu;
 	u8 order_code = kvm_s390_get_base_disp_rs(vcpu, NULL);
 
-	trace_kvm_s390_handle_sigp_pei(vcpu, order_code, cpu_addr);
-
 	if (order_code == SIGP_EXTERNAL_CALL) {
+		trace_kvm_s390_handle_sigp_pei(vcpu, order_code, cpu_addr);
+
 		dest_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, cpu_addr);
 		BUG_ON(dest_vcpu == NULL);
 
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 212632d57db9..c930dff312df 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -397,7 +397,9 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access)
 	flags = FAULT_FLAG_DEFAULT;
 	if (user_mode(regs))
 		flags |= FAULT_FLAG_USER;
-	if (access == VM_WRITE || is_write)
+	if (is_write)
+		access = VM_WRITE;
+	if (access == VM_WRITE)
 		flags |= FAULT_FLAG_WRITE;
 	mmap_read_lock(mm);
 
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 4ce3a2f01c91..ff40bf92db43 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -2726,3 +2726,89 @@ void s390_reset_acc(struct mm_struct *mm)
 	mmput(mm);
 }
 EXPORT_SYMBOL_GPL(s390_reset_acc);
+
+/**
+ * s390_unlist_old_asce - Remove the topmost level of page tables from the
+ * list of page tables of the gmap.
+ * @gmap: the gmap whose table is to be removed
+ *
+ * On s390x, KVM keeps a list of all pages containing the page tables of the
+ * gmap (the CRST list). This list is used at tear down time to free all
+ * pages that are now not needed anymore.
+ *
+ * This function removes the topmost page of the tree (the one pointed to by
+ * the ASCE) from the CRST list.
+ *
+ * This means that it will not be freed when the VM is torn down, and needs
+ * to be handled separately by the caller, unless a leak is actually
+ * intended. Notice that this function will only remove the page from the
+ * list, the page will still be used as a top level page table (and ASCE).
+ */
+void s390_unlist_old_asce(struct gmap *gmap)
+{
+	struct page *old;
+
+	old = virt_to_page(gmap->table);
+	spin_lock(&gmap->guest_table_lock);
+	list_del(&old->lru);
+	/*
+	 * Sometimes the topmost page might need to be "removed" multiple
+	 * times, for example if the VM is rebooted into secure mode several
+	 * times concurrently, or if s390_replace_asce fails after calling
+	 * s390_remove_old_asce and is attempted again later. In that case
+	 * the old asce has been removed from the list, and therefore it
+	 * will not be freed when the VM terminates, but the ASCE is still
+	 * in use and still pointed to.
+	 * A subsequent call to replace_asce will follow the pointer and try
+	 * to remove the same page from the list again.
+	 * Therefore it's necessary that the page of the ASCE has valid
+	 * pointers, so list_del can work (and do nothing) without
+	 * dereferencing stale or invalid pointers.
+	 */
+	INIT_LIST_HEAD(&old->lru);
+	spin_unlock(&gmap->guest_table_lock);
+}
+EXPORT_SYMBOL_GPL(s390_unlist_old_asce);
+
+/**
+ * s390_replace_asce - Try to replace the current ASCE of a gmap with a copy
+ * @gmap: the gmap whose ASCE needs to be replaced
+ *
+ * If the allocation of the new top level page table fails, the ASCE is not
+ * replaced.
+ * In any case, the old ASCE is always removed from the gmap CRST list.
+ * Therefore the caller has to make sure to save a pointer to it
+ * beforehand, unless a leak is actually intended.
+ */
+int s390_replace_asce(struct gmap *gmap)
+{
+	unsigned long asce;
+	struct page *page;
+	void *table;
+
+	s390_unlist_old_asce(gmap);
+
+	page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER);
+	if (!page)
+		return -ENOMEM;
+	table = page_to_virt(page);
+	memcpy(table, gmap->table, 1UL << (CRST_ALLOC_ORDER + PAGE_SHIFT));
+
+	/*
+	 * The caller has to deal with the old ASCE, but here we make sure
+	 * the new one is properly added to the CRST list, so that
+	 * it will be freed when the VM is torn down.
+	 */
+	spin_lock(&gmap->guest_table_lock);
+	list_add(&page->lru, &gmap->crst_list);
+	spin_unlock(&gmap->guest_table_lock);
+
+	/* Set new table origin while preserving existing ASCE control bits */
+	asce = (gmap->asce & ~_ASCE_ORIGIN) | __pa(table);
+	WRITE_ONCE(gmap->asce, asce);
+	WRITE_ONCE(gmap->mm->context.gmap_asce, asce);
+	WRITE_ONCE(gmap->table, table);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(s390_replace_asce);
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index 9663ce3625bc..2ed198b4f7d0 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -123,7 +123,7 @@ static unsigned long __no_sanitize_address _memcpy_real(unsigned long dest,
 /*
  * Copy memory in real mode (kernel to kernel)
  */
-int memcpy_real(void *dest, void *src, size_t count)
+int memcpy_real(void *dest, unsigned long src, size_t count)
 {
 	unsigned long _dest  = (unsigned long)dest;
 	unsigned long _src   = (unsigned long)src;
@@ -175,7 +175,7 @@ void memcpy_absolute(void *dest, void *src, size_t count)
 /*
  * Copy memory from kernel (real) to user (virtual)
  */
-int copy_to_user_real(void __user *dest, void *src, unsigned long count)
+int copy_to_user_real(void __user *dest, unsigned long src, unsigned long count)
 {
 	int offs = 0, size, rc;
 	char *buf;
diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h
index cf9a3ec32406..fba90e670ed4 100644
--- a/arch/sh/include/asm/io.h
+++ b/arch/sh/include/asm/io.h
@@ -271,8 +271,12 @@ static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size,
 #endif /* CONFIG_HAVE_IOREMAP_PROT */
 
 #else /* CONFIG_MMU */
-#define iounmap(addr)		do { } while (0)
-#define ioremap(offset, size)	((void __iomem *)(unsigned long)(offset))
+static inline void __iomem *ioremap(phys_addr_t offset, size_t size)
+{
+	return (void __iomem *)(unsigned long)offset;
+}
+
+static inline void iounmap(volatile void __iomem *addr) { }
 #endif /* CONFIG_MMU */
 
 #define ioremap_uc	ioremap
diff --git a/arch/um/drivers/random.c b/arch/um/drivers/random.c
index 433a3f8f2ef3..32b3341fe970 100644
--- a/arch/um/drivers/random.c
+++ b/arch/um/drivers/random.c
@@ -28,7 +28,7 @@
  * protects against a module being loaded twice at the same time.
  */
 static int random_fd = -1;
-static struct hwrng hwrng = { 0, };
+static struct hwrng hwrng;
 static DECLARE_COMPLETION(have_data);
 
 static int rng_dev_read(struct hwrng *rng, void *buf, size_t max, bool block)
diff --git a/arch/um/drivers/virtio_uml.c b/arch/um/drivers/virtio_uml.c
index 7755cb4ff9fc..82ff3785bf69 100644
--- a/arch/um/drivers/virtio_uml.c
+++ b/arch/um/drivers/virtio_uml.c
@@ -21,6 +21,7 @@
  * Based on Virtio MMIO driver by Pawel Moll, copyright 2011-2014, ARM Ltd.
  */
 #include <linux/module.h>
+#include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/virtio.h>
@@ -49,6 +50,7 @@ struct virtio_uml_platform_data {
 struct virtio_uml_device {
 	struct virtio_device vdev;
 	struct platform_device *pdev;
+	struct virtio_uml_platform_data *pdata;
 
 	spinlock_t sock_lock;
 	int sock, req_fd, irq;
@@ -61,6 +63,7 @@ struct virtio_uml_device {
 
 	u8 config_changed_irq:1;
 	uint64_t vq_irq_vq_map;
+	int recv_rc;
 };
 
 struct virtio_uml_vq_info {
@@ -146,14 +149,6 @@ static int vhost_user_recv(struct virtio_uml_device *vu_dev,
 
 	rc = vhost_user_recv_header(fd, msg);
 
-	if (rc == -ECONNRESET && vu_dev->registered) {
-		struct virtio_uml_platform_data *pdata;
-
-		pdata = vu_dev->pdev->dev.platform_data;
-
-		virtio_break_device(&vu_dev->vdev);
-		schedule_work(&pdata->conn_broken_wk);
-	}
 	if (rc)
 		return rc;
 	size = msg->header.size;
@@ -162,6 +157,21 @@ static int vhost_user_recv(struct virtio_uml_device *vu_dev,
 	return full_read(fd, &msg->payload, size, false);
 }
 
+static void vhost_user_check_reset(struct virtio_uml_device *vu_dev,
+				   int rc)
+{
+	struct virtio_uml_platform_data *pdata = vu_dev->pdata;
+
+	if (rc != -ECONNRESET)
+		return;
+
+	if (!vu_dev->registered)
+		return;
+
+	virtio_break_device(&vu_dev->vdev);
+	schedule_work(&pdata->conn_broken_wk);
+}
+
 static int vhost_user_recv_resp(struct virtio_uml_device *vu_dev,
 				struct vhost_user_msg *msg,
 				size_t max_payload_size)
@@ -169,8 +179,10 @@ static int vhost_user_recv_resp(struct virtio_uml_device *vu_dev,
 	int rc = vhost_user_recv(vu_dev, vu_dev->sock, msg,
 				 max_payload_size, true);
 
-	if (rc)
+	if (rc) {
+		vhost_user_check_reset(vu_dev, rc);
 		return rc;
+	}
 
 	if (msg->header.flags != (VHOST_USER_FLAG_REPLY | VHOST_USER_VERSION))
 		return -EPROTO;
@@ -367,6 +379,7 @@ static irqreturn_t vu_req_read_message(struct virtio_uml_device *vu_dev,
 				 sizeof(msg.msg.payload) +
 				 sizeof(msg.extra_payload));
 
+	vu_dev->recv_rc = rc;
 	if (rc)
 		return IRQ_NONE;
 
@@ -410,7 +423,9 @@ static irqreturn_t vu_req_interrupt(int irq, void *data)
 	if (!um_irq_timetravel_handler_used())
 		ret = vu_req_read_message(vu_dev, NULL);
 
-	if (vu_dev->vq_irq_vq_map) {
+	if (vu_dev->recv_rc) {
+		vhost_user_check_reset(vu_dev, vu_dev->recv_rc);
+	} else if (vu_dev->vq_irq_vq_map) {
 		struct virtqueue *vq;
 
 		virtio_device_for_each_vq((&vu_dev->vdev), vq) {
@@ -1115,21 +1130,63 @@ void virtio_uml_set_no_vq_suspend(struct virtio_device *vdev,
 		 no_vq_suspend ? "dis" : "en");
 }
 
+static void vu_of_conn_broken(struct work_struct *wk)
+{
+	/*
+	 * We can't remove the device from the devicetree so the only thing we
+	 * can do is warn.
+	 */
+	WARN_ON(1);
+}
+
 /* Platform device */
 
+static struct virtio_uml_platform_data *
+virtio_uml_create_pdata(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct virtio_uml_platform_data *pdata;
+	int ret;
+
+	if (!np)
+		return ERR_PTR(-EINVAL);
+
+	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_WORK(&pdata->conn_broken_wk, vu_of_conn_broken);
+	pdata->pdev = pdev;
+
+	ret = of_property_read_string(np, "socket-path", &pdata->socket_path);
+	if (ret)
+		return ERR_PTR(ret);
+
+	ret = of_property_read_u32(np, "virtio-device-id",
+				   &pdata->virtio_device_id);
+	if (ret)
+		return ERR_PTR(ret);
+
+	return pdata;
+}
+
 static int virtio_uml_probe(struct platform_device *pdev)
 {
 	struct virtio_uml_platform_data *pdata = pdev->dev.platform_data;
 	struct virtio_uml_device *vu_dev;
 	int rc;
 
-	if (!pdata)
-		return -EINVAL;
+	if (!pdata) {
+		pdata = virtio_uml_create_pdata(pdev);
+		if (IS_ERR(pdata))
+			return PTR_ERR(pdata);
+	}
 
 	vu_dev = kzalloc(sizeof(*vu_dev), GFP_KERNEL);
 	if (!vu_dev)
 		return -ENOMEM;
 
+	vu_dev->pdata = pdata;
 	vu_dev->vdev.dev.parent = &pdev->dev;
 	vu_dev->vdev.dev.release = virtio_uml_release_dev;
 	vu_dev->vdev.config = &virtio_uml_config_ops;
diff --git a/arch/um/include/asm/archrandom.h b/arch/um/include/asm/archrandom.h
new file mode 100644
index 000000000000..2f24cb96391d
--- /dev/null
+++ b/arch/um/include/asm/archrandom.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_UM_ARCHRANDOM_H__
+#define __ASM_UM_ARCHRANDOM_H__
+
+#include <linux/types.h>
+
+/* This is from <os.h>, but better not to #include that in a global header here. */
+ssize_t os_getrandom(void *buf, size_t len, unsigned int flags);
+
+static inline bool __must_check arch_get_random_long(unsigned long *v)
+{
+	return os_getrandom(v, sizeof(*v), 0) == sizeof(*v);
+}
+
+static inline bool __must_check arch_get_random_int(unsigned int *v)
+{
+	return os_getrandom(v, sizeof(*v), 0) == sizeof(*v);
+}
+
+static inline bool __must_check arch_get_random_seed_long(unsigned long *v)
+{
+	return false;
+}
+
+static inline bool __must_check arch_get_random_seed_int(unsigned int *v)
+{
+	return false;
+}
+
+#endif
diff --git a/arch/um/include/asm/xor.h b/arch/um/include/asm/xor.h
index 22b39de73c24..647fae200c5d 100644
--- a/arch/um/include/asm/xor.h
+++ b/arch/um/include/asm/xor.h
@@ -18,7 +18,7 @@
 #undef XOR_SELECT_TEMPLATE
 /* pick an arbitrary one - measuring isn't possible with inf-cpu */
 #define XOR_SELECT_TEMPLATE(x)	\
-	(time_travel_mode == TT_MODE_INFCPU ? TT_CPU_INF_XOR_DEFAULT : x))
+	(time_travel_mode == TT_MODE_INFCPU ? TT_CPU_INF_XOR_DEFAULT : x)
 #endif
 
 #endif
diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h
index 03ffbdddcc48..90e9c9f86f15 100644
--- a/arch/um/include/shared/os.h
+++ b/arch/um/include/shared/os.h
@@ -11,6 +11,12 @@
 #include <irq_user.h>
 #include <longjmp.h>
 #include <mm_id.h>
+/* This is to get size_t */
+#ifndef __UM_HOST__
+#include <linux/types.h>
+#else
+#include <sys/types.h>
+#endif
 
 #define CATCH_EINTR(expr) while ((errno = 0, ((expr) < 0)) && (errno == EINTR))
 
@@ -252,6 +258,7 @@ extern void stack_protections(unsigned long address);
 extern int raw(int fd);
 extern void setup_machinename(char *machine_out);
 extern void setup_hostinfo(char *buf, int len);
+extern ssize_t os_getrandom(void *buf, size_t len, unsigned int flags);
 extern void os_dump_core(void) __attribute__ ((noreturn));
 extern void um_early_printk(const char *s, unsigned int n);
 extern void os_fix_helper_signals(void);
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index a149a5e9a16a..960f5c35ad1b 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -16,6 +16,7 @@
 #include <linux/sched/task.h>
 #include <linux/kmsg_dump.h>
 #include <linux/suspend.h>
+#include <linux/random.h>
 
 #include <asm/processor.h>
 #include <asm/cpufeature.h>
@@ -404,6 +405,8 @@ int __init __weak read_initrd(void)
 
 void __init setup_arch(char **cmdline_p)
 {
+	u8 rng_seed[32];
+
 	stack_protections((unsigned long) &init_thread_info);
 	setup_physmem(uml_physmem, uml_reserved, physmem_size, highmem);
 	mem_total_pages(physmem_size, iomem_size, highmem);
@@ -413,6 +416,11 @@ void __init setup_arch(char **cmdline_p)
 	strlcpy(boot_command_line, command_line, COMMAND_LINE_SIZE);
 	*cmdline_p = command_line;
 	setup_hostinfo(host_info, sizeof host_info);
+
+	if (os_getrandom(rng_seed, sizeof(rng_seed), 0) == sizeof(rng_seed)) {
+		add_bootloader_randomness(rng_seed, sizeof(rng_seed));
+		memzero_explicit(rng_seed, sizeof(rng_seed));
+	}
 }
 
 void __init check_bugs(void)
@@ -421,6 +429,14 @@ void __init check_bugs(void)
 	os_check_bugs();
 }
 
+void apply_retpolines(s32 *start, s32 *end)
+{
+}
+
+void apply_returns(s32 *start, s32 *end)
+{
+}
+
 void apply_alternatives(struct alt_instr *start, struct alt_instr *end)
 {
 }
diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c
index 87d3129e7362..0df2ebcc97c0 100644
--- a/arch/um/os-Linux/skas/process.c
+++ b/arch/um/os-Linux/skas/process.c
@@ -5,6 +5,7 @@
  */
 
 #include <stdlib.h>
+#include <stdbool.h>
 #include <unistd.h>
 #include <sched.h>
 #include <errno.h>
@@ -707,10 +708,24 @@ void halt_skas(void)
 	UML_LONGJMP(&initial_jmpbuf, INIT_JMP_HALT);
 }
 
+static bool noreboot;
+
+static int __init noreboot_cmd_param(char *str, int *add)
+{
+	noreboot = true;
+	return 0;
+}
+
+__uml_setup("noreboot", noreboot_cmd_param,
+"noreboot\n"
+"    Rather than rebooting, exit always, akin to QEMU's -no-reboot option.\n"
+"    This is useful if you're using CONFIG_PANIC_TIMEOUT in order to catch\n"
+"    crashes in CI\n");
+
 void reboot_skas(void)
 {
 	block_signals_trace();
-	UML_LONGJMP(&initial_jmpbuf, INIT_JMP_REBOOT);
+	UML_LONGJMP(&initial_jmpbuf, noreboot ? INIT_JMP_HALT : INIT_JMP_REBOOT);
 }
 
 void __switch_mm(struct mm_id *mm_idp)
diff --git a/arch/um/os-Linux/util.c b/arch/um/os-Linux/util.c
index 41297ec404bf..fc0f2a9dee5a 100644
--- a/arch/um/os-Linux/util.c
+++ b/arch/um/os-Linux/util.c
@@ -14,6 +14,7 @@
 #include <sys/wait.h>
 #include <sys/mman.h>
 #include <sys/utsname.h>
+#include <sys/random.h>
 #include <init.h>
 #include <os.h>
 
@@ -96,6 +97,11 @@ static inline void __attribute__ ((noreturn)) uml_abort(void)
 			exit(127);
 }
 
+ssize_t os_getrandom(void *buf, size_t len, unsigned int flags)
+{
+	return getrandom(buf, len, flags);
+}
+
 /*
  * UML helper threads must not handle SIGWINCH/INT/TERM
  */
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 1d0f16b53393..57f5e881791a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -260,6 +260,7 @@ config X86
 	select SYSCTL_EXCEPTION_TRACE
 	select THREAD_INFO_IN_TASK
 	select TRACE_IRQFLAGS_SUPPORT
+	select TRACE_IRQFLAGS_NMI_SUPPORT
 	select USER_STACKTRACE_SUPPORT
 	select VIRT_TO_BUS
 	select HAVE_ARCH_KCSAN			if X86_64
@@ -459,27 +460,6 @@ config GOLDFISH
 	def_bool y
 	depends on X86_GOLDFISH
 
-config RETPOLINE
-	bool "Avoid speculative indirect branches in kernel"
-	default y
-	help
-	  Compile kernel with the retpoline compiler options to guard against
-	  kernel-to-user data leaks by avoiding speculative indirect
-	  branches. Requires a compiler with -mindirect-branch=thunk-extern
-	  support for full protection. The kernel may run slower.
-
-config CC_HAS_SLS
-	def_bool $(cc-option,-mharden-sls=all)
-
-config SLS
-	bool "Mitigate Straight-Line-Speculation"
-	depends on CC_HAS_SLS && X86_64
-	default n
-	help
-	  Compile the kernel with straight-line-speculation options to guard
-	  against straight line speculation. The kernel image might be slightly
-	  larger.
-
 config X86_CPU_RESCTRL
 	bool "x86 CPU resource control support"
 	depends on X86 && (CPU_SUP_INTEL || CPU_SUP_AMD)
@@ -2407,6 +2387,88 @@ source "kernel/livepatch/Kconfig"
 
 endmenu
 
+config CC_HAS_SLS
+	def_bool $(cc-option,-mharden-sls=all)
+
+config CC_HAS_RETURN_THUNK
+	def_bool $(cc-option,-mfunction-return=thunk-extern)
+
+menuconfig SPECULATION_MITIGATIONS
+	bool "Mitigations for speculative execution vulnerabilities"
+	default y
+	help
+	  Say Y here to enable options which enable mitigations for
+	  speculative execution hardware vulnerabilities.
+
+	  If you say N, all mitigations will be disabled. You really
+	  should know what you are doing to say so.
+
+if SPECULATION_MITIGATIONS
+
+config PAGE_TABLE_ISOLATION
+	bool "Remove the kernel mapping in user mode"
+	default y
+	depends on (X86_64 || X86_PAE)
+	help
+	  This feature reduces the number of hardware side channels by
+	  ensuring that the majority of kernel addresses are not mapped
+	  into userspace.
+
+	  See Documentation/x86/pti.rst for more details.
+
+config RETPOLINE
+	bool "Avoid speculative indirect branches in kernel"
+	default y
+	help
+	  Compile kernel with the retpoline compiler options to guard against
+	  kernel-to-user data leaks by avoiding speculative indirect
+	  branches. Requires a compiler with -mindirect-branch=thunk-extern
+	  support for full protection. The kernel may run slower.
+
+config RETHUNK
+	bool "Enable return-thunks"
+	depends on RETPOLINE && CC_HAS_RETURN_THUNK
+	default y if X86_64
+	help
+	  Compile the kernel with the return-thunks compiler option to guard
+	  against kernel-to-user data leaks by avoiding return speculation.
+	  Requires a compiler with -mfunction-return=thunk-extern
+	  support for full protection. The kernel may run slower.
+
+config CPU_UNRET_ENTRY
+	bool "Enable UNRET on kernel entry"
+	depends on CPU_SUP_AMD && RETHUNK && X86_64
+	default y
+	help
+	  Compile the kernel with support for the retbleed=unret mitigation.
+
+config CPU_IBPB_ENTRY
+	bool "Enable IBPB on kernel entry"
+	depends on CPU_SUP_AMD && X86_64
+	default y
+	help
+	  Compile the kernel with support for the retbleed=ibpb mitigation.
+
+config CPU_IBRS_ENTRY
+	bool "Enable IBRS on kernel entry"
+	depends on CPU_SUP_INTEL && X86_64
+	default y
+	help
+	  Compile the kernel with support for the spectre_v2=ibrs mitigation.
+	  This mitigates both spectre_v2 and retbleed at great cost to
+	  performance.
+
+config SLS
+	bool "Mitigate Straight-Line-Speculation"
+	depends on CC_HAS_SLS && X86_64
+	default n
+	help
+	  Compile the kernel with straight-line-speculation options to guard
+	  against straight line speculation. The kernel image might be slightly
+	  larger.
+
+endif
+
 config ARCH_HAS_ADD_PAGES
 	def_bool y
 	depends on X86_64 && ARCH_ENABLE_MEMORY_HOTPLUG
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index d3a6f74a94bd..d4d6db4dde22 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -1,8 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
 
-config TRACE_IRQFLAGS_NMI_SUPPORT
-	def_bool y
-
 config EARLY_PRINTK_USB
 	bool
 
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 300227818206..9c09bbd390ce 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -24,7 +24,7 @@ endif
 
 # How to compile the 16-bit code.  Note we always compile for -march=i386;
 # that way we can complain to the user if the CPU is insufficient.
-REALMODE_CFLAGS	:= -m16 -g -Os -DDISABLE_BRANCH_PROFILING \
+REALMODE_CFLAGS	:= -m16 -g -Os -DDISABLE_BRANCH_PROFILING -D__DISABLE_EXPORTS \
 		   -Wall -Wstrict-prototypes -march=i386 -mregparm=3 \
 		   -fno-strict-aliasing -fomit-frame-pointer -fno-pic \
 		   -mno-mmx -mno-sse $(call cc-option,-fcf-protection=none)
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index b5aecb524a8a..ffec8bb01ba8 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -103,7 +103,7 @@ $(obj)/zoffset.h: $(obj)/compressed/vmlinux FORCE
 AFLAGS_header.o += -I$(objtree)/$(obj)
 $(obj)/header.o: $(obj)/zoffset.h
 
-LDFLAGS_setup.elf	:= -m elf_i386 -T
+LDFLAGS_setup.elf	:= -m elf_i386 -z noexecstack -T
 $(obj)/setup.elf: $(src)/setup.ld $(SETUP_OBJS) FORCE
 	$(call if_changed,ld)
 
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index e11813646051..15c5ae62a0e9 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -69,6 +69,10 @@ LDFLAGS_vmlinux := -pie $(call ld-option, --no-dynamic-linker)
 ifdef CONFIG_LD_ORPHAN_WARN
 LDFLAGS_vmlinux += --orphan-handling=warn
 endif
+LDFLAGS_vmlinux += -z noexecstack
+ifeq ($(CONFIG_LD_IS_BFD),y)
+LDFLAGS_vmlinux += $(call ld-option,--no-warn-rwx-segments)
+endif
 LDFLAGS_vmlinux += -T
 
 hostprogs	:= mkpiggy
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index c3af959648e6..fce05e9df56d 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -61,9 +61,7 @@ sha256-ssse3-$(CONFIG_AS_SHA256_NI) += sha256_ni_asm.o
 obj-$(CONFIG_CRYPTO_SHA512_SSSE3) += sha512-ssse3.o
 sha512-ssse3-y := sha512-ssse3-asm.o sha512-avx-asm.o sha512-avx2-asm.o sha512_ssse3_glue.o
 
-obj-$(CONFIG_CRYPTO_BLAKE2S_X86) += blake2s-x86_64.o
-blake2s-x86_64-y := blake2s-shash.o
-obj-$(if $(CONFIG_CRYPTO_BLAKE2S_X86),y) += libblake2s-x86_64.o
+obj-$(CONFIG_CRYPTO_BLAKE2S_X86) += libblake2s-x86_64.o
 libblake2s-x86_64-y := blake2s-core.o blake2s-glue.o
 
 obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o
diff --git a/arch/x86/crypto/blake2s-glue.c b/arch/x86/crypto/blake2s-glue.c
index 69853c13e8fb..aaba21230528 100644
--- a/arch/x86/crypto/blake2s-glue.c
+++ b/arch/x86/crypto/blake2s-glue.c
@@ -4,7 +4,6 @@
  */
 
 #include <crypto/internal/blake2s.h>
-#include <crypto/internal/simd.h>
 
 #include <linux/types.h>
 #include <linux/jump_label.h>
@@ -33,7 +32,7 @@ void blake2s_compress(struct blake2s_state *state, const u8 *block,
 	/* SIMD disables preemption, so relax after processing each page. */
 	BUILD_BUG_ON(SZ_4K / BLAKE2S_BLOCK_SIZE < 8);
 
-	if (!static_branch_likely(&blake2s_use_ssse3) || !crypto_simd_usable()) {
+	if (!static_branch_likely(&blake2s_use_ssse3) || !may_use_simd()) {
 		blake2s_compress_generic(state, block, nblocks, inc);
 		return;
 	}
diff --git a/arch/x86/crypto/blake2s-shash.c b/arch/x86/crypto/blake2s-shash.c
deleted file mode 100644
index 59ae28abe35c..000000000000
--- a/arch/x86/crypto/blake2s-shash.c
+++ /dev/null
@@ -1,77 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0 OR MIT
-/*
- * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
- */
-
-#include <crypto/internal/blake2s.h>
-#include <crypto/internal/simd.h>
-#include <crypto/internal/hash.h>
-
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/sizes.h>
-
-#include <asm/cpufeature.h>
-#include <asm/processor.h>
-
-static int crypto_blake2s_update_x86(struct shash_desc *desc,
-				     const u8 *in, unsigned int inlen)
-{
-	return crypto_blake2s_update(desc, in, inlen, false);
-}
-
-static int crypto_blake2s_final_x86(struct shash_desc *desc, u8 *out)
-{
-	return crypto_blake2s_final(desc, out, false);
-}
-
-#define BLAKE2S_ALG(name, driver_name, digest_size)			\
-	{								\
-		.base.cra_name		= name,				\
-		.base.cra_driver_name	= driver_name,			\
-		.base.cra_priority	= 200,				\
-		.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,	\
-		.base.cra_blocksize	= BLAKE2S_BLOCK_SIZE,		\
-		.base.cra_ctxsize	= sizeof(struct blake2s_tfm_ctx), \
-		.base.cra_module	= THIS_MODULE,			\
-		.digestsize		= digest_size,			\
-		.setkey			= crypto_blake2s_setkey,	\
-		.init			= crypto_blake2s_init,		\
-		.update			= crypto_blake2s_update_x86,	\
-		.final			= crypto_blake2s_final_x86,	\
-		.descsize		= sizeof(struct blake2s_state),	\
-	}
-
-static struct shash_alg blake2s_algs[] = {
-	BLAKE2S_ALG("blake2s-128", "blake2s-128-x86", BLAKE2S_128_HASH_SIZE),
-	BLAKE2S_ALG("blake2s-160", "blake2s-160-x86", BLAKE2S_160_HASH_SIZE),
-	BLAKE2S_ALG("blake2s-224", "blake2s-224-x86", BLAKE2S_224_HASH_SIZE),
-	BLAKE2S_ALG("blake2s-256", "blake2s-256-x86", BLAKE2S_256_HASH_SIZE),
-};
-
-static int __init blake2s_mod_init(void)
-{
-	if (IS_REACHABLE(CONFIG_CRYPTO_HASH) && boot_cpu_has(X86_FEATURE_SSSE3))
-		return crypto_register_shashes(blake2s_algs, ARRAY_SIZE(blake2s_algs));
-	return 0;
-}
-
-static void __exit blake2s_mod_exit(void)
-{
-	if (IS_REACHABLE(CONFIG_CRYPTO_HASH) && boot_cpu_has(X86_FEATURE_SSSE3))
-		crypto_unregister_shashes(blake2s_algs, ARRAY_SIZE(blake2s_algs));
-}
-
-module_init(blake2s_mod_init);
-module_exit(blake2s_mod_exit);
-
-MODULE_ALIAS_CRYPTO("blake2s-128");
-MODULE_ALIAS_CRYPTO("blake2s-128-x86");
-MODULE_ALIAS_CRYPTO("blake2s-160");
-MODULE_ALIAS_CRYPTO("blake2s-160-x86");
-MODULE_ALIAS_CRYPTO("blake2s-224");
-MODULE_ALIAS_CRYPTO("blake2s-224-x86");
-MODULE_ALIAS_CRYPTO("blake2s-256");
-MODULE_ALIAS_CRYPTO("blake2s-256-x86");
-MODULE_LICENSE("GPL v2");
diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile
index 7fec5dcf6438..ca2fe186994b 100644
--- a/arch/x86/entry/Makefile
+++ b/arch/x86/entry/Makefile
@@ -11,12 +11,13 @@ CFLAGS_REMOVE_common.o		= $(CC_FLAGS_FTRACE)
 
 CFLAGS_common.o			+= -fno-stack-protector
 
-obj-y				:= entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o
+obj-y				:= entry.o entry_$(BITS).o syscall_$(BITS).o
 obj-y				+= common.o
 
 obj-y				+= vdso/
 obj-y				+= vsyscall/
 
+obj-$(CONFIG_PREEMPTION)	+= thunk_$(BITS).o
 obj-$(CONFIG_IA32_EMULATION)	+= entry_64_compat.o syscall_32.o
 obj-$(CONFIG_X86_X32_ABI)	+= syscall_x32.o
 
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index a4c061fb7c6e..b00a3a95fbfa 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -7,6 +7,8 @@
 #include <asm/asm-offsets.h>
 #include <asm/processor-flags.h>
 #include <asm/ptrace-abi.h>
+#include <asm/msr.h>
+#include <asm/nospec-branch.h>
 
 /*
 
@@ -119,27 +121,19 @@ For 32-bit we have the following conventions - kernel is built with
 	CLEAR_REGS
 .endm
 
-.macro POP_REGS pop_rdi=1 skip_r11rcx=0
+.macro POP_REGS pop_rdi=1
 	popq %r15
 	popq %r14
 	popq %r13
 	popq %r12
 	popq %rbp
 	popq %rbx
-	.if \skip_r11rcx
-	popq %rsi
-	.else
 	popq %r11
-	.endif
 	popq %r10
 	popq %r9
 	popq %r8
 	popq %rax
-	.if \skip_r11rcx
-	popq %rsi
-	.else
 	popq %rcx
-	.endif
 	popq %rdx
 	popq %rsi
 	.if \pop_rdi
@@ -290,6 +284,66 @@ For 32-bit we have the following conventions - kernel is built with
 #endif
 
 /*
+ * IBRS kernel mitigation for Spectre_v2.
+ *
+ * Assumes full context is established (PUSH_REGS, CR3 and GS) and it clobbers
+ * the regs it uses (AX, CX, DX). Must be called before the first RET
+ * instruction (NOTE! UNTRAIN_RET includes a RET instruction)
+ *
+ * The optional argument is used to save/restore the current value,
+ * which is used on the paranoid paths.
+ *
+ * Assumes x86_spec_ctrl_{base,current} to have SPEC_CTRL_IBRS set.
+ */
+.macro IBRS_ENTER save_reg
+#ifdef CONFIG_CPU_IBRS_ENTRY
+	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_KERNEL_IBRS
+	movl	$MSR_IA32_SPEC_CTRL, %ecx
+
+.ifnb \save_reg
+	rdmsr
+	shl	$32, %rdx
+	or	%rdx, %rax
+	mov	%rax, \save_reg
+	test	$SPEC_CTRL_IBRS, %eax
+	jz	.Ldo_wrmsr_\@
+	lfence
+	jmp	.Lend_\@
+.Ldo_wrmsr_\@:
+.endif
+
+	movq	PER_CPU_VAR(x86_spec_ctrl_current), %rdx
+	movl	%edx, %eax
+	shr	$32, %rdx
+	wrmsr
+.Lend_\@:
+#endif
+.endm
+
+/*
+ * Similar to IBRS_ENTER, requires KERNEL GS,CR3 and clobbers (AX, CX, DX)
+ * regs. Must be called after the last RET.
+ */
+.macro IBRS_EXIT save_reg
+#ifdef CONFIG_CPU_IBRS_ENTRY
+	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_KERNEL_IBRS
+	movl	$MSR_IA32_SPEC_CTRL, %ecx
+
+.ifnb \save_reg
+	mov	\save_reg, %rdx
+.else
+	movq	PER_CPU_VAR(x86_spec_ctrl_current), %rdx
+	andl	$(~SPEC_CTRL_IBRS), %edx
+.endif
+
+	movl	%edx, %eax
+	shr	$32, %rdx
+	wrmsr
+.Lend_\@:
+#endif
+.endm
+
+/*
  * Mitigate Spectre v1 for conditional swapgs code paths.
  *
  * FENCE_SWAPGS_USER_ENTRY is used in the user entry swapgs code path, to
diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S
new file mode 100644
index 000000000000..bfb7bcb362bc
--- /dev/null
+++ b/arch/x86/entry/entry.S
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Common place for both 32- and 64-bit entry routines.
+ */
+
+#include <linux/linkage.h>
+#include <asm/export.h>
+#include <asm/msr-index.h>
+
+.pushsection .noinstr.text, "ax"
+
+SYM_FUNC_START(entry_ibpb)
+	movl	$MSR_IA32_PRED_CMD, %ecx
+	movl	$PRED_CMD_IBPB, %eax
+	xorl	%edx, %edx
+	wrmsr
+	RET
+SYM_FUNC_END(entry_ibpb)
+/* For KVM */
+EXPORT_SYMBOL_GPL(entry_ibpb);
+
+.popsection
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 00413e37feee..6b44263d7efb 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -268,19 +268,16 @@
 1:	popl	%ds
 2:	popl	%es
 3:	popl	%fs
-	addl	$(4 + \pop), %esp	/* pop the unused "gs" slot */
+4:	addl	$(4 + \pop), %esp	/* pop the unused "gs" slot */
 	IRET_FRAME
-.pushsection .fixup, "ax"
-4:	movl	$0, (%esp)
-	jmp	1b
-5:	movl	$0, (%esp)
-	jmp	2b
-6:	movl	$0, (%esp)
-	jmp	3b
-.popsection
-	_ASM_EXTABLE(1b, 4b)
-	_ASM_EXTABLE(2b, 5b)
-	_ASM_EXTABLE(3b, 6b)
+
+	/*
+	 * There is no _ASM_EXTABLE_TYPE_REG() for ASM, however since this is
+	 * ASM the registers are known and we can trivially hard-code them.
+	 */
+	_ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_POP_ZERO|EX_REG_DS)
+	_ASM_EXTABLE_TYPE(2b, 3b, EX_TYPE_POP_ZERO|EX_REG_ES)
+	_ASM_EXTABLE_TYPE(3b, 4b, EX_TYPE_POP_ZERO|EX_REG_FS)
 .endm
 
 .macro RESTORE_ALL_NMI cr3_reg:req pop=0
@@ -701,7 +698,6 @@ SYM_CODE_START(__switch_to_asm)
 	movl	%ebx, PER_CPU_VAR(__stack_chk_guard)
 #endif
 
-#ifdef CONFIG_RETPOLINE
 	/*
 	 * When switching from a shallower to a deeper call stack
 	 * the RSB may either underflow or use entries populated
@@ -710,7 +706,6 @@ SYM_CODE_START(__switch_to_asm)
 	 * speculative execution to prevent attack.
 	 */
 	FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
-#endif
 
 	/* Restore flags or the incoming task to restore AC state. */
 	popfl
@@ -925,10 +920,8 @@ SYM_FUNC_START(entry_SYSENTER_32)
 	sti
 	sysexit
 
-.pushsection .fixup, "ax"
-2:	movl	$0, PT_FS(%esp)
-	jmp	1b
-.popsection
+2:	movl    $0, PT_FS(%esp)
+	jmp     1b
 	_ASM_EXTABLE(1b, 2b)
 
 .Lsysenter_fix_flags:
@@ -996,8 +989,7 @@ restore_all_switch_stack:
 	 */
 	iret
 
-.section .fixup, "ax"
-SYM_CODE_START(asm_iret_error)
+.Lasm_iret_error:
 	pushl	$0				# no error code
 	pushl	$iret_error
 
@@ -1014,9 +1006,8 @@ SYM_CODE_START(asm_iret_error)
 #endif
 
 	jmp	handle_exception
-SYM_CODE_END(asm_iret_error)
-.previous
-	_ASM_EXTABLE(.Lirq_return, asm_iret_error)
+
+	_ASM_EXTABLE(.Lirq_return, .Lasm_iret_error)
 SYM_FUNC_END(entry_INT80_32)
 
 .macro FIXUP_ESPFIX_STACK
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 3acf0af49305..a3af2a9159b1 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -85,7 +85,7 @@
  */
 
 SYM_CODE_START(entry_SYSCALL_64)
-	UNWIND_HINT_EMPTY
+	UNWIND_HINT_ENTRY
 
 	swapgs
 	/* tss.sp2 is scratch space. */
@@ -110,6 +110,11 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL)
 	movq	%rsp, %rdi
 	/* Sign extend the lower 32bit as syscall numbers are treated as int */
 	movslq	%eax, %rsi
+
+	/* clobbers %rax, make sure it is after saving the syscall nr */
+	IBRS_ENTER
+	UNTRAIN_RET
+
 	call	do_syscall_64		/* returns with IRQs disabled */
 
 	/*
@@ -189,8 +194,8 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL)
 	 * perf profiles. Nothing jumps here.
 	 */
 syscall_return_via_sysret:
-	/* rcx and r11 are already restored (see code above) */
-	POP_REGS pop_rdi=0 skip_r11rcx=1
+	IBRS_EXIT
+	POP_REGS pop_rdi=0
 
 	/*
 	 * Now all regs are restored except RSP and RDI.
@@ -243,7 +248,6 @@ SYM_FUNC_START(__switch_to_asm)
 	movq	%rbx, PER_CPU_VAR(fixed_percpu_data) + stack_canary_offset
 #endif
 
-#ifdef CONFIG_RETPOLINE
 	/*
 	 * When switching from a shallower to a deeper call stack
 	 * the RSB may either underflow or use entries populated
@@ -252,7 +256,6 @@ SYM_FUNC_START(__switch_to_asm)
 	 * speculative execution to prevent attack.
 	 */
 	FILL_RETURN_BUFFER %r12, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
-#endif
 
 	/* restore callee-saved registers */
 	popq	%r15
@@ -315,6 +318,14 @@ SYM_CODE_END(ret_from_fork)
 #endif
 .endm
 
+SYM_CODE_START_LOCAL(xen_error_entry)
+	UNWIND_HINT_FUNC
+	PUSH_AND_CLEAR_REGS save_ret=1
+	ENCODE_FRAME_POINTER 8
+	UNTRAIN_RET
+	RET
+SYM_CODE_END(xen_error_entry)
+
 /**
  * idtentry_body - Macro to emit code calling the C function
  * @cfunc:		C function to be called
@@ -322,7 +333,18 @@ SYM_CODE_END(ret_from_fork)
  */
 .macro idtentry_body cfunc has_error_code:req
 
-	call	error_entry
+	/*
+	 * Call error_entry() and switch to the task stack if from userspace.
+	 *
+	 * When in XENPV, it is already in the task stack, and it can't fault
+	 * for native_iret() nor native_load_gs_index() since XENPV uses its
+	 * own pvops for IRET and load_gs_index().  And it doesn't need to
+	 * switch the CR3.  So it can skip invoking error_entry().
+	 */
+	ALTERNATIVE "call error_entry; movq %rax, %rsp", \
+		    "call xen_error_entry", X86_FEATURE_XENPV
+
+	ENCODE_FRAME_POINTER
 	UNWIND_HINT_REGS
 
 	movq	%rsp, %rdi			/* pt_regs pointer into 1st argument*/
@@ -351,6 +373,7 @@ SYM_CODE_END(ret_from_fork)
 SYM_CODE_START(\asmsym)
 	UNWIND_HINT_IRET_REGS offset=\has_error_code*8
 	ASM_CLAC
+	cld
 
 	.if \has_error_code == 0
 		pushq	$-1			/* ORIG_RAX: no syscall to restart */
@@ -418,6 +441,7 @@ SYM_CODE_END(\asmsym)
 SYM_CODE_START(\asmsym)
 	UNWIND_HINT_IRET_REGS
 	ASM_CLAC
+	cld
 
 	pushq	$-1			/* ORIG_RAX: no syscall to restart */
 
@@ -473,6 +497,7 @@ SYM_CODE_END(\asmsym)
 SYM_CODE_START(\asmsym)
 	UNWIND_HINT_IRET_REGS
 	ASM_CLAC
+	cld
 
 	/*
 	 * If the entry is from userspace, switch stacks and treat it as
@@ -535,6 +560,7 @@ SYM_CODE_END(\asmsym)
 SYM_CODE_START(\asmsym)
 	UNWIND_HINT_IRET_REGS offset=8
 	ASM_CLAC
+	cld
 
 	/* paranoid_entry returns GS information for paranoid_exit in EBX. */
 	call	paranoid_entry
@@ -568,6 +594,7 @@ __irqentry_text_end:
 
 SYM_CODE_START_LOCAL(common_interrupt_return)
 SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
+	IBRS_EXIT
 #ifdef CONFIG_DEBUG_ENTRY
 	/* Assert that pt_regs indicates user mode. */
 	testb	$3, CS(%rsp)
@@ -675,6 +702,7 @@ native_irq_return_ldt:
 	pushq	%rdi				/* Stash user RDI */
 	swapgs					/* to kernel GS */
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi	/* to kernel CR3 */
+	UNTRAIN_RET
 
 	movq	PER_CPU_VAR(espfix_waddr), %rdi
 	movq	%rax, (0*8)(%rdi)		/* user RAX */
@@ -846,10 +874,12 @@ SYM_CODE_END(xen_failsafe_callback)
  *              1 -> no SWAPGS on exit
  *
  *     Y        GSBASE value at entry, must be restored in paranoid_exit
+ *
+ * R14 - old CR3
+ * R15 - old SPEC_CTRL
  */
 SYM_CODE_START_LOCAL(paranoid_entry)
 	UNWIND_HINT_FUNC
-	cld
 	PUSH_AND_CLEAR_REGS save_ret=1
 	ENCODE_FRAME_POINTER 8
 
@@ -890,7 +920,7 @@ SYM_CODE_START_LOCAL(paranoid_entry)
 	 * is needed here.
 	 */
 	SAVE_AND_SET_GSBASE scratch_reg=%rax save_reg=%rbx
-	RET
+	jmp .Lparanoid_gsbase_done
 
 .Lparanoid_entry_checkgs:
 	/* EBX = 1 -> kernel GSBASE active, no restore required */
@@ -909,8 +939,16 @@ SYM_CODE_START_LOCAL(paranoid_entry)
 	xorl	%ebx, %ebx
 	swapgs
 .Lparanoid_kernel_gsbase:
-
 	FENCE_SWAPGS_KERNEL_ENTRY
+.Lparanoid_gsbase_done:
+
+	/*
+	 * Once we have CR3 and %GS setup save and set SPEC_CTRL. Just like
+	 * CR3 above, keep the old value in a callee saved register.
+	 */
+	IBRS_ENTER save_reg=%r15
+	UNTRAIN_RET
+
 	RET
 SYM_CODE_END(paranoid_entry)
 
@@ -932,9 +970,19 @@ SYM_CODE_END(paranoid_entry)
  *              1 -> no SWAPGS on exit
  *
  *     Y        User space GSBASE, must be restored unconditionally
+ *
+ * R14 - old CR3
+ * R15 - old SPEC_CTRL
  */
 SYM_CODE_START_LOCAL(paranoid_exit)
 	UNWIND_HINT_REGS
+
+	/*
+	 * Must restore IBRS state before both CR3 and %GS since we need access
+	 * to the per-CPU x86_spec_ctrl_shadow variable.
+	 */
+	IBRS_EXIT save_reg=%r15
+
 	/*
 	 * The order of operations is important. RESTORE_CR3 requires
 	 * kernel GSBASE.
@@ -963,13 +1011,14 @@ SYM_CODE_START_LOCAL(paranoid_exit)
 SYM_CODE_END(paranoid_exit)
 
 /*
- * Save all registers in pt_regs, and switch GS if needed.
+ * Switch GS and CR3 if needed.
  */
 SYM_CODE_START_LOCAL(error_entry)
 	UNWIND_HINT_FUNC
-	cld
+
 	PUSH_AND_CLEAR_REGS save_ret=1
 	ENCODE_FRAME_POINTER 8
+
 	testb	$3, CS+8(%rsp)
 	jz	.Lerror_kernelspace
 
@@ -981,15 +1030,14 @@ SYM_CODE_START_LOCAL(error_entry)
 	FENCE_SWAPGS_USER_ENTRY
 	/* We have user CR3.  Change to kernel CR3. */
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
+	IBRS_ENTER
+	UNTRAIN_RET
 
+	leaq	8(%rsp), %rdi			/* arg0 = pt_regs pointer */
 .Lerror_entry_from_usermode_after_swapgs:
+
 	/* Put us onto the real thread stack. */
-	popq	%r12				/* save return addr in %12 */
-	movq	%rsp, %rdi			/* arg0 = pt_regs pointer */
 	call	sync_regs
-	movq	%rax, %rsp			/* switch stack */
-	ENCODE_FRAME_POINTER
-	pushq	%r12
 	RET
 
 	/*
@@ -1021,6 +1069,8 @@ SYM_CODE_START_LOCAL(error_entry)
 	 */
 .Lerror_entry_done_lfence:
 	FENCE_SWAPGS_KERNEL_ENTRY
+	leaq	8(%rsp), %rax			/* return pt_regs pointer */
+	ANNOTATE_UNRET_END
 	RET
 
 .Lbstep_iret:
@@ -1036,14 +1086,16 @@ SYM_CODE_START_LOCAL(error_entry)
 	SWAPGS
 	FENCE_SWAPGS_USER_ENTRY
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
+	IBRS_ENTER
+	UNTRAIN_RET
 
 	/*
 	 * Pretend that the exception came from user mode: set up pt_regs
 	 * as if we faulted immediately after IRET.
 	 */
-	mov	%rsp, %rdi
+	leaq	8(%rsp), %rdi			/* arg0 = pt_regs pointer */
 	call	fixup_bad_iret
-	mov	%rax, %rsp
+	mov	%rax, %rdi
 	jmp	.Lerror_entry_from_usermode_after_swapgs
 SYM_CODE_END(error_entry)
 
@@ -1105,6 +1157,7 @@ SYM_CODE_START(asm_exc_nmi)
 	 */
 
 	ASM_CLAC
+	cld
 
 	/* Use %rdx as our temp variable throughout */
 	pushq	%rdx
@@ -1124,7 +1177,6 @@ SYM_CODE_START(asm_exc_nmi)
 	 */
 
 	swapgs
-	cld
 	FENCE_SWAPGS_USER_ENTRY
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdx
 	movq	%rsp, %rdx
@@ -1140,6 +1192,9 @@ SYM_CODE_START(asm_exc_nmi)
 	PUSH_AND_CLEAR_REGS rdx=(%rdx)
 	ENCODE_FRAME_POINTER
 
+	IBRS_ENTER
+	UNTRAIN_RET
+
 	/*
 	 * At this point we no longer need to worry about stack damage
 	 * due to nesting -- we're on the normal thread stack and we're
@@ -1362,6 +1417,9 @@ end_repeat_nmi:
 	movq	$-1, %rsi
 	call	exc_nmi
 
+	/* Always restore stashed SPEC_CTRL value (see paranoid_entry) */
+	IBRS_EXIT save_reg=%r15
+
 	/* Always restore stashed CR3 value (see paranoid_entry) */
 	RESTORE_CR3 scratch_reg=%r15 save_reg=%r14
 
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 0051cf5c792d..4d637a965efb 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -4,7 +4,6 @@
  *
  * Copyright 2000-2002 Andi Kleen, SuSE Labs.
  */
-#include "calling.h"
 #include <asm/asm-offsets.h>
 #include <asm/current.h>
 #include <asm/errno.h>
@@ -14,9 +13,12 @@
 #include <asm/irqflags.h>
 #include <asm/asm.h>
 #include <asm/smap.h>
+#include <asm/nospec-branch.h>
 #include <linux/linkage.h>
 #include <linux/err.h>
 
+#include "calling.h"
+
 	.section .entry.text, "ax"
 
 /*
@@ -47,7 +49,7 @@
  * 0(%ebp) arg6
  */
 SYM_CODE_START(entry_SYSENTER_compat)
-	UNWIND_HINT_EMPTY
+	UNWIND_HINT_ENTRY
 	/* Interrupts are off on entry. */
 	SWAPGS
 
@@ -112,6 +114,9 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL)
 
 	cld
 
+	IBRS_ENTER
+	UNTRAIN_RET
+
 	/*
 	 * SYSENTER doesn't filter flags, so we need to clear NT and AC
 	 * ourselves.  To save a few cycles, we can check whether
@@ -197,7 +202,7 @@ SYM_CODE_END(entry_SYSENTER_compat)
  * 0(%esp) arg6
  */
 SYM_CODE_START(entry_SYSCALL_compat)
-	UNWIND_HINT_EMPTY
+	UNWIND_HINT_ENTRY
 	/* Interrupts are off on entry. */
 	swapgs
 
@@ -252,6 +257,9 @@ SYM_INNER_LABEL(entry_SYSCALL_compat_after_hwframe, SYM_L_GLOBAL)
 
 	UNWIND_HINT_REGS
 
+	IBRS_ENTER
+	UNTRAIN_RET
+
 	movq	%rsp, %rdi
 	call	do_fast_syscall_32
 	/* XEN PV guests always use IRET path */
@@ -266,6 +274,8 @@ sysret32_from_system_call:
 	 */
 	STACKLEAK_ERASE
 
+	IBRS_EXIT
+
 	movq	RBX(%rsp), %rbx		/* pt_regs->rbx */
 	movq	RBP(%rsp), %rbp		/* pt_regs->rbp */
 	movq	EFLAGS(%rsp), %r11	/* pt_regs->flags (in r11) */
@@ -339,7 +349,7 @@ SYM_CODE_END(entry_SYSCALL_compat)
  * ebp  arg6
  */
 SYM_CODE_START(entry_INT80_compat)
-	UNWIND_HINT_EMPTY
+	UNWIND_HINT_ENTRY
 	/*
 	 * Interrupts are off on entry.
 	 */
@@ -409,6 +419,9 @@ SYM_CODE_START(entry_INT80_compat)
 
 	cld
 
+	IBRS_ENTER
+	UNTRAIN_RET
+
 	movq	%rsp, %rdi
 	call	do_int80_syscall_32
 	jmp	swapgs_restore_regs_and_return_to_usermode
diff --git a/arch/x86/entry/thunk_32.S b/arch/x86/entry/thunk_32.S
index 7591bab060f7..ff6e7003da97 100644
--- a/arch/x86/entry/thunk_32.S
+++ b/arch/x86/entry/thunk_32.S
@@ -29,10 +29,8 @@ SYM_CODE_START_NOALIGN(\name)
 SYM_CODE_END(\name)
 	.endm
 
-#ifdef CONFIG_PREEMPTION
 	THUNK preempt_schedule_thunk, preempt_schedule
 	THUNK preempt_schedule_notrace_thunk, preempt_schedule_notrace
 	EXPORT_SYMBOL(preempt_schedule_thunk)
 	EXPORT_SYMBOL(preempt_schedule_notrace_thunk)
-#endif
 
diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S
index 505b488fcc65..f38b07d2768b 100644
--- a/arch/x86/entry/thunk_64.S
+++ b/arch/x86/entry/thunk_64.S
@@ -31,14 +31,11 @@ SYM_FUNC_END(\name)
 	_ASM_NOKPROBE(\name)
 	.endm
 
-#ifdef CONFIG_PREEMPTION
 	THUNK preempt_schedule_thunk, preempt_schedule
 	THUNK preempt_schedule_notrace_thunk, preempt_schedule_notrace
 	EXPORT_SYMBOL(preempt_schedule_thunk)
 	EXPORT_SYMBOL(preempt_schedule_notrace_thunk)
-#endif
 
-#ifdef CONFIG_PREEMPTION
 SYM_CODE_START_LOCAL_NOALIGN(__thunk_restore)
 	popq %r11
 	popq %r10
@@ -53,4 +50,3 @@ SYM_CODE_START_LOCAL_NOALIGN(__thunk_restore)
 	RET
 	_ASM_NOKPROBE(__thunk_restore)
 SYM_CODE_END(__thunk_restore)
-#endif
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index a2dddcc189f6..c277c63195ce 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -92,6 +92,7 @@ endif
 endif
 
 $(vobjs): KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO) $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)
+$(vobjs): KBUILD_AFLAGS += -DBUILD_VDSO
 
 #
 # vDSO code runs in userspace and -pg doesn't help with profiling anyway.
@@ -178,7 +179,7 @@ quiet_cmd_vdso = VDSO    $@
 		 sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@'
 
 VDSO_LDFLAGS = -shared --hash-style=both --build-id=sha1 \
-	$(call ld-option, --eh-frame-hdr) -Bsymbolic
+	$(call ld-option, --eh-frame-hdr) -Bsymbolic -z noexecstack
 GCOV_PROFILE := n
 
 quiet_cmd_vdso_and_check = VDSO    $@
diff --git a/arch/x86/entry/vsyscall/vsyscall_emu_64.S b/arch/x86/entry/vsyscall/vsyscall_emu_64.S
index 15e35159ebb6..ef2dd1827243 100644
--- a/arch/x86/entry/vsyscall/vsyscall_emu_64.S
+++ b/arch/x86/entry/vsyscall/vsyscall_emu_64.S
@@ -19,17 +19,20 @@ __vsyscall_page:
 
 	mov $__NR_gettimeofday, %rax
 	syscall
-	RET
+	ret
+	int3
 
 	.balign 1024, 0xcc
 	mov $__NR_time, %rax
 	syscall
-	RET
+	ret
+	int3
 
 	.balign 1024, 0xcc
 	mov $__NR_getcpu, %rax
 	syscall
-	RET
+	ret
+	int3
 
 	.balign 4096, 0xcc
 
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 4dbb55a43dad..266ac8263696 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -236,6 +236,7 @@ static u64 load_latency_data(u64 status)
 static u64 store_latency_data(u64 status)
 {
 	union intel_x86_pebs_dse dse;
+	union perf_mem_data_src src;
 	u64 val;
 
 	dse.val = status;
@@ -263,7 +264,14 @@ static u64 store_latency_data(u64 status)
 
 	val |= P(BLK, NA);
 
-	return val;
+	/*
+	 * the pebs_data_source table is only for loads
+	 * so override the mem_op to say STORE instead
+	 */
+	src.val = val;
+	src.mem_op = P(OP,STORE);
+
+	return src.val;
 }
 
 struct pebs_record_core {
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index f455dd93f921..673721387391 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -1114,6 +1114,14 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event)
 
 	if (static_cpu_has(X86_FEATURE_ARCH_LBR)) {
 		reg->config = mask;
+
+		/*
+		 * The Arch LBR HW can retrieve the common branch types
+		 * from the LBR_INFO. It doesn't require the high overhead
+		 * SW disassemble.
+		 * Enable the branch type by default for the Arch LBR.
+		 */
+		reg->reg |= X86_BR_TYPE_SAVE;
 		return 0;
 	}
 
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index 0f63706cdadf..dc3ae55f79e0 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -788,6 +788,22 @@ int snb_pci2phy_map_init(int devid)
 	return 0;
 }
 
+static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	/*
+	 * SNB IMC counters are 32-bit and are laid out back to back
+	 * in MMIO space. Therefore we must use a 32-bit accessor function
+	 * using readq() from uncore_mmio_read_counter() causes problems
+	 * because it is reading 64-bit at a time. This is okay for the
+	 * uncore_perf_event_update() function because it drops the upper
+	 * 32-bits but not okay for plain uncore_read_counter() as invoked
+	 * in uncore_pmu_event_start().
+	 */
+	return (u64)readl(box->io_addr + hwc->event_base);
+}
+
 static struct pmu snb_uncore_imc_pmu = {
 	.task_ctx_nr	= perf_invalid_context,
 	.event_init	= snb_uncore_imc_event_init,
@@ -807,7 +823,7 @@ static struct intel_uncore_ops snb_uncore_imc_ops = {
 	.disable_event	= snb_uncore_imc_disable_event,
 	.enable_event	= snb_uncore_imc_enable_event,
 	.hw_config	= snb_uncore_imc_hw_config,
-	.read_counter	= uncore_mmio_read_counter,
+	.read_counter	= snb_uncore_imc_read_counter,
 };
 
 static struct intel_uncore_type snb_uncore_imc = {
diff --git a/arch/x86/include/asm/GEN-for-each-reg.h b/arch/x86/include/asm/GEN-for-each-reg.h
index 1b07fb102c4e..07949102a08d 100644
--- a/arch/x86/include/asm/GEN-for-each-reg.h
+++ b/arch/x86/include/asm/GEN-for-each-reg.h
@@ -1,11 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * These are in machine order; things rely on that.
+ */
 #ifdef CONFIG_64BIT
 GEN(rax)
-GEN(rbx)
 GEN(rcx)
 GEN(rdx)
+GEN(rbx)
+GEN(rsp)
+GEN(rbp)
 GEN(rsi)
 GEN(rdi)
-GEN(rbp)
 GEN(r8)
 GEN(r9)
 GEN(r10)
@@ -16,10 +21,11 @@ GEN(r14)
 GEN(r15)
 #else
 GEN(eax)
-GEN(ebx)
 GEN(ecx)
 GEN(edx)
+GEN(ebx)
+GEN(esp)
+GEN(ebp)
 GEN(esi)
 GEN(edi)
-GEN(ebp)
 #endif
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index a3c2315aca12..a364971967c4 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -75,6 +75,8 @@ extern int alternatives_patched;
 
 extern void alternative_instructions(void);
 extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
+extern void apply_retpolines(s32 *start, s32 *end);
+extern void apply_returns(s32 *start, s32 *end);
 
 struct module;
 
diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h
index 4cb726c71ed8..8f80de627c60 100644
--- a/arch/x86/include/asm/asm-prototypes.h
+++ b/arch/x86/include/asm/asm-prototypes.h
@@ -17,21 +17,3 @@
 extern void cmpxchg8b_emu(void);
 #endif
 
-#ifdef CONFIG_RETPOLINE
-
-#undef GEN
-#define GEN(reg) \
-	extern asmlinkage void __x86_indirect_thunk_ ## reg (void);
-#include <asm/GEN-for-each-reg.h>
-
-#undef GEN
-#define GEN(reg) \
-	extern asmlinkage void __x86_indirect_alt_call_ ## reg (void);
-#include <asm/GEN-for-each-reg.h>
-
-#undef GEN
-#define GEN(reg) \
-	extern asmlinkage void __x86_indirect_alt_jmp_ ## reg (void);
-#include <asm/GEN-for-each-reg.h>
-
-#endif /* CONFIG_RETPOLINE */
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 3ad3da9a7d97..6dd47c9ec788 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -122,28 +122,19 @@
 
 #ifdef __KERNEL__
 
+# include <asm/extable_fixup_types.h>
+
 /* Exception table entry */
 #ifdef __ASSEMBLY__
-# define _ASM_EXTABLE_HANDLE(from, to, handler)			\
+
+# define _ASM_EXTABLE_TYPE(from, to, type)			\
 	.pushsection "__ex_table","a" ;				\
 	.balign 4 ;						\
 	.long (from) - . ;					\
 	.long (to) - . ;					\
-	.long (handler) - . ;					\
+	.long type ;						\
 	.popsection
 
-# define _ASM_EXTABLE(from, to)					\
-	_ASM_EXTABLE_HANDLE(from, to, ex_handler_default)
-
-# define _ASM_EXTABLE_UA(from, to)				\
-	_ASM_EXTABLE_HANDLE(from, to, ex_handler_uaccess)
-
-# define _ASM_EXTABLE_CPY(from, to)				\
-	_ASM_EXTABLE_HANDLE(from, to, ex_handler_copy)
-
-# define _ASM_EXTABLE_FAULT(from, to)				\
-	_ASM_EXTABLE_HANDLE(from, to, ex_handler_fault)
-
 # ifdef CONFIG_KPROBES
 #  define _ASM_NOKPROBE(entry)					\
 	.pushsection "_kprobe_blacklist","aw" ;			\
@@ -155,26 +146,51 @@
 # endif
 
 #else /* ! __ASSEMBLY__ */
-# define _EXPAND_EXTABLE_HANDLE(x) #x
-# define _ASM_EXTABLE_HANDLE(from, to, handler)			\
+
+# define DEFINE_EXTABLE_TYPE_REG \
+	".macro extable_type_reg type:req reg:req\n"						\
+	".set .Lfound, 0\n"									\
+	".set .Lregnr, 0\n"									\
+	".irp rs,rax,rcx,rdx,rbx,rsp,rbp,rsi,rdi,r8,r9,r10,r11,r12,r13,r14,r15\n"		\
+	".ifc \\reg, %%\\rs\n"									\
+	".set .Lfound, .Lfound+1\n"								\
+	".long \\type + (.Lregnr << 8)\n"							\
+	".endif\n"										\
+	".set .Lregnr, .Lregnr+1\n"								\
+	".endr\n"										\
+	".set .Lregnr, 0\n"									\
+	".irp rs,eax,ecx,edx,ebx,esp,ebp,esi,edi,r8d,r9d,r10d,r11d,r12d,r13d,r14d,r15d\n"	\
+	".ifc \\reg, %%\\rs\n"									\
+	".set .Lfound, .Lfound+1\n"								\
+	".long \\type + (.Lregnr << 8)\n"							\
+	".endif\n"										\
+	".set .Lregnr, .Lregnr+1\n"								\
+	".endr\n"										\
+	".if (.Lfound != 1)\n"									\
+	".error \"extable_type_reg: bad register argument\"\n"					\
+	".endif\n"										\
+	".endm\n"
+
+# define UNDEFINE_EXTABLE_TYPE_REG \
+	".purgem extable_type_reg\n"
+
+# define _ASM_EXTABLE_TYPE(from, to, type)			\
 	" .pushsection \"__ex_table\",\"a\"\n"			\
 	" .balign 4\n"						\
 	" .long (" #from ") - .\n"				\
 	" .long (" #to ") - .\n"				\
-	" .long (" _EXPAND_EXTABLE_HANDLE(handler) ") - .\n"	\
+	" .long " __stringify(type) " \n"			\
 	" .popsection\n"
 
-# define _ASM_EXTABLE(from, to)					\
-	_ASM_EXTABLE_HANDLE(from, to, ex_handler_default)
-
-# define _ASM_EXTABLE_UA(from, to)				\
-	_ASM_EXTABLE_HANDLE(from, to, ex_handler_uaccess)
-
-# define _ASM_EXTABLE_CPY(from, to)				\
-	_ASM_EXTABLE_HANDLE(from, to, ex_handler_copy)
-
-# define _ASM_EXTABLE_FAULT(from, to)				\
-	_ASM_EXTABLE_HANDLE(from, to, ex_handler_fault)
+# define _ASM_EXTABLE_TYPE_REG(from, to, type, reg)				\
+	" .pushsection \"__ex_table\",\"a\"\n"					\
+	" .balign 4\n"								\
+	" .long (" #from ") - .\n"						\
+	" .long (" #to ") - .\n"						\
+	DEFINE_EXTABLE_TYPE_REG							\
+	"extable_type_reg reg=" __stringify(reg) ", type=" __stringify(type) " \n"\
+	UNDEFINE_EXTABLE_TYPE_REG						\
+	" .popsection\n"
 
 /* For C file, we already have NOKPROBE_SYMBOL macro */
 
@@ -188,6 +204,17 @@ register unsigned long current_stack_pointer asm(_ASM_SP);
 #define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer)
 #endif /* __ASSEMBLY__ */
 
-#endif /* __KERNEL__ */
+#define _ASM_EXTABLE(from, to)					\
+	_ASM_EXTABLE_TYPE(from, to, EX_TYPE_DEFAULT)
 
+#define _ASM_EXTABLE_UA(from, to)				\
+	_ASM_EXTABLE_TYPE(from, to, EX_TYPE_UACCESS)
+
+#define _ASM_EXTABLE_CPY(from, to)				\
+	_ASM_EXTABLE_TYPE(from, to, EX_TYPE_COPY)
+
+#define _ASM_EXTABLE_FAULT(from, to)				\
+	_ASM_EXTABLE_TYPE(from, to, EX_TYPE_FAULT)
+
+#endif /* __KERNEL__ */
 #endif /* _ASM_X86_ASM_H */
diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h
index dd5ea1bdf04c..75efc4c6f076 100644
--- a/arch/x86/include/asm/cpu_entry_area.h
+++ b/arch/x86/include/asm/cpu_entry_area.h
@@ -143,7 +143,7 @@ extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags);
 
 extern struct cpu_entry_area *get_cpu_entry_area(int cpu);
 
-static inline struct entry_stack *cpu_entry_stack(int cpu)
+static __always_inline struct entry_stack *cpu_entry_stack(int cpu)
 {
 	return &get_cpu_entry_area(cpu)->entry_stack_page.stack;
 }
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index b258efa8bf43..2b56bfef9917 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -203,8 +203,8 @@
 #define X86_FEATURE_PROC_FEEDBACK	( 7*32+ 9) /* AMD ProcFeedbackInterface */
 /* FREE!                                ( 7*32+10) */
 #define X86_FEATURE_PTI			( 7*32+11) /* Kernel Page Table Isolation enabled */
-#define X86_FEATURE_RETPOLINE		( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */
-#define X86_FEATURE_RETPOLINE_LFENCE	( 7*32+13) /* "" Use LFENCE for Spectre variant 2 */
+#define X86_FEATURE_KERNEL_IBRS		( 7*32+12) /* "" Set/clear IBRS on kernel entry/exit */
+#define X86_FEATURE_RSB_VMEXIT		( 7*32+13) /* "" Fill RSB on VM-Exit */
 #define X86_FEATURE_INTEL_PPIN		( 7*32+14) /* Intel Processor Inventory Number */
 #define X86_FEATURE_CDP_L2		( 7*32+15) /* Code and Data Prioritization L2 */
 #define X86_FEATURE_MSR_SPEC_CTRL	( 7*32+16) /* "" MSR SPEC_CTRL is implemented */
@@ -294,6 +294,14 @@
 #define X86_FEATURE_PER_THREAD_MBA	(11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */
 #define X86_FEATURE_SGX1		(11*32+ 8) /* "" Basic SGX */
 #define X86_FEATURE_SGX2		(11*32+ 9) /* "" SGX Enclave Dynamic Memory Management (EDMM) */
+#define X86_FEATURE_ENTRY_IBPB		(11*32+10) /* "" Issue an IBPB on kernel entry */
+#define X86_FEATURE_RRSBA_CTRL		(11*32+11) /* "" RET prediction control */
+#define X86_FEATURE_RETPOLINE		(11*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */
+#define X86_FEATURE_RETPOLINE_LFENCE	(11*32+13) /* "" Use LFENCE for Spectre variant 2 */
+#define X86_FEATURE_RETHUNK		(11*32+14) /* "" Use REturn THUNK */
+#define X86_FEATURE_UNRET		(11*32+15) /* "" AMD BTB untrain return */
+#define X86_FEATURE_USE_IBPB_FW		(11*32+16) /* "" Use IBPB during runtime firmware calls */
+#define X86_FEATURE_RSB_VMEXIT_LITE	(11*32+17) /* "" Fill RSB on VM exit when EIBRS is enabled */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
@@ -313,6 +321,7 @@
 #define X86_FEATURE_AMD_SSBD		(13*32+24) /* "" Speculative Store Bypass Disable */
 #define X86_FEATURE_VIRT_SSBD		(13*32+25) /* Virtualized Speculative Store Bypass Disable */
 #define X86_FEATURE_AMD_SSB_NO		(13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */
+#define X86_FEATURE_BTC_NO		(13*32+29) /* "" Not vulnerable to Branch Type Confusion */
 
 /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
 #define X86_FEATURE_DTHERM		(14*32+ 0) /* Digital Thermal Sensor */
@@ -437,5 +446,8 @@
 #define X86_BUG_ITLB_MULTIHIT		X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */
 #define X86_BUG_SRBDS			X86_BUG(24) /* CPU may leak RNG bits if not mitigated */
 #define X86_BUG_MMIO_STALE_DATA		X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */
+#define X86_BUG_MMIO_UNKNOWN		X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */
+#define X86_BUG_RETBLEED		X86_BUG(27) /* CPU is affected by RETBleed */
+#define X86_BUG_EIBRS_PBRSB		X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 8f28fafa98b3..834a3b6d81e1 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -56,6 +56,25 @@
 # define DISABLE_PTI		(1 << (X86_FEATURE_PTI & 31))
 #endif
 
+#ifdef CONFIG_RETPOLINE
+# define DISABLE_RETPOLINE	0
+#else
+# define DISABLE_RETPOLINE	((1 << (X86_FEATURE_RETPOLINE & 31)) | \
+				 (1 << (X86_FEATURE_RETPOLINE_LFENCE & 31)))
+#endif
+
+#ifdef CONFIG_RETHUNK
+# define DISABLE_RETHUNK	0
+#else
+# define DISABLE_RETHUNK	(1 << (X86_FEATURE_RETHUNK & 31))
+#endif
+
+#ifdef CONFIG_CPU_UNRET_ENTRY
+# define DISABLE_UNRET		0
+#else
+# define DISABLE_UNRET		(1 << (X86_FEATURE_UNRET & 31))
+#endif
+
 /* Force disable because it's broken beyond repair */
 #define DISABLE_ENQCMD		(1 << (X86_FEATURE_ENQCMD & 31))
 
@@ -79,7 +98,7 @@
 #define DISABLED_MASK8	0
 #define DISABLED_MASK9	(DISABLE_SMAP|DISABLE_SGX)
 #define DISABLED_MASK10	0
-#define DISABLED_MASK11	0
+#define DISABLED_MASK11	(DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET)
 #define DISABLED_MASK12	0
 #define DISABLED_MASK13	0
 #define DISABLED_MASK14	0
diff --git a/arch/x86/include/asm/extable.h b/arch/x86/include/asm/extable.h
index 1f0cbc52937c..155c991ba95e 100644
--- a/arch/x86/include/asm/extable.h
+++ b/arch/x86/include/asm/extable.h
@@ -1,12 +1,18 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_X86_EXTABLE_H
 #define _ASM_X86_EXTABLE_H
+
+#include <asm/extable_fixup_types.h>
+
 /*
- * The exception table consists of triples of addresses relative to the
- * exception table entry itself. The first address is of an instruction
- * that is allowed to fault, the second is the target at which the program
- * should continue. The third is a handler function to deal with the fault
- * caused by the instruction in the first field.
+ * The exception table consists of two addresses relative to the
+ * exception table entry itself and a type selector field.
+ *
+ * The first address is of an instruction that is allowed to fault, the
+ * second is the target at which the program should continue.
+ *
+ * The type entry is used by fixup_exception() to select the handler to
+ * deal with the fault caused by the instruction in the first field.
  *
  * All the routines below use bits of fixup code that are out of line
  * with the main instruction path.  This means when everything is well,
@@ -15,7 +21,7 @@
  */
 
 struct exception_table_entry {
-	int insn, fixup, handler;
+	int insn, fixup, data;
 };
 struct pt_regs;
 
@@ -25,21 +31,27 @@ struct pt_regs;
 	do {							\
 		(a)->fixup = (b)->fixup + (delta);		\
 		(b)->fixup = (tmp).fixup - (delta);		\
-		(a)->handler = (b)->handler + (delta);		\
-		(b)->handler = (tmp).handler - (delta);		\
+		(a)->data = (b)->data;				\
+		(b)->data = (tmp).data;				\
 	} while (0)
 
-enum handler_type {
-	EX_HANDLER_NONE,
-	EX_HANDLER_FAULT,
-	EX_HANDLER_UACCESS,
-	EX_HANDLER_OTHER
-};
-
 extern int fixup_exception(struct pt_regs *regs, int trapnr,
 			   unsigned long error_code, unsigned long fault_addr);
 extern int fixup_bug(struct pt_regs *regs, int trapnr);
-extern enum handler_type ex_get_fault_handler_type(unsigned long ip);
+extern int ex_get_fixup_type(unsigned long ip);
 extern void early_fixup_exception(struct pt_regs *regs, int trapnr);
 
+#ifdef CONFIG_X86_MCE
+extern void ex_handler_msr_mce(struct pt_regs *regs, bool wrmsr);
+#else
+static inline void ex_handler_msr_mce(struct pt_regs *regs, bool wrmsr) { }
+#endif
+
+#if defined(CONFIG_BPF_JIT) && defined(CONFIG_X86_64)
+bool ex_handler_bpf(const struct exception_table_entry *x, struct pt_regs *regs);
+#else
+static inline bool ex_handler_bpf(const struct exception_table_entry *x,
+				  struct pt_regs *regs) { return false; }
+#endif
+
 #endif
diff --git a/arch/x86/include/asm/extable_fixup_types.h b/arch/x86/include/asm/extable_fixup_types.h
new file mode 100644
index 000000000000..b3b785b9bb14
--- /dev/null
+++ b/arch/x86/include/asm/extable_fixup_types.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_EXTABLE_FIXUP_TYPES_H
+#define _ASM_X86_EXTABLE_FIXUP_TYPES_H
+
+/*
+ * Our IMM is signed, as such it must live at the top end of the word. Also,
+ * since C99 hex constants are of ambigious type, force cast the mask to 'int'
+ * so that FIELD_GET() will DTRT and sign extend the value when it extracts it.
+ */
+#define EX_DATA_TYPE_MASK		((int)0x000000FF)
+#define EX_DATA_REG_MASK		((int)0x00000F00)
+#define EX_DATA_FLAG_MASK		((int)0x0000F000)
+#define EX_DATA_IMM_MASK		((int)0xFFFF0000)
+
+#define EX_DATA_REG_SHIFT		8
+#define EX_DATA_FLAG_SHIFT		12
+#define EX_DATA_IMM_SHIFT		16
+
+#define EX_DATA_REG(reg)		((reg) << EX_DATA_REG_SHIFT)
+#define EX_DATA_FLAG(flag)		((flag) << EX_DATA_FLAG_SHIFT)
+#define EX_DATA_IMM(imm)		((imm) << EX_DATA_IMM_SHIFT)
+
+/* segment regs */
+#define EX_REG_DS			EX_DATA_REG(8)
+#define EX_REG_ES			EX_DATA_REG(9)
+#define EX_REG_FS			EX_DATA_REG(10)
+#define EX_REG_GS			EX_DATA_REG(11)
+
+/* flags */
+#define EX_FLAG_CLEAR_AX		EX_DATA_FLAG(1)
+#define EX_FLAG_CLEAR_DX		EX_DATA_FLAG(2)
+#define EX_FLAG_CLEAR_AX_DX		EX_DATA_FLAG(3)
+
+/* types */
+#define	EX_TYPE_NONE			 0
+#define	EX_TYPE_DEFAULT			 1
+#define	EX_TYPE_FAULT			 2
+#define	EX_TYPE_UACCESS			 3
+#define	EX_TYPE_COPY			 4
+#define	EX_TYPE_CLEAR_FS		 5
+#define	EX_TYPE_FPU_RESTORE		 6
+#define	EX_TYPE_BPF			 7
+#define	EX_TYPE_WRMSR			 8
+#define	EX_TYPE_RDMSR			 9
+#define	EX_TYPE_WRMSR_SAFE		10 /* reg := -EIO */
+#define	EX_TYPE_RDMSR_SAFE		11 /* reg := -EIO */
+#define	EX_TYPE_WRMSR_IN_MCE		12
+#define	EX_TYPE_RDMSR_IN_MCE		13
+#define	EX_TYPE_DEFAULT_MCE_SAFE	14
+#define	EX_TYPE_FAULT_MCE_SAFE		15
+
+#define	EX_TYPE_POP_REG			16 /* sp += sizeof(long) */
+#define EX_TYPE_POP_ZERO		(EX_TYPE_POP_REG | EX_DATA_IMM(0))
+
+#define	EX_TYPE_IMM_REG			17 /* reg := (long)imm */
+#define	EX_TYPE_EFAULT_REG		(EX_TYPE_IMM_REG | EX_DATA_IMM(-EFAULT))
+
+#endif
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 5a18694a89b2..ce6fc4f8d1d1 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -126,7 +126,7 @@ extern void save_fpregs_to_fpstate(struct fpu *fpu);
 #define kernel_insn(insn, output, input...)				\
 	asm volatile("1:" #insn "\n\t"					\
 		     "2:\n"						\
-		     _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_fprestore)	\
+		     _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FPU_RESTORE)	\
 		     : output : input)
 
 static inline int fnsave_to_user_sigframe(struct fregs_state __user *fx)
@@ -253,7 +253,7 @@ static inline void fxsave(struct fxregs_state *fx)
 				 XRSTORS, X86_FEATURE_XSAVES)		\
 		     "\n"						\
 		     "3:\n"						\
-		     _ASM_EXTABLE_HANDLE(661b, 3b, ex_handler_fprestore)\
+		     _ASM_EXTABLE_TYPE(661b, 3b, EX_TYPE_FPU_RESTORE)	\
 		     :							\
 		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
 		     : "memory")
diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h
index f9c00110a69a..99d345b686fa 100644
--- a/arch/x86/include/asm/futex.h
+++ b/arch/x86/include/asm/futex.h
@@ -17,13 +17,9 @@ do {								\
 	int oldval = 0, ret;					\
 	asm volatile("1:\t" insn "\n"				\
 		     "2:\n"					\
-		     "\t.section .fixup,\"ax\"\n"		\
-		     "3:\tmov\t%3, %1\n"			\
-		     "\tjmp\t2b\n"				\
-		     "\t.previous\n"				\
-		     _ASM_EXTABLE_UA(1b, 3b)			\
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %1) \
 		     : "=r" (oldval), "=r" (ret), "+m" (*uaddr)	\
-		     : "i" (-EFAULT), "0" (oparg), "1" (0));	\
+		     : "0" (oparg), "1" (0));	\
 	if (ret)						\
 		goto label;					\
 	*oval = oldval;						\
@@ -39,15 +35,11 @@ do {								\
 		     "3:\t" LOCK_PREFIX "cmpxchgl %3, %2\n"	\
 		     "\tjnz\t2b\n"				\
 		     "4:\n"					\
-		     "\t.section .fixup,\"ax\"\n"		\
-		     "5:\tmov\t%5, %1\n"			\
-		     "\tjmp\t4b\n"				\
-		     "\t.previous\n"				\
-		     _ASM_EXTABLE_UA(1b, 5b)			\
-		     _ASM_EXTABLE_UA(3b, 5b)			\
+		     _ASM_EXTABLE_TYPE_REG(1b, 4b, EX_TYPE_EFAULT_REG, %1) \
+		     _ASM_EXTABLE_TYPE_REG(3b, 4b, EX_TYPE_EFAULT_REG, %1) \
 		     : "=&a" (oldval), "=&r" (ret),		\
 		       "+m" (*uaddr), "=&r" (tem)		\
-		     : "r" (oparg), "i" (-EFAULT), "1" (0));	\
+		     : "r" (oparg), "1" (0));			\
 	if (ret)						\
 		goto label;					\
 	*oval = oldval;						\
@@ -95,15 +87,11 @@ static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	if (!user_access_begin(uaddr, sizeof(u32)))
 		return -EFAULT;
 	asm volatile("\n"
-		"1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n"
+		"1:\t" LOCK_PREFIX "cmpxchgl %3, %2\n"
 		"2:\n"
-		"\t.section .fixup, \"ax\"\n"
-		"3:\tmov     %3, %0\n"
-		"\tjmp     2b\n"
-		"\t.previous\n"
-		_ASM_EXTABLE_UA(1b, 3b)
+		_ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %0) \
 		: "+r" (ret), "=a" (oldval), "+m" (*uaddr)
-		: "i" (-EFAULT), "r" (newval), "1" (oldval)
+		: "r" (newval), "1" (oldval)
 		: "memory"
 	);
 	user_access_end();
diff --git a/arch/x86/include/asm/insn-eval.h b/arch/x86/include/asm/insn-eval.h
index 4ec3613551e3..3df123f437c9 100644
--- a/arch/x86/include/asm/insn-eval.h
+++ b/arch/x86/include/asm/insn-eval.h
@@ -15,6 +15,8 @@
 #define INSN_CODE_SEG_OPND_SZ(params) (params & 0xf)
 #define INSN_CODE_SEG_PARAMS(oper_sz, addr_sz) (oper_sz | (addr_sz << 4))
 
+int pt_regs_offset(struct pt_regs *regs, int regno);
+
 bool insn_has_rep_prefix(struct insn *insn);
 void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs);
 int insn_get_modrm_rm_off(struct insn *insn, struct pt_regs *regs);
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 9e50da3ed01a..23ea8a25cbbe 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -115,6 +115,7 @@ KVM_X86_OP(enable_smi_window)
 KVM_X86_OP_NULL(mem_enc_op)
 KVM_X86_OP_NULL(mem_enc_reg_region)
 KVM_X86_OP_NULL(mem_enc_unreg_region)
+KVM_X86_OP_NULL(guest_memory_reclaimed)
 KVM_X86_OP(get_msr_feature)
 KVM_X86_OP(can_emulate_instruction)
 KVM_X86_OP(apic_init_signal_blocked)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 49d814b2a341..9e800d4d323c 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -498,6 +498,7 @@ struct kvm_pmu {
 	unsigned nr_arch_fixed_counters;
 	unsigned available_event_types;
 	u64 fixed_ctr_ctrl;
+	u64 fixed_ctr_ctrl_mask;
 	u64 global_ctrl;
 	u64 global_status;
 	u64 global_ovf_ctrl;
@@ -642,6 +643,7 @@ struct kvm_vcpu_arch {
 	u64 ia32_misc_enable_msr;
 	u64 smbase;
 	u64 smi_count;
+	bool at_instruction_boundary;
 	bool tpr_access_reporting;
 	bool xsaves_enabled;
 	u64 ia32_xss;
@@ -1271,6 +1273,8 @@ struct kvm_vcpu_stat {
 	u64 nested_run;
 	u64 directed_yield_attempted;
 	u64 directed_yield_successful;
+	u64 preemption_reported;
+	u64 preemption_other;
 	u64 guest_mode;
 };
 
@@ -1472,6 +1476,7 @@ struct kvm_x86_ops {
 	int (*mem_enc_reg_region)(struct kvm *kvm, struct kvm_enc_region *argp);
 	int (*mem_enc_unreg_region)(struct kvm *kvm, struct kvm_enc_region *argp);
 	int (*vm_copy_enc_context_from)(struct kvm *kvm, unsigned int source_fd);
+	void (*guest_memory_reclaimed)(struct kvm *kvm);
 
 	int (*get_msr_feature)(struct kvm_msr_entry *entry);
 
@@ -1559,7 +1564,7 @@ static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm)
 		return -ENOTSUPP;
 }
 
-void kvm_mmu_x86_module_init(void);
+void __init kvm_mmu_x86_module_init(void);
 int kvm_mmu_vendor_module_init(void);
 void kvm_mmu_vendor_module_exit(void);
 
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index 030907922bd0..5000cf59bdf5 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -18,19 +18,27 @@
 #define __ALIGN_STR	__stringify(__ALIGN)
 #endif
 
+#if defined(CONFIG_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO)
+#define RET	jmp __x86_return_thunk
+#else /* CONFIG_RETPOLINE */
 #ifdef CONFIG_SLS
 #define RET	ret; int3
 #else
 #define RET	ret
 #endif
+#endif /* CONFIG_RETPOLINE */
 
 #else /* __ASSEMBLY__ */
 
+#if defined(CONFIG_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO)
+#define ASM_RET	"jmp __x86_return_thunk\n\t"
+#else /* CONFIG_RETPOLINE */
 #ifdef CONFIG_SLS
 #define ASM_RET	"ret; int3\n\t"
 #else
 #define ASM_RET	"ret\n\t"
 #endif
+#endif /* CONFIG_RETPOLINE */
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index adccbc209169..c2b9ab94408e 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -176,13 +176,6 @@ bool hv_vcpu_is_preempted(int vcpu);
 static inline void hv_apic_init(void) {}
 #endif
 
-static inline void hv_set_msi_entry_from_desc(union hv_msi_entry *msi_entry,
-					      struct msi_desc *msi_desc)
-{
-	msi_entry->address.as_uint32 = msi_desc->msg.address_lo;
-	msi_entry->data.as_uint32 = msi_desc->msg.data;
-}
-
 struct irq_domain *hv_create_pci_msi_domain(void);
 
 int hv_map_ioapic_interrupt(int ioapic_id, bool level, int vcpu, int vector,
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 7dc5a3306f37..8f38265bc81d 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -51,6 +51,8 @@
 #define SPEC_CTRL_STIBP			BIT(SPEC_CTRL_STIBP_SHIFT)	/* STIBP mask */
 #define SPEC_CTRL_SSBD_SHIFT		2	   /* Speculative Store Bypass Disable bit */
 #define SPEC_CTRL_SSBD			BIT(SPEC_CTRL_SSBD_SHIFT)	/* Speculative Store Bypass Disable */
+#define SPEC_CTRL_RRSBA_DIS_S_SHIFT	6	   /* Disable RRSBA behavior */
+#define SPEC_CTRL_RRSBA_DIS_S		BIT(SPEC_CTRL_RRSBA_DIS_S_SHIFT)
 
 #define MSR_IA32_PRED_CMD		0x00000049 /* Prediction Command */
 #define PRED_CMD_IBPB			BIT(0)	   /* Indirect Branch Prediction Barrier */
@@ -91,6 +93,7 @@
 #define MSR_IA32_ARCH_CAPABILITIES	0x0000010a
 #define ARCH_CAP_RDCL_NO		BIT(0)	/* Not susceptible to Meltdown */
 #define ARCH_CAP_IBRS_ALL		BIT(1)	/* Enhanced IBRS support */
+#define ARCH_CAP_RSBA			BIT(2)	/* RET may use alternative branch predictors */
 #define ARCH_CAP_SKIP_VMENTRY_L1DFLUSH	BIT(3)	/* Skip L1D flush on vmentry */
 #define ARCH_CAP_SSB_NO			BIT(4)	/*
 						 * Not susceptible to Speculative Store Bypass
@@ -138,6 +141,17 @@
 						 * bit available to control VERW
 						 * behavior.
 						 */
+#define ARCH_CAP_RRSBA			BIT(19)	/*
+						 * Indicates RET may use predictors
+						 * other than the RSB. With eIBRS
+						 * enabled predictions in kernel mode
+						 * are restricted to targets in
+						 * kernel.
+						 */
+#define ARCH_CAP_PBRSB_NO		BIT(24)	/*
+						 * Not susceptible to Post-Barrier
+						 * Return Stack Buffer Predictions.
+						 */
 
 #define MSR_IA32_FLUSH_CMD		0x0000010b
 #define L1D_FLUSH			BIT(0)	/*
@@ -514,6 +528,9 @@
 /* Fam 17h MSRs */
 #define MSR_F17H_IRPERF			0xc00000e9
 
+#define MSR_ZEN2_SPECTRAL_CHICKEN	0xc00110e3
+#define MSR_ZEN2_SPECTRAL_CHICKEN_BIT	BIT_ULL(1)
+
 /* Fam 16h MSRs */
 #define MSR_F16H_L2I_PERF_CTL		0xc0010230
 #define MSR_F16H_L2I_PERF_CTR		0xc0010231
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index a3f87f1015d3..d42e6c6b47b1 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -92,7 +92,7 @@ static __always_inline unsigned long long __rdmsr(unsigned int msr)
 
 	asm volatile("1: rdmsr\n"
 		     "2:\n"
-		     _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_rdmsr_unsafe)
+		     _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_RDMSR)
 		     : EAX_EDX_RET(val, low, high) : "c" (msr));
 
 	return EAX_EDX_VAL(val, low, high);
@@ -102,7 +102,7 @@ static __always_inline void __wrmsr(unsigned int msr, u32 low, u32 high)
 {
 	asm volatile("1: wrmsr\n"
 		     "2:\n"
-		     _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_wrmsr_unsafe)
+		     _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR)
 		     : : "c" (msr), "a"(low), "d" (high) : "memory");
 }
 
@@ -137,17 +137,11 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr,
 {
 	DECLARE_ARGS(val, low, high);
 
-	asm volatile("2: rdmsr ; xor %[err],%[err]\n"
-		     "1:\n\t"
-		     ".section .fixup,\"ax\"\n\t"
-		     "3: mov %[fault],%[err]\n\t"
-		     "xorl %%eax, %%eax\n\t"
-		     "xorl %%edx, %%edx\n\t"
-		     "jmp 1b\n\t"
-		     ".previous\n\t"
-		     _ASM_EXTABLE(2b, 3b)
+	asm volatile("1: rdmsr ; xor %[err],%[err]\n"
+		     "2:\n\t"
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_RDMSR_SAFE, %[err])
 		     : [err] "=r" (*err), EAX_EDX_RET(val, low, high)
-		     : "c" (msr), [fault] "i" (-EIO));
+		     : "c" (msr));
 	if (tracepoint_enabled(read_msr))
 		do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), *err);
 	return EAX_EDX_VAL(val, low, high);
@@ -169,15 +163,11 @@ native_write_msr_safe(unsigned int msr, u32 low, u32 high)
 {
 	int err;
 
-	asm volatile("2: wrmsr ; xor %[err],%[err]\n"
-		     "1:\n\t"
-		     ".section .fixup,\"ax\"\n\t"
-		     "3:  mov %[fault],%[err] ; jmp 1b\n\t"
-		     ".previous\n\t"
-		     _ASM_EXTABLE(2b, 3b)
+	asm volatile("1: wrmsr ; xor %[err],%[err]\n"
+		     "2:\n\t"
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_WRMSR_SAFE, %[err])
 		     : [err] "=a" (err)
-		     : "c" (msr), "0" (low), "d" (high),
-		       [fault] "i" (-EIO)
+		     : "c" (msr), "0" (low), "d" (high)
 		     : "memory");
 	if (tracepoint_enabled(write_msr))
 		do_trace_write_msr(msr, ((u64)high << 32 | low), err);
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 9783c6b08886..f5ce9a0ab233 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -5,11 +5,15 @@
 
 #include <linux/static_key.h>
 #include <linux/objtool.h>
+#include <linux/linkage.h>
 
 #include <asm/alternative.h>
 #include <asm/cpufeatures.h>
 #include <asm/msr-index.h>
 #include <asm/unwind_hints.h>
+#include <asm/percpu.h>
+
+#define RETPOLINE_THUNK_SIZE	32
 
 /*
  * Fill the CPU return stack buffer.
@@ -31,32 +35,57 @@
 #define RSB_CLEAR_LOOPS		32	/* To forcibly overwrite all entries */
 
 /*
+ * Common helper for __FILL_RETURN_BUFFER and __FILL_ONE_RETURN.
+ */
+#define __FILL_RETURN_SLOT			\
+	ANNOTATE_INTRA_FUNCTION_CALL;		\
+	call	772f;				\
+	int3;					\
+772:
+
+/*
+ * Stuff the entire RSB.
+ *
  * Google experimented with loop-unrolling and this turned out to be
  * the optimal version - two calls, each with their own speculation
  * trap should their return address end up getting used, in a loop.
  */
-#define __FILL_RETURN_BUFFER(reg, nr, sp)	\
-	mov	$(nr/2), reg;			\
-771:						\
-	ANNOTATE_INTRA_FUNCTION_CALL;		\
-	call	772f;				\
-773:	/* speculation trap */			\
-	UNWIND_HINT_EMPTY;			\
-	pause;					\
-	lfence;					\
-	jmp	773b;				\
-772:						\
-	ANNOTATE_INTRA_FUNCTION_CALL;		\
-	call	774f;				\
-775:	/* speculation trap */			\
-	UNWIND_HINT_EMPTY;			\
-	pause;					\
-	lfence;					\
-	jmp	775b;				\
-774:						\
-	add	$(BITS_PER_LONG/8) * 2, sp;	\
-	dec	reg;				\
-	jnz	771b;
+#ifdef CONFIG_X86_64
+#define __FILL_RETURN_BUFFER(reg, nr)			\
+	mov	$(nr/2), reg;				\
+771:							\
+	__FILL_RETURN_SLOT				\
+	__FILL_RETURN_SLOT				\
+	add	$(BITS_PER_LONG/8) * 2, %_ASM_SP;	\
+	dec	reg;					\
+	jnz	771b;					\
+	/* barrier for jnz misprediction */		\
+	lfence;
+#else
+/*
+ * i386 doesn't unconditionally have LFENCE, as such it can't
+ * do a loop.
+ */
+#define __FILL_RETURN_BUFFER(reg, nr)			\
+	.rept nr;					\
+	__FILL_RETURN_SLOT;				\
+	.endr;						\
+	add	$(BITS_PER_LONG/8) * nr, %_ASM_SP;
+#endif
+
+/*
+ * Stuff a single RSB slot.
+ *
+ * To mitigate Post-Barrier RSB speculation, one CALL instruction must be
+ * forced to retire before letting a RET instruction execute.
+ *
+ * On PBRSB-vulnerable CPUs, it is not safe for a RET to be executed
+ * before this point.
+ */
+#define __FILL_ONE_RETURN				\
+	__FILL_RETURN_SLOT				\
+	add	$(BITS_PER_LONG/8), %_ASM_SP;		\
+	lfence;
 
 #ifdef __ASSEMBLY__
 
@@ -73,6 +102,23 @@
 .endm
 
 /*
+ * (ab)use RETPOLINE_SAFE on RET to annotate away 'bare' RET instructions
+ * vs RETBleed validation.
+ */
+#define ANNOTATE_UNRET_SAFE ANNOTATE_RETPOLINE_SAFE
+
+/*
+ * Abuse ANNOTATE_RETPOLINE_SAFE on a NOP to indicate UNRET_END, should
+ * eventually turn into it's own annotation.
+ */
+.macro ANNOTATE_UNRET_END
+#ifdef CONFIG_DEBUG_ENTRY
+	ANNOTATE_RETPOLINE_SAFE
+	nop
+#endif
+.endm
+
+/*
  * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple
  * indirect jmp/call which may be susceptible to the Spectre variant 2
  * attack.
@@ -101,11 +147,37 @@
   * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP
   * monstrosity above, manually.
   */
-.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req
-#ifdef CONFIG_RETPOLINE
-	ALTERNATIVE "jmp .Lskip_rsb_\@", "", \ftr
-	__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP)
+.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req ftr2=ALT_NOT(X86_FEATURE_ALWAYS)
+	ALTERNATIVE_2 "jmp .Lskip_rsb_\@", \
+		__stringify(__FILL_RETURN_BUFFER(\reg,\nr)), \ftr, \
+		__stringify(__FILL_ONE_RETURN), \ftr2
+
 .Lskip_rsb_\@:
+.endm
+
+#ifdef CONFIG_CPU_UNRET_ENTRY
+#define CALL_ZEN_UNTRAIN_RET	"call zen_untrain_ret"
+#else
+#define CALL_ZEN_UNTRAIN_RET	""
+#endif
+
+/*
+ * Mitigate RETBleed for AMD/Hygon Zen uarch. Requires KERNEL CR3 because the
+ * return thunk isn't mapped into the userspace tables (then again, AMD
+ * typically has NO_MELTDOWN).
+ *
+ * While zen_untrain_ret() doesn't clobber anything but requires stack,
+ * entry_ibpb() will clobber AX, CX, DX.
+ *
+ * As such, this must be placed after every *SWITCH_TO_KERNEL_CR3 at a point
+ * where we have a stack but before any RET instruction.
+ */
+.macro UNTRAIN_RET
+#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY)
+	ANNOTATE_UNRET_END
+	ALTERNATIVE_2 "",						\
+	              CALL_ZEN_UNTRAIN_RET, X86_FEATURE_UNRET,		\
+		      "call entry_ibpb", X86_FEATURE_ENTRY_IBPB
 #endif
 .endm
 
@@ -117,7 +189,21 @@
 	_ASM_PTR " 999b\n\t"					\
 	".popsection\n\t"
 
+extern void __x86_return_thunk(void);
+extern void zen_untrain_ret(void);
+extern void entry_ibpb(void);
+
 #ifdef CONFIG_RETPOLINE
+
+typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE];
+
+#define GEN(reg) \
+	extern retpoline_thunk_t __x86_indirect_thunk_ ## reg;
+#include <asm/GEN-for-each-reg.h>
+#undef GEN
+
+extern retpoline_thunk_t __x86_indirect_thunk_array[];
+
 #ifdef CONFIG_X86_64
 
 /*
@@ -180,6 +266,7 @@ enum spectre_v2_mitigation {
 	SPECTRE_V2_EIBRS,
 	SPECTRE_V2_EIBRS_RETPOLINE,
 	SPECTRE_V2_EIBRS_LFENCE,
+	SPECTRE_V2_IBRS,
 };
 
 /* The indirect branch speculation control variants */
@@ -222,6 +309,9 @@ static inline void indirect_branch_prediction_barrier(void)
 
 /* The Intel SPEC CTRL MSR base value cache */
 extern u64 x86_spec_ctrl_base;
+DECLARE_PER_CPU(u64, x86_spec_ctrl_current);
+extern void write_spec_ctrl_current(u64 val, bool force);
+extern u64 spec_ctrl_current(void);
 
 /*
  * With retpoline, we must use IBRS to restrict branch prediction
@@ -231,18 +321,18 @@ extern u64 x86_spec_ctrl_base;
  */
 #define firmware_restrict_branch_speculation_start()			\
 do {									\
-	u64 val = x86_spec_ctrl_base | SPEC_CTRL_IBRS;			\
-									\
 	preempt_disable();						\
-	alternative_msr_write(MSR_IA32_SPEC_CTRL, val,			\
+	alternative_msr_write(MSR_IA32_SPEC_CTRL,			\
+			      spec_ctrl_current() | SPEC_CTRL_IBRS,	\
 			      X86_FEATURE_USE_IBRS_FW);			\
+	alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB,		\
+			      X86_FEATURE_USE_IBPB_FW);			\
 } while (0)
 
 #define firmware_restrict_branch_speculation_end()			\
 do {									\
-	u64 val = x86_spec_ctrl_base;					\
-									\
-	alternative_msr_write(MSR_IA32_SPEC_CTRL, val,			\
+	alternative_msr_write(MSR_IA32_SPEC_CTRL,			\
+			      spec_ctrl_current(),			\
 			      X86_FEATURE_USE_IBRS_FW);			\
 	preempt_enable();						\
 } while (0)
@@ -307,63 +397,4 @@ static inline void mds_idle_clear_cpu_buffers(void)
 
 #endif /* __ASSEMBLY__ */
 
-/*
- * Below is used in the eBPF JIT compiler and emits the byte sequence
- * for the following assembly:
- *
- * With retpolines configured:
- *
- *    callq do_rop
- *  spec_trap:
- *    pause
- *    lfence
- *    jmp spec_trap
- *  do_rop:
- *    mov %rcx,(%rsp) for x86_64
- *    mov %edx,(%esp) for x86_32
- *    retq
- *
- * Without retpolines configured:
- *
- *    jmp *%rcx for x86_64
- *    jmp *%edx for x86_32
- */
-#ifdef CONFIG_RETPOLINE
-# ifdef CONFIG_X86_64
-#  define RETPOLINE_RCX_BPF_JIT_SIZE	17
-#  define RETPOLINE_RCX_BPF_JIT()				\
-do {								\
-	EMIT1_off32(0xE8, 7);	 /* callq do_rop */		\
-	/* spec_trap: */					\
-	EMIT2(0xF3, 0x90);       /* pause */			\
-	EMIT3(0x0F, 0xAE, 0xE8); /* lfence */			\
-	EMIT2(0xEB, 0xF9);       /* jmp spec_trap */		\
-	/* do_rop: */						\
-	EMIT4(0x48, 0x89, 0x0C, 0x24); /* mov %rcx,(%rsp) */	\
-	EMIT1(0xC3);             /* retq */			\
-} while (0)
-# else /* !CONFIG_X86_64 */
-#  define RETPOLINE_EDX_BPF_JIT()				\
-do {								\
-	EMIT1_off32(0xE8, 7);	 /* call do_rop */		\
-	/* spec_trap: */					\
-	EMIT2(0xF3, 0x90);       /* pause */			\
-	EMIT3(0x0F, 0xAE, 0xE8); /* lfence */			\
-	EMIT2(0xEB, 0xF9);       /* jmp spec_trap */		\
-	/* do_rop: */						\
-	EMIT3(0x89, 0x14, 0x24); /* mov %edx,(%esp) */		\
-	EMIT1(0xC3);             /* ret */			\
-} while (0)
-# endif
-#else /* !CONFIG_RETPOLINE */
-# ifdef CONFIG_X86_64
-#  define RETPOLINE_RCX_BPF_JIT_SIZE	2
-#  define RETPOLINE_RCX_BPF_JIT()				\
-	EMIT2(0xFF, 0xE1);       /* jmp *%rcx */
-# else /* !CONFIG_X86_64 */
-#  define RETPOLINE_EDX_BPF_JIT()				\
-	EMIT2(0xFF, 0xE2)        /* jmp *%edx */
-# endif
-#endif
-
 #endif /* _ASM_X86_NOSPEC_BRANCH_H_ */
diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
index 4bde0dc66100..56891399fa2a 100644
--- a/arch/x86/include/asm/page_64.h
+++ b/arch/x86/include/asm/page_64.h
@@ -15,7 +15,7 @@ extern unsigned long page_offset_base;
 extern unsigned long vmalloc_base;
 extern unsigned long vmemmap_base;
 
-static inline unsigned long __phys_addr_nodebug(unsigned long x)
+static __always_inline unsigned long __phys_addr_nodebug(unsigned long x)
 {
 	unsigned long y = x - __START_KERNEL_map;
 
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index 72044026eb3c..8dd8e8ec9fa5 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -339,7 +339,7 @@ static inline void __loadsegment_fs(unsigned short value)
 		     "1:	movw %0, %%fs			\n"
 		     "2:					\n"
 
-		     _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_clear_fs)
+		     _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_CLEAR_FS)
 
 		     : : "rm" (value) : "memory");
 }
diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h
index 343234569392..491aadfac611 100644
--- a/arch/x86/include/asm/static_call.h
+++ b/arch/x86/include/asm/static_call.h
@@ -21,6 +21,16 @@
  * relative displacement across sections.
  */
 
+/*
+ * The trampoline is 8 bytes and of the general form:
+ *
+ *   jmp.d32 \func
+ *   ud1 %esp, %ecx
+ *
+ * That trailing #UD provides both a speculation stop and serves as a unique
+ * 3 byte signature identifying static call trampolines. Also see tramp_ud[]
+ * and __static_call_fixup().
+ */
 #define __ARCH_DEFINE_STATIC_CALL_TRAMP(name, insns)			\
 	asm(".pushsection .static_call.text, \"ax\"		\n"	\
 	    ".align 4						\n"	\
@@ -34,8 +44,13 @@
 #define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func)			\
 	__ARCH_DEFINE_STATIC_CALL_TRAMP(name, ".byte 0xe9; .long " #func " - (. + 4)")
 
+#ifdef CONFIG_RETHUNK
+#define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)			\
+	__ARCH_DEFINE_STATIC_CALL_TRAMP(name, "jmp __x86_return_thunk")
+#else
 #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)			\
 	__ARCH_DEFINE_STATIC_CALL_TRAMP(name, "ret; int3; nop; nop; nop")
+#endif
 
 
 #define ARCH_ADD_TRAMP_KEY(name)					\
@@ -44,4 +59,6 @@
 	    ".long " STATIC_CALL_KEY_STR(name) " - .		\n"	\
 	    ".popsection					\n")
 
+extern bool __static_call_fixup(void *tramp, u8 op, void *dest);
+
 #endif /* _ASM_STATIC_CALL_H */
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 6221be7cafc3..1cdd7e8bcba7 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -13,7 +13,7 @@
 #ifdef CONFIG_X86_64
 asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs);
 asmlinkage __visible notrace
-struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s);
+struct pt_regs *fixup_bad_iret(struct pt_regs *bad_regs);
 void __init trap_init(void);
 asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *eregs);
 #endif
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index bb1430283c72..ab5e57737309 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -414,6 +414,103 @@ do {									\
 
 #endif // CONFIG_CC_ASM_GOTO_OUTPUT
 
+#ifdef CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT
+#define __try_cmpxchg_user_asm(itype, ltype, _ptr, _pold, _new, label)	({ \
+	bool success;							\
+	__typeof__(_ptr) _old = (__typeof__(_ptr))(_pold);		\
+	__typeof__(*(_ptr)) __old = *_old;				\
+	__typeof__(*(_ptr)) __new = (_new);				\
+	asm_volatile_goto("\n"						\
+		     "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\
+		     _ASM_EXTABLE_UA(1b, %l[label])			\
+		     : CC_OUT(z) (success),				\
+		       [ptr] "+m" (*_ptr),				\
+		       [old] "+a" (__old)				\
+		     : [new] ltype (__new)				\
+		     : "memory"						\
+		     : label);						\
+	if (unlikely(!success))						\
+		*_old = __old;						\
+	likely(success);					})
+
+#ifdef CONFIG_X86_32
+#define __try_cmpxchg64_user_asm(_ptr, _pold, _new, label)	({	\
+	bool success;							\
+	__typeof__(_ptr) _old = (__typeof__(_ptr))(_pold);		\
+	__typeof__(*(_ptr)) __old = *_old;				\
+	__typeof__(*(_ptr)) __new = (_new);				\
+	asm_volatile_goto("\n"						\
+		     "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n"		\
+		     _ASM_EXTABLE_UA(1b, %l[label])			\
+		     : CC_OUT(z) (success),				\
+		       "+A" (__old),					\
+		       [ptr] "+m" (*_ptr)				\
+		     : "b" ((u32)__new),				\
+		       "c" ((u32)((u64)__new >> 32))			\
+		     : "memory"						\
+		     : label);						\
+	if (unlikely(!success))						\
+		*_old = __old;						\
+	likely(success);					})
+#endif // CONFIG_X86_32
+#else  // !CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT
+#define __try_cmpxchg_user_asm(itype, ltype, _ptr, _pold, _new, label)	({ \
+	int __err = 0;							\
+	bool success;							\
+	__typeof__(_ptr) _old = (__typeof__(_ptr))(_pold);		\
+	__typeof__(*(_ptr)) __old = *_old;				\
+	__typeof__(*(_ptr)) __new = (_new);				\
+	asm volatile("\n"						\
+		     "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\
+		     CC_SET(z)						\
+		     "2:\n"						\
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG,	\
+					   %[errout])			\
+		     : CC_OUT(z) (success),				\
+		       [errout] "+r" (__err),				\
+		       [ptr] "+m" (*_ptr),				\
+		       [old] "+a" (__old)				\
+		     : [new] ltype (__new)				\
+		     : "memory");					\
+	if (unlikely(__err))						\
+		goto label;						\
+	if (unlikely(!success))						\
+		*_old = __old;						\
+	likely(success);					})
+
+#ifdef CONFIG_X86_32
+/*
+ * Unlike the normal CMPXCHG, hardcode ECX for both success/fail and error.
+ * There are only six GPRs available and four (EAX, EBX, ECX, and EDX) are
+ * hardcoded by CMPXCHG8B, leaving only ESI and EDI.  If the compiler uses
+ * both ESI and EDI for the memory operand, compilation will fail if the error
+ * is an input+output as there will be no register available for input.
+ */
+#define __try_cmpxchg64_user_asm(_ptr, _pold, _new, label)	({	\
+	int __result;							\
+	__typeof__(_ptr) _old = (__typeof__(_ptr))(_pold);		\
+	__typeof__(*(_ptr)) __old = *_old;				\
+	__typeof__(*(_ptr)) __new = (_new);				\
+	asm volatile("\n"						\
+		     "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n"		\
+		     "mov $0, %%ecx\n\t"				\
+		     "setz %%cl\n"					\
+		     "2:\n"						\
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %%ecx) \
+		     : [result]"=c" (__result),				\
+		       "+A" (__old),					\
+		       [ptr] "+m" (*_ptr)				\
+		     : "b" ((u32)__new),				\
+		       "c" ((u32)((u64)__new >> 32))			\
+		     : "memory", "cc");					\
+	if (unlikely(__result < 0))					\
+		goto label;						\
+	if (unlikely(!__result))					\
+		*_old = __old;						\
+	likely(__result);					})
+#endif // CONFIG_X86_32
+#endif // CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT
+
 /* FIXME: this hack is definitely wrong -AK */
 struct __large_struct { unsigned long buf[100]; };
 #define __m(x) (*(struct __large_struct __user *)(x))
@@ -506,6 +603,51 @@ do {										\
 } while (0)
 #endif // CONFIG_CC_HAS_ASM_GOTO_OUTPUT
 
+extern void __try_cmpxchg_user_wrong_size(void);
+
+#ifndef CONFIG_X86_32
+#define __try_cmpxchg64_user_asm(_ptr, _oldp, _nval, _label)		\
+	__try_cmpxchg_user_asm("q", "r", (_ptr), (_oldp), (_nval), _label)
+#endif
+
+/*
+ * Force the pointer to u<size> to match the size expected by the asm helper.
+ * clang/LLVM compiles all cases and only discards the unused paths after
+ * processing errors, which breaks i386 if the pointer is an 8-byte value.
+ */
+#define unsafe_try_cmpxchg_user(_ptr, _oldp, _nval, _label) ({			\
+	bool __ret;								\
+	__chk_user_ptr(_ptr);							\
+	switch (sizeof(*(_ptr))) {						\
+	case 1:	__ret = __try_cmpxchg_user_asm("b", "q",			\
+					       (__force u8 *)(_ptr), (_oldp),	\
+					       (_nval), _label);		\
+		break;								\
+	case 2:	__ret = __try_cmpxchg_user_asm("w", "r",			\
+					       (__force u16 *)(_ptr), (_oldp),	\
+					       (_nval), _label);		\
+		break;								\
+	case 4:	__ret = __try_cmpxchg_user_asm("l", "r",			\
+					       (__force u32 *)(_ptr), (_oldp),	\
+					       (_nval), _label);		\
+		break;								\
+	case 8:	__ret = __try_cmpxchg64_user_asm((__force u64 *)(_ptr), (_oldp),\
+						 (_nval), _label);		\
+		break;								\
+	default: __try_cmpxchg_user_wrong_size();				\
+	}									\
+	__ret;						})
+
+/* "Returns" 0 on success, 1 on failure, -EFAULT if the access faults. */
+#define __try_cmpxchg_user(_ptr, _oldp, _nval, _label)	({		\
+	int __ret = -EFAULT;						\
+	__uaccess_begin_nospec();					\
+	__ret = !unsafe_try_cmpxchg_user(_ptr, _oldp, _nval, _label);	\
+_label:									\
+	__uaccess_end();						\
+	__ret;								\
+							})
+
 /*
  * We want the unsafe accessors to always be inlined and use
  * the error labels - thus the macro games.
diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h
index 8e574c0afef8..56664b31b6da 100644
--- a/arch/x86/include/asm/unwind_hints.h
+++ b/arch/x86/include/asm/unwind_hints.h
@@ -8,7 +8,11 @@
 #ifdef __ASSEMBLY__
 
 .macro UNWIND_HINT_EMPTY
-	UNWIND_HINT sp_reg=ORC_REG_UNDEFINED type=UNWIND_HINT_TYPE_CALL end=1
+	UNWIND_HINT type=UNWIND_HINT_TYPE_CALL end=1
+.endm
+
+.macro UNWIND_HINT_ENTRY
+	UNWIND_HINT type=UNWIND_HINT_TYPE_ENTRY end=1
 .endm
 
 .macro UNWIND_HINT_REGS base=%rsp offset=0 indirect=0 extra=1 partial=0
@@ -52,6 +56,14 @@
 	UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=8 type=UNWIND_HINT_TYPE_FUNC
 .endm
 
+.macro UNWIND_HINT_SAVE
+	UNWIND_HINT type=UNWIND_HINT_TYPE_SAVE
+.endm
+
+.macro UNWIND_HINT_RESTORE
+	UNWIND_HINT type=UNWIND_HINT_TYPE_RESTORE
+.endm
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_X86_UNWIND_HINTS_H */
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index ae0f718b8ebb..98a8b59f87f3 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -29,6 +29,7 @@
 #include <asm/io.h>
 #include <asm/fixmap.h>
 #include <asm/paravirt.h>
+#include <asm/asm-prototypes.h>
 
 int __read_mostly alternatives_patched;
 
@@ -113,6 +114,8 @@ static void __init_or_module add_nops(void *insns, unsigned int len)
 	}
 }
 
+extern s32 __retpoline_sites[], __retpoline_sites_end[];
+extern s32 __return_sites[], __return_sites_end[];
 extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
 extern s32 __smp_locks[], __smp_locks_end[];
 void text_poke_early(void *addr, const void *opcode, size_t len);
@@ -221,7 +224,7 @@ static __always_inline int optimize_nops_range(u8 *instr, u8 instrlen, int off)
  * "noinline" to cause control flow change and thus invalidate I$ and
  * cause refetch after modification.
  */
-static void __init_or_module noinline optimize_nops(struct alt_instr *a, u8 *instr)
+static void __init_or_module noinline optimize_nops(u8 *instr, size_t len)
 {
 	struct insn insn;
 	int i = 0;
@@ -239,11 +242,11 @@ static void __init_or_module noinline optimize_nops(struct alt_instr *a, u8 *ins
 		 * optimized.
 		 */
 		if (insn.length == 1 && insn.opcode.bytes[0] == 0x90)
-			i += optimize_nops_range(instr, a->instrlen, i);
+			i += optimize_nops_range(instr, len, i);
 		else
 			i += insn.length;
 
-		if (i >= a->instrlen)
+		if (i >= len)
 			return;
 	}
 }
@@ -331,10 +334,254 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 		text_poke_early(instr, insn_buff, insn_buff_sz);
 
 next:
-		optimize_nops(a, instr);
+		optimize_nops(instr, a->instrlen);
 	}
 }
 
+#if defined(CONFIG_RETPOLINE) && defined(CONFIG_STACK_VALIDATION)
+
+/*
+ * CALL/JMP *%\reg
+ */
+static int emit_indirect(int op, int reg, u8 *bytes)
+{
+	int i = 0;
+	u8 modrm;
+
+	switch (op) {
+	case CALL_INSN_OPCODE:
+		modrm = 0x10; /* Reg = 2; CALL r/m */
+		break;
+
+	case JMP32_INSN_OPCODE:
+		modrm = 0x20; /* Reg = 4; JMP r/m */
+		break;
+
+	default:
+		WARN_ON_ONCE(1);
+		return -1;
+	}
+
+	if (reg >= 8) {
+		bytes[i++] = 0x41; /* REX.B prefix */
+		reg -= 8;
+	}
+
+	modrm |= 0xc0; /* Mod = 3 */
+	modrm += reg;
+
+	bytes[i++] = 0xff; /* opcode */
+	bytes[i++] = modrm;
+
+	return i;
+}
+
+/*
+ * Rewrite the compiler generated retpoline thunk calls.
+ *
+ * For spectre_v2=off (!X86_FEATURE_RETPOLINE), rewrite them into immediate
+ * indirect instructions, avoiding the extra indirection.
+ *
+ * For example, convert:
+ *
+ *   CALL __x86_indirect_thunk_\reg
+ *
+ * into:
+ *
+ *   CALL *%\reg
+ *
+ * It also tries to inline spectre_v2=retpoline,amd when size permits.
+ */
+static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
+{
+	retpoline_thunk_t *target;
+	int reg, ret, i = 0;
+	u8 op, cc;
+
+	target = addr + insn->length + insn->immediate.value;
+	reg = target - __x86_indirect_thunk_array;
+
+	if (WARN_ON_ONCE(reg & ~0xf))
+		return -1;
+
+	/* If anyone ever does: CALL/JMP *%rsp, we're in deep trouble. */
+	BUG_ON(reg == 4);
+
+	if (cpu_feature_enabled(X86_FEATURE_RETPOLINE) &&
+	    !cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE))
+		return -1;
+
+	op = insn->opcode.bytes[0];
+
+	/*
+	 * Convert:
+	 *
+	 *   Jcc.d32 __x86_indirect_thunk_\reg
+	 *
+	 * into:
+	 *
+	 *   Jncc.d8 1f
+	 *   [ LFENCE ]
+	 *   JMP *%\reg
+	 *   [ NOP ]
+	 * 1:
+	 */
+	/* Jcc.d32 second opcode byte is in the range: 0x80-0x8f */
+	if (op == 0x0f && (insn->opcode.bytes[1] & 0xf0) == 0x80) {
+		cc = insn->opcode.bytes[1] & 0xf;
+		cc ^= 1; /* invert condition */
+
+		bytes[i++] = 0x70 + cc;        /* Jcc.d8 */
+		bytes[i++] = insn->length - 2; /* sizeof(Jcc.d8) == 2 */
+
+		/* Continue as if: JMP.d32 __x86_indirect_thunk_\reg */
+		op = JMP32_INSN_OPCODE;
+	}
+
+	/*
+	 * For RETPOLINE_AMD: prepend the indirect CALL/JMP with an LFENCE.
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) {
+		bytes[i++] = 0x0f;
+		bytes[i++] = 0xae;
+		bytes[i++] = 0xe8; /* LFENCE */
+	}
+
+	ret = emit_indirect(op, reg, bytes + i);
+	if (ret < 0)
+		return ret;
+	i += ret;
+
+	for (; i < insn->length;)
+		bytes[i++] = BYTES_NOP1;
+
+	return i;
+}
+
+/*
+ * Generated by 'objtool --retpoline'.
+ */
+void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
+{
+	s32 *s;
+
+	for (s = start; s < end; s++) {
+		void *addr = (void *)s + *s;
+		struct insn insn;
+		int len, ret;
+		u8 bytes[16];
+		u8 op1, op2;
+
+		ret = insn_decode_kernel(&insn, addr);
+		if (WARN_ON_ONCE(ret < 0))
+			continue;
+
+		op1 = insn.opcode.bytes[0];
+		op2 = insn.opcode.bytes[1];
+
+		switch (op1) {
+		case CALL_INSN_OPCODE:
+		case JMP32_INSN_OPCODE:
+			break;
+
+		case 0x0f: /* escape */
+			if (op2 >= 0x80 && op2 <= 0x8f)
+				break;
+			fallthrough;
+		default:
+			WARN_ON_ONCE(1);
+			continue;
+		}
+
+		DPRINTK("retpoline at: %pS (%px) len: %d to: %pS",
+			addr, addr, insn.length,
+			addr + insn.length + insn.immediate.value);
+
+		len = patch_retpoline(addr, &insn, bytes);
+		if (len == insn.length) {
+			optimize_nops(bytes, len);
+			DUMP_BYTES(((u8*)addr),  len, "%px: orig: ", addr);
+			DUMP_BYTES(((u8*)bytes), len, "%px: repl: ", addr);
+			text_poke_early(addr, bytes, len);
+		}
+	}
+}
+
+#ifdef CONFIG_RETHUNK
+/*
+ * Rewrite the compiler generated return thunk tail-calls.
+ *
+ * For example, convert:
+ *
+ *   JMP __x86_return_thunk
+ *
+ * into:
+ *
+ *   RET
+ */
+static int patch_return(void *addr, struct insn *insn, u8 *bytes)
+{
+	int i = 0;
+
+	if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+		return -1;
+
+	bytes[i++] = RET_INSN_OPCODE;
+
+	for (; i < insn->length;)
+		bytes[i++] = INT3_INSN_OPCODE;
+
+	return i;
+}
+
+void __init_or_module noinline apply_returns(s32 *start, s32 *end)
+{
+	s32 *s;
+
+	for (s = start; s < end; s++) {
+		void *dest = NULL, *addr = (void *)s + *s;
+		struct insn insn;
+		int len, ret;
+		u8 bytes[16];
+		u8 op;
+
+		ret = insn_decode_kernel(&insn, addr);
+		if (WARN_ON_ONCE(ret < 0))
+			continue;
+
+		op = insn.opcode.bytes[0];
+		if (op == JMP32_INSN_OPCODE)
+			dest = addr + insn.length + insn.immediate.value;
+
+		if (__static_call_fixup(addr, op, dest) ||
+		    WARN_ONCE(dest != &__x86_return_thunk,
+			      "missing return thunk: %pS-%pS: %*ph",
+			      addr, dest, 5, addr))
+			continue;
+
+		DPRINTK("return thunk at: %pS (%px) len: %d to: %pS",
+			addr, addr, insn.length,
+			addr + insn.length + insn.immediate.value);
+
+		len = patch_return(addr, &insn, bytes);
+		if (len == insn.length) {
+			DUMP_BYTES(((u8*)addr),  len, "%px: orig: ", addr);
+			DUMP_BYTES(((u8*)bytes), len, "%px: repl: ", addr);
+			text_poke_early(addr, bytes, len);
+		}
+	}
+}
+#else
+void __init_or_module noinline apply_returns(s32 *start, s32 *end) { }
+#endif /* CONFIG_RETHUNK */
+
+#else /* !RETPOLINES || !CONFIG_STACK_VALIDATION */
+
+void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) { }
+void __init_or_module noinline apply_returns(s32 *start, s32 *end) { }
+
+#endif /* CONFIG_RETPOLINE && CONFIG_STACK_VALIDATION */
+
 #ifdef CONFIG_SMP
 static void alternatives_smp_lock(const s32 *start, const s32 *end,
 				  u8 *text, u8 *text_end)
@@ -643,6 +890,13 @@ void __init alternative_instructions(void)
 	apply_paravirt(__parainstructions, __parainstructions_end);
 
 	/*
+	 * Rewrite the retpolines, must be done before alternatives since
+	 * those can rewrite the retpoline thunks.
+	 */
+	apply_retpolines(__retpoline_sites, __retpoline_sites_end);
+	apply_returns(__return_sites, __return_sites_end);
+
+	/*
 	 * Then patch alternatives, such that those paravirt calls that are in
 	 * alternatives can be overwritten by their immediate fragments.
 	 */
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 4edb6f0f628c..8b1bf1c14fc3 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -886,6 +886,28 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
 	clear_rdrand_cpuid_bit(c);
 }
 
+void init_spectral_chicken(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_CPU_UNRET_ENTRY
+	u64 value;
+
+	/*
+	 * On Zen2 we offer this chicken (bit) on the altar of Speculation.
+	 *
+	 * This suppresses speculation from the middle of a basic block, i.e. it
+	 * suppresses non-branch predictions.
+	 *
+	 * We use STIBP as a heuristic to filter out Zen2 from the rest of F17H
+	 */
+	if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && cpu_has(c, X86_FEATURE_AMD_STIBP)) {
+		if (!rdmsrl_safe(MSR_ZEN2_SPECTRAL_CHICKEN, &value)) {
+			value |= MSR_ZEN2_SPECTRAL_CHICKEN_BIT;
+			wrmsrl_safe(MSR_ZEN2_SPECTRAL_CHICKEN, value);
+		}
+	}
+#endif
+}
+
 static void init_amd_zn(struct cpuinfo_x86 *c)
 {
 	set_cpu_cap(c, X86_FEATURE_ZEN);
@@ -894,12 +916,21 @@ static void init_amd_zn(struct cpuinfo_x86 *c)
 	node_reclaim_distance = 32;
 #endif
 
-	/*
-	 * Fix erratum 1076: CPB feature bit not being set in CPUID.
-	 * Always set it, except when running under a hypervisor.
-	 */
-	if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && !cpu_has(c, X86_FEATURE_CPB))
-		set_cpu_cap(c, X86_FEATURE_CPB);
+	/* Fix up CPUID bits, but only if not virtualised. */
+	if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) {
+
+		/* Erratum 1076: CPB feature bit not being set in CPUID. */
+		if (!cpu_has(c, X86_FEATURE_CPB))
+			set_cpu_cap(c, X86_FEATURE_CPB);
+
+		/*
+		 * Zen3 (Fam19 model < 0x10) parts are not susceptible to
+		 * Branch Type Confusion, but predate the allocation of the
+		 * BTC_NO bit.
+		 */
+		if (c->x86 == 0x19 && !cpu_has(c, X86_FEATURE_BTC_NO))
+			set_cpu_cap(c, X86_FEATURE_BTC_NO);
+	}
 }
 
 static void init_amd(struct cpuinfo_x86 *c)
@@ -931,7 +962,8 @@ static void init_amd(struct cpuinfo_x86 *c)
 	case 0x12: init_amd_ln(c); break;
 	case 0x15: init_amd_bd(c); break;
 	case 0x16: init_amd_jg(c); break;
-	case 0x17: fallthrough;
+	case 0x17: init_spectral_chicken(c);
+		   fallthrough;
 	case 0x19: init_amd_zn(c); break;
 	}
 
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 2c512ff2ee10..7b15f7ef760d 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -38,6 +38,8 @@
 
 static void __init spectre_v1_select_mitigation(void);
 static void __init spectre_v2_select_mitigation(void);
+static void __init retbleed_select_mitigation(void);
+static void __init spectre_v2_user_select_mitigation(void);
 static void __init ssb_select_mitigation(void);
 static void __init l1tf_select_mitigation(void);
 static void __init mds_select_mitigation(void);
@@ -48,16 +50,40 @@ static void __init mmio_select_mitigation(void);
 static void __init srbds_select_mitigation(void);
 static void __init l1d_flush_select_mitigation(void);
 
-/* The base value of the SPEC_CTRL MSR that always has to be preserved. */
+/* The base value of the SPEC_CTRL MSR without task-specific bits set */
 u64 x86_spec_ctrl_base;
 EXPORT_SYMBOL_GPL(x86_spec_ctrl_base);
+
+/* The current value of the SPEC_CTRL MSR with task-specific bits set */
+DEFINE_PER_CPU(u64, x86_spec_ctrl_current);
+EXPORT_SYMBOL_GPL(x86_spec_ctrl_current);
+
 static DEFINE_MUTEX(spec_ctrl_mutex);
 
 /*
- * The vendor and possibly platform specific bits which can be modified in
- * x86_spec_ctrl_base.
+ * Keep track of the SPEC_CTRL MSR value for the current task, which may differ
+ * from x86_spec_ctrl_base due to STIBP/SSB in __speculation_ctrl_update().
  */
-static u64 __ro_after_init x86_spec_ctrl_mask = SPEC_CTRL_IBRS;
+void write_spec_ctrl_current(u64 val, bool force)
+{
+	if (this_cpu_read(x86_spec_ctrl_current) == val)
+		return;
+
+	this_cpu_write(x86_spec_ctrl_current, val);
+
+	/*
+	 * When KERNEL_IBRS this MSR is written on return-to-user, unless
+	 * forced the update can be delayed until that time.
+	 */
+	if (force || !cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS))
+		wrmsrl(MSR_IA32_SPEC_CTRL, val);
+}
+
+u64 spec_ctrl_current(void)
+{
+	return this_cpu_read(x86_spec_ctrl_current);
+}
+EXPORT_SYMBOL_GPL(spec_ctrl_current);
 
 /*
  * AMD specific MSR info for Speculative Store Bypass control.
@@ -114,13 +140,21 @@ void __init check_bugs(void)
 	if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL))
 		rdmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
 
-	/* Allow STIBP in MSR_SPEC_CTRL if supported */
-	if (boot_cpu_has(X86_FEATURE_STIBP))
-		x86_spec_ctrl_mask |= SPEC_CTRL_STIBP;
-
 	/* Select the proper CPU mitigations before patching alternatives: */
 	spectre_v1_select_mitigation();
 	spectre_v2_select_mitigation();
+	/*
+	 * retbleed_select_mitigation() relies on the state set by
+	 * spectre_v2_select_mitigation(); specifically it wants to know about
+	 * spectre_v2=ibrs.
+	 */
+	retbleed_select_mitigation();
+	/*
+	 * spectre_v2_user_select_mitigation() relies on the state set by
+	 * retbleed_select_mitigation(); specifically the STIBP selection is
+	 * forced for UNRET or IBPB.
+	 */
+	spectre_v2_user_select_mitigation();
 	ssb_select_mitigation();
 	l1tf_select_mitigation();
 	md_clear_select_mitigation();
@@ -161,31 +195,17 @@ void __init check_bugs(void)
 #endif
 }
 
+/*
+ * NOTE: For VMX, this function is not called in the vmexit path.
+ * It uses vmx_spec_ctrl_restore_host() instead.
+ */
 void
 x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest)
 {
-	u64 msrval, guestval, hostval = x86_spec_ctrl_base;
+	u64 msrval, guestval = guest_spec_ctrl, hostval = spec_ctrl_current();
 	struct thread_info *ti = current_thread_info();
 
-	/* Is MSR_SPEC_CTRL implemented ? */
 	if (static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) {
-		/*
-		 * Restrict guest_spec_ctrl to supported values. Clear the
-		 * modifiable bits in the host base value and or the
-		 * modifiable bits from the guest value.
-		 */
-		guestval = hostval & ~x86_spec_ctrl_mask;
-		guestval |= guest_spec_ctrl & x86_spec_ctrl_mask;
-
-		/* SSBD controlled in MSR_SPEC_CTRL */
-		if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) ||
-		    static_cpu_has(X86_FEATURE_AMD_SSBD))
-			hostval |= ssbd_tif_to_spec_ctrl(ti->flags);
-
-		/* Conditional STIBP enabled? */
-		if (static_branch_unlikely(&switch_to_cond_stibp))
-			hostval |= stibp_tif_to_spec_ctrl(ti->flags);
-
 		if (hostval != guestval) {
 			msrval = setguest ? guestval : hostval;
 			wrmsrl(MSR_IA32_SPEC_CTRL, msrval);
@@ -413,7 +433,8 @@ static void __init mmio_select_mitigation(void)
 	u64 ia32_cap;
 
 	if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA) ||
-	    cpu_mitigations_off()) {
+	     boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN) ||
+	     cpu_mitigations_off()) {
 		mmio_mitigation = MMIO_MITIGATION_OFF;
 		return;
 	}
@@ -518,6 +539,8 @@ out:
 		pr_info("TAA: %s\n", taa_strings[taa_mitigation]);
 	if (boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA))
 		pr_info("MMIO Stale Data: %s\n", mmio_strings[mmio_mitigation]);
+	else if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN))
+		pr_info("MMIO Stale Data: Unknown: No mitigations\n");
 }
 
 static void __init md_clear_select_mitigation(void)
@@ -745,12 +768,180 @@ static int __init nospectre_v1_cmdline(char *str)
 }
 early_param("nospectre_v1", nospectre_v1_cmdline);
 
-#undef pr_fmt
-#define pr_fmt(fmt)     "Spectre V2 : " fmt
-
 static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init =
 	SPECTRE_V2_NONE;
 
+#undef pr_fmt
+#define pr_fmt(fmt)     "RETBleed: " fmt
+
+enum retbleed_mitigation {
+	RETBLEED_MITIGATION_NONE,
+	RETBLEED_MITIGATION_UNRET,
+	RETBLEED_MITIGATION_IBPB,
+	RETBLEED_MITIGATION_IBRS,
+	RETBLEED_MITIGATION_EIBRS,
+};
+
+enum retbleed_mitigation_cmd {
+	RETBLEED_CMD_OFF,
+	RETBLEED_CMD_AUTO,
+	RETBLEED_CMD_UNRET,
+	RETBLEED_CMD_IBPB,
+};
+
+const char * const retbleed_strings[] = {
+	[RETBLEED_MITIGATION_NONE]	= "Vulnerable",
+	[RETBLEED_MITIGATION_UNRET]	= "Mitigation: untrained return thunk",
+	[RETBLEED_MITIGATION_IBPB]	= "Mitigation: IBPB",
+	[RETBLEED_MITIGATION_IBRS]	= "Mitigation: IBRS",
+	[RETBLEED_MITIGATION_EIBRS]	= "Mitigation: Enhanced IBRS",
+};
+
+static enum retbleed_mitigation retbleed_mitigation __ro_after_init =
+	RETBLEED_MITIGATION_NONE;
+static enum retbleed_mitigation_cmd retbleed_cmd __ro_after_init =
+	RETBLEED_CMD_AUTO;
+
+static int __ro_after_init retbleed_nosmt = false;
+
+static int __init retbleed_parse_cmdline(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	while (str) {
+		char *next = strchr(str, ',');
+		if (next) {
+			*next = 0;
+			next++;
+		}
+
+		if (!strcmp(str, "off")) {
+			retbleed_cmd = RETBLEED_CMD_OFF;
+		} else if (!strcmp(str, "auto")) {
+			retbleed_cmd = RETBLEED_CMD_AUTO;
+		} else if (!strcmp(str, "unret")) {
+			retbleed_cmd = RETBLEED_CMD_UNRET;
+		} else if (!strcmp(str, "ibpb")) {
+			retbleed_cmd = RETBLEED_CMD_IBPB;
+		} else if (!strcmp(str, "nosmt")) {
+			retbleed_nosmt = true;
+		} else {
+			pr_err("Ignoring unknown retbleed option (%s).", str);
+		}
+
+		str = next;
+	}
+
+	return 0;
+}
+early_param("retbleed", retbleed_parse_cmdline);
+
+#define RETBLEED_UNTRAIN_MSG "WARNING: BTB untrained return thunk mitigation is only effective on AMD/Hygon!\n"
+#define RETBLEED_INTEL_MSG "WARNING: Spectre v2 mitigation leaves CPU vulnerable to RETBleed attacks, data leaks possible!\n"
+
+static void __init retbleed_select_mitigation(void)
+{
+	bool mitigate_smt = false;
+
+	if (!boot_cpu_has_bug(X86_BUG_RETBLEED) || cpu_mitigations_off())
+		return;
+
+	switch (retbleed_cmd) {
+	case RETBLEED_CMD_OFF:
+		return;
+
+	case RETBLEED_CMD_UNRET:
+		if (IS_ENABLED(CONFIG_CPU_UNRET_ENTRY)) {
+			retbleed_mitigation = RETBLEED_MITIGATION_UNRET;
+		} else {
+			pr_err("WARNING: kernel not compiled with CPU_UNRET_ENTRY.\n");
+			goto do_cmd_auto;
+		}
+		break;
+
+	case RETBLEED_CMD_IBPB:
+		if (!boot_cpu_has(X86_FEATURE_IBPB)) {
+			pr_err("WARNING: CPU does not support IBPB.\n");
+			goto do_cmd_auto;
+		} else if (IS_ENABLED(CONFIG_CPU_IBPB_ENTRY)) {
+			retbleed_mitigation = RETBLEED_MITIGATION_IBPB;
+		} else {
+			pr_err("WARNING: kernel not compiled with CPU_IBPB_ENTRY.\n");
+			goto do_cmd_auto;
+		}
+		break;
+
+do_cmd_auto:
+	case RETBLEED_CMD_AUTO:
+	default:
+		if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+		    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) {
+			if (IS_ENABLED(CONFIG_CPU_UNRET_ENTRY))
+				retbleed_mitigation = RETBLEED_MITIGATION_UNRET;
+			else if (IS_ENABLED(CONFIG_CPU_IBPB_ENTRY) && boot_cpu_has(X86_FEATURE_IBPB))
+				retbleed_mitigation = RETBLEED_MITIGATION_IBPB;
+		}
+
+		/*
+		 * The Intel mitigation (IBRS or eIBRS) was already selected in
+		 * spectre_v2_select_mitigation().  'retbleed_mitigation' will
+		 * be set accordingly below.
+		 */
+
+		break;
+	}
+
+	switch (retbleed_mitigation) {
+	case RETBLEED_MITIGATION_UNRET:
+		setup_force_cpu_cap(X86_FEATURE_RETHUNK);
+		setup_force_cpu_cap(X86_FEATURE_UNRET);
+
+		if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
+		    boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
+			pr_err(RETBLEED_UNTRAIN_MSG);
+
+		mitigate_smt = true;
+		break;
+
+	case RETBLEED_MITIGATION_IBPB:
+		setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB);
+		mitigate_smt = true;
+		break;
+
+	default:
+		break;
+	}
+
+	if (mitigate_smt && !boot_cpu_has(X86_FEATURE_STIBP) &&
+	    (retbleed_nosmt || cpu_mitigations_auto_nosmt()))
+		cpu_smt_disable(false);
+
+	/*
+	 * Let IBRS trump all on Intel without affecting the effects of the
+	 * retbleed= cmdline option.
+	 */
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) {
+		switch (spectre_v2_enabled) {
+		case SPECTRE_V2_IBRS:
+			retbleed_mitigation = RETBLEED_MITIGATION_IBRS;
+			break;
+		case SPECTRE_V2_EIBRS:
+		case SPECTRE_V2_EIBRS_RETPOLINE:
+		case SPECTRE_V2_EIBRS_LFENCE:
+			retbleed_mitigation = RETBLEED_MITIGATION_EIBRS;
+			break;
+		default:
+			pr_err(RETBLEED_INTEL_MSG);
+		}
+	}
+
+	pr_info("%s\n", retbleed_strings[retbleed_mitigation]);
+}
+
+#undef pr_fmt
+#define pr_fmt(fmt)     "Spectre V2 : " fmt
+
 static enum spectre_v2_user_mitigation spectre_v2_user_stibp __ro_after_init =
 	SPECTRE_V2_USER_NONE;
 static enum spectre_v2_user_mitigation spectre_v2_user_ibpb __ro_after_init =
@@ -780,6 +971,7 @@ static inline const char *spectre_v2_module_string(void) { return ""; }
 #define SPECTRE_V2_LFENCE_MSG "WARNING: LFENCE mitigation is not recommended for this CPU, data leaks possible!\n"
 #define SPECTRE_V2_EIBRS_EBPF_MSG "WARNING: Unprivileged eBPF is enabled with eIBRS on, data leaks possible via Spectre v2 BHB attacks!\n"
 #define SPECTRE_V2_EIBRS_LFENCE_EBPF_SMT_MSG "WARNING: Unprivileged eBPF is enabled with eIBRS+LFENCE mitigation and SMT, data leaks possible via Spectre v2 BHB attacks!\n"
+#define SPECTRE_V2_IBRS_PERF_MSG "WARNING: IBRS mitigation selected on Enhanced IBRS CPU, this may cause unnecessary performance loss\n"
 
 #ifdef CONFIG_BPF_SYSCALL
 void unpriv_ebpf_notify(int new_state)
@@ -821,6 +1013,7 @@ enum spectre_v2_mitigation_cmd {
 	SPECTRE_V2_CMD_EIBRS,
 	SPECTRE_V2_CMD_EIBRS_RETPOLINE,
 	SPECTRE_V2_CMD_EIBRS_LFENCE,
+	SPECTRE_V2_CMD_IBRS,
 };
 
 enum spectre_v2_user_cmd {
@@ -861,13 +1054,15 @@ static void __init spec_v2_user_print_cond(const char *reason, bool secure)
 		pr_info("spectre_v2_user=%s forced on command line.\n", reason);
 }
 
+static __ro_after_init enum spectre_v2_mitigation_cmd spectre_v2_cmd;
+
 static enum spectre_v2_user_cmd __init
-spectre_v2_parse_user_cmdline(enum spectre_v2_mitigation_cmd v2_cmd)
+spectre_v2_parse_user_cmdline(void)
 {
 	char arg[20];
 	int ret, i;
 
-	switch (v2_cmd) {
+	switch (spectre_v2_cmd) {
 	case SPECTRE_V2_CMD_NONE:
 		return SPECTRE_V2_USER_CMD_NONE;
 	case SPECTRE_V2_CMD_FORCE:
@@ -893,15 +1088,16 @@ spectre_v2_parse_user_cmdline(enum spectre_v2_mitigation_cmd v2_cmd)
 	return SPECTRE_V2_USER_CMD_AUTO;
 }
 
-static inline bool spectre_v2_in_eibrs_mode(enum spectre_v2_mitigation mode)
+static inline bool spectre_v2_in_ibrs_mode(enum spectre_v2_mitigation mode)
 {
-	return (mode == SPECTRE_V2_EIBRS ||
-		mode == SPECTRE_V2_EIBRS_RETPOLINE ||
-		mode == SPECTRE_V2_EIBRS_LFENCE);
+	return mode == SPECTRE_V2_IBRS ||
+	       mode == SPECTRE_V2_EIBRS ||
+	       mode == SPECTRE_V2_EIBRS_RETPOLINE ||
+	       mode == SPECTRE_V2_EIBRS_LFENCE;
 }
 
 static void __init
-spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd)
+spectre_v2_user_select_mitigation(void)
 {
 	enum spectre_v2_user_mitigation mode = SPECTRE_V2_USER_NONE;
 	bool smt_possible = IS_ENABLED(CONFIG_SMP);
@@ -914,7 +1110,7 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd)
 	    cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
 		smt_possible = false;
 
-	cmd = spectre_v2_parse_user_cmdline(v2_cmd);
+	cmd = spectre_v2_parse_user_cmdline();
 	switch (cmd) {
 	case SPECTRE_V2_USER_CMD_NONE:
 		goto set_mode;
@@ -962,12 +1158,12 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd)
 	}
 
 	/*
-	 * If no STIBP, enhanced IBRS is enabled or SMT impossible, STIBP is not
-	 * required.
+	 * If no STIBP, IBRS or enhanced IBRS is enabled, or SMT impossible,
+	 * STIBP is not required.
 	 */
 	if (!boot_cpu_has(X86_FEATURE_STIBP) ||
 	    !smt_possible ||
-	    spectre_v2_in_eibrs_mode(spectre_v2_enabled))
+	    spectre_v2_in_ibrs_mode(spectre_v2_enabled))
 		return;
 
 	/*
@@ -979,6 +1175,14 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd)
 	    boot_cpu_has(X86_FEATURE_AMD_STIBP_ALWAYS_ON))
 		mode = SPECTRE_V2_USER_STRICT_PREFERRED;
 
+	if (retbleed_mitigation == RETBLEED_MITIGATION_UNRET ||
+	    retbleed_mitigation == RETBLEED_MITIGATION_IBPB) {
+		if (mode != SPECTRE_V2_USER_STRICT &&
+		    mode != SPECTRE_V2_USER_STRICT_PREFERRED)
+			pr_info("Selecting STIBP always-on mode to complement retbleed mitigation\n");
+		mode = SPECTRE_V2_USER_STRICT_PREFERRED;
+	}
+
 	spectre_v2_user_stibp = mode;
 
 set_mode:
@@ -992,6 +1196,7 @@ static const char * const spectre_v2_strings[] = {
 	[SPECTRE_V2_EIBRS]			= "Mitigation: Enhanced IBRS",
 	[SPECTRE_V2_EIBRS_LFENCE]		= "Mitigation: Enhanced IBRS + LFENCE",
 	[SPECTRE_V2_EIBRS_RETPOLINE]		= "Mitigation: Enhanced IBRS + Retpolines",
+	[SPECTRE_V2_IBRS]			= "Mitigation: IBRS",
 };
 
 static const struct {
@@ -1009,6 +1214,7 @@ static const struct {
 	{ "eibrs,lfence",	SPECTRE_V2_CMD_EIBRS_LFENCE,	  false },
 	{ "eibrs,retpoline",	SPECTRE_V2_CMD_EIBRS_RETPOLINE,	  false },
 	{ "auto",		SPECTRE_V2_CMD_AUTO,		  false },
+	{ "ibrs",		SPECTRE_V2_CMD_IBRS,              false },
 };
 
 static void __init spec_v2_print_cond(const char *reason, bool secure)
@@ -1071,6 +1277,30 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
 		return SPECTRE_V2_CMD_AUTO;
 	}
 
+	if (cmd == SPECTRE_V2_CMD_IBRS && !IS_ENABLED(CONFIG_CPU_IBRS_ENTRY)) {
+		pr_err("%s selected but not compiled in. Switching to AUTO select\n",
+		       mitigation_options[i].option);
+		return SPECTRE_V2_CMD_AUTO;
+	}
+
+	if (cmd == SPECTRE_V2_CMD_IBRS && boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) {
+		pr_err("%s selected but not Intel CPU. Switching to AUTO select\n",
+		       mitigation_options[i].option);
+		return SPECTRE_V2_CMD_AUTO;
+	}
+
+	if (cmd == SPECTRE_V2_CMD_IBRS && !boot_cpu_has(X86_FEATURE_IBRS)) {
+		pr_err("%s selected but CPU doesn't have IBRS. Switching to AUTO select\n",
+		       mitigation_options[i].option);
+		return SPECTRE_V2_CMD_AUTO;
+	}
+
+	if (cmd == SPECTRE_V2_CMD_IBRS && boot_cpu_has(X86_FEATURE_XENPV)) {
+		pr_err("%s selected but running as XenPV guest. Switching to AUTO select\n",
+		       mitigation_options[i].option);
+		return SPECTRE_V2_CMD_AUTO;
+	}
+
 	spec_v2_print_cond(mitigation_options[i].option,
 			   mitigation_options[i].secure);
 	return cmd;
@@ -1086,6 +1316,69 @@ static enum spectre_v2_mitigation __init spectre_v2_select_retpoline(void)
 	return SPECTRE_V2_RETPOLINE;
 }
 
+/* Disable in-kernel use of non-RSB RET predictors */
+static void __init spec_ctrl_disable_kernel_rrsba(void)
+{
+	u64 ia32_cap;
+
+	if (!boot_cpu_has(X86_FEATURE_RRSBA_CTRL))
+		return;
+
+	ia32_cap = x86_read_arch_cap_msr();
+
+	if (ia32_cap & ARCH_CAP_RRSBA) {
+		x86_spec_ctrl_base |= SPEC_CTRL_RRSBA_DIS_S;
+		write_spec_ctrl_current(x86_spec_ctrl_base, true);
+	}
+}
+
+static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_mitigation mode)
+{
+	/*
+	 * Similar to context switches, there are two types of RSB attacks
+	 * after VM exit:
+	 *
+	 * 1) RSB underflow
+	 *
+	 * 2) Poisoned RSB entry
+	 *
+	 * When retpoline is enabled, both are mitigated by filling/clearing
+	 * the RSB.
+	 *
+	 * When IBRS is enabled, while #1 would be mitigated by the IBRS branch
+	 * prediction isolation protections, RSB still needs to be cleared
+	 * because of #2.  Note that SMEP provides no protection here, unlike
+	 * user-space-poisoned RSB entries.
+	 *
+	 * eIBRS should protect against RSB poisoning, but if the EIBRS_PBRSB
+	 * bug is present then a LITE version of RSB protection is required,
+	 * just a single call needs to retire before a RET is executed.
+	 */
+	switch (mode) {
+	case SPECTRE_V2_NONE:
+		return;
+
+	case SPECTRE_V2_EIBRS_LFENCE:
+	case SPECTRE_V2_EIBRS:
+		if (boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB)) {
+			setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT_LITE);
+			pr_info("Spectre v2 / PBRSB-eIBRS: Retire a single CALL on VMEXIT\n");
+		}
+		return;
+
+	case SPECTRE_V2_EIBRS_RETPOLINE:
+	case SPECTRE_V2_RETPOLINE:
+	case SPECTRE_V2_LFENCE:
+	case SPECTRE_V2_IBRS:
+		setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT);
+		pr_info("Spectre v2 / SpectreRSB : Filling RSB on VMEXIT\n");
+		return;
+	}
+
+	pr_warn_once("Unknown Spectre v2 mode, disabling RSB mitigation at VM exit");
+	dump_stack();
+}
+
 static void __init spectre_v2_select_mitigation(void)
 {
 	enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();
@@ -1110,6 +1403,15 @@ static void __init spectre_v2_select_mitigation(void)
 			break;
 		}
 
+		if (IS_ENABLED(CONFIG_CPU_IBRS_ENTRY) &&
+		    boot_cpu_has_bug(X86_BUG_RETBLEED) &&
+		    retbleed_cmd != RETBLEED_CMD_OFF &&
+		    boot_cpu_has(X86_FEATURE_IBRS) &&
+		    boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) {
+			mode = SPECTRE_V2_IBRS;
+			break;
+		}
+
 		mode = spectre_v2_select_retpoline();
 		break;
 
@@ -1126,6 +1428,10 @@ static void __init spectre_v2_select_mitigation(void)
 		mode = spectre_v2_select_retpoline();
 		break;
 
+	case SPECTRE_V2_CMD_IBRS:
+		mode = SPECTRE_V2_IBRS;
+		break;
+
 	case SPECTRE_V2_CMD_EIBRS:
 		mode = SPECTRE_V2_EIBRS;
 		break;
@@ -1142,10 +1448,9 @@ static void __init spectre_v2_select_mitigation(void)
 	if (mode == SPECTRE_V2_EIBRS && unprivileged_ebpf_enabled())
 		pr_err(SPECTRE_V2_EIBRS_EBPF_MSG);
 
-	if (spectre_v2_in_eibrs_mode(mode)) {
-		/* Force it so VMEXIT will restore correctly */
+	if (spectre_v2_in_ibrs_mode(mode)) {
 		x86_spec_ctrl_base |= SPEC_CTRL_IBRS;
-		wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+		write_spec_ctrl_current(x86_spec_ctrl_base, true);
 	}
 
 	switch (mode) {
@@ -1153,6 +1458,12 @@ static void __init spectre_v2_select_mitigation(void)
 	case SPECTRE_V2_EIBRS:
 		break;
 
+	case SPECTRE_V2_IBRS:
+		setup_force_cpu_cap(X86_FEATURE_KERNEL_IBRS);
+		if (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED))
+			pr_warn(SPECTRE_V2_IBRS_PERF_MSG);
+		break;
+
 	case SPECTRE_V2_LFENCE:
 	case SPECTRE_V2_EIBRS_LFENCE:
 		setup_force_cpu_cap(X86_FEATURE_RETPOLINE_LFENCE);
@@ -1164,43 +1475,96 @@ static void __init spectre_v2_select_mitigation(void)
 		break;
 	}
 
+	/*
+	 * Disable alternate RSB predictions in kernel when indirect CALLs and
+	 * JMPs gets protection against BHI and Intramode-BTI, but RET
+	 * prediction from a non-RSB predictor is still a risk.
+	 */
+	if (mode == SPECTRE_V2_EIBRS_LFENCE ||
+	    mode == SPECTRE_V2_EIBRS_RETPOLINE ||
+	    mode == SPECTRE_V2_RETPOLINE)
+		spec_ctrl_disable_kernel_rrsba();
+
 	spectre_v2_enabled = mode;
 	pr_info("%s\n", spectre_v2_strings[mode]);
 
 	/*
-	 * If spectre v2 protection has been enabled, unconditionally fill
-	 * RSB during a context switch; this protects against two independent
-	 * issues:
+	 * If Spectre v2 protection has been enabled, fill the RSB during a
+	 * context switch.  In general there are two types of RSB attacks
+	 * across context switches, for which the CALLs/RETs may be unbalanced.
+	 *
+	 * 1) RSB underflow
+	 *
+	 *    Some Intel parts have "bottomless RSB".  When the RSB is empty,
+	 *    speculated return targets may come from the branch predictor,
+	 *    which could have a user-poisoned BTB or BHB entry.
+	 *
+	 *    AMD has it even worse: *all* returns are speculated from the BTB,
+	 *    regardless of the state of the RSB.
+	 *
+	 *    When IBRS or eIBRS is enabled, the "user -> kernel" attack
+	 *    scenario is mitigated by the IBRS branch prediction isolation
+	 *    properties, so the RSB buffer filling wouldn't be necessary to
+	 *    protect against this type of attack.
+	 *
+	 *    The "user -> user" attack scenario is mitigated by RSB filling.
+	 *
+	 * 2) Poisoned RSB entry
+	 *
+	 *    If the 'next' in-kernel return stack is shorter than 'prev',
+	 *    'next' could be tricked into speculating with a user-poisoned RSB
+	 *    entry.
+	 *
+	 *    The "user -> kernel" attack scenario is mitigated by SMEP and
+	 *    eIBRS.
+	 *
+	 *    The "user -> user" scenario, also known as SpectreBHB, requires
+	 *    RSB clearing.
+	 *
+	 * So to mitigate all cases, unconditionally fill RSB on context
+	 * switches.
 	 *
-	 *	- RSB underflow (and switch to BTB) on Skylake+
-	 *	- SpectreRSB variant of spectre v2 on X86_BUG_SPECTRE_V2 CPUs
+	 * FIXME: Is this pointless for retbleed-affected AMD?
 	 */
 	setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
 	pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n");
 
+	spectre_v2_determine_rsb_fill_type_at_vmexit(mode);
+
 	/*
-	 * Retpoline means the kernel is safe because it has no indirect
-	 * branches. Enhanced IBRS protects firmware too, so, enable restricted
-	 * speculation around firmware calls only when Enhanced IBRS isn't
-	 * supported.
+	 * Retpoline protects the kernel, but doesn't protect firmware.  IBRS
+	 * and Enhanced IBRS protect firmware too, so enable IBRS around
+	 * firmware calls only when IBRS / Enhanced IBRS aren't otherwise
+	 * enabled.
 	 *
 	 * Use "mode" to check Enhanced IBRS instead of boot_cpu_has(), because
 	 * the user might select retpoline on the kernel command line and if
 	 * the CPU supports Enhanced IBRS, kernel might un-intentionally not
 	 * enable IBRS around firmware calls.
 	 */
-	if (boot_cpu_has(X86_FEATURE_IBRS) && !spectre_v2_in_eibrs_mode(mode)) {
+	if (boot_cpu_has_bug(X86_BUG_RETBLEED) &&
+	    boot_cpu_has(X86_FEATURE_IBPB) &&
+	    (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+	     boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)) {
+
+		if (retbleed_cmd != RETBLEED_CMD_IBPB) {
+			setup_force_cpu_cap(X86_FEATURE_USE_IBPB_FW);
+			pr_info("Enabling Speculation Barrier for firmware calls\n");
+		}
+
+	} else if (boot_cpu_has(X86_FEATURE_IBRS) && !spectre_v2_in_ibrs_mode(mode)) {
 		setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW);
 		pr_info("Enabling Restricted Speculation for firmware calls\n");
 	}
 
 	/* Set up IBPB and STIBP depending on the general spectre V2 command */
-	spectre_v2_user_select_mitigation(cmd);
+	spectre_v2_cmd = cmd;
 }
 
 static void update_stibp_msr(void * __unused)
 {
-	wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+	u64 val = spec_ctrl_current() | (x86_spec_ctrl_base & SPEC_CTRL_STIBP);
+	write_spec_ctrl_current(val, true);
 }
 
 /* Update x86_spec_ctrl_base in case SMT state changed. */
@@ -1417,16 +1781,6 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void)
 	}
 
 	/*
-	 * If SSBD is controlled by the SPEC_CTRL MSR, then set the proper
-	 * bit in the mask to allow guests to use the mitigation even in the
-	 * case where the host does not enable it.
-	 */
-	if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) ||
-	    static_cpu_has(X86_FEATURE_AMD_SSBD)) {
-		x86_spec_ctrl_mask |= SPEC_CTRL_SSBD;
-	}
-
-	/*
 	 * We have three CPU feature flags that are in play here:
 	 *  - X86_BUG_SPEC_STORE_BYPASS - CPU is susceptible.
 	 *  - X86_FEATURE_SSBD - CPU is able to turn off speculative store bypass
@@ -1443,7 +1797,7 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void)
 			x86_amd_ssb_disable();
 		} else {
 			x86_spec_ctrl_base |= SPEC_CTRL_SSBD;
-			wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+			write_spec_ctrl_current(x86_spec_ctrl_base, true);
 		}
 	}
 
@@ -1694,7 +2048,7 @@ int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which)
 void x86_spec_ctrl_setup_ap(void)
 {
 	if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL))
-		wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+		write_spec_ctrl_current(x86_spec_ctrl_base, true);
 
 	if (ssb_mode == SPEC_STORE_BYPASS_DISABLE)
 		x86_amd_ssb_disable();
@@ -1917,6 +2271,9 @@ static ssize_t tsx_async_abort_show_state(char *buf)
 
 static ssize_t mmio_stale_data_show_state(char *buf)
 {
+	if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN))
+		return sysfs_emit(buf, "Unknown: No mitigations\n");
+
 	if (mmio_mitigation == MMIO_MITIGATION_OFF)
 		return sysfs_emit(buf, "%s\n", mmio_strings[mmio_mitigation]);
 
@@ -1931,7 +2288,7 @@ static ssize_t mmio_stale_data_show_state(char *buf)
 
 static char *stibp_state(void)
 {
-	if (spectre_v2_in_eibrs_mode(spectre_v2_enabled))
+	if (spectre_v2_in_ibrs_mode(spectre_v2_enabled))
 		return "";
 
 	switch (spectre_v2_user_stibp) {
@@ -1961,6 +2318,19 @@ static char *ibpb_state(void)
 	return "";
 }
 
+static char *pbrsb_eibrs_state(void)
+{
+	if (boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB)) {
+		if (boot_cpu_has(X86_FEATURE_RSB_VMEXIT_LITE) ||
+		    boot_cpu_has(X86_FEATURE_RSB_VMEXIT))
+			return ", PBRSB-eIBRS: SW sequence";
+		else
+			return ", PBRSB-eIBRS: Vulnerable";
+	} else {
+		return ", PBRSB-eIBRS: Not affected";
+	}
+}
+
 static ssize_t spectre_v2_show_state(char *buf)
 {
 	if (spectre_v2_enabled == SPECTRE_V2_LFENCE)
@@ -1973,12 +2343,13 @@ static ssize_t spectre_v2_show_state(char *buf)
 	    spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE)
 		return sprintf(buf, "Vulnerable: eIBRS+LFENCE with unprivileged eBPF and SMT\n");
 
-	return sprintf(buf, "%s%s%s%s%s%s\n",
+	return sprintf(buf, "%s%s%s%s%s%s%s\n",
 		       spectre_v2_strings[spectre_v2_enabled],
 		       ibpb_state(),
 		       boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "",
 		       stibp_state(),
 		       boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "",
+		       pbrsb_eibrs_state(),
 		       spectre_v2_module_string());
 }
 
@@ -1987,6 +2358,25 @@ static ssize_t srbds_show_state(char *buf)
 	return sprintf(buf, "%s\n", srbds_strings[srbds_mitigation]);
 }
 
+static ssize_t retbleed_show_state(char *buf)
+{
+	if (retbleed_mitigation == RETBLEED_MITIGATION_UNRET ||
+	    retbleed_mitigation == RETBLEED_MITIGATION_IBPB) {
+	    if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
+		boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
+		    return sprintf(buf, "Vulnerable: untrained return thunk / IBPB on non-AMD based uarch\n");
+
+	    return sprintf(buf, "%s; SMT %s\n",
+			   retbleed_strings[retbleed_mitigation],
+			   !sched_smt_active() ? "disabled" :
+			   spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||
+			   spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED ?
+			   "enabled with STIBP protection" : "vulnerable");
+	}
+
+	return sprintf(buf, "%s\n", retbleed_strings[retbleed_mitigation]);
+}
+
 static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
 			       char *buf, unsigned int bug)
 {
@@ -2030,8 +2420,12 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 		return srbds_show_state(buf);
 
 	case X86_BUG_MMIO_STALE_DATA:
+	case X86_BUG_MMIO_UNKNOWN:
 		return mmio_stale_data_show_state(buf);
 
+	case X86_BUG_RETBLEED:
+		return retbleed_show_state(buf);
+
 	default:
 		break;
 	}
@@ -2086,6 +2480,14 @@ ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, char *
 
 ssize_t cpu_show_mmio_stale_data(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA);
+	if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN))
+		return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_UNKNOWN);
+	else
+		return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA);
+}
+
+ssize_t cpu_show_retbleed(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_RETBLEED);
 }
 #endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index bd390c56e551..9c1df6222df9 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1027,6 +1027,8 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
 #define NO_SWAPGS		BIT(6)
 #define NO_ITLB_MULTIHIT	BIT(7)
 #define NO_SPECTRE_V2		BIT(8)
+#define NO_MMIO			BIT(9)
+#define NO_EIBRS_PBRSB		BIT(10)
 
 #define VULNWL(vendor, family, model, whitelist)	\
 	X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, whitelist)
@@ -1047,6 +1049,11 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 	VULNWL(NSC,	5, X86_MODEL_ANY,	NO_SPECULATION),
 
 	/* Intel Family 6 */
+	VULNWL_INTEL(TIGERLAKE,			NO_MMIO),
+	VULNWL_INTEL(TIGERLAKE_L,		NO_MMIO),
+	VULNWL_INTEL(ALDERLAKE,			NO_MMIO),
+	VULNWL_INTEL(ALDERLAKE_L,		NO_MMIO),
+
 	VULNWL_INTEL(ATOM_SALTWELL,		NO_SPECULATION | NO_ITLB_MULTIHIT),
 	VULNWL_INTEL(ATOM_SALTWELL_TABLET,	NO_SPECULATION | NO_ITLB_MULTIHIT),
 	VULNWL_INTEL(ATOM_SALTWELL_MID,		NO_SPECULATION | NO_ITLB_MULTIHIT),
@@ -1065,9 +1072,9 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 	VULNWL_INTEL(ATOM_AIRMONT_MID,		NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
 	VULNWL_INTEL(ATOM_AIRMONT_NP,		NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
 
-	VULNWL_INTEL(ATOM_GOLDMONT,		NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_INTEL(ATOM_GOLDMONT_D,		NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_INTEL(ATOM_GOLDMONT_PLUS,	NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
+	VULNWL_INTEL(ATOM_GOLDMONT,		NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+	VULNWL_INTEL(ATOM_GOLDMONT_D,		NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+	VULNWL_INTEL(ATOM_GOLDMONT_PLUS,	NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB),
 
 	/*
 	 * Technically, swapgs isn't serializing on AMD (despite it previously
@@ -1077,66 +1084,80 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 	 * good enough for our purposes.
 	 */
 
-	VULNWL_INTEL(ATOM_TREMONT_D,		NO_ITLB_MULTIHIT),
+	VULNWL_INTEL(ATOM_TREMONT,		NO_EIBRS_PBRSB),
+	VULNWL_INTEL(ATOM_TREMONT_L,		NO_EIBRS_PBRSB),
+	VULNWL_INTEL(ATOM_TREMONT_D,		NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB),
 
 	/* AMD Family 0xf - 0x12 */
-	VULNWL_AMD(0x0f,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_AMD(0x10,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_AMD(0x11,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_AMD(0x12,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
+	VULNWL_AMD(0x0f,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+	VULNWL_AMD(0x10,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+	VULNWL_AMD(0x11,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+	VULNWL_AMD(0x12,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
 
 	/* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */
-	VULNWL_AMD(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_HYGON(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
+	VULNWL_AMD(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+	VULNWL_HYGON(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
 
 	/* Zhaoxin Family 7 */
-	VULNWL(CENTAUR,	7, X86_MODEL_ANY,	NO_SPECTRE_V2 | NO_SWAPGS),
-	VULNWL(ZHAOXIN,	7, X86_MODEL_ANY,	NO_SPECTRE_V2 | NO_SWAPGS),
+	VULNWL(CENTAUR,	7, X86_MODEL_ANY,	NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO),
+	VULNWL(ZHAOXIN,	7, X86_MODEL_ANY,	NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO),
 	{}
 };
 
+#define VULNBL(vendor, family, model, blacklist)	\
+	X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, blacklist)
+
 #define VULNBL_INTEL_STEPPINGS(model, steppings, issues)		   \
 	X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(INTEL, 6,		   \
 					    INTEL_FAM6_##model, steppings, \
 					    X86_FEATURE_ANY, issues)
 
+#define VULNBL_AMD(family, blacklist)		\
+	VULNBL(AMD, family, X86_MODEL_ANY, blacklist)
+
+#define VULNBL_HYGON(family, blacklist)		\
+	VULNBL(HYGON, family, X86_MODEL_ANY, blacklist)
+
 #define SRBDS		BIT(0)
 /* CPU is affected by X86_BUG_MMIO_STALE_DATA */
 #define MMIO		BIT(1)
 /* CPU is affected by Shared Buffers Data Sampling (SBDS), a variant of X86_BUG_MMIO_STALE_DATA */
 #define MMIO_SBDS	BIT(2)
+/* CPU is affected by RETbleed, speculating where you would not expect it */
+#define RETBLEED	BIT(3)
 
 static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
 	VULNBL_INTEL_STEPPINGS(IVYBRIDGE,	X86_STEPPING_ANY,		SRBDS),
 	VULNBL_INTEL_STEPPINGS(HASWELL,		X86_STEPPING_ANY,		SRBDS),
 	VULNBL_INTEL_STEPPINGS(HASWELL_L,	X86_STEPPING_ANY,		SRBDS),
 	VULNBL_INTEL_STEPPINGS(HASWELL_G,	X86_STEPPING_ANY,		SRBDS),
-	VULNBL_INTEL_STEPPINGS(HASWELL_X,	BIT(2) | BIT(4),		MMIO),
-	VULNBL_INTEL_STEPPINGS(BROADWELL_D,	X86_STEPPINGS(0x3, 0x5),	MMIO),
+	VULNBL_INTEL_STEPPINGS(HASWELL_X,	X86_STEPPING_ANY,		MMIO),
+	VULNBL_INTEL_STEPPINGS(BROADWELL_D,	X86_STEPPING_ANY,		MMIO),
 	VULNBL_INTEL_STEPPINGS(BROADWELL_G,	X86_STEPPING_ANY,		SRBDS),
 	VULNBL_INTEL_STEPPINGS(BROADWELL_X,	X86_STEPPING_ANY,		MMIO),
 	VULNBL_INTEL_STEPPINGS(BROADWELL,	X86_STEPPING_ANY,		SRBDS),
-	VULNBL_INTEL_STEPPINGS(SKYLAKE_L,	X86_STEPPINGS(0x3, 0x3),	SRBDS | MMIO),
-	VULNBL_INTEL_STEPPINGS(SKYLAKE_L,	X86_STEPPING_ANY,		SRBDS),
-	VULNBL_INTEL_STEPPINGS(SKYLAKE_X,	BIT(3) | BIT(4) | BIT(6) |
-						BIT(7) | BIT(0xB),              MMIO),
-	VULNBL_INTEL_STEPPINGS(SKYLAKE,		X86_STEPPINGS(0x3, 0x3),	SRBDS | MMIO),
-	VULNBL_INTEL_STEPPINGS(SKYLAKE,		X86_STEPPING_ANY,		SRBDS),
-	VULNBL_INTEL_STEPPINGS(KABYLAKE_L,	X86_STEPPINGS(0x9, 0xC),	SRBDS | MMIO),
-	VULNBL_INTEL_STEPPINGS(KABYLAKE_L,	X86_STEPPINGS(0x0, 0x8),	SRBDS),
-	VULNBL_INTEL_STEPPINGS(KABYLAKE,	X86_STEPPINGS(0x9, 0xD),	SRBDS | MMIO),
-	VULNBL_INTEL_STEPPINGS(KABYLAKE,	X86_STEPPINGS(0x0, 0x8),	SRBDS),
-	VULNBL_INTEL_STEPPINGS(ICELAKE_L,	X86_STEPPINGS(0x5, 0x5),	MMIO | MMIO_SBDS),
-	VULNBL_INTEL_STEPPINGS(ICELAKE_D,	X86_STEPPINGS(0x1, 0x1),	MMIO),
-	VULNBL_INTEL_STEPPINGS(ICELAKE_X,	X86_STEPPINGS(0x4, 0x6),	MMIO),
-	VULNBL_INTEL_STEPPINGS(COMETLAKE,	BIT(2) | BIT(3) | BIT(5),	MMIO | MMIO_SBDS),
-	VULNBL_INTEL_STEPPINGS(COMETLAKE_L,	X86_STEPPINGS(0x1, 0x1),	MMIO | MMIO_SBDS),
-	VULNBL_INTEL_STEPPINGS(COMETLAKE_L,	X86_STEPPINGS(0x0, 0x0),	MMIO),
-	VULNBL_INTEL_STEPPINGS(LAKEFIELD,	X86_STEPPINGS(0x1, 0x1),	MMIO | MMIO_SBDS),
-	VULNBL_INTEL_STEPPINGS(ROCKETLAKE,	X86_STEPPINGS(0x1, 0x1),	MMIO),
-	VULNBL_INTEL_STEPPINGS(ATOM_TREMONT,	X86_STEPPINGS(0x1, 0x1),	MMIO | MMIO_SBDS),
+	VULNBL_INTEL_STEPPINGS(SKYLAKE_L,	X86_STEPPING_ANY,		SRBDS | MMIO | RETBLEED),
+	VULNBL_INTEL_STEPPINGS(SKYLAKE_X,	X86_STEPPING_ANY,		MMIO | RETBLEED),
+	VULNBL_INTEL_STEPPINGS(SKYLAKE,		X86_STEPPING_ANY,		SRBDS | MMIO | RETBLEED),
+	VULNBL_INTEL_STEPPINGS(KABYLAKE_L,	X86_STEPPING_ANY,		SRBDS | MMIO | RETBLEED),
+	VULNBL_INTEL_STEPPINGS(KABYLAKE,	X86_STEPPING_ANY,		SRBDS | MMIO | RETBLEED),
+	VULNBL_INTEL_STEPPINGS(CANNONLAKE_L,	X86_STEPPING_ANY,		RETBLEED),
+	VULNBL_INTEL_STEPPINGS(ICELAKE_L,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS | RETBLEED),
+	VULNBL_INTEL_STEPPINGS(ICELAKE_D,	X86_STEPPING_ANY,		MMIO),
+	VULNBL_INTEL_STEPPINGS(ICELAKE_X,	X86_STEPPING_ANY,		MMIO),
+	VULNBL_INTEL_STEPPINGS(COMETLAKE,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS | RETBLEED),
+	VULNBL_INTEL_STEPPINGS(COMETLAKE_L,	X86_STEPPINGS(0x0, 0x0),	MMIO | RETBLEED),
+	VULNBL_INTEL_STEPPINGS(COMETLAKE_L,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS | RETBLEED),
+	VULNBL_INTEL_STEPPINGS(LAKEFIELD,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS | RETBLEED),
+	VULNBL_INTEL_STEPPINGS(ROCKETLAKE,	X86_STEPPING_ANY,		MMIO | RETBLEED),
+	VULNBL_INTEL_STEPPINGS(ATOM_TREMONT,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS),
 	VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D,	X86_STEPPING_ANY,		MMIO),
-	VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L,	X86_STEPPINGS(0x0, 0x0),	MMIO | MMIO_SBDS),
+	VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS),
+
+	VULNBL_AMD(0x15, RETBLEED),
+	VULNBL_AMD(0x16, RETBLEED),
+	VULNBL_AMD(0x17, RETBLEED),
+	VULNBL_HYGON(0x18, RETBLEED),
 	{}
 };
 
@@ -1233,10 +1254,26 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	 * Affected CPU list is generally enough to enumerate the vulnerability,
 	 * but for virtualization case check for ARCH_CAP MSR bits also, VMM may
 	 * not want the guest to enumerate the bug.
+	 *
+	 * Set X86_BUG_MMIO_UNKNOWN for CPUs that are neither in the blacklist,
+	 * nor in the whitelist and also don't enumerate MSR ARCH_CAP MMIO bits.
 	 */
-	if (cpu_matches(cpu_vuln_blacklist, MMIO) &&
-	    !arch_cap_mmio_immune(ia32_cap))
-		setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA);
+	if (!arch_cap_mmio_immune(ia32_cap)) {
+		if (cpu_matches(cpu_vuln_blacklist, MMIO))
+			setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA);
+		else if (!cpu_matches(cpu_vuln_whitelist, NO_MMIO))
+			setup_force_cpu_bug(X86_BUG_MMIO_UNKNOWN);
+	}
+
+	if (!cpu_has(c, X86_FEATURE_BTC_NO)) {
+		if (cpu_matches(cpu_vuln_blacklist, RETBLEED) || (ia32_cap & ARCH_CAP_RSBA))
+			setup_force_cpu_bug(X86_BUG_RETBLEED);
+	}
+
+	if (cpu_has(c, X86_FEATURE_IBRS_ENHANCED) &&
+	    !cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) &&
+	    !(ia32_cap & ARCH_CAP_PBRSB_NO))
+		setup_force_cpu_bug(X86_BUG_EIBRS_PBRSB);
 
 	if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
 		return;
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 2a8e584fc991..7c9b5893c30a 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -61,6 +61,8 @@ static inline void tsx_init(void) { }
 static inline void tsx_ap_init(void) { }
 #endif /* CONFIG_CPU_SUP_INTEL */
 
+extern void init_spectral_chicken(struct cpuinfo_x86 *c);
+
 extern void get_cpu_cap(struct cpuinfo_x86 *c);
 extern void get_cpu_address_sizes(struct cpuinfo_x86 *c);
 extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c);
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
index 3fcdda4c1e11..21fd425088fe 100644
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -302,6 +302,12 @@ static void init_hygon(struct cpuinfo_x86 *c)
 	/* get apicid instead of initial apic id from cpuid */
 	c->apicid = hard_smp_processor_id();
 
+	/*
+	 * XXX someone from Hygon needs to confirm this DTRT
+	 *
+	init_spectral_chicken(c);
+	 */
+
 	set_cpu_cap(c, X86_FEATURE_ZEN);
 	set_cpu_cap(c, X86_FEATURE_CPB);
 
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 2c87d62f191e..ae7d4c85f4f4 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -1145,22 +1145,23 @@ static void bus_lock_init(void)
 {
 	u64 val;
 
-	/*
-	 * Warn and fatal are handled by #AC for split lock if #AC for
-	 * split lock is supported.
-	 */
-	if (!boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT) ||
-	    (boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT) &&
-	    (sld_state == sld_warn || sld_state == sld_fatal)) ||
-	    sld_state == sld_off)
+	if (!boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT))
 		return;
 
-	/*
-	 * Enable #DB for bus lock. All bus locks are handled in #DB except
-	 * split locks are handled in #AC in the fatal case.
-	 */
 	rdmsrl(MSR_IA32_DEBUGCTLMSR, val);
-	val |= DEBUGCTLMSR_BUS_LOCK_DETECT;
+
+	if ((boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT) &&
+	    (sld_state == sld_warn || sld_state == sld_fatal)) ||
+	    sld_state == sld_off) {
+		/*
+		 * Warn and fatal are handled by #AC for split lock if #AC for
+		 * split lock is supported.
+		 */
+		val &= ~DEBUGCTLMSR_BUS_LOCK_DETECT;
+	} else {
+		val |= DEBUGCTLMSR_BUS_LOCK_DETECT;
+	}
+
 	wrmsrl(MSR_IA32_DEBUGCTLMSR, val);
 }
 
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index e23e74e2f928..773037e5fd76 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -382,13 +382,16 @@ static int msr_to_offset(u32 msr)
 	return -1;
 }
 
-__visible bool ex_handler_rdmsr_fault(const struct exception_table_entry *fixup,
-				      struct pt_regs *regs, int trapnr,
-				      unsigned long error_code,
-				      unsigned long fault_addr)
+void ex_handler_msr_mce(struct pt_regs *regs, bool wrmsr)
 {
-	pr_emerg("MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pS)\n",
-		 (unsigned int)regs->cx, regs->ip, (void *)regs->ip);
+	if (wrmsr) {
+		pr_emerg("MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pS)\n",
+			 (unsigned int)regs->cx, (unsigned int)regs->dx, (unsigned int)regs->ax,
+			 regs->ip, (void *)regs->ip);
+	} else {
+		pr_emerg("MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pS)\n",
+			 (unsigned int)regs->cx, regs->ip, (void *)regs->ip);
+	}
 
 	show_stack_regs(regs);
 
@@ -396,8 +399,6 @@ __visible bool ex_handler_rdmsr_fault(const struct exception_table_entry *fixup,
 
 	while (true)
 		cpu_relax();
-
-	return true;
 }
 
 /* MSR access wrappers used for error injection */
@@ -429,32 +430,13 @@ static noinstr u64 mce_rdmsrl(u32 msr)
 	 */
 	asm volatile("1: rdmsr\n"
 		     "2:\n"
-		     _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_rdmsr_fault)
+		     _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_RDMSR_IN_MCE)
 		     : EAX_EDX_RET(val, low, high) : "c" (msr));
 
 
 	return EAX_EDX_VAL(val, low, high);
 }
 
-__visible bool ex_handler_wrmsr_fault(const struct exception_table_entry *fixup,
-				      struct pt_regs *regs, int trapnr,
-				      unsigned long error_code,
-				      unsigned long fault_addr)
-{
-	pr_emerg("MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pS)\n",
-		 (unsigned int)regs->cx, (unsigned int)regs->dx, (unsigned int)regs->ax,
-		  regs->ip, (void *)regs->ip);
-
-	show_stack_regs(regs);
-
-	panic("MCA architectural violation!\n");
-
-	while (true)
-		cpu_relax();
-
-	return true;
-}
-
 static noinstr void mce_wrmsrl(u32 msr, u64 v)
 {
 	u32 low, high;
@@ -479,7 +461,7 @@ static noinstr void mce_wrmsrl(u32 msr, u64 v)
 	/* See comment in mce_rdmsrl() */
 	asm volatile("1: wrmsr\n"
 		     "2:\n"
-		     _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_wrmsr_fault)
+		     _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR_IN_MCE)
 		     : : "c" (msr), "a"(low), "d" (high) : "memory");
 }
 
@@ -1297,10 +1279,12 @@ static void kill_me_maybe(struct callback_head *cb)
 
 	/*
 	 * -EHWPOISON from memory_failure() means that it already sent SIGBUS
-	 * to the current process with the proper error info, so no need to
-	 * send SIGBUS here again.
+	 * to the current process with the proper error info,
+	 * -EOPNOTSUPP means hwpoison_filter() filtered the error event,
+	 *
+	 * In both cases, no further processing is required.
 	 */
-	if (ret == -EHWPOISON)
+	if (ret == -EHWPOISON || ret == -EOPNOTSUPP)
 		return;
 
 	if (p->mce_vaddr != (void __user *)-1l) {
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index 88dcc79cfb07..80dc94313bcf 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -186,14 +186,4 @@ extern bool amd_filter_mce(struct mce *m);
 static inline bool amd_filter_mce(struct mce *m)			{ return false; };
 #endif
 
-__visible bool ex_handler_rdmsr_fault(const struct exception_table_entry *fixup,
-				      struct pt_regs *regs, int trapnr,
-				      unsigned long error_code,
-				      unsigned long fault_addr);
-
-__visible bool ex_handler_wrmsr_fault(const struct exception_table_entry *fixup,
-				      struct pt_regs *regs, int trapnr,
-				      unsigned long error_code,
-				      unsigned long fault_addr);
-
 #endif /* __X86_MCE_INTERNAL_H__ */
diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c
index 17e631443116..d9b77a74f8d2 100644
--- a/arch/x86/kernel/cpu/mce/severity.c
+++ b/arch/x86/kernel/cpu/mce/severity.c
@@ -265,25 +265,26 @@ static bool is_copy_from_user(struct pt_regs *regs)
  */
 static int error_context(struct mce *m, struct pt_regs *regs)
 {
-	enum handler_type t;
-
 	if ((m->cs & 3) == 3)
 		return IN_USER;
 	if (!mc_recoverable(m->mcgstatus))
 		return IN_KERNEL;
 
-	t = ex_get_fault_handler_type(m->ip);
-	if (t == EX_HANDLER_FAULT) {
-		m->kflags |= MCE_IN_KERNEL_RECOV;
-		return IN_KERNEL_RECOV;
-	}
-	if (t == EX_HANDLER_UACCESS && regs && is_copy_from_user(regs)) {
-		m->kflags |= MCE_IN_KERNEL_RECOV;
+	switch (ex_get_fixup_type(m->ip)) {
+	case EX_TYPE_UACCESS:
+	case EX_TYPE_COPY:
+		if (!regs || !is_copy_from_user(regs))
+			return IN_KERNEL;
 		m->kflags |= MCE_IN_KERNEL_COPYIN;
+		fallthrough;
+	case EX_TYPE_FAULT:
+	case EX_TYPE_FAULT_MCE_SAFE:
+	case EX_TYPE_DEFAULT_MCE_SAFE:
+		m->kflags |= MCE_IN_KERNEL_RECOV;
 		return IN_KERNEL_RECOV;
+	default:
+		return IN_KERNEL;
 	}
-
-	return IN_KERNEL;
 }
 
 static int mce_severity_amd_smca(struct mce *m, enum context err_ctx)
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 21d1f062895a..06bfef1c4175 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -26,6 +26,7 @@ struct cpuid_bit {
 static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_APERFMPERF,       CPUID_ECX,  0, 0x00000006, 0 },
 	{ X86_FEATURE_EPB,		CPUID_ECX,  3, 0x00000006, 0 },
+	{ X86_FEATURE_RRSBA_CTRL,	CPUID_EDX,  2, 0x00000007, 2 },
 	{ X86_FEATURE_CQM_LLC,		CPUID_EDX,  1, 0x0000000f, 0 },
 	{ X86_FEATURE_CQM_OCCUP_LLC,	CPUID_EDX,  0, 0x0000000f, 1 },
 	{ X86_FEATURE_CQM_MBM_TOTAL,	CPUID_EDX,  1, 0x0000000f, 1 },
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 847776cc1aa4..b3c9ef01d6c0 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -93,6 +93,7 @@ static int ftrace_verify_code(unsigned long ip, const char *old_code)
 
 	/* Make sure it is what we expect it to be */
 	if (memcmp(cur_code, old_code, MCOUNT_INSN_SIZE) != 0) {
+		ftrace_expected = old_code;
 		WARN_ON(1);
 		return -EINVAL;
 	}
@@ -308,7 +309,7 @@ union ftrace_op_code_union {
 	} __attribute__((packed));
 };
 
-#define RET_SIZE		1 + IS_ENABLED(CONFIG_SLS)
+#define RET_SIZE		(IS_ENABLED(CONFIG_RETPOLINE) ? 5 : 1 + IS_ENABLED(CONFIG_SLS))
 
 static unsigned long
 create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
@@ -321,12 +322,12 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	unsigned long offset;
 	unsigned long npages;
 	unsigned long size;
-	unsigned long retq;
 	unsigned long *ptr;
 	void *trampoline;
 	void *ip;
 	/* 48 8b 15 <offset> is movq <offset>(%rip), %rdx */
 	unsigned const char op_ref[] = { 0x48, 0x8b, 0x15 };
+	unsigned const char retq[] = { RET_INSN_OPCODE, INT3_INSN_OPCODE };
 	union ftrace_op_code_union op_ptr;
 	int ret;
 
@@ -366,10 +367,10 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	ip = trampoline + size;
 
 	/* The trampoline ends with ret(q) */
-	retq = (unsigned long)ftrace_stub;
-	ret = copy_from_kernel_nofault(ip, (void *)retq, RET_SIZE);
-	if (WARN_ON(ret < 0))
-		goto fail;
+	if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+		memcpy(ip, text_gen_insn(JMP32_INSN_OPCODE, ip, &__x86_return_thunk), JMP32_INSN_SIZE);
+	else
+		memcpy(ip, retq, sizeof(retq));
 
 	/* No need to test direct calls on created trampolines */
 	if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index d6af81d1b788..6cc14a835991 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -181,7 +181,6 @@ SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL)
 
 /*
  * This is weak to keep gas from relaxing the jumps.
- * It is also used to copy the RET for trampolines.
  */
 SYM_INNER_LABEL_ALIGN(ftrace_stub, SYM_L_WEAK)
 	UNWIND_HINT_FUNC
@@ -335,7 +334,7 @@ SYM_FUNC_START(ftrace_graph_caller)
 SYM_FUNC_END(ftrace_graph_caller)
 
 SYM_FUNC_START(return_to_handler)
-	subq  $24, %rsp
+	subq  $16, %rsp
 
 	/* Save the return values */
 	movq %rax, (%rsp)
@@ -347,7 +346,19 @@ SYM_FUNC_START(return_to_handler)
 	movq %rax, %rdi
 	movq 8(%rsp), %rdx
 	movq (%rsp), %rax
-	addq $24, %rsp
-	JMP_NOSPEC rdi
+
+	addq $16, %rsp
+	/*
+	 * Jump back to the old return address. This cannot be JMP_NOSPEC rdi
+	 * since IBT would demand that contain ENDBR, which simply isn't so for
+	 * return addresses. Use a retpoline here to keep the RSB balanced.
+	 */
+	ANNOTATE_INTRA_FUNCTION_CALL
+	call .Ldo_rop
+	int3
+.Ldo_rop:
+	mov %rdi, (%rsp)
+	UNWIND_HINT_FUNC
+	RET
 SYM_FUNC_END(return_to_handler)
 #endif
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index de01903c3735..5036104d5470 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -418,6 +418,8 @@ static void __init clear_bss(void)
 {
 	memset(__bss_start, 0,
 	       (unsigned long) __bss_stop - (unsigned long) __bss_start);
+	memset(__brk_base, 0,
+	       (unsigned long) __brk_limit - (unsigned long) __brk_base);
 }
 
 static unsigned long get_cmd_line_ptr(void)
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index eb8656bac99b..9b7acc9c7874 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -23,6 +23,7 @@
 #include <asm/cpufeatures.h>
 #include <asm/percpu.h>
 #include <asm/nops.h>
+#include <asm/nospec-branch.h>
 #include <asm/bootparam.h>
 #include <asm/export.h>
 #include <asm/pgtable_32.h>
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index d8b3ebd2bb85..81f1ae278718 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -312,6 +312,8 @@ SYM_CODE_END(start_cpu0)
 SYM_CODE_START_NOALIGN(vc_boot_ghcb)
 	UNWIND_HINT_IRET_REGS offset=8
 
+	ANNOTATE_UNRET_END
+
 	/* Build pt_regs */
 	PUSH_AND_CLEAR_REGS
 
@@ -369,6 +371,7 @@ SYM_CODE_START(early_idt_handler_array)
 SYM_CODE_END(early_idt_handler_array)
 
 SYM_CODE_START_LOCAL(early_idt_handler_common)
+	ANNOTATE_UNRET_END
 	/*
 	 * The stack is the hardware frame, an error code or zero, and the
 	 * vector number.
@@ -415,6 +418,8 @@ SYM_CODE_END(early_idt_handler_common)
 SYM_CODE_START_NOALIGN(vc_no_ghcb)
 	UNWIND_HINT_IRET_REGS offset=8
 
+	ANNOTATE_UNRET_END
+
 	/* Build pt_regs */
 	PUSH_AND_CLEAR_REGS
 
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index f6727c67ae02..6872f3834668 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -495,7 +495,7 @@ static void kprobe_emulate_jcc(struct kprobe *p, struct pt_regs *regs)
 		match = ((regs->flags & X86_EFLAGS_SF) >> X86_EFLAGS_SF_BIT) ^
 			((regs->flags & X86_EFLAGS_OF) >> X86_EFLAGS_OF_BIT);
 		if (p->ainsn.jcc.type >= 0xe)
-			match = match && (regs->flags & X86_EFLAGS_ZF);
+			match = match || (regs->flags & X86_EFLAGS_ZF);
 	}
 	__kprobe_emulate_jmp(p, regs, (match && !invert) || (!match && invert));
 }
@@ -816,16 +816,20 @@ NOKPROBE_SYMBOL(arch_prepare_kretprobe);
 static void kprobe_post_process(struct kprobe *cur, struct pt_regs *regs,
 			       struct kprobe_ctlblk *kcb)
 {
-	if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) {
-		kcb->kprobe_status = KPROBE_HIT_SSDONE;
-		cur->post_handler(cur, regs, 0);
-	}
-
 	/* Restore back the original saved kprobes variables and continue. */
-	if (kcb->kprobe_status == KPROBE_REENTER)
+	if (kcb->kprobe_status == KPROBE_REENTER) {
+		/* This will restore both kcb and current_kprobe */
 		restore_previous_kprobe(kcb);
-	else
+	} else {
+		/*
+		 * Always update the kcb status because
+		 * reset_curent_kprobe() doesn't update kcb.
+		 */
+		kcb->kprobe_status = KPROBE_HIT_SSDONE;
+		if (cur->post_handler)
+			cur->post_handler(cur, regs, 0);
 		reset_current_kprobe();
+	}
 }
 NOKPROBE_SYMBOL(kprobe_post_process);
 
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 32e546e41629..06b53ea940bf 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -252,7 +252,8 @@ int module_finalize(const Elf_Ehdr *hdr,
 		    struct module *me)
 {
 	const Elf_Shdr *s, *text = NULL, *alt = NULL, *locks = NULL,
-		*para = NULL, *orc = NULL, *orc_ip = NULL;
+		*para = NULL, *orc = NULL, *orc_ip = NULL,
+		*retpolines = NULL, *returns = NULL;
 	char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
 
 	for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
@@ -268,6 +269,10 @@ int module_finalize(const Elf_Ehdr *hdr,
 			orc = s;
 		if (!strcmp(".orc_unwind_ip", secstrings + s->sh_name))
 			orc_ip = s;
+		if (!strcmp(".retpoline_sites", secstrings + s->sh_name))
+			retpolines = s;
+		if (!strcmp(".return_sites", secstrings + s->sh_name))
+			returns = s;
 	}
 
 	/*
@@ -278,6 +283,14 @@ int module_finalize(const Elf_Ehdr *hdr,
 		void *pseg = (void *)para->sh_addr;
 		apply_paravirt(pseg, pseg + para->sh_size);
 	}
+	if (retpolines) {
+		void *rseg = (void *)retpolines->sh_addr;
+		apply_retpolines(rseg, rseg + retpolines->sh_size);
+	}
+	if (returns) {
+		void *rseg = (void *)returns->sh_addr;
+		apply_returns(rseg, rseg + returns->sh_size);
+	}
 	if (alt) {
 		/* patch .altinstructions */
 		void *aseg = (void *)alt->sh_addr;
diff --git a/arch/x86/kernel/pmem.c b/arch/x86/kernel/pmem.c
index 6b07faaa1579..23154d24b117 100644
--- a/arch/x86/kernel/pmem.c
+++ b/arch/x86/kernel/pmem.c
@@ -27,6 +27,11 @@ static __init int register_e820_pmem(void)
 	 * simply here to trigger the module to load on demand.
 	 */
 	pdev = platform_device_alloc("e820_pmem", -1);
-	return platform_device_add(pdev);
+
+	rc = platform_device_add(pdev);
+	if (rc)
+		platform_device_put(pdev);
+
+	return rc;
 }
 device_initcall(register_e820_pmem);
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index f2f733bcb2b9..707376453525 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -584,7 +584,7 @@ static __always_inline void __speculation_ctrl_update(unsigned long tifp,
 	}
 
 	if (updmsr)
-		wrmsrl(MSR_IA32_SPEC_CTRL, msr);
+		write_spec_ctrl_current(msr, false);
 }
 
 static unsigned long speculation_ctrl_update_tif(struct task_struct *tsk)
@@ -805,6 +805,10 @@ static void amd_e400_idle(void)
  */
 static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c)
 {
+	/* User has disallowed the use of MWAIT. Fallback to HALT */
+	if (boot_option_idle_override == IDLE_NOMWAIT)
+		return 0;
+
 	if (c->x86_vendor != X86_VENDOR_INTEL)
 		return 0;
 
@@ -913,9 +917,8 @@ static int __init idle_setup(char *str)
 	} else if (!strcmp(str, "nomwait")) {
 		/*
 		 * If the boot option of "idle=nomwait" is added,
-		 * it means that mwait will be disabled for CPU C2/C3
-		 * states. In such case it won't touch the variable
-		 * of boot_option_idle_override.
+		 * it means that mwait will be disabled for CPU C1/C2/C3
+		 * states.
 		 */
 		boot_option_idle_override = IDLE_NOMWAIT;
 	} else
diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S
index fcc8a7699103..c7c4b1917336 100644
--- a/arch/x86/kernel/relocate_kernel_32.S
+++ b/arch/x86/kernel/relocate_kernel_32.S
@@ -7,10 +7,12 @@
 #include <linux/linkage.h>
 #include <asm/page_types.h>
 #include <asm/kexec.h>
+#include <asm/nospec-branch.h>
 #include <asm/processor-flags.h>
 
 /*
- * Must be relocatable PIC code callable as a C function
+ * Must be relocatable PIC code callable as a C function, in particular
+ * there must be a plain RET and not jump to return thunk.
  */
 
 #define PTR(x) (x << 2)
@@ -91,7 +93,9 @@ SYM_CODE_START_NOALIGN(relocate_kernel)
 	movl    %edi, %eax
 	addl    $(identity_mapped - relocate_kernel), %eax
 	pushl   %eax
-	RET
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
 SYM_CODE_END(relocate_kernel)
 
 SYM_CODE_START_LOCAL_NOALIGN(identity_mapped)
@@ -159,12 +163,15 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped)
 	xorl    %edx, %edx
 	xorl    %esi, %esi
 	xorl    %ebp, %ebp
-	RET
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
 1:
 	popl	%edx
 	movl	CP_PA_SWAP_PAGE(%edi), %esp
 	addl	$PAGE_SIZE, %esp
 2:
+	ANNOTATE_RETPOLINE_SAFE
 	call	*%edx
 
 	/* get the re-entry point of the peer system */
@@ -190,7 +197,9 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped)
 	movl	%edi, %eax
 	addl	$(virtual_mapped - relocate_kernel), %eax
 	pushl	%eax
-	RET
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
 SYM_CODE_END(identity_mapped)
 
 SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped)
@@ -208,7 +217,9 @@ SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped)
 	popl	%edi
 	popl	%esi
 	popl	%ebx
-	RET
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
 SYM_CODE_END(virtual_mapped)
 
 	/* Do the copies */
@@ -271,7 +282,9 @@ SYM_CODE_START_LOCAL_NOALIGN(swap_pages)
 	popl	%edi
 	popl	%ebx
 	popl	%ebp
-	RET
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
 SYM_CODE_END(swap_pages)
 
 	.globl kexec_control_code_size
diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S
index 5019091af059..8a9cea950e39 100644
--- a/arch/x86/kernel/relocate_kernel_64.S
+++ b/arch/x86/kernel/relocate_kernel_64.S
@@ -13,7 +13,8 @@
 #include <asm/unwind_hints.h>
 
 /*
- * Must be relocatable PIC code callable as a C function
+ * Must be relocatable PIC code callable as a C function, in particular
+ * there must be a plain RET and not jump to return thunk.
  */
 
 #define PTR(x) (x << 3)
@@ -104,7 +105,9 @@ SYM_CODE_START_NOALIGN(relocate_kernel)
 	/* jump to identity mapped page */
 	addq	$(identity_mapped - relocate_kernel), %r8
 	pushq	%r8
-	RET
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
 SYM_CODE_END(relocate_kernel)
 
 SYM_CODE_START_LOCAL_NOALIGN(identity_mapped)
@@ -191,7 +194,9 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped)
 	xorl	%r14d, %r14d
 	xorl	%r15d, %r15d
 
-	RET
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
 
 1:
 	popq	%rdx
@@ -210,7 +215,9 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped)
 	call	swap_pages
 	movq	$virtual_mapped, %rax
 	pushq	%rax
-	RET
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
 SYM_CODE_END(identity_mapped)
 
 SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped)
@@ -231,7 +238,9 @@ SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped)
 	popq	%r12
 	popq	%rbp
 	popq	%rbx
-	RET
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
 SYM_CODE_END(virtual_mapped)
 
 	/* Do the copies */
@@ -288,7 +297,9 @@ SYM_CODE_START_LOCAL_NOALIGN(swap_pages)
 	lea	PAGE_SIZE(%rax), %rsi
 	jmp	0b
 3:
-	RET
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
 SYM_CODE_END(swap_pages)
 
 	.globl kexec_control_code_size
diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index 3ec2cb881eef..2fc4f96702e6 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -12,13 +12,21 @@ enum insn_type {
 };
 
 /*
+ * ud1 %esp, %ecx - a 3 byte #UD that is unique to trampolines, chosen such
+ * that there is no false-positive trampoline identification while also being a
+ * speculation stop.
+ */
+static const u8 tramp_ud[] = { 0x0f, 0xb9, 0xcc };
+
+/*
  * cs cs cs xorl %eax, %eax - a single 5 byte instruction that clears %[er]ax
  */
 static const u8 xor5rax[] = { 0x2e, 0x2e, 0x2e, 0x31, 0xc0 };
 
 static const u8 retinsn[] = { RET_INSN_OPCODE, 0xcc, 0xcc, 0xcc, 0xcc };
 
-static void __ref __static_call_transform(void *insn, enum insn_type type, void *func)
+static void __ref __static_call_transform(void *insn, enum insn_type type,
+					  void *func, bool modinit)
 {
 	const void *emulate = NULL;
 	int size = CALL_INSN_SIZE;
@@ -43,14 +51,17 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, void
 		break;
 
 	case RET:
-		code = &retinsn;
+		if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+			code = text_gen_insn(JMP32_INSN_OPCODE, insn, &__x86_return_thunk);
+		else
+			code = &retinsn;
 		break;
 	}
 
 	if (memcmp(insn, code, size) == 0)
 		return;
 
-	if (unlikely(system_state == SYSTEM_BOOTING))
+	if (system_state == SYSTEM_BOOTING || modinit)
 		return text_poke_early(insn, code, size);
 
 	text_poke_bp(insn, code, size, emulate);
@@ -98,14 +109,42 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail)
 
 	if (tramp) {
 		__static_call_validate(tramp, true);
-		__static_call_transform(tramp, __sc_insn(!func, true), func);
+		__static_call_transform(tramp, __sc_insn(!func, true), func, false);
 	}
 
 	if (IS_ENABLED(CONFIG_HAVE_STATIC_CALL_INLINE) && site) {
 		__static_call_validate(site, tail);
-		__static_call_transform(site, __sc_insn(!func, tail), func);
+		__static_call_transform(site, __sc_insn(!func, tail), func, false);
 	}
 
 	mutex_unlock(&text_mutex);
 }
 EXPORT_SYMBOL_GPL(arch_static_call_transform);
+
+#ifdef CONFIG_RETHUNK
+/*
+ * This is called by apply_returns() to fix up static call trampolines,
+ * specifically ARCH_DEFINE_STATIC_CALL_NULL_TRAMP which is recorded as
+ * having a return trampoline.
+ *
+ * The problem is that static_call() is available before determining
+ * X86_FEATURE_RETHUNK and, by implication, running alternatives.
+ *
+ * This means that __static_call_transform() above can have overwritten the
+ * return trampoline and we now need to fix things up to be consistent.
+ */
+bool __static_call_fixup(void *tramp, u8 op, void *dest)
+{
+	if (memcmp(tramp+5, tramp_ud, 3)) {
+		/* Not a trampoline site, not our problem. */
+		return false;
+	}
+
+	mutex_lock(&text_mutex);
+	if (op == RET_INSN_OPCODE || dest == &__x86_return_thunk)
+		__static_call_transform(tramp, RET, NULL, true);
+	mutex_unlock(&text_mutex);
+
+	return true;
+}
+#endif
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 928e1ac820e6..ca47080e3774 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -762,14 +762,10 @@ sync:
 }
 #endif
 
-struct bad_iret_stack {
-	void *error_entry_ret;
-	struct pt_regs regs;
-};
-
-asmlinkage __visible noinstr
-struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s)
+asmlinkage __visible noinstr struct pt_regs *fixup_bad_iret(struct pt_regs *bad_regs)
 {
+	struct pt_regs tmp, *new_stack;
+
 	/*
 	 * This is called from entry_64.S early in handling a fault
 	 * caused by a bad iret to user mode.  To handle the fault
@@ -778,19 +774,18 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s)
 	 * just below the IRET frame) and we want to pretend that the
 	 * exception came from the IRET target.
 	 */
-	struct bad_iret_stack tmp, *new_stack =
-		(struct bad_iret_stack *)__this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1;
+	new_stack = (struct pt_regs *)__this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1;
 
 	/* Copy the IRET target to the temporary storage. */
-	__memcpy(&tmp.regs.ip, (void *)s->regs.sp, 5*8);
+	__memcpy(&tmp.ip, (void *)bad_regs->sp, 5*8);
 
 	/* Copy the remainder of the stack from the current stack. */
-	__memcpy(&tmp, s, offsetof(struct bad_iret_stack, regs.ip));
+	__memcpy(&tmp, bad_regs, offsetof(struct pt_regs, ip));
 
 	/* Update the entry stack */
 	__memcpy(new_stack, &tmp, sizeof(tmp));
 
-	BUG_ON(!user_mode(&new_stack->regs));
+	BUG_ON(!user_mode(new_stack));
 	return new_stack;
 }
 #endif
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index a1202536fc57..3423aaea4ad8 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -93,22 +93,27 @@ static struct orc_entry *orc_find(unsigned long ip);
 static struct orc_entry *orc_ftrace_find(unsigned long ip)
 {
 	struct ftrace_ops *ops;
-	unsigned long caller;
+	unsigned long tramp_addr, offset;
 
 	ops = ftrace_ops_trampoline(ip);
 	if (!ops)
 		return NULL;
 
+	/* Set tramp_addr to the start of the code copied by the trampoline */
 	if (ops->flags & FTRACE_OPS_FL_SAVE_REGS)
-		caller = (unsigned long)ftrace_regs_call;
+		tramp_addr = (unsigned long)ftrace_regs_caller;
 	else
-		caller = (unsigned long)ftrace_call;
+		tramp_addr = (unsigned long)ftrace_caller;
+
+	/* Now place tramp_addr to the location within the trampoline ip is at */
+	offset = ip - ops->trampoline;
+	tramp_addr += offset;
 
 	/* Prevent unlikely recursion */
-	if (ip == caller)
+	if (ip == tramp_addr)
 		return NULL;
 
-	return orc_find(caller);
+	return orc_find(tramp_addr);
 }
 #else
 static struct orc_entry *orc_ftrace_find(unsigned long ip)
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index efd9e9ea17f2..c1efcd194ad7 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -142,7 +142,7 @@ SECTIONS
 
 #ifdef CONFIG_RETPOLINE
 		__indirect_thunk_start = .;
-		*(.text.__x86.indirect_thunk)
+		*(.text.__x86.*)
 		__indirect_thunk_end = .;
 #endif
 	} :text =0xcccc
@@ -272,6 +272,27 @@ SECTIONS
 		__parainstructions_end = .;
 	}
 
+#ifdef CONFIG_RETPOLINE
+	/*
+	 * List of instructions that call/jmp/jcc to retpoline thunks
+	 * __x86_indirect_thunk_*(). These instructions can be patched along
+	 * with alternatives, after which the section can be freed.
+	 */
+	. = ALIGN(8);
+	.retpoline_sites : AT(ADDR(.retpoline_sites) - LOAD_OFFSET) {
+		__retpoline_sites = .;
+		*(.retpoline_sites)
+		__retpoline_sites_end = .;
+	}
+
+	. = ALIGN(8);
+	.return_sites : AT(ADDR(.return_sites) - LOAD_OFFSET) {
+		__return_sites = .;
+		*(.return_sites)
+		__return_sites_end = .;
+	}
+#endif
+
 	/*
 	 * struct alt_inst entries. From the header (alternative.h):
 	 * "Alternative instructions for different CPU types or capabilities"
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 82eff14bd064..8496ffc67c32 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -187,9 +187,6 @@
 #define X8(x...) X4(x), X4(x)
 #define X16(x...) X8(x), X8(x)
 
-#define NR_FASTOP (ilog2(sizeof(ulong)) + 1)
-#define FASTOP_SIZE 8
-
 struct opcode {
 	u64 flags : 56;
 	u64 intercept : 8;
@@ -303,9 +300,15 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt)
  * Moreover, they are all exactly FASTOP_SIZE bytes long, so functions for
  * different operand sizes can be reached by calculation, rather than a jump
  * table (which would be bigger than the code).
+ *
+ * The 16 byte alignment, considering 5 bytes for the RET thunk, 3 for ENDBR
+ * and 1 for the straight line speculation INT3, leaves 7 bytes for the
+ * body of the function.  Currently none is larger than 4.
  */
 static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop);
 
+#define FASTOP_SIZE	16
+
 #define __FOP_FUNC(name) \
 	".align " __stringify(FASTOP_SIZE) " \n\t" \
 	".type " name ", @function \n\t" \
@@ -321,13 +324,15 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop);
 #define FOP_RET(name) \
 	__FOP_RET(#name)
 
-#define FOP_START(op) \
+#define __FOP_START(op, align) \
 	extern void em_##op(struct fastop *fake); \
 	asm(".pushsection .text, \"ax\" \n\t" \
 	    ".global em_" #op " \n\t" \
-	    ".align " __stringify(FASTOP_SIZE) " \n\t" \
+	    ".align " __stringify(align) " \n\t" \
 	    "em_" #op ":\n\t"
 
+#define FOP_START(op) __FOP_START(op, FASTOP_SIZE)
+
 #define FOP_END \
 	    ".popsection")
 
@@ -431,29 +436,25 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop);
 /*
  * Depending on .config the SETcc functions look like:
  *
- * SETcc %al   [3 bytes]
- * RET         [1 byte]
- * INT3        [1 byte; CONFIG_SLS]
- *
- * Which gives possible sizes 4 or 5.  When rounded up to the
- * next power-of-two alignment they become 4 or 8.
+ * SETcc %al			[3 bytes]
+ * RET | JMP __x86_return_thunk	[1,5 bytes; CONFIG_RETHUNK]
+ * INT3				[1 byte; CONFIG_SLS]
  */
-#define SETCC_LENGTH	(4 + IS_ENABLED(CONFIG_SLS))
-#define SETCC_ALIGN	(4 << IS_ENABLED(CONFIG_SLS))
-static_assert(SETCC_LENGTH <= SETCC_ALIGN);
+#define SETCC_ALIGN	16
 
 #define FOP_SETCC(op) \
 	".align " __stringify(SETCC_ALIGN) " \n\t" \
 	".type " #op ", @function \n\t" \
 	#op ": \n\t" \
 	#op " %al \n\t" \
-	__FOP_RET(#op)
+	__FOP_RET(#op) \
+	".skip " __stringify(SETCC_ALIGN) " - (.-" #op "), 0xcc \n\t"
 
 asm(".pushsection .fixup, \"ax\"\n"
     "kvm_fastop_exception: xor %esi, %esi; " ASM_RET
     ".popsection");
 
-FOP_START(setcc)
+__FOP_START(setcc, SETCC_ALIGN)
 FOP_SETCC(seto)
 FOP_SETCC(setno)
 FOP_SETCC(setc)
@@ -1668,16 +1669,6 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 	case VCPU_SREG_TR:
 		if (seg_desc.s || (seg_desc.type != 1 && seg_desc.type != 9))
 			goto exception;
-		if (!seg_desc.p) {
-			err_vec = NP_VECTOR;
-			goto exception;
-		}
-		old_desc = seg_desc;
-		seg_desc.type |= 2; /* busy */
-		ret = ctxt->ops->cmpxchg_emulated(ctxt, desc_addr, &old_desc, &seg_desc,
-						  sizeof(seg_desc), &ctxt->exception);
-		if (ret != X86EMUL_CONTINUE)
-			return ret;
 		break;
 	case VCPU_SREG_LDTR:
 		if (seg_desc.s || seg_desc.type != 2)
@@ -1715,8 +1706,17 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 		if (ret != X86EMUL_CONTINUE)
 			return ret;
 		if (emul_is_noncanonical_address(get_desc_base(&seg_desc) |
-				((u64)base3 << 32), ctxt))
-			return emulate_gp(ctxt, 0);
+						 ((u64)base3 << 32), ctxt))
+			return emulate_gp(ctxt, err_code);
+	}
+
+	if (seg == VCPU_SREG_TR) {
+		old_desc = seg_desc;
+		seg_desc.type |= 2; /* busy */
+		ret = ctxt->ops->cmpxchg_emulated(ctxt, desc_addr, &old_desc, &seg_desc,
+						  sizeof(seg_desc), &ctxt->exception);
+		if (ret != X86EMUL_CONTINUE)
+			return ret;
 	}
 load:
 	ctxt->ops->set_segment(ctxt, selector, &seg_desc, base3, seg);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 3417405077ad..f267cca9fe09 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -6115,7 +6115,7 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp)
  * nx_huge_pages needs to be resolved to true/false when kvm.ko is loaded, as
  * its default value of -1 is technically undefined behavior for a boolean.
  */
-void kvm_mmu_x86_module_init(void)
+void __init kvm_mmu_x86_module_init(void)
 {
 	if (nx_huge_pages == -1)
 		__set_nx_huge_pages(get_nx_auto_mode());
diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c
index 21427e84a82e..630ae70bb6bd 100644
--- a/arch/x86/kvm/mmu/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
@@ -36,8 +36,8 @@ int kvm_page_track_create_memslot(struct kvm_memory_slot *slot,
 
 	for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) {
 		slot->arch.gfn_track[i] =
-			kvcalloc(npages, sizeof(*slot->arch.gfn_track[i]),
-				 GFP_KERNEL_ACCOUNT);
+			__vcalloc(npages, sizeof(*slot->arch.gfn_track[i]),
+				  GFP_KERNEL_ACCOUNT);
 		if (!slot->arch.gfn_track[i])
 			goto track_free;
 	}
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 853780eb033b..6c2bb60ccd88 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -1098,13 +1098,8 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range,
 				 bool flush)
 {
-	struct kvm_mmu_page *root;
-
-	for_each_tdp_mmu_root(kvm, root, range->slot->as_id)
-		flush = zap_gfn_range(kvm, root, range->start, range->end,
-				      range->may_block, flush, false);
-
-	return flush;
+	return __kvm_tdp_mmu_zap_gfn_range(kvm, range->slot->as_id, range->start,
+					   range->end, range->may_block, flush);
 }
 
 typedef bool (*tdp_handler_t)(struct kvm *kvm, struct tdp_iter *iter,
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 993daa6fb128..78f1138753e6 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -275,7 +275,8 @@ static bool nested_vmcb_check_cr3_cr4(struct kvm_vcpu *vcpu,
 			return false;
 	}
 
-	if (CC(!kvm_is_valid_cr4(vcpu, save->cr4)))
+	/* Note, SVM doesn't have any additional restrictions on CR4. */
+	if (CC(!__kvm_is_valid_cr4(vcpu, save->cr4)))
 		return false;
 
 	return true;
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 4a4dc105552e..eeedcb3d40e8 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -832,7 +832,7 @@ static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr,
 
 	/* If source buffer is not aligned then use an intermediate buffer */
 	if (!IS_ALIGNED((unsigned long)vaddr, 16)) {
-		src_tpage = alloc_page(GFP_KERNEL);
+		src_tpage = alloc_page(GFP_KERNEL_ACCOUNT);
 		if (!src_tpage)
 			return -ENOMEM;
 
@@ -853,7 +853,7 @@ static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr,
 	if (!IS_ALIGNED((unsigned long)dst_vaddr, 16) || !IS_ALIGNED(size, 16)) {
 		int dst_offset;
 
-		dst_tpage = alloc_page(GFP_KERNEL);
+		dst_tpage = alloc_page(GFP_KERNEL_ACCOUNT);
 		if (!dst_tpage) {
 			ret = -ENOMEM;
 			goto e_free;
@@ -2037,6 +2037,14 @@ static void sev_flush_guest_memory(struct vcpu_svm *svm, void *va,
 	wbinvd_on_all_cpus();
 }
 
+void sev_guest_memory_reclaimed(struct kvm *kvm)
+{
+	if (!sev_guest(kvm))
+		return;
+
+	wbinvd_on_all_cpus();
+}
+
 void sev_free_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm;
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 26f2da1590ed..49bb3db2761a 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -394,6 +394,10 @@ static void svm_queue_exception(struct kvm_vcpu *vcpu)
 		 */
 		(void)skip_emulated_instruction(vcpu);
 		rip = kvm_rip_read(vcpu);
+
+		if (boot_cpu_has(X86_FEATURE_NRIPS))
+			svm->vmcb->control.next_rip = rip;
+
 		svm->int3_rip = rip + svm->vmcb->save.cs.base;
 		svm->int3_injected = rip - old_rip;
 	}
@@ -3417,8 +3421,6 @@ static void svm_set_irq(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	BUG_ON(!(gif_set(svm)));
-
 	trace_kvm_inj_virq(vcpu->arch.interrupt.nr);
 	++vcpu->stat.irq_injections;
 
@@ -3682,6 +3684,18 @@ static void svm_complete_interrupts(struct kvm_vcpu *vcpu)
 	vector = exitintinfo & SVM_EXITINTINFO_VEC_MASK;
 	type = exitintinfo & SVM_EXITINTINFO_TYPE_MASK;
 
+	/*
+	 * If NextRIP isn't enabled, KVM must manually advance RIP prior to
+	 * injecting the soft exception/interrupt.  That advancement needs to
+	 * be unwound if vectoring didn't complete.  Note, the new event may
+	 * not be the injected event, e.g. if KVM injected an INTn, the INTn
+	 * hit a #NP in the guest, and the #NP encountered a #PF, the #NP will
+	 * be the reported vectored event, but RIP still needs to be unwound.
+	 */
+	if (int3_injected && type == SVM_EXITINTINFO_TYPE_EXEPT &&
+	   kvm_is_linear_rip(vcpu, svm->int3_rip))
+		kvm_rip_write(vcpu, kvm_rip_read(vcpu) - int3_injected);
+
 	switch (type) {
 	case SVM_EXITINTINFO_TYPE_NMI:
 		vcpu->arch.nmi_injected = true;
@@ -3695,16 +3709,11 @@ static void svm_complete_interrupts(struct kvm_vcpu *vcpu)
 
 		/*
 		 * In case of software exceptions, do not reinject the vector,
-		 * but re-execute the instruction instead. Rewind RIP first
-		 * if we emulated INT3 before.
+		 * but re-execute the instruction instead.
 		 */
-		if (kvm_exception_is_soft(vector)) {
-			if (vector == BP_VECTOR && int3_injected &&
-			    kvm_is_linear_rip(vcpu, svm->int3_rip))
-				kvm_rip_write(vcpu,
-					      kvm_rip_read(vcpu) - int3_injected);
+		if (kvm_exception_is_soft(vector))
 			break;
-		}
+
 		if (exitintinfo & SVM_EXITINTINFO_VALID_ERR) {
 			u32 err = svm->vmcb->control.exit_int_info_err;
 			kvm_requeue_exception_e(vcpu, vector, err);
@@ -4263,6 +4272,8 @@ out:
 
 static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu)
 {
+	if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_INTR)
+		vcpu->arch.at_instruction_boundary = true;
 }
 
 static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu)
@@ -4667,6 +4678,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.mem_enc_op = svm_mem_enc_op,
 	.mem_enc_reg_region = svm_register_enc_region,
 	.mem_enc_unreg_region = svm_unregister_enc_region,
+	.guest_memory_reclaimed = sev_guest_memory_reclaimed,
 
 	.vm_copy_enc_context_from = svm_vm_copy_asid_from,
 
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index cf2d8365aeb4..7004f356edf9 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -555,6 +555,8 @@ int svm_register_enc_region(struct kvm *kvm,
 int svm_unregister_enc_region(struct kvm *kvm,
 			      struct kvm_enc_region *range);
 int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd);
+void sev_guest_memory_reclaimed(struct kvm *kvm);
+
 void pre_sev_run(struct vcpu_svm *svm, int cpu);
 void __init sev_set_cpu_caps(void);
 void __init sev_hardware_setup(void);
diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S
index dfaeb47fcf2a..723f8534986c 100644
--- a/arch/x86/kvm/svm/vmenter.S
+++ b/arch/x86/kvm/svm/vmenter.S
@@ -111,6 +111,15 @@ SYM_FUNC_START(__svm_vcpu_run)
 #endif
 
 	/*
+	 * Mitigate RETBleed for AMD/Hygon Zen uarch. RET should be
+	 * untrained as soon as we exit the VM and are back to the
+	 * kernel. This should be done before re-enabling interrupts
+	 * because interrupt handlers won't sanitize 'ret' if the return is
+	 * from the kernel.
+	 */
+	UNTRAIN_RET
+
+	/*
 	 * Clear all general purpose registers except RSP and RAX to prevent
 	 * speculative use of the guest's values, even those that are reloaded
 	 * via the stack.  In theory, an L1 cache miss when restoring registers
@@ -190,6 +199,15 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run)
 	FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE
 #endif
 
+	/*
+	 * Mitigate RETBleed for AMD/Hygon Zen uarch. RET should be
+	 * untrained as soon as we exit the VM and are back to the
+	 * kernel. This should be done before re-enabling interrupts
+	 * because interrupt handlers won't sanitize RET if the return is
+	 * from the kernel.
+	 */
+	UNTRAIN_RET
+
 	pop %_ASM_BX
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index f7bdb62d6cec..61d601387058 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -1217,7 +1217,7 @@ static int vmx_restore_vmx_basic(struct vcpu_vmx *vmx, u64 data)
 		BIT_ULL(49) | BIT_ULL(54) | BIT_ULL(55) |
 		/* reserved */
 		BIT_ULL(31) | GENMASK_ULL(47, 45) | GENMASK_ULL(63, 56);
-	u64 vmx_basic = vmx->nested.msrs.basic;
+	u64 vmx_basic = vmcs_config.nested.basic;
 
 	if (!is_bitwise_subset(vmx_basic, data, feature_and_reserved))
 		return -EINVAL;
@@ -1240,36 +1240,42 @@ static int vmx_restore_vmx_basic(struct vcpu_vmx *vmx, u64 data)
 	return 0;
 }
 
-static int
-vmx_restore_control_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data)
+static void vmx_get_control_msr(struct nested_vmx_msrs *msrs, u32 msr_index,
+				u32 **low, u32 **high)
 {
-	u64 supported;
-	u32 *lowp, *highp;
-
 	switch (msr_index) {
 	case MSR_IA32_VMX_TRUE_PINBASED_CTLS:
-		lowp = &vmx->nested.msrs.pinbased_ctls_low;
-		highp = &vmx->nested.msrs.pinbased_ctls_high;
+		*low = &msrs->pinbased_ctls_low;
+		*high = &msrs->pinbased_ctls_high;
 		break;
 	case MSR_IA32_VMX_TRUE_PROCBASED_CTLS:
-		lowp = &vmx->nested.msrs.procbased_ctls_low;
-		highp = &vmx->nested.msrs.procbased_ctls_high;
+		*low = &msrs->procbased_ctls_low;
+		*high = &msrs->procbased_ctls_high;
 		break;
 	case MSR_IA32_VMX_TRUE_EXIT_CTLS:
-		lowp = &vmx->nested.msrs.exit_ctls_low;
-		highp = &vmx->nested.msrs.exit_ctls_high;
+		*low = &msrs->exit_ctls_low;
+		*high = &msrs->exit_ctls_high;
 		break;
 	case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
-		lowp = &vmx->nested.msrs.entry_ctls_low;
-		highp = &vmx->nested.msrs.entry_ctls_high;
+		*low = &msrs->entry_ctls_low;
+		*high = &msrs->entry_ctls_high;
 		break;
 	case MSR_IA32_VMX_PROCBASED_CTLS2:
-		lowp = &vmx->nested.msrs.secondary_ctls_low;
-		highp = &vmx->nested.msrs.secondary_ctls_high;
+		*low = &msrs->secondary_ctls_low;
+		*high = &msrs->secondary_ctls_high;
 		break;
 	default:
 		BUG();
 	}
+}
+
+static int
+vmx_restore_control_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data)
+{
+	u32 *lowp, *highp;
+	u64 supported;
+
+	vmx_get_control_msr(&vmcs_config.nested, msr_index, &lowp, &highp);
 
 	supported = vmx_control_msr(*lowp, *highp);
 
@@ -1281,6 +1287,7 @@ vmx_restore_control_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data)
 	if (!is_bitwise_subset(supported, data, GENMASK_ULL(63, 32)))
 		return -EINVAL;
 
+	vmx_get_control_msr(&vmx->nested.msrs, msr_index, &lowp, &highp);
 	*lowp = data;
 	*highp = data >> 32;
 	return 0;
@@ -1294,10 +1301,8 @@ static int vmx_restore_vmx_misc(struct vcpu_vmx *vmx, u64 data)
 		BIT_ULL(28) | BIT_ULL(29) | BIT_ULL(30) |
 		/* reserved */
 		GENMASK_ULL(13, 9) | BIT_ULL(31);
-	u64 vmx_misc;
-
-	vmx_misc = vmx_control_msr(vmx->nested.msrs.misc_low,
-				   vmx->nested.msrs.misc_high);
+	u64 vmx_misc = vmx_control_msr(vmcs_config.nested.misc_low,
+				       vmcs_config.nested.misc_high);
 
 	if (!is_bitwise_subset(vmx_misc, data, feature_and_reserved_bits))
 		return -EINVAL;
@@ -1325,10 +1330,8 @@ static int vmx_restore_vmx_misc(struct vcpu_vmx *vmx, u64 data)
 
 static int vmx_restore_vmx_ept_vpid_cap(struct vcpu_vmx *vmx, u64 data)
 {
-	u64 vmx_ept_vpid_cap;
-
-	vmx_ept_vpid_cap = vmx_control_msr(vmx->nested.msrs.ept_caps,
-					   vmx->nested.msrs.vpid_caps);
+	u64 vmx_ept_vpid_cap = vmx_control_msr(vmcs_config.nested.ept_caps,
+					       vmcs_config.nested.vpid_caps);
 
 	/* Every bit is either reserved or a feature bit. */
 	if (!is_bitwise_subset(vmx_ept_vpid_cap, data, -1ULL))
@@ -1339,20 +1342,21 @@ static int vmx_restore_vmx_ept_vpid_cap(struct vcpu_vmx *vmx, u64 data)
 	return 0;
 }
 
-static int vmx_restore_fixed0_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data)
+static u64 *vmx_get_fixed0_msr(struct nested_vmx_msrs *msrs, u32 msr_index)
 {
-	u64 *msr;
-
 	switch (msr_index) {
 	case MSR_IA32_VMX_CR0_FIXED0:
-		msr = &vmx->nested.msrs.cr0_fixed0;
-		break;
+		return &msrs->cr0_fixed0;
 	case MSR_IA32_VMX_CR4_FIXED0:
-		msr = &vmx->nested.msrs.cr4_fixed0;
-		break;
+		return &msrs->cr4_fixed0;
 	default:
 		BUG();
 	}
+}
+
+static int vmx_restore_fixed0_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data)
+{
+	const u64 *msr = vmx_get_fixed0_msr(&vmcs_config.nested, msr_index);
 
 	/*
 	 * 1 bits (which indicates bits which "must-be-1" during VMX operation)
@@ -1361,7 +1365,7 @@ static int vmx_restore_fixed0_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data)
 	if (!is_bitwise_subset(data, *msr, -1ULL))
 		return -EINVAL;
 
-	*msr = data;
+	*vmx_get_fixed0_msr(&vmx->nested.msrs, msr_index) = data;
 	return 0;
 }
 
@@ -1422,7 +1426,7 @@ int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
 		vmx->nested.msrs.vmcs_enum = data;
 		return 0;
 	case MSR_IA32_VMX_VMFUNC:
-		if (data & ~vmx->nested.msrs.vmfunc_controls)
+		if (data & ~vmcs_config.nested.vmfunc_controls)
 			return -EINVAL;
 		vmx->nested.msrs.vmfunc_controls = data;
 		return 0;
@@ -2269,7 +2273,6 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0
 				  SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
 				  SECONDARY_EXEC_APIC_REGISTER_VIRT |
 				  SECONDARY_EXEC_ENABLE_VMFUNC |
-				  SECONDARY_EXEC_TSC_SCALING |
 				  SECONDARY_EXEC_DESC);
 
 		if (nested_cpu_has(vmcs12,
@@ -2608,6 +2611,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 		vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested;
 
 	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) &&
+	    intel_pmu_has_perf_global_ctrl(vcpu_to_pmu(vcpu)) &&
 	    WARN_ON_ONCE(kvm_set_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL,
 				     vmcs12->guest_ia32_perf_global_ctrl))) {
 		*entry_failure_code = ENTRY_FAIL_DEFAULT;
@@ -3077,7 +3081,7 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu)
 	}
 
 	vm_fail = __vmx_vcpu_run(vmx, (unsigned long *)&vcpu->arch.regs,
-				 vmx->loaded_vmcs->launched);
+				 __vmx_vcpu_run_flags(vmx));
 
 	if (vmx->msr_autoload.host.nr)
 		vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
@@ -3364,10 +3368,12 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
 	if (likely(!evaluate_pending_interrupts) && kvm_vcpu_apicv_active(vcpu))
 		evaluate_pending_interrupts |= vmx_has_apicv_interrupt(vcpu);
 
-	if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS))
+	if (!vmx->nested.nested_run_pending ||
+	    !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS))
 		vmx->nested.vmcs01_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
 	if (kvm_mpx_supported() &&
-		!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))
+	    (!vmx->nested.nested_run_pending ||
+	     !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)))
 		vmx->nested.vmcs01_guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS);
 
 	/*
@@ -4324,7 +4330,8 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 		vmcs_write64(GUEST_IA32_PAT, vmcs12->host_ia32_pat);
 		vcpu->arch.pat = vmcs12->host_ia32_pat;
 	}
-	if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
+	if ((vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) &&
+	    intel_pmu_has_perf_global_ctrl(vcpu_to_pmu(vcpu)))
 		WARN_ON_ONCE(kvm_set_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL,
 					 vmcs12->host_ia32_perf_global_ctrl));
 
@@ -4946,20 +4953,25 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 		| FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX;
 
 	/*
-	 * The Intel VMX Instruction Reference lists a bunch of bits that are
-	 * prerequisite to running VMXON, most notably cr4.VMXE must be set to
-	 * 1 (see vmx_is_valid_cr4() for when we allow the guest to set this).
-	 * Otherwise, we should fail with #UD.  But most faulting conditions
-	 * have already been checked by hardware, prior to the VM-exit for
-	 * VMXON.  We do test guest cr4.VMXE because processor CR4 always has
-	 * that bit set to 1 in non-root mode.
+	 * Note, KVM cannot rely on hardware to perform the CR0/CR4 #UD checks
+	 * that have higher priority than VM-Exit (see Intel SDM's pseudocode
+	 * for VMXON), as KVM must load valid CR0/CR4 values into hardware while
+	 * running the guest, i.e. KVM needs to check the _guest_ values.
+	 *
+	 * Rely on hardware for the other two pre-VM-Exit checks, !VM86 and
+	 * !COMPATIBILITY modes.  KVM may run the guest in VM86 to emulate Real
+	 * Mode, but KVM will never take the guest out of those modes.
 	 */
-	if (!kvm_read_cr4_bits(vcpu, X86_CR4_VMXE)) {
+	if (!nested_host_cr0_valid(vcpu, kvm_read_cr0(vcpu)) ||
+	    !nested_host_cr4_valid(vcpu, kvm_read_cr4(vcpu))) {
 		kvm_queue_exception(vcpu, UD_VECTOR);
 		return 1;
 	}
 
-	/* CPL=0 must be checked manually. */
+	/*
+	 * CPL=0 and all other checks that are lower priority than VM-Exit must
+	 * be checked manually.
+	 */
 	if (vmx_get_cpl(vcpu)) {
 		kvm_inject_gp(vcpu, 0);
 		return 1;
@@ -6726,6 +6738,9 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
 	rdmsrl(MSR_IA32_VMX_CR0_FIXED1, msrs->cr0_fixed1);
 	rdmsrl(MSR_IA32_VMX_CR4_FIXED1, msrs->cr4_fixed1);
 
+	if (vmx_umip_emulated())
+		msrs->cr4_fixed1 |= X86_CR4_UMIP;
+
 	msrs->vmcs_enum = nested_vmx_calc_vmcs_enum_msr();
 }
 
diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h
index b69a80f43b37..2d0ac8a86d4a 100644
--- a/arch/x86/kvm/vmx/nested.h
+++ b/arch/x86/kvm/vmx/nested.h
@@ -280,7 +280,8 @@ static inline bool nested_cr4_valid(struct kvm_vcpu *vcpu, unsigned long val)
 	u64 fixed0 = to_vmx(vcpu)->nested.msrs.cr4_fixed0;
 	u64 fixed1 = to_vmx(vcpu)->nested.msrs.cr4_fixed1;
 
-	return fixed_bits_valid(val, fixed0, fixed1);
+	return fixed_bits_valid(val, fixed0, fixed1) &&
+	       __kvm_is_valid_cr4(vcpu, val);
 }
 
 /* No difference in the restrictions on guest and host CR4 in VMX operation. */
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index e7275ce15a8b..e624a39365ec 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -104,6 +104,9 @@ static bool intel_pmc_is_enabled(struct kvm_pmc *pmc)
 {
 	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
 
+	if (!intel_pmu_has_perf_global_ctrl(pmu))
+		return true;
+
 	return test_bit(pmc->idx, (unsigned long *)&pmu->global_ctrl);
 }
 
@@ -219,7 +222,7 @@ static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
 	case MSR_CORE_PERF_GLOBAL_STATUS:
 	case MSR_CORE_PERF_GLOBAL_CTRL:
 	case MSR_CORE_PERF_GLOBAL_OVF_CTRL:
-		ret = pmu->version > 1;
+		return intel_pmu_has_perf_global_ctrl(pmu);
 		break;
 	default:
 		ret = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0) ||
@@ -402,7 +405,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_CORE_PERF_FIXED_CTR_CTRL:
 		if (pmu->fixed_ctr_ctrl == data)
 			return 0;
-		if (!(data & 0xfffffffffffff444ull)) {
+		if (!(data & pmu->fixed_ctr_ctrl_mask)) {
 			reprogram_fixed_counters(pmu, data);
 			return 0;
 		}
@@ -472,6 +475,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 	struct kvm_cpuid_entry2 *entry;
 	union cpuid10_eax eax;
 	union cpuid10_edx edx;
+	int i;
 
 	pmu->nr_arch_gp_counters = 0;
 	pmu->nr_arch_fixed_counters = 0;
@@ -480,6 +484,9 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 	pmu->version = 0;
 	pmu->reserved_bits = 0xffffffff00200000ull;
 	pmu->raw_event_mask = X86_RAW_EVENT_MASK;
+	pmu->global_ctrl_mask = ~0ull;
+	pmu->global_ovf_ctrl_mask = ~0ull;
+	pmu->fixed_ctr_ctrl_mask = ~0ull;
 
 	entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
 	if (!entry)
@@ -513,6 +520,8 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 			((u64)1 << edx.split.bit_width_fixed) - 1;
 	}
 
+	for (i = 0; i < pmu->nr_arch_fixed_counters; i++)
+		pmu->fixed_ctr_ctrl_mask &= ~(0xbull << (i * 4));
 	pmu->global_ctrl = ((1ull << pmu->nr_arch_gp_counters) - 1) |
 		(((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED);
 	pmu->global_ctrl_mask = ~pmu->global_ctrl;
diff --git a/arch/x86/kvm/vmx/run_flags.h b/arch/x86/kvm/vmx/run_flags.h
new file mode 100644
index 000000000000..edc3f16cc189
--- /dev/null
+++ b/arch/x86/kvm/vmx/run_flags.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __KVM_X86_VMX_RUN_FLAGS_H
+#define __KVM_X86_VMX_RUN_FLAGS_H
+
+#define VMX_RUN_VMRESUME	(1 << 0)
+#define VMX_RUN_SAVE_SPEC_CTRL	(1 << 1)
+
+#endif /* __KVM_X86_VMX_RUN_FLAGS_H */
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index 435c187927c4..982138bebb70 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -5,6 +5,7 @@
 #include <asm/kvm_vcpu_regs.h>
 #include <asm/nospec-branch.h>
 #include <asm/segment.h>
+#include "run_flags.h"
 
 #define WORD_SIZE (BITS_PER_LONG / 8)
 
@@ -31,72 +32,11 @@
 .section .noinstr.text, "ax"
 
 /**
- * vmx_vmenter - VM-Enter the current loaded VMCS
- *
- * %RFLAGS.ZF:	!VMCS.LAUNCHED, i.e. controls VMLAUNCH vs. VMRESUME
- *
- * Returns:
- *	%RFLAGS.CF is set on VM-Fail Invalid
- *	%RFLAGS.ZF is set on VM-Fail Valid
- *	%RFLAGS.{CF,ZF} are cleared on VM-Success, i.e. VM-Exit
- *
- * Note that VMRESUME/VMLAUNCH fall-through and return directly if
- * they VM-Fail, whereas a successful VM-Enter + VM-Exit will jump
- * to vmx_vmexit.
- */
-SYM_FUNC_START_LOCAL(vmx_vmenter)
-	/* EFLAGS.ZF is set if VMCS.LAUNCHED == 0 */
-	je 2f
-
-1:	vmresume
-	RET
-
-2:	vmlaunch
-	RET
-
-3:	cmpb $0, kvm_rebooting
-	je 4f
-	RET
-4:	ud2
-
-	_ASM_EXTABLE(1b, 3b)
-	_ASM_EXTABLE(2b, 3b)
-
-SYM_FUNC_END(vmx_vmenter)
-
-/**
- * vmx_vmexit - Handle a VMX VM-Exit
- *
- * Returns:
- *	%RFLAGS.{CF,ZF} are cleared on VM-Success, i.e. VM-Exit
- *
- * This is vmx_vmenter's partner in crime.  On a VM-Exit, control will jump
- * here after hardware loads the host's state, i.e. this is the destination
- * referred to by VMCS.HOST_RIP.
- */
-SYM_FUNC_START(vmx_vmexit)
-#ifdef CONFIG_RETPOLINE
-	ALTERNATIVE "jmp .Lvmexit_skip_rsb", "", X86_FEATURE_RETPOLINE
-	/* Preserve guest's RAX, it's used to stuff the RSB. */
-	push %_ASM_AX
-
-	/* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
-	FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE
-
-	/* Clear RFLAGS.CF and RFLAGS.ZF to preserve VM-Exit, i.e. !VM-Fail. */
-	or $1, %_ASM_AX
-
-	pop %_ASM_AX
-.Lvmexit_skip_rsb:
-#endif
-	RET
-SYM_FUNC_END(vmx_vmexit)
-
-/**
  * __vmx_vcpu_run - Run a vCPU via a transition to VMX guest mode
- * @vmx:	struct vcpu_vmx * (forwarded to vmx_update_host_rsp)
+ * @vmx:	struct vcpu_vmx *
  * @regs:	unsigned long * (to guest registers)
- * @launched:	%true if the VMCS has been launched
+ * @flags:	VMX_RUN_VMRESUME:	use VMRESUME instead of VMLAUNCH
+ *		VMX_RUN_SAVE_SPEC_CTRL: save guest SPEC_CTRL into vmx->spec_ctrl
  *
  * Returns:
  *	0 on VM-Exit, 1 on VM-Fail
@@ -115,24 +55,29 @@ SYM_FUNC_START(__vmx_vcpu_run)
 #endif
 	push %_ASM_BX
 
+	/* Save @vmx for SPEC_CTRL handling */
+	push %_ASM_ARG1
+
+	/* Save @flags for SPEC_CTRL handling */
+	push %_ASM_ARG3
+
 	/*
 	 * Save @regs, _ASM_ARG2 may be modified by vmx_update_host_rsp() and
 	 * @regs is needed after VM-Exit to save the guest's register values.
 	 */
 	push %_ASM_ARG2
 
-	/* Copy @launched to BL, _ASM_ARG3 is volatile. */
+	/* Copy @flags to BL, _ASM_ARG3 is volatile. */
 	mov %_ASM_ARG3B, %bl
 
-	/* Adjust RSP to account for the CALL to vmx_vmenter(). */
-	lea -WORD_SIZE(%_ASM_SP), %_ASM_ARG2
+	lea (%_ASM_SP), %_ASM_ARG2
 	call vmx_update_host_rsp
 
 	/* Load @regs to RAX. */
 	mov (%_ASM_SP), %_ASM_AX
 
 	/* Check if vmlaunch or vmresume is needed */
-	testb %bl, %bl
+	testb $VMX_RUN_VMRESUME, %bl
 
 	/* Load guest registers.  Don't clobber flags. */
 	mov VCPU_RCX(%_ASM_AX), %_ASM_CX
@@ -154,11 +99,36 @@ SYM_FUNC_START(__vmx_vcpu_run)
 	/* Load guest RAX.  This kills the @regs pointer! */
 	mov VCPU_RAX(%_ASM_AX), %_ASM_AX
 
-	/* Enter guest mode */
-	call vmx_vmenter
+	/* Check EFLAGS.ZF from 'testb' above */
+	jz .Lvmlaunch
 
-	/* Jump on VM-Fail. */
-	jbe 2f
+	/*
+	 * After a successful VMRESUME/VMLAUNCH, control flow "magically"
+	 * resumes below at 'vmx_vmexit' due to the VMCS HOST_RIP setting.
+	 * So this isn't a typical function and objtool needs to be told to
+	 * save the unwind state here and restore it below.
+	 */
+	UNWIND_HINT_SAVE
+
+/*
+ * If VMRESUME/VMLAUNCH and corresponding vmexit succeed, execution resumes at
+ * the 'vmx_vmexit' label below.
+ */
+.Lvmresume:
+	vmresume
+	jmp .Lvmfail
+
+.Lvmlaunch:
+	vmlaunch
+	jmp .Lvmfail
+
+	_ASM_EXTABLE(.Lvmresume, .Lfixup)
+	_ASM_EXTABLE(.Lvmlaunch, .Lfixup)
+
+SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL)
+
+	/* Restore unwind state from before the VMRESUME/VMLAUNCH. */
+	UNWIND_HINT_RESTORE
 
 	/* Temporarily save guest's RAX. */
 	push %_ASM_AX
@@ -185,21 +155,23 @@ SYM_FUNC_START(__vmx_vcpu_run)
 	mov %r15, VCPU_R15(%_ASM_AX)
 #endif
 
-	/* Clear RAX to indicate VM-Exit (as opposed to VM-Fail). */
-	xor %eax, %eax
+	/* Clear return value to indicate VM-Exit (as opposed to VM-Fail). */
+	xor %ebx, %ebx
 
+.Lclear_regs:
 	/*
-	 * Clear all general purpose registers except RSP and RAX to prevent
+	 * Clear all general purpose registers except RSP and RBX to prevent
 	 * speculative use of the guest's values, even those that are reloaded
 	 * via the stack.  In theory, an L1 cache miss when restoring registers
 	 * could lead to speculative execution with the guest's values.
 	 * Zeroing XORs are dirt cheap, i.e. the extra paranoia is essentially
 	 * free.  RSP and RAX are exempt as RSP is restored by hardware during
-	 * VM-Exit and RAX is explicitly loaded with 0 or 1 to return VM-Fail.
+	 * VM-Exit and RBX is explicitly loaded with 0 or 1 to hold the return
+	 * value.
 	 */
-1:	xor %ecx, %ecx
+	xor %eax, %eax
+	xor %ecx, %ecx
 	xor %edx, %edx
-	xor %ebx, %ebx
 	xor %ebp, %ebp
 	xor %esi, %esi
 	xor %edi, %edi
@@ -216,8 +188,32 @@ SYM_FUNC_START(__vmx_vcpu_run)
 
 	/* "POP" @regs. */
 	add $WORD_SIZE, %_ASM_SP
-	pop %_ASM_BX
 
+	/*
+	 * IMPORTANT: RSB filling and SPEC_CTRL handling must be done before
+	 * the first unbalanced RET after vmexit!
+	 *
+	 * For retpoline or IBRS, RSB filling is needed to prevent poisoned RSB
+	 * entries and (in some cases) RSB underflow.
+	 *
+	 * eIBRS has its own protection against poisoned RSB, so it doesn't
+	 * need the RSB filling sequence.  But it does need to be enabled, and a
+	 * single call to retire, before the first unbalanced RET.
+         */
+
+	FILL_RETURN_BUFFER %_ASM_CX, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT,\
+			   X86_FEATURE_RSB_VMEXIT_LITE
+
+
+	pop %_ASM_ARG2	/* @flags */
+	pop %_ASM_ARG1	/* @vmx */
+
+	call vmx_spec_ctrl_restore_host
+
+	/* Put return value in AX */
+	mov %_ASM_BX, %_ASM_AX
+
+	pop %_ASM_BX
 #ifdef CONFIG_X86_64
 	pop %r12
 	pop %r13
@@ -230,9 +226,15 @@ SYM_FUNC_START(__vmx_vcpu_run)
 	pop %_ASM_BP
 	RET
 
-	/* VM-Fail.  Out-of-line to avoid a taken Jcc after VM-Exit. */
-2:	mov $1, %eax
-	jmp 1b
+.Lfixup:
+	cmpb $0, kvm_rebooting
+	jne .Lvmfail
+	ud2
+.Lvmfail:
+	/* VM-Fail: set return value to 1 */
+	mov $1, %_ASM_BX
+	jmp .Lclear_regs
+
 SYM_FUNC_END(__vmx_vcpu_run)
 
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 1533ab7b579e..e5584e974c77 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -380,9 +380,9 @@ static __always_inline void vmx_disable_fb_clear(struct vcpu_vmx *vmx)
 	if (!vmx->disable_fb_clear)
 		return;
 
-	rdmsrl(MSR_IA32_MCU_OPT_CTRL, msr);
+	msr = __rdmsr(MSR_IA32_MCU_OPT_CTRL);
 	msr |= FB_CLEAR_DIS;
-	wrmsrl(MSR_IA32_MCU_OPT_CTRL, msr);
+	native_wrmsrl(MSR_IA32_MCU_OPT_CTRL, msr);
 	/* Cache the MSR value to avoid reading it later */
 	vmx->msr_ia32_mcu_opt_ctrl = msr;
 }
@@ -393,7 +393,7 @@ static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx)
 		return;
 
 	vmx->msr_ia32_mcu_opt_ctrl &= ~FB_CLEAR_DIS;
-	wrmsrl(MSR_IA32_MCU_OPT_CTRL, vmx->msr_ia32_mcu_opt_ctrl);
+	native_wrmsrl(MSR_IA32_MCU_OPT_CTRL, vmx->msr_ia32_mcu_opt_ctrl);
 }
 
 static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx)
@@ -831,8 +831,25 @@ static bool msr_write_intercepted(struct vcpu_vmx *vmx, u32 msr)
 	if (!(exec_controls_get(vmx) & CPU_BASED_USE_MSR_BITMAPS))
 		return true;
 
-	return vmx_test_msr_bitmap_write(vmx->loaded_vmcs->msr_bitmap,
-					 MSR_IA32_SPEC_CTRL);
+	return vmx_test_msr_bitmap_write(vmx->loaded_vmcs->msr_bitmap, msr);
+}
+
+unsigned int __vmx_vcpu_run_flags(struct vcpu_vmx *vmx)
+{
+	unsigned int flags = 0;
+
+	if (vmx->loaded_vmcs->launched)
+		flags |= VMX_RUN_VMRESUME;
+
+	/*
+	 * If writes to the SPEC_CTRL MSR aren't intercepted, the guest is free
+	 * to change it directly without causing a vmexit.  In that case read
+	 * it after vmexit and store it in vmx->spec_ctrl.
+	 */
+	if (unlikely(!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL)))
+		flags |= VMX_RUN_SAVE_SPEC_CTRL;
+
+	return flags;
 }
 
 static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx,
@@ -3195,8 +3212,8 @@ static bool vmx_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
 	/*
 	 * We operate under the default treatment of SMM, so VMX cannot be
-	 * enabled under SMM.  Note, whether or not VMXE is allowed at all is
-	 * handled by kvm_is_valid_cr4().
+	 * enabled under SMM.  Note, whether or not VMXE is allowed at all,
+	 * i.e. is a reserved bit, is handled by common x86 code.
 	 */
 	if ((cr4 & X86_CR4_VMXE) && is_smm(vcpu))
 		return false;
@@ -6453,6 +6470,7 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu)
 		return;
 
 	handle_interrupt_nmi_irqoff(vcpu, gate_offset(desc));
+	vcpu->arch.at_instruction_boundary = true;
 }
 
 static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu)
@@ -6654,6 +6672,31 @@ void noinstr vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp)
 	}
 }
 
+void noinstr vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx,
+					unsigned int flags)
+{
+	u64 hostval = this_cpu_read(x86_spec_ctrl_current);
+
+	if (!cpu_feature_enabled(X86_FEATURE_MSR_SPEC_CTRL))
+		return;
+
+	if (flags & VMX_RUN_SAVE_SPEC_CTRL)
+		vmx->spec_ctrl = __rdmsr(MSR_IA32_SPEC_CTRL);
+
+	/*
+	 * If the guest/host SPEC_CTRL values differ, restore the host value.
+	 *
+	 * For legacy IBRS, the IBRS bit always needs to be written after
+	 * transitioning from a less privileged predictor mode, regardless of
+	 * whether the guest/host values differ.
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) ||
+	    vmx->spec_ctrl != hostval)
+		native_wrmsrl(MSR_IA32_SPEC_CTRL, hostval);
+
+	barrier_nospec();
+}
+
 static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu)
 {
 	switch (to_vmx(vcpu)->exit_reason.basic) {
@@ -6667,7 +6710,8 @@ static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu)
 }
 
 static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
-					struct vcpu_vmx *vmx)
+					struct vcpu_vmx *vmx,
+					unsigned long flags)
 {
 	kvm_guest_enter_irqoff();
 
@@ -6686,7 +6730,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 		native_write_cr2(vcpu->arch.cr2);
 
 	vmx->fail = __vmx_vcpu_run(vmx, (unsigned long *)&vcpu->arch.regs,
-				   vmx->loaded_vmcs->launched);
+				   flags);
 
 	vcpu->arch.cr2 = native_read_cr2();
 
@@ -6786,27 +6830,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	x86_spec_ctrl_set_guest(vmx->spec_ctrl, 0);
 
 	/* The actual VMENTER/EXIT is in the .noinstr.text section. */
-	vmx_vcpu_enter_exit(vcpu, vmx);
-
-	/*
-	 * We do not use IBRS in the kernel. If this vCPU has used the
-	 * SPEC_CTRL MSR it may have left it on; save the value and
-	 * turn it off. This is much more efficient than blindly adding
-	 * it to the atomic save/restore list. Especially as the former
-	 * (Saving guest MSRs on vmexit) doesn't even exist in KVM.
-	 *
-	 * For non-nested case:
-	 * If the L01 MSR bitmap does not intercept the MSR, then we need to
-	 * save it.
-	 *
-	 * For nested case:
-	 * If the L02 MSR bitmap does not intercept the MSR, then we need to
-	 * save it.
-	 */
-	if (unlikely(!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL)))
-		vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
-
-	x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0);
+	vmx_vcpu_enter_exit(vcpu, vmx, __vmx_vcpu_run_flags(vmx));
 
 	/* All fields are clean at this point */
 	if (static_branch_unlikely(&enable_evmcs)) {
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 12fe7b31cbf6..20f1213a9368 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -13,6 +13,7 @@
 #include "vmcs.h"
 #include "vmx_ops.h"
 #include "cpuid.h"
+#include "run_flags.h"
 
 #define MSR_TYPE_R	1
 #define MSR_TYPE_W	2
@@ -91,6 +92,18 @@ union vmx_exit_reason {
 	u32 full;
 };
 
+static inline bool intel_pmu_has_perf_global_ctrl(struct kvm_pmu *pmu)
+{
+	/*
+	 * Architecturally, Intel's SDM states that IA32_PERF_GLOBAL_CTRL is
+	 * supported if "CPUID.0AH: EAX[7:0] > 0", i.e. if the PMU version is
+	 * greater than zero.  However, KVM only exposes and emulates the MSR
+	 * to/for the guest if the guest PMU supports at least "Architectural
+	 * Performance Monitoring Version 2".
+	 */
+	return pmu->version > 1;
+}
+
 #define vcpu_to_lbr_desc(vcpu) (&to_vmx(vcpu)->lbr_desc)
 #define vcpu_to_lbr_records(vcpu) (&to_vmx(vcpu)->lbr_desc.records)
 
@@ -382,7 +395,10 @@ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu);
 struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr);
 void pt_update_intercept_for_msr(struct kvm_vcpu *vcpu);
 void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp);
-bool __vmx_vcpu_run(struct vcpu_vmx *vmx, unsigned long *regs, bool launched);
+void vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx, unsigned int flags);
+unsigned int __vmx_vcpu_run_flags(struct vcpu_vmx *vmx);
+bool __vmx_vcpu_run(struct vcpu_vmx *vmx, unsigned long *regs,
+		    unsigned int flags);
 int vmx_find_loadstore_msr_slot(struct vmx_msrs *m, u32 msr);
 void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu);
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 39aaa21e28f7..11e73d02fb3a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -277,6 +277,8 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
 	STATS_DESC_COUNTER(VCPU, nested_run),
 	STATS_DESC_COUNTER(VCPU, directed_yield_attempted),
 	STATS_DESC_COUNTER(VCPU, directed_yield_successful),
+	STATS_DESC_COUNTER(VCPU, preemption_reported),
+	STATS_DESC_COUNTER(VCPU, preemption_other),
 	STATS_DESC_ICOUNTER(VCPU, guest_mode)
 };
 
@@ -1029,7 +1031,7 @@ int kvm_emulate_xsetbv(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_xsetbv);
 
-bool kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
+bool __kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
 	if (cr4 & cr4_reserved_bits)
 		return false;
@@ -1037,9 +1039,15 @@ bool kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	if (cr4 & vcpu->arch.cr4_guest_rsvd_bits)
 		return false;
 
-	return static_call(kvm_x86_is_valid_cr4)(vcpu, cr4);
+	return true;
+}
+EXPORT_SYMBOL_GPL(__kvm_is_valid_cr4);
+
+static bool kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
+{
+	return __kvm_is_valid_cr4(vcpu, cr4) &&
+	       static_call(kvm_x86_is_valid_cr4)(vcpu, cr4);
 }
-EXPORT_SYMBOL_GPL(kvm_is_valid_cr4);
 
 void kvm_post_set_cr4(struct kvm_vcpu *vcpu, unsigned long old_cr4, unsigned long cr4)
 {
@@ -1457,12 +1465,32 @@ static const u32 msr_based_features_all[] = {
 static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all)];
 static unsigned int num_msr_based_features;
 
+/*
+ * Some IA32_ARCH_CAPABILITIES bits have dependencies on MSRs that KVM
+ * does not yet virtualize. These include:
+ *   10 - MISC_PACKAGE_CTRLS
+ *   11 - ENERGY_FILTERING_CTL
+ *   12 - DOITM
+ *   18 - FB_CLEAR_CTRL
+ *   21 - XAPIC_DISABLE_STATUS
+ *   23 - OVERCLOCKING_STATUS
+ */
+
+#define KVM_SUPPORTED_ARCH_CAP \
+	(ARCH_CAP_RDCL_NO | ARCH_CAP_IBRS_ALL | ARCH_CAP_RSBA | \
+	 ARCH_CAP_SKIP_VMENTRY_L1DFLUSH | ARCH_CAP_SSB_NO | ARCH_CAP_MDS_NO | \
+	 ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \
+	 ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \
+	 ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO)
+
 static u64 kvm_get_arch_capabilities(void)
 {
 	u64 data = 0;
 
-	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
+	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) {
 		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, data);
+		data &= KVM_SUPPORTED_ARCH_CAP;
+	}
 
 	/*
 	 * If nx_huge_pages is enabled, KVM's shadow paging will ensure that
@@ -1510,9 +1538,6 @@ static u64 kvm_get_arch_capabilities(void)
 		 */
 	}
 
-	/* Guests don't need to know "Fill buffer clear control" exists */
-	data &= ~ARCH_CAP_FB_CLEAR_CTRL;
-
 	return data;
 }
 
@@ -3094,17 +3119,20 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			/* only 0 or all 1s can be written to IA32_MCi_CTL
 			 * some Linux kernels though clear bit 10 in bank 4 to
 			 * workaround a BIOS/GART TBL issue on AMD K8s, ignore
-			 * this to avoid an uncatched #GP in the guest
+			 * this to avoid an uncatched #GP in the guest.
+			 *
+			 * UNIXWARE clears bit 0 of MC1_CTL to ignore
+			 * correctable, single-bit ECC data errors.
 			 */
 			if ((offset & 0x3) == 0 &&
-			    data != 0 && (data | (1 << 10)) != ~(u64)0)
-				return -1;
+			    data != 0 && (data | (1 << 10) | 1) != ~(u64)0)
+				return 1;
 
 			/* MCi_STATUS */
 			if (!msr_info->host_initiated &&
 			    (offset & 0x3) == 1 && data != 0) {
 				if (!can_set_mci_status(vcpu))
-					return -1;
+					return 1;
 			}
 
 			vcpu->arch.mce_banks[offset] = data;
@@ -3236,6 +3264,7 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
 	struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache;
 	struct kvm_steal_time __user *st;
 	struct kvm_memslots *slots;
+	gpa_t gpa = vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS;
 	u64 steal;
 	u32 version;
 
@@ -3253,13 +3282,12 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
 	slots = kvm_memslots(vcpu->kvm);
 
 	if (unlikely(slots->generation != ghc->generation ||
+		     gpa != ghc->gpa ||
 		     kvm_is_error_hva(ghc->hva) || !ghc->memslot)) {
-		gfn_t gfn = vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS;
-
 		/* We rely on the fact that it fits in a single page. */
 		BUILD_BUG_ON((sizeof(*st) - 1) & KVM_STEAL_VALID_BITS);
 
-		if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, gfn, sizeof(*st)) ||
+		if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, gpa, sizeof(*st)) ||
 		    kvm_is_error_hva(ghc->hva) || !ghc->memslot)
 			return;
 	}
@@ -4370,7 +4398,21 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu)
 	struct kvm_steal_time __user *st;
 	struct kvm_memslots *slots;
 	static const u8 preempted = KVM_VCPU_PREEMPTED;
+	gpa_t gpa = vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS;
 
+	/*
+	 * The vCPU can be marked preempted if and only if the VM-Exit was on
+	 * an instruction boundary and will not trigger guest emulation of any
+	 * kind (see vcpu_run).  Vendor specific code controls (conservatively)
+	 * when this is true, for example allowing the vCPU to be marked
+	 * preempted if and only if the VM-Exit was due to a host interrupt.
+	 */
+	if (!vcpu->arch.at_instruction_boundary) {
+		vcpu->stat.preemption_other++;
+		return;
+	}
+
+	vcpu->stat.preemption_reported++;
 	if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
 		return;
 
@@ -4384,6 +4426,7 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu)
 	slots = kvm_memslots(vcpu->kvm);
 
 	if (unlikely(slots->generation != ghc->generation ||
+		     gpa != ghc->gpa ||
 		     kvm_is_error_hva(ghc->hva) || !ghc->memslot))
 		return;
 
@@ -4400,19 +4443,21 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	int idx;
 
-	if (vcpu->preempted && !vcpu->arch.guest_state_protected)
-		vcpu->arch.preempted_in_kernel = !static_call(kvm_x86_get_cpl)(vcpu);
+	if (vcpu->preempted) {
+		if (!vcpu->arch.guest_state_protected)
+			vcpu->arch.preempted_in_kernel = !static_call(kvm_x86_get_cpl)(vcpu);
 
-	/*
-	 * Take the srcu lock as memslots will be accessed to check the gfn
-	 * cache generation against the memslots generation.
-	 */
-	idx = srcu_read_lock(&vcpu->kvm->srcu);
-	if (kvm_xen_msr_enabled(vcpu->kvm))
-		kvm_xen_runstate_set_preempted(vcpu);
-	else
-		kvm_steal_time_set_preempted(vcpu);
-	srcu_read_unlock(&vcpu->kvm->srcu, idx);
+		/*
+		 * Take the srcu lock as memslots will be accessed to check the gfn
+		 * cache generation against the memslots generation.
+		 */
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
+		if (kvm_xen_msr_enabled(vcpu->kvm))
+			kvm_xen_runstate_set_preempted(vcpu);
+		else
+			kvm_steal_time_set_preempted(vcpu);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
+	}
 
 	static_call(kvm_x86_vcpu_put)(vcpu);
 	vcpu->arch.last_host_tsc = rdtsc();
@@ -6894,15 +6939,8 @@ static int emulator_write_emulated(struct x86_emulate_ctxt *ctxt,
 				   exception, &write_emultor);
 }
 
-#define CMPXCHG_TYPE(t, ptr, old, new) \
-	(cmpxchg((t *)(ptr), *(t *)(old), *(t *)(new)) == *(t *)(old))
-
-#ifdef CONFIG_X86_64
-#  define CMPXCHG64(ptr, old, new) CMPXCHG_TYPE(u64, ptr, old, new)
-#else
-#  define CMPXCHG64(ptr, old, new) \
-	(cmpxchg64((u64 *)(ptr), *(u64 *)(old), *(u64 *)(new)) == *(u64 *)(old))
-#endif
+#define emulator_try_cmpxchg_user(t, ptr, old, new) \
+	(__try_cmpxchg_user((t __user *)(ptr), (t *)(old), *(t *)(new), efault ## t))
 
 static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt,
 				     unsigned long addr,
@@ -6911,12 +6949,11 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt,
 				     unsigned int bytes,
 				     struct x86_exception *exception)
 {
-	struct kvm_host_map map;
 	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
 	u64 page_line_mask;
+	unsigned long hva;
 	gpa_t gpa;
-	char *kaddr;
-	bool exchanged;
+	int r;
 
 	/* guests cmpxchg8b have to be emulated atomically */
 	if (bytes > 8 || (bytes & (bytes - 1)))
@@ -6940,31 +6977,32 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt,
 	if (((gpa + bytes - 1) & page_line_mask) != (gpa & page_line_mask))
 		goto emul_write;
 
-	if (kvm_vcpu_map(vcpu, gpa_to_gfn(gpa), &map))
+	hva = kvm_vcpu_gfn_to_hva(vcpu, gpa_to_gfn(gpa));
+	if (kvm_is_error_hva(hva))
 		goto emul_write;
 
-	kaddr = map.hva + offset_in_page(gpa);
+	hva += offset_in_page(gpa);
 
 	switch (bytes) {
 	case 1:
-		exchanged = CMPXCHG_TYPE(u8, kaddr, old, new);
+		r = emulator_try_cmpxchg_user(u8, hva, old, new);
 		break;
 	case 2:
-		exchanged = CMPXCHG_TYPE(u16, kaddr, old, new);
+		r = emulator_try_cmpxchg_user(u16, hva, old, new);
 		break;
 	case 4:
-		exchanged = CMPXCHG_TYPE(u32, kaddr, old, new);
+		r = emulator_try_cmpxchg_user(u32, hva, old, new);
 		break;
 	case 8:
-		exchanged = CMPXCHG64(kaddr, old, new);
+		r = emulator_try_cmpxchg_user(u64, hva, old, new);
 		break;
 	default:
 		BUG();
 	}
 
-	kvm_vcpu_unmap(vcpu, &map, true);
-
-	if (!exchanged)
+	if (r < 0)
+		goto emul_write;
+	if (r)
 		return X86EMUL_CMPXCHG_FAILED;
 
 	kvm_page_track_write(vcpu, gpa, new, bytes);
@@ -8713,15 +8751,17 @@ static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr,
  */
 static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid)
 {
-	struct kvm_lapic_irq lapic_irq;
-
-	lapic_irq.shorthand = APIC_DEST_NOSHORT;
-	lapic_irq.dest_mode = APIC_DEST_PHYSICAL;
-	lapic_irq.level = 0;
-	lapic_irq.dest_id = apicid;
-	lapic_irq.msi_redir_hint = false;
+	/*
+	 * All other fields are unused for APIC_DM_REMRD, but may be consumed by
+	 * common code, e.g. for tracing. Defer initialization to the compiler.
+	 */
+	struct kvm_lapic_irq lapic_irq = {
+		.delivery_mode = APIC_DM_REMRD,
+		.dest_mode = APIC_DEST_PHYSICAL,
+		.shorthand = APIC_DEST_NOSHORT,
+		.dest_id = apicid,
+	};
 
-	lapic_irq.delivery_mode = APIC_DM_REMRD;
 	kvm_irq_delivery_to_apic(kvm, NULL, &lapic_irq, NULL);
 }
 
@@ -9517,6 +9557,11 @@ void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
 		kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD);
 }
 
+void kvm_arch_guest_memory_reclaimed(struct kvm *kvm)
+{
+	static_call_cond(kvm_x86_guest_memory_reclaimed)(kvm);
+}
+
 void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
 {
 	if (!lapic_in_kernel(vcpu))
@@ -9939,6 +9984,13 @@ static int vcpu_run(struct kvm_vcpu *vcpu)
 	vcpu->arch.l1tf_flush_l1d = true;
 
 	for (;;) {
+		/*
+		 * If another guest vCPU requests a PV TLB flush in the middle
+		 * of instruction emulation, the rest of the emulation could
+		 * use a stale page translation. Assume that any code after
+		 * this point can start executing an instruction.
+		 */
+		vcpu->arch.at_instruction_boundary = false;
 		if (kvm_vcpu_running(vcpu)) {
 			r = vcpu_enter_guest(vcpu);
 		} else {
@@ -11552,7 +11604,7 @@ static int memslot_rmap_alloc(struct kvm_memory_slot *slot,
 		if (slot->arch.rmap[i])
 			continue;
 
-		slot->arch.rmap[i] = kvcalloc(lpages, sz, GFP_KERNEL_ACCOUNT);
+		slot->arch.rmap[i] = __vcalloc(lpages, sz, GFP_KERNEL_ACCOUNT);
 		if (!slot->arch.rmap[i]) {
 			memslot_rmap_free(slot);
 			return -ENOMEM;
@@ -11633,7 +11685,7 @@ static int kvm_alloc_memslot_metadata(struct kvm *kvm,
 
 		lpages = __kvm_mmu_slot_lpages(slot, npages, level);
 
-		linfo = kvcalloc(lpages, sizeof(*linfo), GFP_KERNEL_ACCOUNT);
+		linfo = __vcalloc(lpages, sizeof(*linfo), GFP_KERNEL_ACCOUNT);
 		if (!linfo)
 			goto out_free;
 
@@ -12177,9 +12229,9 @@ void kvm_arch_end_assignment(struct kvm *kvm)
 }
 EXPORT_SYMBOL_GPL(kvm_arch_end_assignment);
 
-bool kvm_arch_has_assigned_device(struct kvm *kvm)
+bool noinstr kvm_arch_has_assigned_device(struct kvm *kvm)
 {
-	return atomic_read(&kvm->arch.assigned_device_count);
+	return arch_atomic_read(&kvm->arch.assigned_device_count);
 }
 EXPORT_SYMBOL_GPL(kvm_arch_has_assigned_device);
 
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index bc7ef6820ac8..cd0c93ec72fa 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -26,7 +26,7 @@ static __always_inline void kvm_guest_enter_irqoff(void)
 	 */
 	instrumentation_begin();
 	trace_hardirqs_on_prepare();
-	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+	lockdep_hardirqs_on_prepare();
 	instrumentation_end();
 
 	guest_enter_irqoff();
@@ -448,7 +448,7 @@ static inline void kvm_machine_check(void)
 void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu);
 void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu);
 int kvm_spec_ctrl_test_value(u64 value);
-bool kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
+bool __kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
 int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r,
 			      struct x86_exception *e);
 int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva);
diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h
index cc0cf5f37450..a7693a286e40 100644
--- a/arch/x86/kvm/xen.h
+++ b/arch/x86/kvm/xen.h
@@ -97,8 +97,10 @@ static inline void kvm_xen_runstate_set_preempted(struct kvm_vcpu *vcpu)
 	 * behalf of the vCPU. Only if the VMM does actually block
 	 * does it need to enter RUNSTATE_blocked.
 	 */
-	if (vcpu->preempted)
-		kvm_xen_update_runstate_guest(vcpu, RUNSTATE_runnable);
+	if (WARN_ON_ONCE(!vcpu->preempted))
+		return;
+
+	kvm_xen_update_runstate_guest(vcpu, RUNSTATE_runnable);
 }
 
 /* 32-bit compatibility definitions, also used natively in 32-bit build */
diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c
index eb3ccffb9b9d..c8a962c2e653 100644
--- a/arch/x86/lib/insn-eval.c
+++ b/arch/x86/lib/insn-eval.c
@@ -412,32 +412,44 @@ static short get_segment_selector(struct pt_regs *regs, int seg_reg_idx)
 #endif /* CONFIG_X86_64 */
 }
 
-static int get_reg_offset(struct insn *insn, struct pt_regs *regs,
-			  enum reg_type type)
+static const int pt_regoff[] = {
+	offsetof(struct pt_regs, ax),
+	offsetof(struct pt_regs, cx),
+	offsetof(struct pt_regs, dx),
+	offsetof(struct pt_regs, bx),
+	offsetof(struct pt_regs, sp),
+	offsetof(struct pt_regs, bp),
+	offsetof(struct pt_regs, si),
+	offsetof(struct pt_regs, di),
+#ifdef CONFIG_X86_64
+	offsetof(struct pt_regs, r8),
+	offsetof(struct pt_regs, r9),
+	offsetof(struct pt_regs, r10),
+	offsetof(struct pt_regs, r11),
+	offsetof(struct pt_regs, r12),
+	offsetof(struct pt_regs, r13),
+	offsetof(struct pt_regs, r14),
+	offsetof(struct pt_regs, r15),
+#else
+	offsetof(struct pt_regs, ds),
+	offsetof(struct pt_regs, es),
+	offsetof(struct pt_regs, fs),
+	offsetof(struct pt_regs, gs),
+#endif
+};
+
+int pt_regs_offset(struct pt_regs *regs, int regno)
+{
+	if ((unsigned)regno < ARRAY_SIZE(pt_regoff))
+		return pt_regoff[regno];
+	return -EDOM;
+}
+
+static int get_regno(struct insn *insn, enum reg_type type)
 {
+	int nr_registers = ARRAY_SIZE(pt_regoff);
 	int regno = 0;
 
-	static const int regoff[] = {
-		offsetof(struct pt_regs, ax),
-		offsetof(struct pt_regs, cx),
-		offsetof(struct pt_regs, dx),
-		offsetof(struct pt_regs, bx),
-		offsetof(struct pt_regs, sp),
-		offsetof(struct pt_regs, bp),
-		offsetof(struct pt_regs, si),
-		offsetof(struct pt_regs, di),
-#ifdef CONFIG_X86_64
-		offsetof(struct pt_regs, r8),
-		offsetof(struct pt_regs, r9),
-		offsetof(struct pt_regs, r10),
-		offsetof(struct pt_regs, r11),
-		offsetof(struct pt_regs, r12),
-		offsetof(struct pt_regs, r13),
-		offsetof(struct pt_regs, r14),
-		offsetof(struct pt_regs, r15),
-#endif
-	};
-	int nr_registers = ARRAY_SIZE(regoff);
 	/*
 	 * Don't possibly decode a 32-bit instructions as
 	 * reading a 64-bit-only register.
@@ -505,7 +517,18 @@ static int get_reg_offset(struct insn *insn, struct pt_regs *regs,
 		WARN_ONCE(1, "decoded an instruction with an invalid register");
 		return -EINVAL;
 	}
-	return regoff[regno];
+	return regno;
+}
+
+static int get_reg_offset(struct insn *insn, struct pt_regs *regs,
+			  enum reg_type type)
+{
+	int regno = get_regno(insn, type);
+
+	if (regno < 0)
+		return regno;
+
+	return pt_regs_offset(regs, regno);
 }
 
 /**
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index 50ea390df712..4b8ee3a2fcc3 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -40,7 +40,7 @@ SYM_FUNC_START(__memmove)
 	/* FSRM implies ERMS => no length checks, do the copy directly */
 .Lmemmove_begin_forward:
 	ALTERNATIVE "cmp $0x20, %rdx; jb 1f", "", X86_FEATURE_FSRM
-	ALTERNATIVE "", __stringify(movq %rdx, %rcx; rep movsb; RET), X86_FEATURE_ERMS
+	ALTERNATIVE "", "jmp .Lmemmove_erms", X86_FEATURE_ERMS
 
 	/*
 	 * movsq instruction have many startup latency
@@ -206,6 +206,11 @@ SYM_FUNC_START(__memmove)
 	movb %r11b, (%rdi)
 13:
 	RET
+
+.Lmemmove_erms:
+	movq %rdx, %rcx
+	rep movsb
+	RET
 SYM_FUNC_END(__memmove)
 SYM_FUNC_END_ALIAS(memmove)
 EXPORT_SYMBOL(__memmove)
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index 9556ff5f4773..1221bb099afb 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -28,45 +28,13 @@
 
 .macro THUNK reg
 
-	.align 32
-
-SYM_FUNC_START(__x86_indirect_thunk_\reg)
-
-	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \
-		      __stringify(RETPOLINE \reg), X86_FEATURE_RETPOLINE, \
-		      __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg; int3), X86_FEATURE_RETPOLINE_LFENCE
-
-SYM_FUNC_END(__x86_indirect_thunk_\reg)
-
-.endm
-
-/*
- * This generates .altinstr_replacement symbols for use by objtool. They,
- * however, must not actually live in .altinstr_replacement since that will be
- * discarded after init, but module alternatives will also reference these
- * symbols.
- *
- * Their names matches the "__x86_indirect_" prefix to mark them as retpolines.
- */
-.macro ALT_THUNK reg
-
-	.align 1
-
-SYM_FUNC_START_NOALIGN(__x86_indirect_alt_call_\reg)
-	ANNOTATE_RETPOLINE_SAFE
-1:	call	*%\reg
-2:	.skip	5-(2b-1b), 0x90
-SYM_FUNC_END(__x86_indirect_alt_call_\reg)
-
-STACK_FRAME_NON_STANDARD(__x86_indirect_alt_call_\reg)
-
-SYM_FUNC_START_NOALIGN(__x86_indirect_alt_jmp_\reg)
-	ANNOTATE_RETPOLINE_SAFE
-1:	jmp	*%\reg
-2:	.skip	5-(2b-1b), 0x90
-SYM_FUNC_END(__x86_indirect_alt_jmp_\reg)
+	.align RETPOLINE_THUNK_SIZE
+SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL)
+	UNWIND_HINT_EMPTY
 
-STACK_FRAME_NON_STANDARD(__x86_indirect_alt_jmp_\reg)
+	ALTERNATIVE_2 __stringify(RETPOLINE \reg), \
+		      __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg; int3), X86_FEATURE_RETPOLINE_LFENCE, \
+		      __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), ALT_NOT(X86_FEATURE_RETPOLINE)
 
 .endm
 
@@ -85,22 +53,89 @@ STACK_FRAME_NON_STANDARD(__x86_indirect_alt_jmp_\reg)
 #define __EXPORT_THUNK(sym)	_ASM_NOKPROBE(sym); EXPORT_SYMBOL(sym)
 #define EXPORT_THUNK(reg)	__EXPORT_THUNK(__x86_indirect_thunk_ ## reg)
 
-#undef GEN
+	.align RETPOLINE_THUNK_SIZE
+SYM_CODE_START(__x86_indirect_thunk_array)
+
 #define GEN(reg) THUNK reg
 #include <asm/GEN-for-each-reg.h>
-
 #undef GEN
+
+	.align RETPOLINE_THUNK_SIZE
+SYM_CODE_END(__x86_indirect_thunk_array)
+
 #define GEN(reg) EXPORT_THUNK(reg)
 #include <asm/GEN-for-each-reg.h>
-
 #undef GEN
-#define GEN(reg) ALT_THUNK reg
-#include <asm/GEN-for-each-reg.h>
 
-#undef GEN
-#define GEN(reg) __EXPORT_THUNK(__x86_indirect_alt_call_ ## reg)
-#include <asm/GEN-for-each-reg.h>
+/*
+ * This function name is magical and is used by -mfunction-return=thunk-extern
+ * for the compiler to generate JMPs to it.
+ */
+#ifdef CONFIG_RETHUNK
 
-#undef GEN
-#define GEN(reg) __EXPORT_THUNK(__x86_indirect_alt_jmp_ ## reg)
-#include <asm/GEN-for-each-reg.h>
+	.section .text.__x86.return_thunk
+
+/*
+ * Safety details here pertain to the AMD Zen{1,2} microarchitecture:
+ * 1) The RET at __x86_return_thunk must be on a 64 byte boundary, for
+ *    alignment within the BTB.
+ * 2) The instruction at zen_untrain_ret must contain, and not
+ *    end with, the 0xc3 byte of the RET.
+ * 3) STIBP must be enabled, or SMT disabled, to prevent the sibling thread
+ *    from re-poisioning the BTB prediction.
+ */
+	.align 64
+	.skip 63, 0xcc
+SYM_FUNC_START_NOALIGN(zen_untrain_ret);
+
+	/*
+	 * As executed from zen_untrain_ret, this is:
+	 *
+	 *   TEST $0xcc, %bl
+	 *   LFENCE
+	 *   JMP __x86_return_thunk
+	 *
+	 * Executing the TEST instruction has a side effect of evicting any BTB
+	 * prediction (potentially attacker controlled) attached to the RET, as
+	 * __x86_return_thunk + 1 isn't an instruction boundary at the moment.
+	 */
+	.byte	0xf6
+
+	/*
+	 * As executed from __x86_return_thunk, this is a plain RET.
+	 *
+	 * As part of the TEST above, RET is the ModRM byte, and INT3 the imm8.
+	 *
+	 * We subsequently jump backwards and architecturally execute the RET.
+	 * This creates a correct BTB prediction (type=ret), but in the
+	 * meantime we suffer Straight Line Speculation (because the type was
+	 * no branch) which is halted by the INT3.
+	 *
+	 * With SMT enabled and STIBP active, a sibling thread cannot poison
+	 * RET's prediction to a type of its choice, but can evict the
+	 * prediction due to competitive sharing. If the prediction is
+	 * evicted, __x86_return_thunk will suffer Straight Line Speculation
+	 * which will be contained safely by the INT3.
+	 */
+SYM_INNER_LABEL(__x86_return_thunk, SYM_L_GLOBAL)
+	ret
+	int3
+SYM_CODE_END(__x86_return_thunk)
+
+	/*
+	 * Ensure the TEST decoding / BTB invalidation is complete.
+	 */
+	lfence
+
+	/*
+	 * Jump back and execute the RET in the middle of the TEST instruction.
+	 * INT3 is for SLS protection.
+	 */
+	jmp __x86_return_thunk
+	int3
+SYM_FUNC_END(zen_untrain_ret)
+__EXPORT_THUNK(zen_untrain_ret)
+
+EXPORT_SYMBOL(__x86_return_thunk)
+
+#endif /* CONFIG_RETHUNK */
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index e1664e9f969c..a9c7efd4b794 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -2,48 +2,50 @@
 #include <linux/extable.h>
 #include <linux/uaccess.h>
 #include <linux/sched/debug.h>
+#include <linux/bitfield.h>
 #include <xen/xen.h>
 
 #include <asm/fpu/internal.h>
 #include <asm/sev.h>
 #include <asm/traps.h>
 #include <asm/kdebug.h>
+#include <asm/insn-eval.h>
 
-typedef bool (*ex_handler_t)(const struct exception_table_entry *,
-			    struct pt_regs *, int, unsigned long,
-			    unsigned long);
+static inline unsigned long *pt_regs_nr(struct pt_regs *regs, int nr)
+{
+	int reg_offset = pt_regs_offset(regs, nr);
+	static unsigned long __dummy;
+
+	if (WARN_ON_ONCE(reg_offset < 0))
+		return &__dummy;
+
+	return (unsigned long *)((unsigned long)regs + reg_offset);
+}
 
 static inline unsigned long
 ex_fixup_addr(const struct exception_table_entry *x)
 {
 	return (unsigned long)&x->fixup + x->fixup;
 }
-static inline ex_handler_t
-ex_fixup_handler(const struct exception_table_entry *x)
-{
-	return (ex_handler_t)((unsigned long)&x->handler + x->handler);
-}
 
-__visible bool ex_handler_default(const struct exception_table_entry *fixup,
-				  struct pt_regs *regs, int trapnr,
-				  unsigned long error_code,
-				  unsigned long fault_addr)
+static bool ex_handler_default(const struct exception_table_entry *e,
+			       struct pt_regs *regs)
 {
-	regs->ip = ex_fixup_addr(fixup);
+	if (e->data & EX_FLAG_CLEAR_AX)
+		regs->ax = 0;
+	if (e->data & EX_FLAG_CLEAR_DX)
+		regs->dx = 0;
+
+	regs->ip = ex_fixup_addr(e);
 	return true;
 }
-EXPORT_SYMBOL(ex_handler_default);
 
-__visible bool ex_handler_fault(const struct exception_table_entry *fixup,
-				struct pt_regs *regs, int trapnr,
-				unsigned long error_code,
-				unsigned long fault_addr)
+static bool ex_handler_fault(const struct exception_table_entry *fixup,
+			     struct pt_regs *regs, int trapnr)
 {
-	regs->ip = ex_fixup_addr(fixup);
 	regs->ax = trapnr;
-	return true;
+	return ex_handler_default(fixup, regs);
 }
-EXPORT_SYMBOL_GPL(ex_handler_fault);
 
 /*
  * Handler for when we fail to restore a task's FPU state.  We should never get
@@ -55,10 +57,8 @@ EXPORT_SYMBOL_GPL(ex_handler_fault);
  * of vulnerability by restoring from the initial state (essentially, zeroing
  * out all the FPU registers) if we can't restore from the task's FPU state.
  */
-__visible bool ex_handler_fprestore(const struct exception_table_entry *fixup,
-				    struct pt_regs *regs, int trapnr,
-				    unsigned long error_code,
-				    unsigned long fault_addr)
+static bool ex_handler_fprestore(const struct exception_table_entry *fixup,
+				 struct pt_regs *regs)
 {
 	regs->ip = ex_fixup_addr(fixup);
 
@@ -68,98 +68,77 @@ __visible bool ex_handler_fprestore(const struct exception_table_entry *fixup,
 	__restore_fpregs_from_fpstate(&init_fpstate, xfeatures_mask_fpstate());
 	return true;
 }
-EXPORT_SYMBOL_GPL(ex_handler_fprestore);
 
-__visible bool ex_handler_uaccess(const struct exception_table_entry *fixup,
-				  struct pt_regs *regs, int trapnr,
-				  unsigned long error_code,
-				  unsigned long fault_addr)
+static bool ex_handler_uaccess(const struct exception_table_entry *fixup,
+			       struct pt_regs *regs, int trapnr)
 {
 	WARN_ONCE(trapnr == X86_TRAP_GP, "General protection fault in user access. Non-canonical address?");
-	regs->ip = ex_fixup_addr(fixup);
-	return true;
+	return ex_handler_default(fixup, regs);
 }
-EXPORT_SYMBOL(ex_handler_uaccess);
 
-__visible bool ex_handler_copy(const struct exception_table_entry *fixup,
-			       struct pt_regs *regs, int trapnr,
-			       unsigned long error_code,
-			       unsigned long fault_addr)
+static bool ex_handler_copy(const struct exception_table_entry *fixup,
+			    struct pt_regs *regs, int trapnr)
 {
 	WARN_ONCE(trapnr == X86_TRAP_GP, "General protection fault in user access. Non-canonical address?");
-	regs->ip = ex_fixup_addr(fixup);
-	regs->ax = trapnr;
-	return true;
+	return ex_handler_fault(fixup, regs, trapnr);
 }
-EXPORT_SYMBOL(ex_handler_copy);
 
-__visible bool ex_handler_rdmsr_unsafe(const struct exception_table_entry *fixup,
-				       struct pt_regs *regs, int trapnr,
-				       unsigned long error_code,
-				       unsigned long fault_addr)
+static bool ex_handler_msr(const struct exception_table_entry *fixup,
+			   struct pt_regs *regs, bool wrmsr, bool safe, int reg)
 {
-	if (pr_warn_once("unchecked MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pS)\n",
-			 (unsigned int)regs->cx, regs->ip, (void *)regs->ip))
+	if (__ONCE_LITE_IF(!safe && wrmsr)) {
+		pr_warn("unchecked MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pS)\n",
+			(unsigned int)regs->cx, (unsigned int)regs->dx,
+			(unsigned int)regs->ax,  regs->ip, (void *)regs->ip);
 		show_stack_regs(regs);
+	}
 
-	/* Pretend that the read succeeded and returned 0. */
-	regs->ip = ex_fixup_addr(fixup);
-	regs->ax = 0;
-	regs->dx = 0;
-	return true;
-}
-EXPORT_SYMBOL(ex_handler_rdmsr_unsafe);
-
-__visible bool ex_handler_wrmsr_unsafe(const struct exception_table_entry *fixup,
-				       struct pt_regs *regs, int trapnr,
-				       unsigned long error_code,
-				       unsigned long fault_addr)
-{
-	if (pr_warn_once("unchecked MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pS)\n",
-			 (unsigned int)regs->cx, (unsigned int)regs->dx,
-			 (unsigned int)regs->ax,  regs->ip, (void *)regs->ip))
+	if (__ONCE_LITE_IF(!safe && !wrmsr)) {
+		pr_warn("unchecked MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pS)\n",
+			(unsigned int)regs->cx, regs->ip, (void *)regs->ip);
 		show_stack_regs(regs);
+	}
 
-	/* Pretend that the write succeeded. */
-	regs->ip = ex_fixup_addr(fixup);
-	return true;
+	if (!wrmsr) {
+		/* Pretend that the read succeeded and returned 0. */
+		regs->ax = 0;
+		regs->dx = 0;
+	}
+
+	if (safe)
+		*pt_regs_nr(regs, reg) = -EIO;
+
+	return ex_handler_default(fixup, regs);
 }
-EXPORT_SYMBOL(ex_handler_wrmsr_unsafe);
 
-__visible bool ex_handler_clear_fs(const struct exception_table_entry *fixup,
-				   struct pt_regs *regs, int trapnr,
-				   unsigned long error_code,
-				   unsigned long fault_addr)
+static bool ex_handler_clear_fs(const struct exception_table_entry *fixup,
+				struct pt_regs *regs)
 {
 	if (static_cpu_has(X86_BUG_NULL_SEG))
 		asm volatile ("mov %0, %%fs" : : "rm" (__USER_DS));
 	asm volatile ("mov %0, %%fs" : : "rm" (0));
-	return ex_handler_default(fixup, regs, trapnr, error_code, fault_addr);
+	return ex_handler_default(fixup, regs);
 }
-EXPORT_SYMBOL(ex_handler_clear_fs);
 
-enum handler_type ex_get_fault_handler_type(unsigned long ip)
+static bool ex_handler_imm_reg(const struct exception_table_entry *fixup,
+			       struct pt_regs *regs, int reg, int imm)
 {
-	const struct exception_table_entry *e;
-	ex_handler_t handler;
+	*pt_regs_nr(regs, reg) = (long)imm;
+	return ex_handler_default(fixup, regs);
+}
 
-	e = search_exception_tables(ip);
-	if (!e)
-		return EX_HANDLER_NONE;
-	handler = ex_fixup_handler(e);
-	if (handler == ex_handler_fault)
-		return EX_HANDLER_FAULT;
-	else if (handler == ex_handler_uaccess || handler == ex_handler_copy)
-		return EX_HANDLER_UACCESS;
-	else
-		return EX_HANDLER_OTHER;
+int ex_get_fixup_type(unsigned long ip)
+{
+	const struct exception_table_entry *e = search_exception_tables(ip);
+
+	return e ? FIELD_GET(EX_DATA_TYPE_MASK, e->data) : EX_TYPE_NONE;
 }
 
 int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code,
 		    unsigned long fault_addr)
 {
 	const struct exception_table_entry *e;
-	ex_handler_t handler;
+	int type, reg, imm;
 
 #ifdef CONFIG_PNPBIOS
 	if (unlikely(SEGMENT_IS_PNP_CODE(regs->cs))) {
@@ -179,8 +158,48 @@ int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code,
 	if (!e)
 		return 0;
 
-	handler = ex_fixup_handler(e);
-	return handler(e, regs, trapnr, error_code, fault_addr);
+	type = FIELD_GET(EX_DATA_TYPE_MASK, e->data);
+	reg  = FIELD_GET(EX_DATA_REG_MASK,  e->data);
+	imm  = FIELD_GET(EX_DATA_IMM_MASK,  e->data);
+
+	switch (type) {
+	case EX_TYPE_DEFAULT:
+	case EX_TYPE_DEFAULT_MCE_SAFE:
+		return ex_handler_default(e, regs);
+	case EX_TYPE_FAULT:
+	case EX_TYPE_FAULT_MCE_SAFE:
+		return ex_handler_fault(e, regs, trapnr);
+	case EX_TYPE_UACCESS:
+		return ex_handler_uaccess(e, regs, trapnr);
+	case EX_TYPE_COPY:
+		return ex_handler_copy(e, regs, trapnr);
+	case EX_TYPE_CLEAR_FS:
+		return ex_handler_clear_fs(e, regs);
+	case EX_TYPE_FPU_RESTORE:
+		return ex_handler_fprestore(e, regs);
+	case EX_TYPE_BPF:
+		return ex_handler_bpf(e, regs);
+	case EX_TYPE_WRMSR:
+		return ex_handler_msr(e, regs, true, false, reg);
+	case EX_TYPE_RDMSR:
+		return ex_handler_msr(e, regs, false, false, reg);
+	case EX_TYPE_WRMSR_SAFE:
+		return ex_handler_msr(e, regs, true, true, reg);
+	case EX_TYPE_RDMSR_SAFE:
+		return ex_handler_msr(e, regs, false, true, reg);
+	case EX_TYPE_WRMSR_IN_MCE:
+		ex_handler_msr_mce(regs, true);
+		break;
+	case EX_TYPE_RDMSR_IN_MCE:
+		ex_handler_msr_mce(regs, false);
+		break;
+	case EX_TYPE_POP_REG:
+		regs->sp += sizeof(long);
+		fallthrough;
+	case EX_TYPE_IMM_REG:
+		return ex_handler_imm_reg(e, regs, reg, imm);
+	}
+	BUG();
 }
 
 extern unsigned int early_recursion_flag;
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 23a14d82e783..0e3667e529ab 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -78,10 +78,20 @@ static uint8_t __pte2cachemode_tbl[8] = {
 	[__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC,
 };
 
-/* Check that the write-protect PAT entry is set for write-protect */
+/*
+ * Check that the write-protect PAT entry is set for write-protect.
+ * To do this without making assumptions how PAT has been set up (Xen has
+ * another layout than the kernel), translate the _PAGE_CACHE_MODE_WP cache
+ * mode via the __cachemode2pte_tbl[] into protection bits (those protection
+ * bits will select a cache mode of WP or better), and then translate the
+ * protection bits back into the cache mode using __pte2cm_idx() and the
+ * __pte2cachemode_tbl[] array. This will return the really used cache mode.
+ */
 bool x86_has_pat_wp(void)
 {
-	return __pte2cachemode_tbl[_PAGE_CACHE_MODE_WP] == _PAGE_CACHE_MODE_WP;
+	uint16_t prot = __cachemode2pte_tbl[_PAGE_CACHE_MODE_WP];
+
+	return __pte2cachemode_tbl[__pte2cm_idx(prot)] == _PAGE_CACHE_MODE_WP;
 }
 
 enum page_cache_mode pgprot2cachemode(pgprot_t pgprot)
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index b01f5d2caad0..200ad5ceeb43 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -646,7 +646,7 @@ phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end,
 			pages++;
 			spin_lock(&init_mm.page_table_lock);
 
-			prot = __pgprot(pgprot_val(prot) | __PAGE_KERNEL_LARGE);
+			prot = __pgprot(pgprot_val(prot) | _PAGE_PSE);
 
 			set_pte_init((pte_t *)pud,
 				     pfn_pte((paddr & PUD_MASK) >> PAGE_SHIFT,
diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S
index 3d1dba05fce4..9de3d900bc92 100644
--- a/arch/x86/mm/mem_encrypt_boot.S
+++ b/arch/x86/mm/mem_encrypt_boot.S
@@ -65,7 +65,10 @@ SYM_FUNC_START(sme_encrypt_execute)
 	movq	%rbp, %rsp		/* Restore original stack pointer */
 	pop	%rbp
 
-	RET
+	/* Offset to __x86_return_thunk would be wrong here */
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
 SYM_FUNC_END(sme_encrypt_execute)
 
 SYM_FUNC_START(__enc_copy)
@@ -151,6 +154,9 @@ SYM_FUNC_START(__enc_copy)
 	pop	%r12
 	pop	%r15
 
-	RET
+	/* Offset to __x86_return_thunk would be wrong here */
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
 .L__enc_copy_end:
 SYM_FUNC_END(__enc_copy)
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 1e9b93b088db..e360c6892a58 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -860,7 +860,7 @@ void debug_cpumask_set_cpu(int cpu, int node, bool enable)
 		return;
 	}
 	mask = node_to_cpumask_map[node];
-	if (!mask) {
+	if (!cpumask_available(mask)) {
 		pr_err("node_to_cpumask_map[%i] NULL\n", node);
 		dump_stack();
 		return;
@@ -906,7 +906,7 @@ const struct cpumask *cpumask_of_node(int node)
 		dump_stack();
 		return cpu_none_mask;
 	}
-	if (node_to_cpumask_map[node] == NULL) {
+	if (!cpumask_available(node_to_cpumask_map[node])) {
 		printk(KERN_WARNING
 			"cpumask_of_node(%d): no node_to_cpumask_map!\n",
 			node);
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 8dca2bcbb0ea..dccaab2113f9 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -15,7 +15,6 @@
 #include <asm/set_memory.h>
 #include <asm/nospec-branch.h>
 #include <asm/text-patching.h>
-#include <asm/asm-prototypes.h>
 
 static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 {
@@ -225,6 +224,14 @@ static void jit_fill_hole(void *area, unsigned int size)
 
 struct jit_context {
 	int cleanup_addr; /* Epilogue code offset */
+
+	/*
+	 * Program specific offsets of labels in the code; these rely on the
+	 * JIT doing at least 2 passes, recording the position on the first
+	 * pass, only to generate the correct offset on the second pass.
+	 */
+	int tail_call_direct_label;
+	int tail_call_indirect_label;
 };
 
 /* Maximum number of bytes emitted while JITing one eBPF insn */
@@ -380,20 +387,38 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 	return __bpf_arch_text_poke(ip, t, old_addr, new_addr, true);
 }
 
-static int get_pop_bytes(bool *callee_regs_used)
+#define EMIT_LFENCE()	EMIT3(0x0F, 0xAE, 0xE8)
+
+static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip)
 {
-	int bytes = 0;
+	u8 *prog = *pprog;
 
-	if (callee_regs_used[3])
-		bytes += 2;
-	if (callee_regs_used[2])
-		bytes += 2;
-	if (callee_regs_used[1])
-		bytes += 2;
-	if (callee_regs_used[0])
-		bytes += 1;
+#ifdef CONFIG_RETPOLINE
+	if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) {
+		EMIT_LFENCE();
+		EMIT2(0xFF, 0xE0 + reg);
+	} else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) {
+		emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip);
+	} else
+#endif
+	EMIT2(0xFF, 0xE0 + reg);
+
+	*pprog = prog;
+}
+
+static void emit_return(u8 **pprog, u8 *ip)
+{
+	u8 *prog = *pprog;
+
+	if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) {
+		emit_jump(&prog, &__x86_return_thunk, ip);
+	} else {
+		EMIT1(0xC3);		/* ret */
+		if (IS_ENABLED(CONFIG_SLS))
+			EMIT1(0xCC);	/* int3 */
+	}
 
-	return bytes;
+	*pprog = prog;
 }
 
 /*
@@ -411,29 +436,12 @@ static int get_pop_bytes(bool *callee_regs_used)
  * out:
  */
 static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
-					u32 stack_depth)
+					u32 stack_depth, u8 *ip,
+					struct jit_context *ctx)
 {
 	int tcc_off = -4 - round_up(stack_depth, 8);
-	u8 *prog = *pprog;
-	int pop_bytes = 0;
-	int off1 = 42;
-	int off2 = 31;
-	int off3 = 9;
-
-	/* count the additional bytes used for popping callee regs from stack
-	 * that need to be taken into account for each of the offsets that
-	 * are used for bailing out of the tail call
-	 */
-	pop_bytes = get_pop_bytes(callee_regs_used);
-	off1 += pop_bytes;
-	off2 += pop_bytes;
-	off3 += pop_bytes;
-
-	if (stack_depth) {
-		off1 += 7;
-		off2 += 7;
-		off3 += 7;
-	}
+	u8 *prog = *pprog, *start = *pprog;
+	int offset;
 
 	/*
 	 * rdi - pointer to ctx
@@ -448,8 +456,9 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
 	EMIT2(0x89, 0xD2);                        /* mov edx, edx */
 	EMIT3(0x39, 0x56,                         /* cmp dword ptr [rsi + 16], edx */
 	      offsetof(struct bpf_array, map.max_entries));
-#define OFFSET1 (off1 + RETPOLINE_RCX_BPF_JIT_SIZE) /* Number of bytes to jump */
-	EMIT2(X86_JBE, OFFSET1);                  /* jbe out */
+
+	offset = ctx->tail_call_indirect_label - (prog + 2 - start);
+	EMIT2(X86_JBE, offset);                   /* jbe out */
 
 	/*
 	 * if (tail_call_cnt > MAX_TAIL_CALL_CNT)
@@ -457,8 +466,9 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
 	 */
 	EMIT2_off32(0x8B, 0x85, tcc_off);         /* mov eax, dword ptr [rbp - tcc_off] */
 	EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT);     /* cmp eax, MAX_TAIL_CALL_CNT */
-#define OFFSET2 (off2 + RETPOLINE_RCX_BPF_JIT_SIZE)
-	EMIT2(X86_JA, OFFSET2);                   /* ja out */
+
+	offset = ctx->tail_call_indirect_label - (prog + 2 - start);
+	EMIT2(X86_JA, offset);                    /* ja out */
 	EMIT3(0x83, 0xC0, 0x01);                  /* add eax, 1 */
 	EMIT2_off32(0x89, 0x85, tcc_off);         /* mov dword ptr [rbp - tcc_off], eax */
 
@@ -471,12 +481,11 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
 	 *	goto out;
 	 */
 	EMIT3(0x48, 0x85, 0xC9);                  /* test rcx,rcx */
-#define OFFSET3 (off3 + RETPOLINE_RCX_BPF_JIT_SIZE)
-	EMIT2(X86_JE, OFFSET3);                   /* je out */
 
-	*pprog = prog;
-	pop_callee_regs(pprog, callee_regs_used);
-	prog = *pprog;
+	offset = ctx->tail_call_indirect_label - (prog + 2 - start);
+	EMIT2(X86_JE, offset);                    /* je out */
+
+	pop_callee_regs(&prog, callee_regs_used);
 
 	EMIT1(0x58);                              /* pop rax */
 	if (stack_depth)
@@ -493,41 +502,21 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
 	 * rdi == ctx (1st arg)
 	 * rcx == prog->bpf_func + X86_TAIL_CALL_OFFSET
 	 */
-	RETPOLINE_RCX_BPF_JIT();
+	emit_indirect_jump(&prog, 1 /* rcx */, ip + (prog - start));
 
 	/* out: */
+	ctx->tail_call_indirect_label = prog - start;
 	*pprog = prog;
 }
 
 static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke,
-				      u8 **pprog, int addr, u8 *image,
-				      bool *callee_regs_used, u32 stack_depth)
+				      u8 **pprog, u8 *ip,
+				      bool *callee_regs_used, u32 stack_depth,
+				      struct jit_context *ctx)
 {
 	int tcc_off = -4 - round_up(stack_depth, 8);
-	u8 *prog = *pprog;
-	int pop_bytes = 0;
-	int off1 = 20;
-	int poke_off;
-
-	/* count the additional bytes used for popping callee regs to stack
-	 * that need to be taken into account for jump offset that is used for
-	 * bailing out from of the tail call when limit is reached
-	 */
-	pop_bytes = get_pop_bytes(callee_regs_used);
-	off1 += pop_bytes;
-
-	/*
-	 * total bytes for:
-	 * - nop5/ jmpq $off
-	 * - pop callee regs
-	 * - sub rsp, $val if depth > 0
-	 * - pop rax
-	 */
-	poke_off = X86_PATCH_SIZE + pop_bytes + 1;
-	if (stack_depth) {
-		poke_off += 7;
-		off1 += 7;
-	}
+	u8 *prog = *pprog, *start = *pprog;
+	int offset;
 
 	/*
 	 * if (tail_call_cnt > MAX_TAIL_CALL_CNT)
@@ -535,28 +524,30 @@ static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke,
 	 */
 	EMIT2_off32(0x8B, 0x85, tcc_off);             /* mov eax, dword ptr [rbp - tcc_off] */
 	EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT);         /* cmp eax, MAX_TAIL_CALL_CNT */
-	EMIT2(X86_JA, off1);                          /* ja out */
+
+	offset = ctx->tail_call_direct_label - (prog + 2 - start);
+	EMIT2(X86_JA, offset);                        /* ja out */
 	EMIT3(0x83, 0xC0, 0x01);                      /* add eax, 1 */
 	EMIT2_off32(0x89, 0x85, tcc_off);             /* mov dword ptr [rbp - tcc_off], eax */
 
-	poke->tailcall_bypass = image + (addr - poke_off - X86_PATCH_SIZE);
+	poke->tailcall_bypass = ip + (prog - start);
 	poke->adj_off = X86_TAIL_CALL_OFFSET;
-	poke->tailcall_target = image + (addr - X86_PATCH_SIZE);
+	poke->tailcall_target = ip + ctx->tail_call_direct_label - X86_PATCH_SIZE;
 	poke->bypass_addr = (u8 *)poke->tailcall_target + X86_PATCH_SIZE;
 
 	emit_jump(&prog, (u8 *)poke->tailcall_target + X86_PATCH_SIZE,
 		  poke->tailcall_bypass);
 
-	*pprog = prog;
-	pop_callee_regs(pprog, callee_regs_used);
-	prog = *pprog;
+	pop_callee_regs(&prog, callee_regs_used);
 	EMIT1(0x58);                                  /* pop rax */
 	if (stack_depth)
 		EMIT3_off32(0x48, 0x81, 0xC4, round_up(stack_depth, 8));
 
 	memcpy(prog, x86_nops[5], X86_PATCH_SIZE);
 	prog += X86_PATCH_SIZE;
+
 	/* out: */
+	ctx->tail_call_direct_label = prog - start;
 
 	*pprog = prog;
 }
@@ -841,9 +832,7 @@ static int emit_atomic(u8 **pprog, u8 atomic_op,
 	return 0;
 }
 
-static bool ex_handler_bpf(const struct exception_table_entry *x,
-			   struct pt_regs *regs, int trapnr,
-			   unsigned long error_code, unsigned long fault_addr)
+bool ex_handler_bpf(const struct exception_table_entry *x, struct pt_regs *regs)
 {
 	u32 reg = x->fixup >> 8;
 
@@ -1228,8 +1217,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			/* speculation barrier */
 		case BPF_ST | BPF_NOSPEC:
 			if (boot_cpu_has(X86_FEATURE_XMM2))
-				/* Emit 'lfence' */
-				EMIT3(0x0F, 0xAE, 0xE8);
+				EMIT_LFENCE();
 			break;
 
 			/* ST: *(u8*)(dst_reg + off) = imm */
@@ -1354,12 +1342,7 @@ st:			if (is_imm8(insn->off))
 				}
 				ex->insn = delta;
 
-				delta = (u8 *)ex_handler_bpf - (u8 *)&ex->handler;
-				if (!is_simm32(delta)) {
-					pr_err("extable->handler doesn't fit into 32-bit\n");
-					return -EFAULT;
-				}
-				ex->handler = delta;
+				ex->data = EX_TYPE_BPF;
 
 				if (dst_reg > BPF_REG_9) {
 					pr_err("verifier error\n");
@@ -1454,13 +1437,16 @@ st:			if (is_imm8(insn->off))
 		case BPF_JMP | BPF_TAIL_CALL:
 			if (imm32)
 				emit_bpf_tail_call_direct(&bpf_prog->aux->poke_tab[imm32 - 1],
-							  &prog, addrs[i], image,
+							  &prog, image + addrs[i - 1],
 							  callee_regs_used,
-							  bpf_prog->aux->stack_depth);
+							  bpf_prog->aux->stack_depth,
+							  ctx);
 			else
 				emit_bpf_tail_call_indirect(&prog,
 							    callee_regs_used,
-							    bpf_prog->aux->stack_depth);
+							    bpf_prog->aux->stack_depth,
+							    image + addrs[i - 1],
+							    ctx);
 			break;
 
 			/* cond jump */
@@ -1703,7 +1689,7 @@ emit_jmp:
 			ctx->cleanup_addr = proglen;
 			pop_callee_regs(&prog, callee_regs_used);
 			EMIT1(0xC9);         /* leave */
-			EMIT1(0xC3);         /* ret */
+			emit_return(&prog, image + addrs[i - 1] + (prog - temp));
 			break;
 
 		default:
@@ -2149,7 +2135,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	if (flags & BPF_TRAMP_F_SKIP_FRAME)
 		/* skip our return address and return to parent */
 		EMIT4(0x48, 0x83, 0xC4, 8); /* add rsp, 8 */
-	EMIT1(0xC3); /* ret */
+	emit_return(&prog, prog);
 	/* Make sure the trampoline generation logic doesn't overflow */
 	if (WARN_ON_ONCE(prog > (u8 *)image_end - BPF_INSN_SAFETY)) {
 		ret = -EFAULT;
@@ -2162,24 +2148,6 @@ cleanup:
 	return ret;
 }
 
-static int emit_fallback_jump(u8 **pprog)
-{
-	u8 *prog = *pprog;
-	int err = 0;
-
-#ifdef CONFIG_RETPOLINE
-	/* Note that this assumes the the compiler uses external
-	 * thunks for indirect calls. Both clang and GCC use the same
-	 * naming convention for external thunks.
-	 */
-	err = emit_jump(&prog, __x86_indirect_thunk_rdx, prog);
-#else
-	EMIT2(0xFF, 0xE2);	/* jmp rdx */
-#endif
-	*pprog = prog;
-	return err;
-}
-
 static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs)
 {
 	u8 *jg_reloc, *prog = *pprog;
@@ -2201,9 +2169,7 @@ static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs)
 		if (err)
 			return err;
 
-		err = emit_fallback_jump(&prog);	/* jmp thunk/indirect */
-		if (err)
-			return err;
+		emit_indirect_jump(&prog, 2 /* rdx */, prog);
 
 		*pprog = prog;
 		return 0;
diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c
index 3bfda5f502cb..da9b7cfa4632 100644
--- a/arch/x86/net/bpf_jit_comp32.c
+++ b/arch/x86/net/bpf_jit_comp32.c
@@ -15,6 +15,7 @@
 #include <asm/cacheflush.h>
 #include <asm/set_memory.h>
 #include <asm/nospec-branch.h>
+#include <asm/asm-prototypes.h>
 #include <linux/bpf.h>
 
 /*
@@ -1267,6 +1268,21 @@ static void emit_epilogue(u8 **pprog, u32 stack_depth)
 	*pprog = prog;
 }
 
+static int emit_jmp_edx(u8 **pprog, u8 *ip)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+
+#ifdef CONFIG_RETPOLINE
+	EMIT1_off32(0xE9, (u8 *)__x86_indirect_thunk_edx - (ip + 5));
+#else
+	EMIT2(0xFF, 0xE2);
+#endif
+	*pprog = prog;
+
+	return cnt;
+}
+
 /*
  * Generate the following code:
  * ... bpf_tail_call(void *ctx, struct bpf_array *array, u64 index) ...
@@ -1280,7 +1296,7 @@ static void emit_epilogue(u8 **pprog, u32 stack_depth)
  *   goto *(prog->bpf_func + prologue_size);
  * out:
  */
-static void emit_bpf_tail_call(u8 **pprog)
+static void emit_bpf_tail_call(u8 **pprog, u8 *ip)
 {
 	u8 *prog = *pprog;
 	int cnt = 0;
@@ -1362,7 +1378,7 @@ static void emit_bpf_tail_call(u8 **pprog)
 	 * eax == ctx (1st arg)
 	 * edx == prog->bpf_func + prologue_size
 	 */
-	RETPOLINE_EDX_BPF_JIT();
+	cnt += emit_jmp_edx(&prog, ip + cnt);
 
 	if (jmp_label1 == -1)
 		jmp_label1 = cnt;
@@ -2122,7 +2138,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			break;
 		}
 		case BPF_JMP | BPF_TAIL_CALL:
-			emit_bpf_tail_call(&prog);
+			emit_bpf_tail_call(&prog, image + addrs[i - 1]);
 			break;
 
 		/* cond jump */
diff --git a/arch/x86/platform/efi/efi_thunk_64.S b/arch/x86/platform/efi/efi_thunk_64.S
index f2a8eec69f8f..a7ffe30e8614 100644
--- a/arch/x86/platform/efi/efi_thunk_64.S
+++ b/arch/x86/platform/efi/efi_thunk_64.S
@@ -22,6 +22,7 @@
 #include <linux/linkage.h>
 #include <asm/page_types.h>
 #include <asm/segment.h>
+#include <asm/nospec-branch.h>
 
 	.text
 	.code64
@@ -63,7 +64,9 @@ SYM_CODE_START(__efi64_thunk)
 1:	movq	24(%rsp), %rsp
 	pop	%rbx
 	pop	%rbp
-	RET
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
 
 	.code32
 2:	pushl	$__KERNEL_CS
diff --git a/arch/x86/platform/olpc/olpc-xo1-sci.c b/arch/x86/platform/olpc/olpc-xo1-sci.c
index f03a6883dcc6..89f25af4b3c3 100644
--- a/arch/x86/platform/olpc/olpc-xo1-sci.c
+++ b/arch/x86/platform/olpc/olpc-xo1-sci.c
@@ -80,7 +80,7 @@ static void send_ebook_state(void)
 		return;
 	}
 
-	if (!!test_bit(SW_TABLET_MODE, ebook_switch_idev->sw) == state)
+	if (test_bit(SW_TABLET_MODE, ebook_switch_idev->sw) == !!state)
 		return; /* Nothing new to report. */
 
 	input_report_switch(ebook_switch_idev, SW_TABLET_MODE, state);
diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile
index 5ccb18290d71..a8591ec8ae68 100644
--- a/arch/x86/um/Makefile
+++ b/arch/x86/um/Makefile
@@ -28,7 +28,8 @@ else
 
 obj-y += syscalls_64.o vdso/
 
-subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o ../entry/thunk_64.o
+subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o
+subarch-$(CONFIG_PREEMPTION) += ../entry/thunk_64.o
 
 endif
 
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 8bfc10330107..1f80dd3a2dd4 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -922,7 +922,7 @@ void xen_enable_sysenter(void)
 	if (!boot_cpu_has(sysenter_feature))
 		return;
 
-	ret = register_callback(CALLBACKTYPE_sysenter, xen_sysenter_target);
+	ret = register_callback(CALLBACKTYPE_sysenter, xen_entry_SYSENTER_compat);
 	if(ret != 0)
 		setup_clear_cpu_cap(sysenter_feature);
 }
@@ -931,7 +931,7 @@ void xen_enable_syscall(void)
 {
 	int ret;
 
-	ret = register_callback(CALLBACKTYPE_syscall, xen_syscall_target);
+	ret = register_callback(CALLBACKTYPE_syscall, xen_entry_SYSCALL_64);
 	if (ret != 0) {
 		printk(KERN_ERR "Failed to set syscall callback: %d\n", ret);
 		/* Pretty fatal; 64-bit userspace has no other
@@ -940,7 +940,7 @@ void xen_enable_syscall(void)
 
 	if (boot_cpu_has(X86_FEATURE_SYSCALL32)) {
 		ret = register_callback(CALLBACKTYPE_syscall32,
-					xen_syscall32_target);
+					xen_entry_SYSCALL_compat);
 		if (ret != 0)
 			setup_clear_cpu_cap(X86_FEATURE_SYSCALL32);
 	}
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 962d30ea01a2..1b757a1ee1bb 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -120,7 +120,7 @@ SYM_FUNC_END(xen_read_cr2_direct);
 
 .macro xen_pv_trap name
 SYM_CODE_START(xen_\name)
-	UNWIND_HINT_EMPTY
+	UNWIND_HINT_ENTRY
 	pop %rcx
 	pop %r11
 	jmp  \name
@@ -227,8 +227,8 @@ SYM_CODE_END(xenpv_restore_regs_and_return_to_usermode)
  */
 
 /* Normal 64-bit system call target */
-SYM_CODE_START(xen_syscall_target)
-	UNWIND_HINT_EMPTY
+SYM_CODE_START(xen_entry_SYSCALL_64)
+	UNWIND_HINT_ENTRY
 	popq %rcx
 	popq %r11
 
@@ -241,13 +241,13 @@ SYM_CODE_START(xen_syscall_target)
 	movq $__USER_CS, 1*8(%rsp)
 
 	jmp entry_SYSCALL_64_after_hwframe
-SYM_CODE_END(xen_syscall_target)
+SYM_CODE_END(xen_entry_SYSCALL_64)
 
 #ifdef CONFIG_IA32_EMULATION
 
 /* 32-bit compat syscall target */
-SYM_CODE_START(xen_syscall32_target)
-	UNWIND_HINT_EMPTY
+SYM_CODE_START(xen_entry_SYSCALL_compat)
+	UNWIND_HINT_ENTRY
 	popq %rcx
 	popq %r11
 
@@ -260,11 +260,11 @@ SYM_CODE_START(xen_syscall32_target)
 	movq $__USER32_CS, 1*8(%rsp)
 
 	jmp entry_SYSCALL_compat_after_hwframe
-SYM_CODE_END(xen_syscall32_target)
+SYM_CODE_END(xen_entry_SYSCALL_compat)
 
 /* 32-bit compat sysenter target */
-SYM_CODE_START(xen_sysenter_target)
-	UNWIND_HINT_EMPTY
+SYM_CODE_START(xen_entry_SYSENTER_compat)
+	UNWIND_HINT_ENTRY
 	/*
 	 * NB: Xen is polite and clears TF from EFLAGS for us.  This means
 	 * that we don't need to guard against single step exceptions here.
@@ -281,18 +281,18 @@ SYM_CODE_START(xen_sysenter_target)
 	movq $__USER32_CS, 1*8(%rsp)
 
 	jmp entry_SYSENTER_compat_after_hwframe
-SYM_CODE_END(xen_sysenter_target)
+SYM_CODE_END(xen_entry_SYSENTER_compat)
 
 #else /* !CONFIG_IA32_EMULATION */
 
-SYM_CODE_START(xen_syscall32_target)
-SYM_CODE_START(xen_sysenter_target)
-	UNWIND_HINT_EMPTY
+SYM_CODE_START(xen_entry_SYSCALL_compat)
+SYM_CODE_START(xen_entry_SYSENTER_compat)
+	UNWIND_HINT_ENTRY
 	lea 16(%rsp), %rsp	/* strip %rcx, %r11 */
 	mov $-ENOSYS, %rax
 	pushq $0
 	jmp hypercall_iret
-SYM_CODE_END(xen_sysenter_target)
-SYM_CODE_END(xen_syscall32_target)
+SYM_CODE_END(xen_entry_SYSENTER_compat)
+SYM_CODE_END(xen_entry_SYSCALL_compat)
 
 #endif	/* CONFIG_IA32_EMULATION */
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 565062932ef1..2a3ef5fcba34 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -69,8 +69,9 @@ SYM_CODE_END(asm_cpu_bringup_and_idle)
 SYM_CODE_START(hypercall_page)
 	.rept (PAGE_SIZE / 32)
 		UNWIND_HINT_FUNC
-		.skip 31, 0x90
-		RET
+		ANNOTATE_UNRET_SAFE
+		ret
+		.skip 31, 0xcc
 	.endr
 
 #define HYPERCALL(n) \
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 8bc8b72a205d..16aed4b12129 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -10,10 +10,10 @@
 /* These are code, but not functions.  Defined in entry.S */
 extern const char xen_failsafe_callback[];
 
-void xen_sysenter_target(void);
+void xen_entry_SYSENTER_compat(void);
 #ifdef CONFIG_X86_64
-void xen_syscall_target(void);
-void xen_syscall32_target(void);
+void xen_entry_SYSCALL_64(void);
+void xen_entry_SYSCALL_compat(void);
 #endif
 
 extern void *xen_initial_gdt;
diff --git a/arch/xtensa/platforms/iss/network.c b/arch/xtensa/platforms/iss/network.c
index 4986226a5ab2..08d70c868c13 100644
--- a/arch/xtensa/platforms/iss/network.c
+++ b/arch/xtensa/platforms/iss/network.c
@@ -502,16 +502,24 @@ static const struct net_device_ops iss_netdev_ops = {
 	.ndo_set_rx_mode	= iss_net_set_multicast_list,
 };
 
-static int iss_net_configure(int index, char *init)
+static void iss_net_pdev_release(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct iss_net_private *lp =
+		container_of(pdev, struct iss_net_private, pdev);
+
+	free_netdev(lp->dev);
+}
+
+static void iss_net_configure(int index, char *init)
 {
 	struct net_device *dev;
 	struct iss_net_private *lp;
-	int err;
 
 	dev = alloc_etherdev(sizeof(*lp));
 	if (dev == NULL) {
 		pr_err("eth_configure: failed to allocate device\n");
-		return 1;
+		return;
 	}
 
 	/* Initialize private element. */
@@ -540,7 +548,7 @@ static int iss_net_configure(int index, char *init)
 	if (!tuntap_probe(lp, index, init)) {
 		pr_err("%s: invalid arguments. Skipping device!\n",
 		       dev->name);
-		goto errout;
+		goto err_free_netdev;
 	}
 
 	pr_info("Netdevice %d (%pM)\n", index, dev->dev_addr);
@@ -548,7 +556,8 @@ static int iss_net_configure(int index, char *init)
 	/* sysfs register */
 
 	if (!driver_registered) {
-		platform_driver_register(&iss_net_driver);
+		if (platform_driver_register(&iss_net_driver))
+			goto err_free_netdev;
 		driver_registered = 1;
 	}
 
@@ -558,7 +567,9 @@ static int iss_net_configure(int index, char *init)
 
 	lp->pdev.id = index;
 	lp->pdev.name = DRIVER_NAME;
-	platform_device_register(&lp->pdev);
+	lp->pdev.dev.release = iss_net_pdev_release;
+	if (platform_device_register(&lp->pdev))
+		goto err_free_netdev;
 	SET_NETDEV_DEV(dev, &lp->pdev.dev);
 
 	dev->netdev_ops = &iss_netdev_ops;
@@ -567,23 +578,20 @@ static int iss_net_configure(int index, char *init)
 	dev->irq = -1;
 
 	rtnl_lock();
-	err = register_netdevice(dev);
-	rtnl_unlock();
-
-	if (err) {
+	if (register_netdevice(dev)) {
+		rtnl_unlock();
 		pr_err("%s: error registering net device!\n", dev->name);
-		/* XXX: should we call ->remove() here? */
-		free_netdev(dev);
-		return 1;
+		platform_device_unregister(&lp->pdev);
+		return;
 	}
+	rtnl_unlock();
 
 	timer_setup(&lp->tl, iss_net_user_timer_expire, 0);
 
-	return 0;
+	return;
 
-errout:
-	/* FIXME: unregister; free, etc.. */
-	return -EIO;
+err_free_netdev:
+	free_netdev(dev);
 }
 
 /* ------------------------------------------------------------------------- */
diff --git a/block/bio.c b/block/bio.c
index 8381c6690dd6..ba9120d4fe49 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -910,7 +910,7 @@ EXPORT_SYMBOL(bio_add_pc_page);
 int bio_add_zone_append_page(struct bio *bio, struct page *page,
 			     unsigned int len, unsigned int offset)
 {
-	struct request_queue *q = bio->bi_bdev->bd_disk->queue;
+	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
 	bool same_page = false;
 
 	if (WARN_ON_ONCE(bio_op(bio) != REQ_OP_ZONE_APPEND))
@@ -1054,7 +1054,7 @@ static int bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
 
 static int bio_iov_bvec_set_append(struct bio *bio, struct iov_iter *iter)
 {
-	struct request_queue *q = bio->bi_bdev->bd_disk->queue;
+	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
 	struct iov_iter i = *iter;
 
 	iov_iter_truncate(&i, queue_max_zone_append_sectors(q) << 9);
@@ -1071,6 +1071,37 @@ static void bio_put_pages(struct page **pages, size_t size, size_t off)
 		put_page(pages[i]);
 }
 
+static int bio_iov_add_page(struct bio *bio, struct page *page,
+		unsigned int len, unsigned int offset)
+{
+	bool same_page = false;
+
+	if (!__bio_try_merge_page(bio, page, len, offset, &same_page)) {
+		if (WARN_ON_ONCE(bio_full(bio, len)))
+			return -EINVAL;
+		__bio_add_page(bio, page, len, offset);
+		return 0;
+	}
+
+	if (same_page)
+		put_page(page);
+	return 0;
+}
+
+static int bio_iov_add_zone_append_page(struct bio *bio, struct page *page,
+		unsigned int len, unsigned int offset)
+{
+	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
+	bool same_page = false;
+
+	if (bio_add_hw_page(q, bio, page, len, offset,
+			queue_max_zone_append_sectors(q), &same_page) != len)
+		return -EINVAL;
+	if (same_page)
+		put_page(page);
+	return 0;
+}
+
 #define PAGE_PTRS_PER_BVEC     (sizeof(struct bio_vec) / sizeof(struct page *))
 
 /**
@@ -1089,61 +1120,11 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt;
 	struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
 	struct page **pages = (struct page **)bv;
-	bool same_page = false;
-	ssize_t size, left;
-	unsigned len, i;
-	size_t offset;
-
-	/*
-	 * Move page array up in the allocated memory for the bio vecs as far as
-	 * possible so that we can start filling biovecs from the beginning
-	 * without overwriting the temporary page array.
-	*/
-	BUILD_BUG_ON(PAGE_PTRS_PER_BVEC < 2);
-	pages += entries_left * (PAGE_PTRS_PER_BVEC - 1);
-
-	size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset);
-	if (unlikely(size <= 0))
-		return size ? size : -EFAULT;
-
-	for (left = size, i = 0; left > 0; left -= len, i++) {
-		struct page *page = pages[i];
-
-		len = min_t(size_t, PAGE_SIZE - offset, left);
-
-		if (__bio_try_merge_page(bio, page, len, offset, &same_page)) {
-			if (same_page)
-				put_page(page);
-		} else {
-			if (WARN_ON_ONCE(bio_full(bio, len))) {
-				bio_put_pages(pages + i, left, offset);
-				return -EINVAL;
-			}
-			__bio_add_page(bio, page, len, offset);
-		}
-		offset = 0;
-	}
-
-	iov_iter_advance(iter, size);
-	return 0;
-}
-
-static int __bio_iov_append_get_pages(struct bio *bio, struct iov_iter *iter)
-{
-	unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt;
-	unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt;
-	struct request_queue *q = bio->bi_bdev->bd_disk->queue;
-	unsigned int max_append_sectors = queue_max_zone_append_sectors(q);
-	struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
-	struct page **pages = (struct page **)bv;
 	ssize_t size, left;
 	unsigned len, i;
 	size_t offset;
 	int ret = 0;
 
-	if (WARN_ON_ONCE(!max_append_sectors))
-		return 0;
-
 	/*
 	 * Move page array up in the allocated memory for the bio vecs as far as
 	 * possible so that we can start filling biovecs from the beginning
@@ -1158,17 +1139,18 @@ static int __bio_iov_append_get_pages(struct bio *bio, struct iov_iter *iter)
 
 	for (left = size, i = 0; left > 0; left -= len, i++) {
 		struct page *page = pages[i];
-		bool same_page = false;
 
 		len = min_t(size_t, PAGE_SIZE - offset, left);
-		if (bio_add_hw_page(q, bio, page, len, offset,
-				max_append_sectors, &same_page) != len) {
+		if (bio_op(bio) == REQ_OP_ZONE_APPEND)
+			ret = bio_iov_add_zone_append_page(bio, page, len,
+					offset);
+		else
+			ret = bio_iov_add_page(bio, page, len, offset);
+
+		if (ret) {
 			bio_put_pages(pages + i, left, offset);
-			ret = -EINVAL;
 			break;
 		}
-		if (same_page)
-			put_page(page);
 		offset = 0;
 	}
 
@@ -1210,10 +1192,7 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	}
 
 	do {
-		if (bio_op(bio) == REQ_OP_ZONE_APPEND)
-			ret = __bio_iov_append_get_pages(bio, iter);
-		else
-			ret = __bio_iov_iter_get_pages(bio, iter);
+		ret = __bio_iov_iter_get_pages(bio, iter);
 	} while (!ret && iov_iter_count(iter) && !bio_full(bio, 0));
 
 	/* don't account direct I/O as memory stall */
@@ -1470,11 +1449,10 @@ again:
 	if (!bio_integrity_endio(bio))
 		return;
 
-	if (bio->bi_bdev && bio_flagged(bio, BIO_TRACKED))
-		rq_qos_done_bio(bio->bi_bdev->bd_disk->queue, bio);
+	rq_qos_done_bio(bio);
 
 	if (bio->bi_bdev && bio_flagged(bio, BIO_TRACE_COMPLETION)) {
-		trace_block_bio_complete(bio->bi_bdev->bd_disk->queue, bio);
+		trace_block_bio_complete(bdev_get_queue(bio->bi_bdev), bio);
 		bio_clear_flag(bio, BIO_TRACE_COMPLETION);
 	}
 
diff --git a/block/blk-core.c b/block/blk-core.c
index 5009b9f1c3c9..13e1fca1e923 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -447,7 +447,7 @@ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
 
 	while (!blk_try_enter_queue(q, pm)) {
 		if (flags & BLK_MQ_REQ_NOWAIT)
-			return -EBUSY;
+			return -EAGAIN;
 
 		/*
 		 * read pair of barrier in blk_freeze_queue_start(), we need to
@@ -478,7 +478,7 @@ static inline int bio_queue_enter(struct bio *bio)
 			if (test_bit(GD_DEAD, &disk->state))
 				goto dead;
 			bio_wouldblock_error(bio);
-			return -EBUSY;
+			return -EAGAIN;
 		}
 
 		/*
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 57299f860d41..90c05971f71e 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -265,6 +265,7 @@ int create_task_io_context(struct task_struct *task, gfp_t gfp_flags, int node)
 	INIT_RADIX_TREE(&ioc->icq_tree, GFP_ATOMIC);
 	INIT_HLIST_HEAD(&ioc->icq_list);
 	INIT_WORK(&ioc->release_work, ioc_release_fn);
+	ioc->ioprio = IOPRIO_DEFAULT;
 
 	/*
 	 * Try to install.  ioc shouldn't be installed if someone else
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index 10851493940c..069193dee95b 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -2893,15 +2893,21 @@ static int blk_iocost_init(struct request_queue *q)
 	 * called before policy activation completion, can't assume that the
 	 * target bio has an iocg associated and need to test for NULL iocg.
 	 */
-	rq_qos_add(q, rqos);
+	ret = rq_qos_add(q, rqos);
+	if (ret)
+		goto err_free_ioc;
+
 	ret = blkcg_activate_policy(q, &blkcg_policy_iocost);
-	if (ret) {
-		rq_qos_del(q, rqos);
-		free_percpu(ioc->pcpu_stat);
-		kfree(ioc);
-		return ret;
-	}
+	if (ret)
+		goto err_del_qos;
 	return 0;
+
+err_del_qos:
+	rq_qos_del(q, rqos);
+err_free_ioc:
+	free_percpu(ioc->pcpu_stat);
+	kfree(ioc);
+	return ret;
 }
 
 static struct blkcg_policy_data *ioc_cpd_alloc(gfp_t gfp)
diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c
index ce3847499d85..bdef8395af6e 100644
--- a/block/blk-iolatency.c
+++ b/block/blk-iolatency.c
@@ -601,7 +601,7 @@ static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio)
 	int inflight = 0;
 
 	blkg = bio->bi_blkg;
-	if (!blkg || !bio_flagged(bio, BIO_TRACKED))
+	if (!blkg || !bio_flagged(bio, BIO_QOS_THROTTLED))
 		return;
 
 	iolat = blkg_to_lat(bio->bi_blkg);
@@ -772,19 +772,23 @@ int blk_iolatency_init(struct request_queue *q)
 	rqos->ops = &blkcg_iolatency_ops;
 	rqos->q = q;
 
-	rq_qos_add(q, rqos);
-
+	ret = rq_qos_add(q, rqos);
+	if (ret)
+		goto err_free;
 	ret = blkcg_activate_policy(q, &blkcg_policy_iolatency);
-	if (ret) {
-		rq_qos_del(q, rqos);
-		kfree(blkiolat);
-		return ret;
-	}
+	if (ret)
+		goto err_qos_del;
 
 	timer_setup(&blkiolat->timer, blkiolatency_timer_fn, 0);
 	INIT_WORK(&blkiolat->enable_work, blkiolatency_enable_work_fn);
 
 	return 0;
+
+err_qos_del:
+	rq_qos_del(q, rqos);
+err_free:
+	kfree(blkiolat);
+	return ret;
 }
 
 static void iolatency_set_min_lat_nsec(struct blkcg_gq *blkg, u64 val)
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 3b38d15723de..7023257a133d 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -879,6 +879,9 @@ void blk_mq_debugfs_register_hctx(struct request_queue *q,
 	char name[20];
 	int i;
 
+	if (!q->debugfs_dir)
+		return;
+
 	snprintf(name, sizeof(name), "hctx%u", hctx->queue_num);
 	hctx->debugfs_dir = debugfs_create_dir(name, q->debugfs_dir);
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 95993c4efa49..1a28ba9017ed 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1400,7 +1400,8 @@ out:
 	/* If we didn't flush the entire list, we could have told the driver
 	 * there was more coming, but that turned out to be a lie.
 	 */
-	if ((!list_empty(list) || errors) && q->mq_ops->commit_rqs && queued)
+	if ((!list_empty(list) || errors || needs_resource ||
+	     ret == BLK_STS_DEV_RESOURCE) && q->mq_ops->commit_rqs && queued)
 		q->mq_ops->commit_rqs(hctx);
 	/*
 	 * Any items that need requeuing? Stuff them into hctx->dispatch,
@@ -2111,6 +2112,7 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 		list_del_init(&rq->queuelist);
 		ret = blk_mq_request_issue_directly(rq, list_empty(list));
 		if (ret != BLK_STS_OK) {
+			errors++;
 			if (ret == BLK_STS_RESOURCE ||
 					ret == BLK_STS_DEV_RESOURCE) {
 				blk_mq_request_bypass_insert(rq, false,
@@ -2118,7 +2120,6 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 				break;
 			}
 			blk_mq_end_request(rq, ret);
-			errors++;
 		} else
 			queued++;
 	}
diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h
index f000f83e0621..1655f76b6a1b 100644
--- a/block/blk-rq-qos.h
+++ b/block/blk-rq-qos.h
@@ -86,7 +86,7 @@ static inline void rq_wait_init(struct rq_wait *rq_wait)
 	init_waitqueue_head(&rq_wait->wait);
 }
 
-static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos)
+static inline int rq_qos_add(struct request_queue *q, struct rq_qos *rqos)
 {
 	/*
 	 * No IO can be in-flight when adding rqos, so freeze queue, which
@@ -98,6 +98,8 @@ static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos)
 	blk_mq_freeze_queue(q);
 
 	spin_lock_irq(&q->queue_lock);
+	if (rq_qos_id(q, rqos->id))
+		goto ebusy;
 	rqos->next = q->rq_qos;
 	q->rq_qos = rqos;
 	spin_unlock_irq(&q->queue_lock);
@@ -106,6 +108,13 @@ static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos)
 
 	if (rqos->ops->debugfs_attrs)
 		blk_mq_debugfs_register_rqos(rqos);
+
+	return 0;
+ebusy:
+	spin_unlock_irq(&q->queue_lock);
+	blk_mq_unfreeze_queue(q);
+	return -EBUSY;
+
 }
 
 static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos)
@@ -177,21 +186,22 @@ static inline void rq_qos_requeue(struct request_queue *q, struct request *rq)
 		__rq_qos_requeue(q->rq_qos, rq);
 }
 
-static inline void rq_qos_done_bio(struct request_queue *q, struct bio *bio)
+static inline void rq_qos_done_bio(struct bio *bio)
 {
-	if (q->rq_qos)
-		__rq_qos_done_bio(q->rq_qos, bio);
+	if (bio->bi_bdev && (bio_flagged(bio, BIO_QOS_THROTTLED) ||
+			     bio_flagged(bio, BIO_QOS_MERGED))) {
+		struct request_queue *q = bdev_get_queue(bio->bi_bdev);
+		if (q->rq_qos)
+			__rq_qos_done_bio(q->rq_qos, bio);
+	}
 }
 
 static inline void rq_qos_throttle(struct request_queue *q, struct bio *bio)
 {
-	/*
-	 * BIO_TRACKED lets controllers know that a bio went through the
-	 * normal rq_qos path.
-	 */
-	bio_set_flag(bio, BIO_TRACKED);
-	if (q->rq_qos)
+	if (q->rq_qos) {
+		bio_set_flag(bio, BIO_QOS_THROTTLED);
 		__rq_qos_throttle(q->rq_qos, bio);
+	}
 }
 
 static inline void rq_qos_track(struct request_queue *q, struct request *rq,
@@ -204,8 +214,10 @@ static inline void rq_qos_track(struct request_queue *q, struct request *rq,
 static inline void rq_qos_merge(struct request_queue *q, struct request *rq,
 				struct bio *bio)
 {
-	if (q->rq_qos)
+	if (q->rq_qos) {
+		bio_set_flag(bio, BIO_QOS_MERGED);
 		__rq_qos_merge(q->rq_qos, rq, bio);
+	}
 }
 
 static inline void rq_qos_queue_depth_changed(struct request_queue *q)
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index 0c119be0e813..ae6ea0b54579 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -820,6 +820,7 @@ int wbt_init(struct request_queue *q)
 {
 	struct rq_wb *rwb;
 	int i;
+	int ret;
 
 	rwb = kzalloc(sizeof(*rwb), GFP_KERNEL);
 	if (!rwb)
@@ -846,7 +847,10 @@ int wbt_init(struct request_queue *q)
 	/*
 	 * Assign rwb and add the stats callback.
 	 */
-	rq_qos_add(q, &rwb->rqos);
+	ret = rq_qos_add(q, &rwb->rqos);
+	if (ret)
+		goto err_free;
+
 	blk_stat_add_callback(q, rwb->cb);
 
 	rwb->min_lat_nsec = wbt_default_latency_nsec(q);
@@ -855,4 +859,10 @@ int wbt_init(struct request_queue *q)
 	wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
 
 	return 0;
+
+err_free:
+	blk_stat_free_callback(rwb->cb);
+	kfree(rwb);
+	return ret;
+
 }
diff --git a/block/ioprio.c b/block/ioprio.c
index 6f01d35a5145..6c830154856f 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -189,9 +189,9 @@ out:
 int ioprio_best(unsigned short aprio, unsigned short bprio)
 {
 	if (!ioprio_valid(aprio))
-		aprio = IOPRIO_DEFAULT;
+		aprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_BE_NORM);
 	if (!ioprio_valid(bprio))
-		bprio = IOPRIO_DEFAULT;
+		bprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_BE_NORM);
 
 	return min(aprio, bprio);
 }
diff --git a/crypto/Kconfig b/crypto/Kconfig
index 7acc545a5349..f1905ef79748 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -704,26 +704,8 @@ config CRYPTO_BLAKE2B
 
 	  See https://blake2.net for further information.
 
-config CRYPTO_BLAKE2S
-	tristate "BLAKE2s digest algorithm"
-	select CRYPTO_LIB_BLAKE2S_GENERIC
-	select CRYPTO_HASH
-	help
-	  Implementation of cryptographic hash function BLAKE2s
-	  optimized for 8-32bit platforms and can produce digests of any size
-	  between 1 to 32.  The keyed hash is also implemented.
-
-	  This module provides the following algorithms:
-
-	  - blake2s-128
-	  - blake2s-160
-	  - blake2s-224
-	  - blake2s-256
-
-	  See https://blake2.net for further information.
-
 config CRYPTO_BLAKE2S_X86
-	tristate "BLAKE2s digest algorithm (x86 accelerated version)"
+	bool "BLAKE2s digest algorithm (x86 accelerated version)"
 	depends on X86 && 64BIT
 	select CRYPTO_LIB_BLAKE2S_GENERIC
 	select CRYPTO_ARCH_HAVE_LIB_BLAKE2S
diff --git a/crypto/Makefile b/crypto/Makefile
index ca961dc61f7e..3724001c511b 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -83,7 +83,6 @@ obj-$(CONFIG_CRYPTO_STREEBOG) += streebog_generic.o
 obj-$(CONFIG_CRYPTO_WP512) += wp512.o
 CFLAGS_wp512.o := $(call cc-option,-fno-schedule-insns)  # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79149
 obj-$(CONFIG_CRYPTO_BLAKE2B) += blake2b_generic.o
-obj-$(CONFIG_CRYPTO_BLAKE2S) += blake2s_generic.o
 obj-$(CONFIG_CRYPTO_GF128MUL) += gf128mul.o
 obj-$(CONFIG_CRYPTO_ECB) += ecb.o
 obj-$(CONFIG_CRYPTO_CBC) += cbc.o
diff --git a/crypto/asymmetric_keys/public_key.c b/crypto/asymmetric_keys/public_key.c
index 7c9e6be35c30..2f8352e88860 100644
--- a/crypto/asymmetric_keys/public_key.c
+++ b/crypto/asymmetric_keys/public_key.c
@@ -304,6 +304,10 @@ static int cert_sig_digest_update(const struct public_key_signature *sig,
 
 	BUG_ON(!sig->data);
 
+	/* SM2 signatures always use the SM3 hash algorithm */
+	if (!sig->hash_algo || strcmp(sig->hash_algo, "sm3") != 0)
+		return -EINVAL;
+
 	ret = sm2_compute_z_digest(tfm_pkey, SM2_DEFAULT_USERID,
 					SM2_DEFAULT_USERID_LEN, dgst);
 	if (ret)
@@ -414,8 +418,7 @@ int public_key_verify_signature(const struct public_key *pkey,
 	if (ret)
 		goto error_free_key;
 
-	if (sig->pkey_algo && strcmp(sig->pkey_algo, "sm2") == 0 &&
-	    sig->data_size) {
+	if (strcmp(pkey->pkey_algo, "sm2") == 0 && sig->data_size) {
 		ret = cert_sig_digest_update(sig, tfm);
 		if (ret)
 			goto error_free_key;
diff --git a/crypto/blake2s_generic.c b/crypto/blake2s_generic.c
deleted file mode 100644
index 5f96a21f8788..000000000000
--- a/crypto/blake2s_generic.c
+++ /dev/null
@@ -1,75 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0 OR MIT
-/*
- * shash interface to the generic implementation of BLAKE2s
- *
- * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
- */
-
-#include <crypto/internal/blake2s.h>
-#include <crypto/internal/hash.h>
-
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-
-static int crypto_blake2s_update_generic(struct shash_desc *desc,
-					 const u8 *in, unsigned int inlen)
-{
-	return crypto_blake2s_update(desc, in, inlen, true);
-}
-
-static int crypto_blake2s_final_generic(struct shash_desc *desc, u8 *out)
-{
-	return crypto_blake2s_final(desc, out, true);
-}
-
-#define BLAKE2S_ALG(name, driver_name, digest_size)			\
-	{								\
-		.base.cra_name		= name,				\
-		.base.cra_driver_name	= driver_name,			\
-		.base.cra_priority	= 100,				\
-		.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,	\
-		.base.cra_blocksize	= BLAKE2S_BLOCK_SIZE,		\
-		.base.cra_ctxsize	= sizeof(struct blake2s_tfm_ctx), \
-		.base.cra_module	= THIS_MODULE,			\
-		.digestsize		= digest_size,			\
-		.setkey			= crypto_blake2s_setkey,	\
-		.init			= crypto_blake2s_init,		\
-		.update			= crypto_blake2s_update_generic, \
-		.final			= crypto_blake2s_final_generic,	\
-		.descsize		= sizeof(struct blake2s_state),	\
-	}
-
-static struct shash_alg blake2s_algs[] = {
-	BLAKE2S_ALG("blake2s-128", "blake2s-128-generic",
-		    BLAKE2S_128_HASH_SIZE),
-	BLAKE2S_ALG("blake2s-160", "blake2s-160-generic",
-		    BLAKE2S_160_HASH_SIZE),
-	BLAKE2S_ALG("blake2s-224", "blake2s-224-generic",
-		    BLAKE2S_224_HASH_SIZE),
-	BLAKE2S_ALG("blake2s-256", "blake2s-256-generic",
-		    BLAKE2S_256_HASH_SIZE),
-};
-
-static int __init blake2s_mod_init(void)
-{
-	return crypto_register_shashes(blake2s_algs, ARRAY_SIZE(blake2s_algs));
-}
-
-static void __exit blake2s_mod_exit(void)
-{
-	crypto_unregister_shashes(blake2s_algs, ARRAY_SIZE(blake2s_algs));
-}
-
-subsys_initcall(blake2s_mod_init);
-module_exit(blake2s_mod_exit);
-
-MODULE_ALIAS_CRYPTO("blake2s-128");
-MODULE_ALIAS_CRYPTO("blake2s-128-generic");
-MODULE_ALIAS_CRYPTO("blake2s-160");
-MODULE_ALIAS_CRYPTO("blake2s-160-generic");
-MODULE_ALIAS_CRYPTO("blake2s-224");
-MODULE_ALIAS_CRYPTO("blake2s-224-generic");
-MODULE_ALIAS_CRYPTO("blake2s-256");
-MODULE_ALIAS_CRYPTO("blake2s-256-generic");
-MODULE_LICENSE("GPL v2");
diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c
index 0970f103f691..3147d73c7bcd 100644
--- a/crypto/tcrypt.c
+++ b/crypto/tcrypt.c
@@ -1873,10 +1873,6 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 		ret += tcrypt_test("rmd160");
 		break;
 
-	case 41:
-		ret += tcrypt_test("blake2s-256");
-		break;
-
 	case 42:
 		ret += tcrypt_test("blake2b-512");
 		break;
@@ -2454,10 +2450,6 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 		test_hash_speed("rmd160", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
 		fallthrough;
-	case 316:
-		test_hash_speed("blake2s-256", sec, generic_hash_speed_template);
-		if (mode > 300 && mode < 400) break;
-		fallthrough;
 	case 317:
 		test_hash_speed("blake2b-512", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
@@ -2566,10 +2558,6 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 		test_ahash_speed("rmd160", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
 		fallthrough;
-	case 416:
-		test_ahash_speed("blake2s-256", sec, generic_hash_speed_template);
-		if (mode > 400 && mode < 500) break;
-		fallthrough;
 	case 417:
 		test_ahash_speed("blake2b-512", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index 6babb9cd2f9e..cdfe62f40c5f 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -4559,30 +4559,6 @@ static const struct alg_test_desc alg_test_descs[] = {
 			.hash = __VECS(blake2b_512_tv_template)
 		}
 	}, {
-		.alg = "blake2s-128",
-		.test = alg_test_hash,
-		.suite = {
-			.hash = __VECS(blakes2s_128_tv_template)
-		}
-	}, {
-		.alg = "blake2s-160",
-		.test = alg_test_hash,
-		.suite = {
-			.hash = __VECS(blakes2s_160_tv_template)
-		}
-	}, {
-		.alg = "blake2s-224",
-		.test = alg_test_hash,
-		.suite = {
-			.hash = __VECS(blakes2s_224_tv_template)
-		}
-	}, {
-		.alg = "blake2s-256",
-		.test = alg_test_hash,
-		.suite = {
-			.hash = __VECS(blakes2s_256_tv_template)
-		}
-	}, {
 		.alg = "cbc(aes)",
 		.test = alg_test_skcipher,
 		.fips_allowed = 1,
diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index 3e1ca798279f..3a2b8d3ced77 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -33128,221 +33128,4 @@ static const struct hash_testvec blake2b_512_tv_template[] = {{
 			  0xae, 0x15, 0x81, 0x15, 0xd0, 0x88, 0xa0, 0x3c, },
 }};
 
-static const struct hash_testvec blakes2s_128_tv_template[] = {{
-	.digest = (u8[]){ 0x64, 0x55, 0x0d, 0x6f, 0xfe, 0x2c, 0x0a, 0x01,
-			  0xa1, 0x4a, 0xba, 0x1e, 0xad, 0xe0, 0x20, 0x0c, },
-}, {
-	.plaintext = blake2_ordered_sequence,
-	.psize = 64,
-	.digest = (u8[]){ 0xdc, 0x66, 0xca, 0x8f, 0x03, 0x86, 0x58, 0x01,
-			  0xb0, 0xff, 0xe0, 0x6e, 0xd8, 0xa1, 0xa9, 0x0e, },
-}, {
-	.ksize = 16,
-	.key = blake2_ordered_sequence,
-	.plaintext = blake2_ordered_sequence,
-	.psize = 1,
-	.digest = (u8[]){ 0x88, 0x1e, 0x42, 0xe7, 0xbb, 0x35, 0x80, 0x82,
-			  0x63, 0x7c, 0x0a, 0x0f, 0xd7, 0xec, 0x6c, 0x2f, },
-}, {
-	.ksize = 32,
-	.key = blake2_ordered_sequence,
-	.plaintext = blake2_ordered_sequence,
-	.psize = 7,
-	.digest = (u8[]){ 0xcf, 0x9e, 0x07, 0x2a, 0xd5, 0x22, 0xf2, 0xcd,
-			  0xa2, 0xd8, 0x25, 0x21, 0x80, 0x86, 0x73, 0x1c, },
-}, {
-	.ksize = 1,
-	.key = "B",
-	.plaintext = blake2_ordered_sequence,
-	.psize = 15,
-	.digest = (u8[]){ 0xf6, 0x33, 0x5a, 0x2c, 0x22, 0xa0, 0x64, 0xb2,
-			  0xb6, 0x3f, 0xeb, 0xbc, 0xd1, 0xc3, 0xe5, 0xb2, },
-}, {
-	.ksize = 16,
-	.key = blake2_ordered_sequence,
-	.plaintext = blake2_ordered_sequence,
-	.psize = 247,
-	.digest = (u8[]){ 0x72, 0x66, 0x49, 0x60, 0xf9, 0x4a, 0xea, 0xbe,
-			  0x1f, 0xf4, 0x60, 0xce, 0xb7, 0x81, 0xcb, 0x09, },
-}, {
-	.ksize = 32,
-	.key = blake2_ordered_sequence,
-	.plaintext = blake2_ordered_sequence,
-	.psize = 256,
-	.digest = (u8[]){ 0xd5, 0xa4, 0x0e, 0xc3, 0x16, 0xc7, 0x51, 0xa6,
-			  0x3c, 0xd0, 0xd9, 0x11, 0x57, 0xfa, 0x1e, 0xbb, },
-}};
-
-static const struct hash_testvec blakes2s_160_tv_template[] = {{
-	.plaintext = blake2_ordered_sequence,
-	.psize = 7,
-	.digest = (u8[]){ 0xb4, 0xf2, 0x03, 0x49, 0x37, 0xed, 0xb1, 0x3e,
-			  0x5b, 0x2a, 0xca, 0x64, 0x82, 0x74, 0xf6, 0x62,
-			  0xe3, 0xf2, 0x84, 0xff, },
-}, {
-	.plaintext = blake2_ordered_sequence,
-	.psize = 256,
-	.digest = (u8[]){ 0xaa, 0x56, 0x9b, 0xdc, 0x98, 0x17, 0x75, 0xf2,
-			  0xb3, 0x68, 0x83, 0xb7, 0x9b, 0x8d, 0x48, 0xb1,
-			  0x9b, 0x2d, 0x35, 0x05, },
-}, {
-	.ksize = 1,
-	.key = "B",
-	.digest = (u8[]){ 0x50, 0x16, 0xe7, 0x0c, 0x01, 0xd0, 0xd3, 0xc3,
-			  0xf4, 0x3e, 0xb1, 0x6e, 0x97, 0xa9, 0x4e, 0xd1,
-			  0x79, 0x65, 0x32, 0x93, },
-}, {
-	.ksize = 32,
-	.key = blake2_ordered_sequence,
-	.plaintext = blake2_ordered_sequence,
-	.psize = 1,
-	.digest = (u8[]){ 0x1c, 0x2b, 0xcd, 0x9a, 0x68, 0xca, 0x8c, 0x71,
-			  0x90, 0x29, 0x6c, 0x54, 0xfa, 0x56, 0x4a, 0xef,
-			  0xa2, 0x3a, 0x56, 0x9c, },
-}, {
-	.ksize = 16,
-	.key = blake2_ordered_sequence,
-	.plaintext = blake2_ordered_sequence,
-	.psize = 15,
-	.digest = (u8[]){ 0x36, 0xc3, 0x5f, 0x9a, 0xdc, 0x7e, 0xbf, 0x19,
-			  0x68, 0xaa, 0xca, 0xd8, 0x81, 0xbf, 0x09, 0x34,
-			  0x83, 0x39, 0x0f, 0x30, },
-}, {
-	.ksize = 1,
-	.key = "B",
-	.plaintext = blake2_ordered_sequence,
-	.psize = 64,
-	.digest = (u8[]){ 0x86, 0x80, 0x78, 0xa4, 0x14, 0xec, 0x03, 0xe5,
-			  0xb6, 0x9a, 0x52, 0x0e, 0x42, 0xee, 0x39, 0x9d,
-			  0xac, 0xa6, 0x81, 0x63, },
-}, {
-	.ksize = 32,
-	.key = blake2_ordered_sequence,
-	.plaintext = blake2_ordered_sequence,
-	.psize = 247,
-	.digest = (u8[]){ 0x2d, 0xd8, 0xd2, 0x53, 0x66, 0xfa, 0xa9, 0x01,
-			  0x1c, 0x9c, 0xaf, 0xa3, 0xe2, 0x9d, 0x9b, 0x10,
-			  0x0a, 0xf6, 0x73, 0xe8, },
-}};
-
-static const struct hash_testvec blakes2s_224_tv_template[] = {{
-	.plaintext = blake2_ordered_sequence,
-	.psize = 1,
-	.digest = (u8[]){ 0x61, 0xb9, 0x4e, 0xc9, 0x46, 0x22, 0xa3, 0x91,
-			  0xd2, 0xae, 0x42, 0xe6, 0x45, 0x6c, 0x90, 0x12,
-			  0xd5, 0x80, 0x07, 0x97, 0xb8, 0x86, 0x5a, 0xfc,
-			  0x48, 0x21, 0x97, 0xbb, },
-}, {
-	.plaintext = blake2_ordered_sequence,
-	.psize = 247,
-	.digest = (u8[]){ 0x9e, 0xda, 0xc7, 0x20, 0x2c, 0xd8, 0x48, 0x2e,
-			  0x31, 0x94, 0xab, 0x46, 0x6d, 0x94, 0xd8, 0xb4,
-			  0x69, 0xcd, 0xae, 0x19, 0x6d, 0x9e, 0x41, 0xcc,
-			  0x2b, 0xa4, 0xd5, 0xf6, },
-}, {
-	.ksize = 16,
-	.key = blake2_ordered_sequence,
-	.digest = (u8[]){ 0x32, 0xc0, 0xac, 0xf4, 0x3b, 0xd3, 0x07, 0x9f,
-			  0xbe, 0xfb, 0xfa, 0x4d, 0x6b, 0x4e, 0x56, 0xb3,
-			  0xaa, 0xd3, 0x27, 0xf6, 0x14, 0xbf, 0xb9, 0x32,
-			  0xa7, 0x19, 0xfc, 0xb8, },
-}, {
-	.ksize = 1,
-	.key = "B",
-	.plaintext = blake2_ordered_sequence,
-	.psize = 7,
-	.digest = (u8[]){ 0x73, 0xad, 0x5e, 0x6d, 0xb9, 0x02, 0x8e, 0x76,
-			  0xf2, 0x66, 0x42, 0x4b, 0x4c, 0xfa, 0x1f, 0xe6,
-			  0x2e, 0x56, 0x40, 0xe5, 0xa2, 0xb0, 0x3c, 0xe8,
-			  0x7b, 0x45, 0xfe, 0x05, },
-}, {
-	.ksize = 32,
-	.key = blake2_ordered_sequence,
-	.plaintext = blake2_ordered_sequence,
-	.psize = 15,
-	.digest = (u8[]){ 0x16, 0x60, 0xfb, 0x92, 0x54, 0xb3, 0x6e, 0x36,
-			  0x81, 0xf4, 0x16, 0x41, 0xc3, 0x3d, 0xd3, 0x43,
-			  0x84, 0xed, 0x10, 0x6f, 0x65, 0x80, 0x7a, 0x3e,
-			  0x25, 0xab, 0xc5, 0x02, },
-}, {
-	.ksize = 16,
-	.key = blake2_ordered_sequence,
-	.plaintext = blake2_ordered_sequence,
-	.psize = 64,
-	.digest = (u8[]){ 0xca, 0xaa, 0x39, 0x67, 0x9c, 0xf7, 0x6b, 0xc7,
-			  0xb6, 0x82, 0xca, 0x0e, 0x65, 0x36, 0x5b, 0x7c,
-			  0x24, 0x00, 0xfa, 0x5f, 0xda, 0x06, 0x91, 0x93,
-			  0x6a, 0x31, 0x83, 0xb5, },
-}, {
-	.ksize = 1,
-	.key = "B",
-	.plaintext = blake2_ordered_sequence,
-	.psize = 256,
-	.digest = (u8[]){ 0x90, 0x02, 0x26, 0xb5, 0x06, 0x9c, 0x36, 0x86,
-			  0x94, 0x91, 0x90, 0x1e, 0x7d, 0x2a, 0x71, 0xb2,
-			  0x48, 0xb5, 0xe8, 0x16, 0xfd, 0x64, 0x33, 0x45,
-			  0xb3, 0xd7, 0xec, 0xcc, },
-}};
-
-static const struct hash_testvec blakes2s_256_tv_template[] = {{
-	.plaintext = blake2_ordered_sequence,
-	.psize = 15,
-	.digest = (u8[]){ 0xd9, 0x7c, 0x82, 0x8d, 0x81, 0x82, 0xa7, 0x21,
-			  0x80, 0xa0, 0x6a, 0x78, 0x26, 0x83, 0x30, 0x67,
-			  0x3f, 0x7c, 0x4e, 0x06, 0x35, 0x94, 0x7c, 0x04,
-			  0xc0, 0x23, 0x23, 0xfd, 0x45, 0xc0, 0xa5, 0x2d, },
-}, {
-	.ksize = 32,
-	.key = blake2_ordered_sequence,
-	.digest = (u8[]){ 0x48, 0xa8, 0x99, 0x7d, 0xa4, 0x07, 0x87, 0x6b,
-			  0x3d, 0x79, 0xc0, 0xd9, 0x23, 0x25, 0xad, 0x3b,
-			  0x89, 0xcb, 0xb7, 0x54, 0xd8, 0x6a, 0xb7, 0x1a,
-			  0xee, 0x04, 0x7a, 0xd3, 0x45, 0xfd, 0x2c, 0x49, },
-}, {
-	.ksize = 1,
-	.key = "B",
-	.plaintext = blake2_ordered_sequence,
-	.psize = 1,
-	.digest = (u8[]){ 0x22, 0x27, 0xae, 0xaa, 0x6e, 0x81, 0x56, 0x03,
-			  0xa7, 0xe3, 0xa1, 0x18, 0xa5, 0x9a, 0x2c, 0x18,
-			  0xf4, 0x63, 0xbc, 0x16, 0x70, 0xf1, 0xe7, 0x4b,
-			  0x00, 0x6d, 0x66, 0x16, 0xae, 0x9e, 0x74, 0x4e, },
-}, {
-	.ksize = 16,
-	.key = blake2_ordered_sequence,
-	.plaintext = blake2_ordered_sequence,
-	.psize = 7,
-	.digest = (u8[]){ 0x58, 0x5d, 0xa8, 0x60, 0x1c, 0xa4, 0xd8, 0x03,
-			  0x86, 0x86, 0x84, 0x64, 0xd7, 0xa0, 0x8e, 0x15,
-			  0x2f, 0x05, 0xa2, 0x1b, 0xbc, 0xef, 0x7a, 0x34,
-			  0xb3, 0xc5, 0xbc, 0x4b, 0xf0, 0x32, 0xeb, 0x12, },
-}, {
-	.ksize = 32,
-	.key = blake2_ordered_sequence,
-	.plaintext = blake2_ordered_sequence,
-	.psize = 64,
-	.digest = (u8[]){ 0x89, 0x75, 0xb0, 0x57, 0x7f, 0xd3, 0x55, 0x66,
-			  0xd7, 0x50, 0xb3, 0x62, 0xb0, 0x89, 0x7a, 0x26,
-			  0xc3, 0x99, 0x13, 0x6d, 0xf0, 0x7b, 0xab, 0xab,
-			  0xbd, 0xe6, 0x20, 0x3f, 0xf2, 0x95, 0x4e, 0xd4, },
-}, {
-	.ksize = 1,
-	.key = "B",
-	.plaintext = blake2_ordered_sequence,
-	.psize = 247,
-	.digest = (u8[]){ 0x2e, 0x74, 0x1c, 0x1d, 0x03, 0xf4, 0x9d, 0x84,
-			  0x6f, 0xfc, 0x86, 0x32, 0x92, 0x49, 0x7e, 0x66,
-			  0xd7, 0xc3, 0x10, 0x88, 0xfe, 0x28, 0xb3, 0xe0,
-			  0xbf, 0x50, 0x75, 0xad, 0x8e, 0xa4, 0xe6, 0xb2, },
-}, {
-	.ksize = 16,
-	.key = blake2_ordered_sequence,
-	.plaintext = blake2_ordered_sequence,
-	.psize = 256,
-	.digest = (u8[]){ 0xb9, 0xd2, 0x81, 0x0e, 0x3a, 0xb1, 0x62, 0x9b,
-			  0xad, 0x44, 0x05, 0xf4, 0x92, 0x2e, 0x99, 0xc1,
-			  0x4a, 0x47, 0xbb, 0x5b, 0x6f, 0xb2, 0x96, 0xed,
-			  0xd5, 0x06, 0xb5, 0x3a, 0x7c, 0x7a, 0x65, 0x1d, },
-}};
-
 #endif	/* _CRYPTO_TESTMGR_H */
diff --git a/drivers/accessibility/speakup/spk_ttyio.c b/drivers/accessibility/speakup/spk_ttyio.c
index 0d1f397cd896..08cf8a17754b 100644
--- a/drivers/accessibility/speakup/spk_ttyio.c
+++ b/drivers/accessibility/speakup/spk_ttyio.c
@@ -88,7 +88,7 @@ static int spk_ttyio_receive_buf2(struct tty_struct *tty,
 	}
 
 	if (!ldisc_data->buf_free)
-		/* ttyio_in will tty_schedule_flip */
+		/* ttyio_in will tty_flip_buffer_push */
 		return 0;
 
 	/* Make sure the consumer has read buf before we have seen
@@ -312,7 +312,7 @@ static unsigned char ttyio_in(struct spk_synth *in_synth, int timeout)
 	mb();
 	ldisc_data->buf_free = true;
 	/* Let TTY push more characters */
-	tty_schedule_flip(tty->port);
+	tty_flip_buffer_push(tty->port);
 
 	return rv;
 }
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 30b1f511c2af..f609f9d62efd 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -403,6 +403,9 @@ static int register_device_clock(struct acpi_device *adev,
 	if (!lpss_clk_dev)
 		lpt_register_clock_device();
 
+	if (IS_ERR(lpss_clk_dev))
+		return PTR_ERR(lpss_clk_dev);
+
 	clk_data = platform_get_drvdata(lpss_clk_dev);
 	if (!clk_data)
 		return -ENODEV;
diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c
index 42ede059728c..390af28f6faf 100644
--- a/drivers/acpi/acpi_video.c
+++ b/drivers/acpi/acpi_video.c
@@ -73,6 +73,7 @@ module_param(device_id_scheme, bool, 0444);
 static int only_lcd = -1;
 module_param(only_lcd, int, 0444);
 
+static bool may_report_brightness_keys;
 static int register_count;
 static DEFINE_MUTEX(register_count_mutex);
 static DEFINE_MUTEX(video_list_lock);
@@ -1222,6 +1223,9 @@ acpi_video_bus_get_one_device(struct acpi_device *device,
 	acpi_video_device_bind(video, data);
 	acpi_video_device_find_cap(data);
 
+	if (data->cap._BCM && data->cap._BCL)
+		may_report_brightness_keys = true;
+
 	mutex_lock(&video->device_list_lock);
 	list_add_tail(&data->entry, &video->video_device_list);
 	mutex_unlock(&video->device_list_lock);
@@ -1689,6 +1693,9 @@ static void acpi_video_device_notify(acpi_handle handle, u32 event, void *data)
 		break;
 	}
 
+	if (keycode)
+		may_report_brightness_keys = true;
+
 	acpi_notifier_call_chain(device, event, 0);
 
 	if (keycode && (report_key_events & REPORT_BRIGHTNESS_KEY_EVENTS)) {
@@ -2251,6 +2258,7 @@ void acpi_video_unregister(void)
 	if (register_count) {
 		acpi_bus_unregister_driver(&acpi_video_bus);
 		register_count = 0;
+		may_report_brightness_keys = false;
 	}
 	mutex_unlock(&register_count_mutex);
 }
@@ -2272,13 +2280,7 @@ void acpi_video_unregister_backlight(void)
 
 bool acpi_video_handles_brightness_key_presses(void)
 {
-	bool have_video_busses;
-
-	mutex_lock(&video_list_lock);
-	have_video_busses = !list_empty(&video_bus_head);
-	mutex_unlock(&video_list_lock);
-
-	return have_video_busses &&
+	return may_report_brightness_keys &&
 	       (report_key_events & REPORT_BRIGHTNESS_KEY_EVENTS);
 }
 EXPORT_SYMBOL(acpi_video_handles_brightness_key_presses);
diff --git a/drivers/acpi/apei/bert.c b/drivers/acpi/apei/bert.c
index 598fd19b65fa..45973aa6e06d 100644
--- a/drivers/acpi/apei/bert.c
+++ b/drivers/acpi/apei/bert.c
@@ -29,16 +29,26 @@
 
 #undef pr_fmt
 #define pr_fmt(fmt) "BERT: " fmt
+
+#define ACPI_BERT_PRINT_MAX_RECORDS 5
 #define ACPI_BERT_PRINT_MAX_LEN 1024
 
 static int bert_disable;
 
+/*
+ * Print "all" the error records in the BERT table, but avoid huge spam to
+ * the console if the BIOS included oversize records, or too many records.
+ * Skipping some records here does not lose anything because the full
+ * data is available to user tools in:
+ *	/sys/firmware/acpi/tables/data/BERT
+ */
 static void __init bert_print_all(struct acpi_bert_region *region,
 				  unsigned int region_len)
 {
 	struct acpi_hest_generic_status *estatus =
 		(struct acpi_hest_generic_status *)region;
 	int remain = region_len;
+	int printed = 0, skipped = 0;
 	u32 estatus_len;
 
 	while (remain >= sizeof(struct acpi_bert_region)) {
@@ -46,24 +56,26 @@ static void __init bert_print_all(struct acpi_bert_region *region,
 		if (remain < estatus_len) {
 			pr_err(FW_BUG "Truncated status block (length: %u).\n",
 			       estatus_len);
-			return;
+			break;
 		}
 
 		/* No more error records. */
 		if (!estatus->block_status)
-			return;
+			break;
 
 		if (cper_estatus_check(estatus)) {
 			pr_err(FW_BUG "Invalid error record.\n");
-			return;
+			break;
 		}
 
-		pr_info_once("Error records from previous boot:\n");
-		if (region_len < ACPI_BERT_PRINT_MAX_LEN)
+		if (estatus_len < ACPI_BERT_PRINT_MAX_LEN &&
+		    printed < ACPI_BERT_PRINT_MAX_RECORDS) {
+			pr_info_once("Error records from previous boot:\n");
 			cper_estatus_print(KERN_INFO HW_ERR, estatus);
-		else
-			pr_info_once("Max print length exceeded, table data is available at:\n"
-				     "/sys/firmware/acpi/tables/data/BERT");
+			printed++;
+		} else {
+			skipped++;
+		}
 
 		/*
 		 * Because the boot error source is "one-time polled" type,
@@ -75,6 +87,9 @@ static void __init bert_print_all(struct acpi_bert_region *region,
 		estatus = (void *)estatus + estatus_len;
 		remain -= estatus_len;
 	}
+
+	if (skipped)
+		pr_info(HW_ERR "Skipped %d error records\n", skipped);
 }
 
 static int __init setup_bert_disable(char *str)
diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj.c
index 2882450c443e..2e0ab898cce3 100644
--- a/drivers/acpi/apei/einj.c
+++ b/drivers/acpi/apei/einj.c
@@ -544,6 +544,8 @@ static int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
 	    ((region_intersects(base_addr, size, IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE)
 				!= REGION_INTERSECTS) &&
 	     (region_intersects(base_addr, size, IORESOURCE_MEM, IORES_DESC_PERSISTENT_MEMORY)
+				!= REGION_INTERSECTS) &&
+	     (region_intersects(base_addr, size, IORESOURCE_MEM, IORES_DESC_SOFT_RESERVED)
 				!= REGION_INTERSECTS)))
 		return -EINVAL;
 
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 0c8330ed1ffd..06b0184fa912 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -1457,33 +1457,35 @@ static struct platform_driver ghes_platform_driver = {
 	.remove		= ghes_remove,
 };
 
-static int __init ghes_init(void)
+void __init ghes_init(void)
 {
 	int rc;
 
+	sdei_init();
+
 	if (acpi_disabled)
-		return -ENODEV;
+		return;
 
 	switch (hest_disable) {
 	case HEST_NOT_FOUND:
-		return -ENODEV;
+		return;
 	case HEST_DISABLED:
 		pr_info(GHES_PFX "HEST is not enabled!\n");
-		return -EINVAL;
+		return;
 	default:
 		break;
 	}
 
 	if (ghes_disable) {
 		pr_info(GHES_PFX "GHES is not enabled!\n");
-		return -EINVAL;
+		return;
 	}
 
 	ghes_nmi_init_cxt();
 
 	rc = platform_driver_register(&ghes_platform_driver);
 	if (rc)
-		goto err;
+		return;
 
 	rc = apei_osc_setup();
 	if (rc == 0 && osc_sb_apei_support_acked)
@@ -1494,9 +1496,4 @@ static int __init ghes_init(void)
 		pr_info(GHES_PFX "APEI firmware first mode is enabled by APEI bit.\n");
 	else
 		pr_info(GHES_PFX "Failed to enable APEI firmware first mode.\n");
-
-	return 0;
-err:
-	return rc;
 }
-device_initcall(ghes_init);
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 3500744e6862..7774b603a796 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -1340,6 +1340,9 @@ static int __init acpi_init(void)
 
 	pci_mmcfg_late_init();
 	acpi_iort_init();
+	acpi_viot_early_init();
+	acpi_hest_init();
+	ghes_init();
 	acpi_scan_init();
 	acpi_ec_init();
 	acpi_debugfs_init();
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index ed1341030684..7cc9183c8dc8 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -597,33 +597,6 @@ static int pcc_data_alloc(int pcc_ss_id)
 	return 0;
 }
 
-/* Check if CPPC revision + num_ent combination is supported */
-static bool is_cppc_supported(int revision, int num_ent)
-{
-	int expected_num_ent;
-
-	switch (revision) {
-	case CPPC_V2_REV:
-		expected_num_ent = CPPC_V2_NUM_ENT;
-		break;
-	case CPPC_V3_REV:
-		expected_num_ent = CPPC_V3_NUM_ENT;
-		break;
-	default:
-		pr_debug("Firmware exports unsupported CPPC revision: %d\n",
-			revision);
-		return false;
-	}
-
-	if (expected_num_ent != num_ent) {
-		pr_debug("Firmware exports %d entries. Expected: %d for CPPC rev:%d\n",
-			num_ent, expected_num_ent, revision);
-		return false;
-	}
-
-	return true;
-}
-
 /*
  * An example CPC table looks like the following.
  *
@@ -723,7 +696,6 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
 				cpc_obj->type);
 		goto out_free;
 	}
-	cpc_ptr->num_entries = num_ent;
 
 	/* Second entry should be revision. */
 	cpc_obj = &out_obj->package.elements[1];
@@ -734,10 +706,32 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
 				cpc_obj->type);
 		goto out_free;
 	}
-	cpc_ptr->version = cpc_rev;
 
-	if (!is_cppc_supported(cpc_rev, num_ent))
+	if (cpc_rev < CPPC_V2_REV) {
+		pr_debug("Unsupported _CPC Revision (%d) for CPU:%d\n", cpc_rev,
+			 pr->id);
+		goto out_free;
+	}
+
+	/*
+	 * Disregard _CPC if the number of entries in the return pachage is not
+	 * as expected, but support future revisions being proper supersets of
+	 * the v3 and only causing more entries to be returned by _CPC.
+	 */
+	if ((cpc_rev == CPPC_V2_REV && num_ent != CPPC_V2_NUM_ENT) ||
+	    (cpc_rev == CPPC_V3_REV && num_ent != CPPC_V3_NUM_ENT) ||
+	    (cpc_rev > CPPC_V3_REV && num_ent <= CPPC_V3_NUM_ENT)) {
+		pr_debug("Unexpected number of _CPC return package entries (%d) for CPU:%d\n",
+			 num_ent, pr->id);
 		goto out_free;
+	}
+	if (cpc_rev > CPPC_V3_REV) {
+		num_ent = CPPC_V3_NUM_ENT;
+		cpc_rev = CPPC_V3_REV;
+	}
+
+	cpc_ptr->num_entries = num_ent;
+	cpc_ptr->version = cpc_rev;
 
 	/* Iterate through remaining entries in _CPC */
 	for (i = 2; i < num_ent; i++) {
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 9b859ff976e8..4e583a8cb562 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -183,7 +183,6 @@ static struct workqueue_struct *ec_wq;
 static struct workqueue_struct *ec_query_wq;
 
 static int EC_FLAGS_CORRECT_ECDT; /* Needs ECDT port address correction */
-static int EC_FLAGS_IGNORE_DSDT_GPE; /* Needs ECDT GPE as correction setting */
 static int EC_FLAGS_TRUST_DSDT_GPE; /* Needs DSDT GPE as correction setting */
 static int EC_FLAGS_CLEAR_ON_RESUME; /* Needs acpi_ec_clear() on boot/resume */
 
@@ -1392,24 +1391,16 @@ ec_parse_device(acpi_handle handle, u32 Level, void *context, void **retval)
 	if (ec->data_addr == 0 || ec->command_addr == 0)
 		return AE_OK;
 
-	if (boot_ec && boot_ec_is_ecdt && EC_FLAGS_IGNORE_DSDT_GPE) {
-		/*
-		 * Always inherit the GPE number setting from the ECDT
-		 * EC.
-		 */
-		ec->gpe = boot_ec->gpe;
-	} else {
-		/* Get GPE bit assignment (EC events). */
-		/* TODO: Add support for _GPE returning a package */
-		status = acpi_evaluate_integer(handle, "_GPE", NULL, &tmp);
-		if (ACPI_SUCCESS(status))
-			ec->gpe = tmp;
+	/* Get GPE bit assignment (EC events). */
+	/* TODO: Add support for _GPE returning a package */
+	status = acpi_evaluate_integer(handle, "_GPE", NULL, &tmp);
+	if (ACPI_SUCCESS(status))
+		ec->gpe = tmp;
+	/*
+	 * Errors are non-fatal, allowing for ACPI Reduced Hardware
+	 * platforms which use GpioInt instead of GPE.
+	 */
 
-		/*
-		 * Errors are non-fatal, allowing for ACPI Reduced Hardware
-		 * platforms which use GpioInt instead of GPE.
-		 */
-	}
 	/* Use the global lock for all EC transactions? */
 	tmp = 0;
 	acpi_evaluate_integer(handle, "_GLK", NULL, &tmp);
@@ -1847,60 +1838,12 @@ static int ec_honor_dsdt_gpe(const struct dmi_system_id *id)
 	return 0;
 }
 
-/*
- * Some DSDTs contain wrong GPE setting.
- * Asus FX502VD/VE, GL702VMK, X550VXK, X580VD
- * https://bugzilla.kernel.org/show_bug.cgi?id=195651
- */
-static int ec_honor_ecdt_gpe(const struct dmi_system_id *id)
-{
-	pr_debug("Detected system needing ignore DSDT GPE setting.\n");
-	EC_FLAGS_IGNORE_DSDT_GPE = 1;
-	return 0;
-}
-
 static const struct dmi_system_id ec_dmi_table[] __initconst = {
 	{
 	ec_correct_ecdt, "MSI MS-171F", {
 	DMI_MATCH(DMI_SYS_VENDOR, "Micro-Star"),
 	DMI_MATCH(DMI_PRODUCT_NAME, "MS-171F"),}, NULL},
 	{
-	ec_honor_ecdt_gpe, "ASUS FX502VD", {
-	DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-	DMI_MATCH(DMI_PRODUCT_NAME, "FX502VD"),}, NULL},
-	{
-	ec_honor_ecdt_gpe, "ASUS FX502VE", {
-	DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-	DMI_MATCH(DMI_PRODUCT_NAME, "FX502VE"),}, NULL},
-	{
-	ec_honor_ecdt_gpe, "ASUS GL702VMK", {
-	DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-	DMI_MATCH(DMI_PRODUCT_NAME, "GL702VMK"),}, NULL},
-	{
-	ec_honor_ecdt_gpe, "ASUSTeK COMPUTER INC. X505BA", {
-	DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-	DMI_MATCH(DMI_PRODUCT_NAME, "X505BA"),}, NULL},
-	{
-	ec_honor_ecdt_gpe, "ASUSTeK COMPUTER INC. X505BP", {
-	DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-	DMI_MATCH(DMI_PRODUCT_NAME, "X505BP"),}, NULL},
-	{
-	ec_honor_ecdt_gpe, "ASUSTeK COMPUTER INC. X542BA", {
-	DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-	DMI_MATCH(DMI_PRODUCT_NAME, "X542BA"),}, NULL},
-	{
-	ec_honor_ecdt_gpe, "ASUSTeK COMPUTER INC. X542BP", {
-	DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-	DMI_MATCH(DMI_PRODUCT_NAME, "X542BP"),}, NULL},
-	{
-	ec_honor_ecdt_gpe, "ASUS X550VXK", {
-	DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-	DMI_MATCH(DMI_PRODUCT_NAME, "X550VXK"),}, NULL},
-	{
-	ec_honor_ecdt_gpe, "ASUS X580VD", {
-	DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-	DMI_MATCH(DMI_PRODUCT_NAME, "X580VD"),}, NULL},
-	{
 	/* https://bugzilla.kernel.org/show_bug.cgi?id=209989 */
 	ec_honor_dsdt_gpe, "HP Pavilion Gaming Laptop 15-cx0xxx", {
 	DMI_MATCH(DMI_SYS_VENDOR, "HP"),
@@ -2168,13 +2111,6 @@ static const struct dmi_system_id acpi_ec_no_wakeup[] = {
 		},
 	},
 	{
-		.ident = "ThinkPad X1 Carbon 6th",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-			DMI_MATCH(DMI_PRODUCT_FAMILY, "ThinkPad X1 Carbon 6th"),
-		},
-	},
-	{
 		.ident = "ThinkPad X1 Yoga 3rd",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
diff --git a/drivers/acpi/pci_mcfg.c b/drivers/acpi/pci_mcfg.c
index 53cab975f612..63b98eae5e75 100644
--- a/drivers/acpi/pci_mcfg.c
+++ b/drivers/acpi/pci_mcfg.c
@@ -41,6 +41,8 @@ struct mcfg_fixup {
 static struct mcfg_fixup mcfg_quirks[] = {
 /*	{ OEM_ID, OEM_TABLE_ID, REV, SEGMENT, BUS_RANGE, ops, cfgres }, */
 
+#ifdef CONFIG_ARM64
+
 #define AL_ECAM(table_id, rev, seg, ops) \
 	{ "AMAZON", table_id, rev, seg, MCFG_BUS_ANY, ops }
 
@@ -169,6 +171,7 @@ static struct mcfg_fixup mcfg_quirks[] = {
 	ALTRA_ECAM_QUIRK(1, 13),
 	ALTRA_ECAM_QUIRK(1, 14),
 	ALTRA_ECAM_QUIRK(1, 15),
+#endif /* ARM64 */
 };
 
 static char mcfg_oem_id[ACPI_OEM_ID_SIZE];
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index d7deedf3548e..223aa010dd8d 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -22,8 +22,6 @@
 #include <linux/slab.h>
 #include <linux/dmi.h>
 #include <linux/platform_data/x86/apple.h>
-#include <acpi/apei.h>	/* for acpi_hest_init() */
-
 #include "internal.h"
 
 #define ACPI_PCI_ROOT_CLASS		"pci_bridge"
@@ -938,7 +936,6 @@ out_release_info:
 
 void __init acpi_pci_root_init(void)
 {
-	acpi_hest_init();
 	if (acpi_pci_disabled)
 		return;
 
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index aedcb92491f2..dc880dad2ade 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -604,7 +604,7 @@ static DEFINE_RAW_SPINLOCK(c3_lock);
  * @cx: Target state context
  * @index: index of target state
  */
-static int acpi_idle_enter_bm(struct cpuidle_driver *drv,
+static int __cpuidle acpi_idle_enter_bm(struct cpuidle_driver *drv,
 			       struct acpi_processor *pr,
 			       struct acpi_processor_cx *cx,
 			       int index)
@@ -661,7 +661,7 @@ static int acpi_idle_enter_bm(struct cpuidle_driver *drv,
 	return index;
 }
 
-static int acpi_idle_enter(struct cpuidle_device *dev,
+static int __cpuidle acpi_idle_enter(struct cpuidle_device *dev,
 			   struct cpuidle_driver *drv, int index)
 {
 	struct acpi_processor_cx *cx = per_cpu(acpi_cstate[index], dev->cpu);
@@ -690,7 +690,7 @@ static int acpi_idle_enter(struct cpuidle_device *dev,
 	return index;
 }
 
-static int acpi_idle_enter_s2idle(struct cpuidle_device *dev,
+static int __cpuidle acpi_idle_enter_s2idle(struct cpuidle_device *dev,
 				  struct cpuidle_driver *drv, int index)
 {
 	struct acpi_processor_cx *cx = per_cpu(acpi_cstate[index], dev->cpu);
diff --git a/drivers/acpi/processor_thermal.c b/drivers/acpi/processor_thermal.c
index a3d34e3f9f94..921a0b5a58e5 100644
--- a/drivers/acpi/processor_thermal.c
+++ b/drivers/acpi/processor_thermal.c
@@ -144,7 +144,7 @@ void acpi_thermal_cpufreq_exit(struct cpufreq_policy *policy)
 	unsigned int cpu;
 
 	for_each_cpu(cpu, policy->related_cpus) {
-		struct acpi_processor *pr = per_cpu(processors, policy->cpu);
+		struct acpi_processor *pr = per_cpu(processors, cpu);
 
 		if (pr)
 			freq_qos_remove_request(&pr->thermal_req);
diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index b86d3b869a58..488915328646 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -155,10 +155,10 @@ static bool acpi_nondev_subnode_ok(acpi_handle scope,
 	return acpi_nondev_subnode_data_ok(handle, link, list, parent);
 }
 
-static int acpi_add_nondev_subnodes(acpi_handle scope,
-				    const union acpi_object *links,
-				    struct list_head *list,
-				    struct fwnode_handle *parent)
+static bool acpi_add_nondev_subnodes(acpi_handle scope,
+				     const union acpi_object *links,
+				     struct list_head *list,
+				     struct fwnode_handle *parent)
 {
 	bool ret = false;
 	int i;
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 3c25ce8c95ba..19358a641610 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -416,6 +416,16 @@ static bool acpi_dev_irq_override(u32 gsi, u8 triggering, u8 polarity,
 {
 	int i;
 
+#ifdef CONFIG_X86
+	/*
+	 * IRQ override isn't needed on modern AMD Zen systems and
+	 * this override breaks active low IRQs on AMD Ryzen 6000 and
+	 * newer systems. Skip it.
+	 */
+	if (boot_cpu_has(X86_FEATURE_ZEN))
+		return false;
+#endif
+
 	for (i = 0; i < ARRAY_SIZE(skip_override_table); i++) {
 		const struct irq_override_cmp *entry = &skip_override_table[i];
 
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 07515139141e..d7194047d256 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -361,6 +361,14 @@ static const struct dmi_system_id acpisleep_dmi_table[] __initconst = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "80E3"),
 		},
 	},
+	{
+	.callback = init_nvs_save_s3,
+	.ident = "Lenovo G40-45",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "80E1"),
+		},
+	},
 	/*
 	 * ThinkPad X1 Tablet(2016) cannot do suspend-to-idle using
 	 * the Low Power S0 Idle firmware interface (see
diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c
index 95105db642b9..155bbabcc6f5 100644
--- a/drivers/acpi/thermal.c
+++ b/drivers/acpi/thermal.c
@@ -1098,8 +1098,6 @@ static int acpi_thermal_resume(struct device *dev)
 		return -EINVAL;
 
 	for (i = 0; i < ACPI_THERMAL_MAX_ACTIVE; i++) {
-		if (!(&tz->trips.active[i]))
-			break;
 		if (!tz->trips.active[i].flags.valid)
 			break;
 		tz->trips.active[i].flags.enabled = 1;
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index 7b9793cb55c5..e39d59ad6496 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -424,7 +424,6 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
 	.callback = video_detect_force_native,
 	.ident = "Clevo NL5xRU",
 	.matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"),
 		DMI_MATCH(DMI_BOARD_NAME, "NL5xRU"),
 		},
 	},
@@ -432,59 +431,75 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
 	.callback = video_detect_force_native,
 	.ident = "Clevo NL5xRU",
 	.matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "SchenkerTechnologiesGmbH"),
-		DMI_MATCH(DMI_BOARD_NAME, "NL5xRU"),
+		DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"),
+		DMI_MATCH(DMI_BOARD_NAME, "AURA1501"),
 		},
 	},
 	{
 	.callback = video_detect_force_native,
 	.ident = "Clevo NL5xRU",
 	.matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "Notebook"),
-		DMI_MATCH(DMI_BOARD_NAME, "NL5xRU"),
+		DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"),
+		DMI_MATCH(DMI_BOARD_NAME, "EDUBOOK1502"),
 		},
 	},
 	{
 	.callback = video_detect_force_native,
-	.ident = "Clevo NL5xRU",
+	.ident = "Clevo NL5xNU",
 	.matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"),
-		DMI_MATCH(DMI_BOARD_NAME, "AURA1501"),
+		DMI_MATCH(DMI_BOARD_NAME, "NL5xNU"),
 		},
 	},
+	/*
+	 * The TongFang PF5PU1G, PF4NU1F, PF5NU1G, and PF5LUXG/TUXEDO BA15 Gen10,
+	 * Pulse 14/15 Gen1, and Pulse 15 Gen2 have the same problem as the Clevo
+	 * NL5xRU and NL5xNU/TUXEDO Aura 15 Gen1 and Gen2. See the description
+	 * above.
+	 */
 	{
 	.callback = video_detect_force_native,
-	.ident = "Clevo NL5xRU",
+	.ident = "TongFang PF5PU1G",
 	.matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"),
-		DMI_MATCH(DMI_BOARD_NAME, "EDUBOOK1502"),
+		DMI_MATCH(DMI_BOARD_NAME, "PF5PU1G"),
 		},
 	},
 	{
 	.callback = video_detect_force_native,
-	.ident = "Clevo NL5xNU",
+	.ident = "TongFang PF4NU1F",
+	.matches = {
+		DMI_MATCH(DMI_BOARD_NAME, "PF4NU1F"),
+		},
+	},
+	{
+	.callback = video_detect_force_native,
+	.ident = "TongFang PF4NU1F",
 	.matches = {
 		DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"),
-		DMI_MATCH(DMI_BOARD_NAME, "NL5xNU"),
+		DMI_MATCH(DMI_BOARD_NAME, "PULSE1401"),
 		},
 	},
 	{
 	.callback = video_detect_force_native,
-	.ident = "Clevo NL5xNU",
+	.ident = "TongFang PF5NU1G",
 	.matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "SchenkerTechnologiesGmbH"),
-		DMI_MATCH(DMI_BOARD_NAME, "NL5xNU"),
+		DMI_MATCH(DMI_BOARD_NAME, "PF5NU1G"),
 		},
 	},
 	{
 	.callback = video_detect_force_native,
-	.ident = "Clevo NL5xNU",
+	.ident = "TongFang PF5NU1G",
 	.matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "Notebook"),
-		DMI_MATCH(DMI_BOARD_NAME, "NL5xNU"),
+		DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"),
+		DMI_MATCH(DMI_BOARD_NAME, "PULSE1501"),
+		},
+	},
+	{
+	.callback = video_detect_force_native,
+	.ident = "TongFang PF5LUXG",
+	.matches = {
+		DMI_MATCH(DMI_BOARD_NAME, "PF5LUXG"),
 		},
 	},
-
 	/*
 	 * Desktops which falsely report a backlight and which our heuristics
 	 * for this do not catch.
diff --git a/drivers/acpi/viot.c b/drivers/acpi/viot.c
index d2256326c73a..647f11cf165d 100644
--- a/drivers/acpi/viot.c
+++ b/drivers/acpi/viot.c
@@ -249,6 +249,26 @@ err_free:
 }
 
 /**
+ * acpi_viot_early_init - Test the presence of VIOT and enable ACS
+ *
+ * If the VIOT does exist, ACS must be enabled. This cannot be
+ * done in acpi_viot_init() which is called after the bus scan
+ */
+void __init acpi_viot_early_init(void)
+{
+#ifdef CONFIG_PCI
+	acpi_status status;
+	struct acpi_table_header *hdr;
+
+	status = acpi_get_table(ACPI_SIG_VIOT, 0, &hdr);
+	if (ACPI_FAILURE(status))
+		return;
+	pci_request_acs();
+	acpi_put_table(hdr);
+#endif
+}
+
+/**
  * acpi_viot_init - Parse the VIOT table
  *
  * Parse the VIOT table, prepare the list of endpoints to be used during DMA
@@ -319,12 +339,6 @@ static int viot_pci_dev_iommu_init(struct pci_dev *pdev, u16 dev_id, void *data)
 			epid = ((domain_nr - ep->segment_start) << 16) +
 				dev_id - ep->bdf_start + ep->endpoint_id;
 
-			/*
-			 * If we found a PCI range managed by the viommu, we're
-			 * the one that has to request ACS.
-			 */
-			pci_request_acs();
-
 			return viot_dev_iommu_init(&pdev->dev, ep->viommu,
 						   epid);
 		}
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 99ae919255f4..00c6c03ff822 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -170,8 +170,32 @@ static inline void binder_stats_created(enum binder_stat_types type)
 	atomic_inc(&binder_stats.obj_created[type]);
 }
 
-struct binder_transaction_log binder_transaction_log;
-struct binder_transaction_log binder_transaction_log_failed;
+struct binder_transaction_log_entry {
+	int debug_id;
+	int debug_id_done;
+	int call_type;
+	int from_proc;
+	int from_thread;
+	int target_handle;
+	int to_proc;
+	int to_thread;
+	int to_node;
+	int data_size;
+	int offsets_size;
+	int return_error_line;
+	uint32_t return_error;
+	uint32_t return_error_param;
+	char context_name[BINDERFS_MAX_NAME + 1];
+};
+
+struct binder_transaction_log {
+	atomic_t cur;
+	bool full;
+	struct binder_transaction_log_entry entry[32];
+};
+
+static struct binder_transaction_log binder_transaction_log;
+static struct binder_transaction_log binder_transaction_log_failed;
 
 static struct binder_transaction_log_entry *binder_transaction_log_add(
 	struct binder_transaction_log *log)
@@ -1334,6 +1358,18 @@ static int binder_inc_ref_for_node(struct binder_proc *proc,
 	}
 	ret = binder_inc_ref_olocked(ref, strong, target_list);
 	*rdata = ref->data;
+	if (ret && ref == new_ref) {
+		/*
+		 * Cleanup the failed reference here as the target
+		 * could now be dead and have already released its
+		 * references by now. Calling on the new reference
+		 * with strong=0 and a tmp_refs will not decrement
+		 * the node. The new_ref gets kfree'd below.
+		 */
+		binder_cleanup_ref_olocked(new_ref);
+		ref = NULL;
+	}
+
 	binder_proc_unlock(proc);
 	if (new_ref && ref != new_ref)
 		/*
@@ -5801,8 +5837,7 @@ static void print_binder_proc_stats(struct seq_file *m,
 	print_binder_stats(m, "  ", &proc->stats);
 }
 
-
-int binder_state_show(struct seq_file *m, void *unused)
+static int state_show(struct seq_file *m, void *unused)
 {
 	struct binder_proc *proc;
 	struct binder_node *node;
@@ -5841,7 +5876,7 @@ int binder_state_show(struct seq_file *m, void *unused)
 	return 0;
 }
 
-int binder_stats_show(struct seq_file *m, void *unused)
+static int stats_show(struct seq_file *m, void *unused)
 {
 	struct binder_proc *proc;
 
@@ -5857,7 +5892,7 @@ int binder_stats_show(struct seq_file *m, void *unused)
 	return 0;
 }
 
-int binder_transactions_show(struct seq_file *m, void *unused)
+static int transactions_show(struct seq_file *m, void *unused)
 {
 	struct binder_proc *proc;
 
@@ -5913,7 +5948,7 @@ static void print_binder_transaction_log_entry(struct seq_file *m,
 			"\n" : " (incomplete)\n");
 }
 
-int binder_transaction_log_show(struct seq_file *m, void *unused)
+static int transaction_log_show(struct seq_file *m, void *unused)
 {
 	struct binder_transaction_log *log = m->private;
 	unsigned int log_cur = atomic_read(&log->cur);
@@ -5945,6 +5980,45 @@ const struct file_operations binder_fops = {
 	.release = binder_release,
 };
 
+DEFINE_SHOW_ATTRIBUTE(state);
+DEFINE_SHOW_ATTRIBUTE(stats);
+DEFINE_SHOW_ATTRIBUTE(transactions);
+DEFINE_SHOW_ATTRIBUTE(transaction_log);
+
+const struct binder_debugfs_entry binder_debugfs_entries[] = {
+	{
+		.name = "state",
+		.mode = 0444,
+		.fops = &state_fops,
+		.data = NULL,
+	},
+	{
+		.name = "stats",
+		.mode = 0444,
+		.fops = &stats_fops,
+		.data = NULL,
+	},
+	{
+		.name = "transactions",
+		.mode = 0444,
+		.fops = &transactions_fops,
+		.data = NULL,
+	},
+	{
+		.name = "transaction_log",
+		.mode = 0444,
+		.fops = &transaction_log_fops,
+		.data = &binder_transaction_log,
+	},
+	{
+		.name = "failed_transaction_log",
+		.mode = 0444,
+		.fops = &transaction_log_fops,
+		.data = &binder_transaction_log_failed,
+	},
+	{} /* terminator */
+};
+
 static int __init init_binder_device(const char *name)
 {
 	int ret;
@@ -5990,36 +6064,18 @@ static int __init binder_init(void)
 	atomic_set(&binder_transaction_log_failed.cur, ~0U);
 
 	binder_debugfs_dir_entry_root = debugfs_create_dir("binder", NULL);
-	if (binder_debugfs_dir_entry_root)
+	if (binder_debugfs_dir_entry_root) {
+		const struct binder_debugfs_entry *db_entry;
+
+		binder_for_each_debugfs_entry(db_entry)
+			debugfs_create_file(db_entry->name,
+					    db_entry->mode,
+					    binder_debugfs_dir_entry_root,
+					    db_entry->data,
+					    db_entry->fops);
+
 		binder_debugfs_dir_entry_proc = debugfs_create_dir("proc",
 						 binder_debugfs_dir_entry_root);
-
-	if (binder_debugfs_dir_entry_root) {
-		debugfs_create_file("state",
-				    0444,
-				    binder_debugfs_dir_entry_root,
-				    NULL,
-				    &binder_state_fops);
-		debugfs_create_file("stats",
-				    0444,
-				    binder_debugfs_dir_entry_root,
-				    NULL,
-				    &binder_stats_fops);
-		debugfs_create_file("transactions",
-				    0444,
-				    binder_debugfs_dir_entry_root,
-				    NULL,
-				    &binder_transactions_fops);
-		debugfs_create_file("transaction_log",
-				    0444,
-				    binder_debugfs_dir_entry_root,
-				    &binder_transaction_log,
-				    &binder_transaction_log_fops);
-		debugfs_create_file("failed_transaction_log",
-				    0444,
-				    binder_debugfs_dir_entry_root,
-				    &binder_transaction_log_failed,
-				    &binder_transaction_log_fops);
 	}
 
 	if (!IS_ENABLED(CONFIG_ANDROID_BINDERFS) &&
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 47bc74a8c7b6..8ed450125c92 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -213,7 +213,7 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
 
 	if (mm) {
 		mmap_read_lock(mm);
-		vma = alloc->vma;
+		vma = vma_lookup(mm, alloc->vma_addr);
 	}
 
 	if (!vma && need_mm) {
@@ -313,16 +313,14 @@ err_no_vma:
 static inline void binder_alloc_set_vma(struct binder_alloc *alloc,
 		struct vm_area_struct *vma)
 {
-	if (vma)
-		alloc->vma_vm_mm = vma->vm_mm;
-	/*
-	 * If we see alloc->vma is not NULL, buffer data structures set up
-	 * completely. Look at smp_rmb side binder_alloc_get_vma.
-	 * We also want to guarantee new alloc->vma_vm_mm is always visible
-	 * if alloc->vma is set.
-	 */
-	smp_wmb();
-	alloc->vma = vma;
+	unsigned long vm_start = 0;
+
+	if (vma) {
+		vm_start = vma->vm_start;
+		mmap_assert_write_locked(alloc->vma_vm_mm);
+	}
+
+	alloc->vma_addr = vm_start;
 }
 
 static inline struct vm_area_struct *binder_alloc_get_vma(
@@ -330,11 +328,9 @@ static inline struct vm_area_struct *binder_alloc_get_vma(
 {
 	struct vm_area_struct *vma = NULL;
 
-	if (alloc->vma) {
-		/* Look at description in binder_alloc_set_vma */
-		smp_rmb();
-		vma = alloc->vma;
-	}
+	if (alloc->vma_addr)
+		vma = vma_lookup(alloc->vma_vm_mm, alloc->vma_addr);
+
 	return vma;
 }
 
@@ -398,12 +394,15 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 	size_t size, data_offsets_size;
 	int ret;
 
+	mmap_read_lock(alloc->vma_vm_mm);
 	if (!binder_alloc_get_vma(alloc)) {
+		mmap_read_unlock(alloc->vma_vm_mm);
 		binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
 				   "%d: binder_alloc_buf, no vma\n",
 				   alloc->pid);
 		return ERR_PTR(-ESRCH);
 	}
+	mmap_read_unlock(alloc->vma_vm_mm);
 
 	data_offsets_size = ALIGN(data_size, sizeof(void *)) +
 		ALIGN(offsets_size, sizeof(void *));
@@ -788,7 +787,6 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc,
 	binder_insert_free_buffer(alloc, buffer);
 	alloc->free_async_space = alloc->buffer_size / 2;
 	binder_alloc_set_vma(alloc, vma);
-	mmgrab(alloc->vma_vm_mm);
 
 	return 0;
 
@@ -817,7 +815,8 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc)
 
 	buffers = 0;
 	mutex_lock(&alloc->mutex);
-	BUG_ON(alloc->vma);
+	BUG_ON(alloc->vma_addr &&
+	       vma_lookup(alloc->vma_vm_mm, alloc->vma_addr));
 
 	while ((n = rb_first(&alloc->allocated_buffers))) {
 		buffer = rb_entry(n, struct binder_buffer, rb_node);
@@ -924,17 +923,25 @@ void binder_alloc_print_pages(struct seq_file *m,
 	 * Make sure the binder_alloc is fully initialized, otherwise we might
 	 * read inconsistent state.
 	 */
-	if (binder_alloc_get_vma(alloc) != NULL) {
-		for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) {
-			page = &alloc->pages[i];
-			if (!page->page_ptr)
-				free++;
-			else if (list_empty(&page->lru))
-				active++;
-			else
-				lru++;
-		}
+
+	mmap_read_lock(alloc->vma_vm_mm);
+	if (binder_alloc_get_vma(alloc) == NULL) {
+		mmap_read_unlock(alloc->vma_vm_mm);
+		goto uninitialized;
+	}
+
+	mmap_read_unlock(alloc->vma_vm_mm);
+	for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) {
+		page = &alloc->pages[i];
+		if (!page->page_ptr)
+			free++;
+		else if (list_empty(&page->lru))
+			active++;
+		else
+			lru++;
 	}
+
+uninitialized:
 	mutex_unlock(&alloc->mutex);
 	seq_printf(m, "  pages: %d:%d:%d\n", active, lru, free);
 	seq_printf(m, "  pages high watermark: %zu\n", alloc->pages_high);
@@ -1079,6 +1086,8 @@ static struct shrinker binder_shrinker = {
 void binder_alloc_init(struct binder_alloc *alloc)
 {
 	alloc->pid = current->group_leader->pid;
+	alloc->vma_vm_mm = current->mm;
+	mmgrab(alloc->vma_vm_mm);
 	mutex_init(&alloc->mutex);
 	INIT_LIST_HEAD(&alloc->buffers);
 }
diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h
index 7dea57a84c79..1e4fd37af5e0 100644
--- a/drivers/android/binder_alloc.h
+++ b/drivers/android/binder_alloc.h
@@ -100,7 +100,7 @@ struct binder_lru_page {
  */
 struct binder_alloc {
 	struct mutex mutex;
-	struct vm_area_struct *vma;
+	unsigned long vma_addr;
 	struct mm_struct *vma_vm_mm;
 	void __user *buffer;
 	struct list_head buffers;
diff --git a/drivers/android/binder_alloc_selftest.c b/drivers/android/binder_alloc_selftest.c
index c2b323bc3b3a..43a881073a42 100644
--- a/drivers/android/binder_alloc_selftest.c
+++ b/drivers/android/binder_alloc_selftest.c
@@ -287,7 +287,7 @@ void binder_selftest_alloc(struct binder_alloc *alloc)
 	if (!binder_selftest_run)
 		return;
 	mutex_lock(&binder_selftest_lock);
-	if (!binder_selftest_run || !alloc->vma)
+	if (!binder_selftest_run || !alloc->vma_addr)
 		goto done;
 	pr_info("STARTED\n");
 	binder_selftest_alloc_offset(alloc, end_offset, 0);
diff --git a/drivers/android/binder_internal.h b/drivers/android/binder_internal.h
index d6b6b8cb7346..1ade9799c8d5 100644
--- a/drivers/android/binder_internal.h
+++ b/drivers/android/binder_internal.h
@@ -107,41 +107,19 @@ static inline int __init init_binderfs(void)
 }
 #endif
 
-int binder_stats_show(struct seq_file *m, void *unused);
-DEFINE_SHOW_ATTRIBUTE(binder_stats);
-
-int binder_state_show(struct seq_file *m, void *unused);
-DEFINE_SHOW_ATTRIBUTE(binder_state);
-
-int binder_transactions_show(struct seq_file *m, void *unused);
-DEFINE_SHOW_ATTRIBUTE(binder_transactions);
-
-int binder_transaction_log_show(struct seq_file *m, void *unused);
-DEFINE_SHOW_ATTRIBUTE(binder_transaction_log);
-
-struct binder_transaction_log_entry {
-	int debug_id;
-	int debug_id_done;
-	int call_type;
-	int from_proc;
-	int from_thread;
-	int target_handle;
-	int to_proc;
-	int to_thread;
-	int to_node;
-	int data_size;
-	int offsets_size;
-	int return_error_line;
-	uint32_t return_error;
-	uint32_t return_error_param;
-	char context_name[BINDERFS_MAX_NAME + 1];
+struct binder_debugfs_entry {
+	const char *name;
+	umode_t mode;
+	const struct file_operations *fops;
+	void *data;
 };
 
-struct binder_transaction_log {
-	atomic_t cur;
-	bool full;
-	struct binder_transaction_log_entry entry[32];
-};
+extern const struct binder_debugfs_entry binder_debugfs_entries[];
+
+#define binder_for_each_debugfs_entry(entry)	\
+	for ((entry) = binder_debugfs_entries;	\
+	     (entry)->name;			\
+	     (entry)++)
 
 enum binder_stat_types {
 	BINDER_STAT_PROC,
@@ -575,6 +553,4 @@ struct binder_object {
 	};
 };
 
-extern struct binder_transaction_log binder_transaction_log;
-extern struct binder_transaction_log binder_transaction_log_failed;
 #endif /* _LINUX_BINDER_INTERNAL_H */
diff --git a/drivers/android/binderfs.c b/drivers/android/binderfs.c
index e3605cdd4335..6d717ed76766 100644
--- a/drivers/android/binderfs.c
+++ b/drivers/android/binderfs.c
@@ -621,6 +621,7 @@ static int init_binder_features(struct super_block *sb)
 static int init_binder_logs(struct super_block *sb)
 {
 	struct dentry *binder_logs_root_dir, *dentry, *proc_log_dir;
+	const struct binder_debugfs_entry *db_entry;
 	struct binderfs_info *info;
 	int ret = 0;
 
@@ -631,43 +632,15 @@ static int init_binder_logs(struct super_block *sb)
 		goto out;
 	}
 
-	dentry = binderfs_create_file(binder_logs_root_dir, "stats",
-				      &binder_stats_fops, NULL);
-	if (IS_ERR(dentry)) {
-		ret = PTR_ERR(dentry);
-		goto out;
-	}
-
-	dentry = binderfs_create_file(binder_logs_root_dir, "state",
-				      &binder_state_fops, NULL);
-	if (IS_ERR(dentry)) {
-		ret = PTR_ERR(dentry);
-		goto out;
-	}
-
-	dentry = binderfs_create_file(binder_logs_root_dir, "transactions",
-				      &binder_transactions_fops, NULL);
-	if (IS_ERR(dentry)) {
-		ret = PTR_ERR(dentry);
-		goto out;
-	}
-
-	dentry = binderfs_create_file(binder_logs_root_dir,
-				      "transaction_log",
-				      &binder_transaction_log_fops,
-				      &binder_transaction_log);
-	if (IS_ERR(dentry)) {
-		ret = PTR_ERR(dentry);
-		goto out;
-	}
-
-	dentry = binderfs_create_file(binder_logs_root_dir,
-				      "failed_transaction_log",
-				      &binder_transaction_log_fops,
-				      &binder_transaction_log_failed);
-	if (IS_ERR(dentry)) {
-		ret = PTR_ERR(dentry);
-		goto out;
+	binder_for_each_debugfs_entry(db_entry) {
+		dentry = binderfs_create_file(binder_logs_root_dir,
+					      db_entry->name,
+					      db_entry->fops,
+					      db_entry->data);
+		if (IS_ERR(dentry)) {
+			ret = PTR_ERR(dentry);
+			goto out;
+		}
 	}
 
 	proc_log_dir = binderfs_create_dir(binder_logs_root_dir, "proc");
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 78d25f6ab6c0..90c009d9d38d 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -2138,6 +2138,7 @@ const char *ata_get_cmd_descript(u8 command)
 		{ ATA_CMD_WRITE_QUEUED_FUA_EXT, "WRITE DMA QUEUED FUA EXT" },
 		{ ATA_CMD_FPDMA_READ,		"READ FPDMA QUEUED" },
 		{ ATA_CMD_FPDMA_WRITE,		"WRITE FPDMA QUEUED" },
+		{ ATA_CMD_NCQ_NON_DATA,		"NCQ NON-DATA" },
 		{ ATA_CMD_FPDMA_SEND,		"SEND FPDMA QUEUED" },
 		{ ATA_CMD_FPDMA_RECV,		"RECEIVE FPDMA QUEUED" },
 		{ ATA_CMD_PIO_READ,		"READ SECTOR(S)" },
diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c
index 81ce81a75fc6..681cb3786794 100644
--- a/drivers/atm/idt77252.c
+++ b/drivers/atm/idt77252.c
@@ -3752,6 +3752,7 @@ static void __exit idt77252_exit(void)
 		card = idt77252_chain;
 		dev = card->atmdev;
 		idt77252_chain = card->next;
+		del_timer_sync(&card->tst_timer);
 
 		if (dev->phy->stop)
 			dev->phy->stop(dev);
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 8e73a34e1005..10e027e92692 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -485,7 +485,8 @@ static void device_link_release_fn(struct work_struct *work)
 	/* Ensure that all references to the link object have been dropped. */
 	device_link_synchronize_removal();
 
-	pm_runtime_release_supplier(link, true);
+	pm_runtime_release_supplier(link);
+	pm_request_idle(link->supplier);
 
 	put_device(link->consumer);
 	put_device(link->supplier);
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index fddd08e482fc..55405ebf23ab 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -570,6 +570,12 @@ ssize_t __weak cpu_show_mmio_stale_data(struct device *dev,
 	return sysfs_emit(buf, "Not affected\n");
 }
 
+ssize_t __weak cpu_show_retbleed(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "Not affected\n");
+}
+
 static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
 static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
 static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL);
@@ -580,6 +586,7 @@ static DEVICE_ATTR(tsx_async_abort, 0444, cpu_show_tsx_async_abort, NULL);
 static DEVICE_ATTR(itlb_multihit, 0444, cpu_show_itlb_multihit, NULL);
 static DEVICE_ATTR(srbds, 0444, cpu_show_srbds, NULL);
 static DEVICE_ATTR(mmio_stale_data, 0444, cpu_show_mmio_stale_data, NULL);
+static DEVICE_ATTR(retbleed, 0444, cpu_show_retbleed, NULL);
 
 static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_meltdown.attr,
@@ -592,6 +599,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_itlb_multihit.attr,
 	&dev_attr_srbds.attr,
 	&dev_attr_mmio_stale_data.attr,
+	&dev_attr_retbleed.attr,
 	NULL
 };
 
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index a54c6ac88e03..e0934d2b8022 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -877,6 +877,11 @@ static int __device_attach_driver(struct device_driver *drv, void *_data)
 		dev_dbg(dev, "Device match requests probe deferral\n");
 		dev->can_match = true;
 		driver_deferred_probe_add(dev);
+		/*
+		 * Device can't match with a driver right now, so don't attempt
+		 * to match or bind with other drivers on the bus.
+		 */
+		return ret;
 	} else if (ret < 0) {
 		dev_dbg(dev, "Bus failed to match device: %d\n", ret);
 		return ret;
@@ -1094,6 +1099,7 @@ static void __driver_attach_async_helper(void *_dev, async_cookie_t cookie)
 static int __driver_attach(struct device *dev, void *data)
 {
 	struct device_driver *drv = data;
+	bool async = false;
 	int ret;
 
 	/*
@@ -1114,6 +1120,11 @@ static int __driver_attach(struct device *dev, void *data)
 		dev_dbg(dev, "Device match requests probe deferral\n");
 		dev->can_match = true;
 		driver_deferred_probe_add(dev);
+		/*
+		 * Driver could not match with device, but may match with
+		 * another device on the bus.
+		 */
+		return 0;
 	} else if (ret < 0) {
 		dev_dbg(dev, "Bus failed to match device: %d\n", ret);
 		return ret;
@@ -1132,9 +1143,11 @@ static int __driver_attach(struct device *dev, void *data)
 		if (!dev->driver) {
 			get_device(dev);
 			dev->p->async_driver = drv;
-			async_schedule_dev(__driver_attach_async_helper, dev);
+			async = true;
 		}
 		device_unlock(dev);
+		if (async)
+			async_schedule_dev(__driver_attach_async_helper, dev);
 		return 0;
 	}
 
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index c0d501a3a714..c778d1df7455 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -555,6 +555,8 @@ static ssize_t hard_offline_page_store(struct device *dev,
 		return -EINVAL;
 	pfn >>= PAGE_SHIFT;
 	ret = memory_failure(pfn, 0);
+	if (ret == -EOPNOTSUPP)
+		ret = 0;
 	return ret ? ret : count;
 }
 
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 0f5319b79fad..5366d1b5359c 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -45,7 +45,7 @@ static inline ssize_t cpumap_read(struct file *file, struct kobject *kobj,
 	return n;
 }
 
-static BIN_ATTR_RO(cpumap, 0);
+static BIN_ATTR_RO(cpumap, CPUMAP_FILE_MAX_BYTES);
 
 static inline ssize_t cpulist_read(struct file *file, struct kobject *kobj,
 				   struct bin_attribute *attr, char *buf,
@@ -66,7 +66,7 @@ static inline ssize_t cpulist_read(struct file *file, struct kobject *kobj,
 	return n;
 }
 
-static BIN_ATTR_RO(cpulist, 0);
+static BIN_ATTR_RO(cpulist, CPULIST_FILE_MAX_BYTES);
 
 /**
  * struct node_access_nodes - Access class device to hold user visible
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 1de11af7b8a9..6fa50e883aaa 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -219,6 +219,9 @@ static void genpd_debug_remove(struct generic_pm_domain *genpd)
 {
 	struct dentry *d;
 
+	if (!genpd_debugfs_dir)
+		return;
+
 	d = debugfs_lookup(genpd->name, genpd_debugfs_dir);
 	debugfs_remove(d);
 }
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 44ae3909e64b..3179c9265471 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -308,13 +308,10 @@ static int rpm_get_suppliers(struct device *dev)
 /**
  * pm_runtime_release_supplier - Drop references to device link's supplier.
  * @link: Target device link.
- * @check_idle: Whether or not to check if the supplier device is idle.
  *
- * Drop all runtime PM references associated with @link to its supplier device
- * and if @check_idle is set, check if that device is idle (and so it can be
- * suspended).
+ * Drop all runtime PM references associated with @link to its supplier device.
  */
-void pm_runtime_release_supplier(struct device_link *link, bool check_idle)
+void pm_runtime_release_supplier(struct device_link *link)
 {
 	struct device *supplier = link->supplier;
 
@@ -327,9 +324,6 @@ void pm_runtime_release_supplier(struct device_link *link, bool check_idle)
 	while (refcount_dec_not_one(&link->rpm_active) &&
 	       atomic_read(&supplier->power.usage_count) > 0)
 		pm_runtime_put_noidle(supplier);
-
-	if (check_idle)
-		pm_request_idle(supplier);
 }
 
 static void __rpm_put_suppliers(struct device *dev, bool try_to_suspend)
@@ -337,8 +331,11 @@ static void __rpm_put_suppliers(struct device *dev, bool try_to_suspend)
 	struct device_link *link;
 
 	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node,
-				device_links_read_lock_held())
-		pm_runtime_release_supplier(link, try_to_suspend);
+				device_links_read_lock_held()) {
+		pm_runtime_release_supplier(link);
+		if (try_to_suspend)
+			pm_request_idle(link->supplier);
+	}
 }
 
 static void rpm_put_suppliers(struct device *dev)
@@ -1791,7 +1788,8 @@ void pm_runtime_drop_link(struct device_link *link)
 		return;
 
 	pm_runtime_drop_link_count(link->consumer);
-	pm_runtime_release_supplier(link, true);
+	pm_runtime_release_supplier(link);
+	pm_request_idle(link->supplier);
 }
 
 static bool pm_runtime_need_not_resume(struct device *dev)
diff --git a/drivers/base/topology.c b/drivers/base/topology.c
index 43c0940643f5..5df6d861bc21 100644
--- a/drivers/base/topology.c
+++ b/drivers/base/topology.c
@@ -52,39 +52,39 @@ define_id_show_func(core_id);
 static DEVICE_ATTR_RO(core_id);
 
 define_siblings_read_func(thread_siblings, sibling_cpumask);
-static BIN_ATTR_RO(thread_siblings, 0);
-static BIN_ATTR_RO(thread_siblings_list, 0);
+static BIN_ATTR_RO(thread_siblings, CPUMAP_FILE_MAX_BYTES);
+static BIN_ATTR_RO(thread_siblings_list, CPULIST_FILE_MAX_BYTES);
 
 define_siblings_read_func(core_cpus, sibling_cpumask);
-static BIN_ATTR_RO(core_cpus, 0);
-static BIN_ATTR_RO(core_cpus_list, 0);
+static BIN_ATTR_RO(core_cpus, CPUMAP_FILE_MAX_BYTES);
+static BIN_ATTR_RO(core_cpus_list, CPULIST_FILE_MAX_BYTES);
 
 define_siblings_read_func(core_siblings, core_cpumask);
-static BIN_ATTR_RO(core_siblings, 0);
-static BIN_ATTR_RO(core_siblings_list, 0);
+static BIN_ATTR_RO(core_siblings, CPUMAP_FILE_MAX_BYTES);
+static BIN_ATTR_RO(core_siblings_list, CPULIST_FILE_MAX_BYTES);
 
 define_siblings_read_func(die_cpus, die_cpumask);
-static BIN_ATTR_RO(die_cpus, 0);
-static BIN_ATTR_RO(die_cpus_list, 0);
+static BIN_ATTR_RO(die_cpus, CPUMAP_FILE_MAX_BYTES);
+static BIN_ATTR_RO(die_cpus_list, CPULIST_FILE_MAX_BYTES);
 
 define_siblings_read_func(package_cpus, core_cpumask);
-static BIN_ATTR_RO(package_cpus, 0);
-static BIN_ATTR_RO(package_cpus_list, 0);
+static BIN_ATTR_RO(package_cpus, CPUMAP_FILE_MAX_BYTES);
+static BIN_ATTR_RO(package_cpus_list, CPULIST_FILE_MAX_BYTES);
 
 #ifdef CONFIG_SCHED_BOOK
 define_id_show_func(book_id);
 static DEVICE_ATTR_RO(book_id);
 define_siblings_read_func(book_siblings, book_cpumask);
-static BIN_ATTR_RO(book_siblings, 0);
-static BIN_ATTR_RO(book_siblings_list, 0);
+static BIN_ATTR_RO(book_siblings, CPUMAP_FILE_MAX_BYTES);
+static BIN_ATTR_RO(book_siblings_list, CPULIST_FILE_MAX_BYTES);
 #endif
 
 #ifdef CONFIG_SCHED_DRAWER
 define_id_show_func(drawer_id);
 static DEVICE_ATTR_RO(drawer_id);
 define_siblings_read_func(drawer_siblings, drawer_cpumask);
-static BIN_ATTR_RO(drawer_siblings, 0);
-static BIN_ATTR_RO(drawer_siblings_list, 0);
+static BIN_ATTR_RO(drawer_siblings, CPUMAP_FILE_MAX_BYTES);
+static BIN_ATTR_RO(drawer_siblings_list, CPULIST_FILE_MAX_BYTES);
 #endif
 
 static struct bin_attribute *bin_attrs[] = {
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index f93cb989241c..28ed157b1203 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -410,6 +410,7 @@ config XEN_BLKDEV_BACKEND
 config VIRTIO_BLK
 	tristate "Virtio block driver"
 	depends on VIRTIO
+	select SG_POOL
 	help
 	  This is the virtual block driver for virtio.  It can be used with
           QEMU based VMMs (like KVM or Xen).  Say Y or M.
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 8ba2fe356f01..d59af26d7703 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2795,10 +2795,12 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 
 	if (init_submitter(device)) {
 		err = ERR_NOMEM;
-		goto out_idr_remove_vol;
+		goto out_idr_remove_from_resource;
 	}
 
-	add_disk(disk);
+	err = add_disk(disk);
+	if (err)
+		goto out_idr_remove_from_resource;
 
 	/* inherit the connection state */
 	device->state.conn = first_connection(resource)->cstate;
@@ -2812,8 +2814,6 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 	drbd_debugfs_device_add(device);
 	return NO_ERROR;
 
-out_idr_remove_vol:
-	idr_remove(&connection->peer_devices, vnr);
 out_idr_remove_from_resource:
 	for_each_connection(connection, resource) {
 		peer_device = idr_remove(&connection->peer_devices, vnr);
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 8cba10aafadb..79e485949b60 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1154,6 +1154,11 @@ loop_set_status_from_info(struct loop_device *lo,
 
 	lo->lo_offset = info->lo_offset;
 	lo->lo_sizelimit = info->lo_sizelimit;
+
+	/* loff_t vars have been assigned __u64 */
+	if (lo->lo_offset < 0 || lo->lo_sizelimit < 0)
+		return -EOVERFLOW;
+
 	memcpy(lo->lo_file_name, info->lo_file_name, LO_NAME_SIZE);
 	memcpy(lo->lo_crypt_name, info->lo_crypt_name, LO_NAME_SIZE);
 	lo->lo_file_name[LO_NAME_SIZE-1] = 0;
diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index 187d779c8ca0..4c8b4101516c 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -1884,8 +1884,13 @@ static int null_add_dev(struct nullb_device *dev)
 	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, nullb->q);
 
 	mutex_lock(&lock);
-	nullb->index = ida_simple_get(&nullb_indexes, 0, 0, GFP_KERNEL);
-	dev->index = nullb->index;
+	rv = ida_simple_get(&nullb_indexes, 0, 0, GFP_KERNEL);
+	if (rv < 0) {
+		mutex_unlock(&lock);
+		goto out_cleanup_zone;
+	}
+	nullb->index = rv;
+	dev->index = rv;
 	mutex_unlock(&lock);
 
 	blk_queue_logical_block_size(nullb->q, dev->blocksize);
@@ -1905,13 +1910,16 @@ static int null_add_dev(struct nullb_device *dev)
 
 	rv = null_gendisk_register(nullb);
 	if (rv)
-		goto out_cleanup_zone;
+		goto out_ida_free;
 
 	mutex_lock(&lock);
 	list_add_tail(&nullb->list, &nullb_list);
 	mutex_unlock(&lock);
 
 	return 0;
+
+out_ida_free:
+	ida_free(&nullb_indexes, nullb->index);
 out_cleanup_zone:
 	null_free_zoned_dev(dev);
 out_cleanup_disk:
diff --git a/drivers/block/rnbd/rnbd-srv.c b/drivers/block/rnbd/rnbd-srv.c
index aafecfe97055..1896cde8135e 100644
--- a/drivers/block/rnbd/rnbd-srv.c
+++ b/drivers/block/rnbd/rnbd-srv.c
@@ -266,12 +266,12 @@ out:
 static int create_sess(struct rtrs_srv *rtrs)
 {
 	struct rnbd_srv_session *srv_sess;
-	char sessname[NAME_MAX];
+	char pathname[NAME_MAX];
 	int err;
 
-	err = rtrs_srv_get_sess_name(rtrs, sessname, sizeof(sessname));
+	err = rtrs_srv_get_path_name(rtrs, pathname, sizeof(pathname));
 	if (err) {
-		pr_err("rtrs_srv_get_sess_name(%s): %d\n", sessname, err);
+		pr_err("rtrs_srv_get_path_name(%s): %d\n", pathname, err);
 
 		return err;
 	}
@@ -284,8 +284,8 @@ static int create_sess(struct rtrs_srv *rtrs)
 			  offsetof(struct rnbd_dev_blk_io, bio),
 			  BIOSET_NEED_BVECS);
 	if (err) {
-		pr_err("Allocating srv_session for session %s failed\n",
-		       sessname);
+		pr_err("Allocating srv_session for path %s failed\n",
+		       pathname);
 		kfree(srv_sess);
 		return err;
 	}
@@ -298,7 +298,7 @@ static int create_sess(struct rtrs_srv *rtrs)
 	mutex_unlock(&sess_lock);
 
 	srv_sess->rtrs = rtrs;
-	strscpy(srv_sess->sessname, sessname, sizeof(srv_sess->sessname));
+	strscpy(srv_sess->sessname, pathname, sizeof(srv_sess->sessname));
 
 	rtrs_srv_set_sess_priv(rtrs, srv_sess);
 
@@ -333,10 +333,11 @@ void rnbd_srv_sess_dev_force_close(struct rnbd_srv_sess_dev *sess_dev,
 {
 	struct rnbd_srv_session	*sess = sess_dev->sess;
 
-	sess_dev->keep_id = true;
 	/* It is already started to close by client's close message. */
 	if (!mutex_trylock(&sess->lock))
 		return;
+
+	sess_dev->keep_id = true;
 	/* first remove sysfs itself to avoid deadlock */
 	sysfs_remove_file_self(&sess_dev->kobj, &attr->attr);
 	rnbd_srv_destroy_dev_session_sysfs(sess_dev);
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index c05138a28475..d2ba849bb8d1 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -24,6 +24,12 @@
 /* The maximum number of sg elements that fit into a virtqueue */
 #define VIRTIO_BLK_MAX_SG_ELEMS 32768
 
+#ifdef CONFIG_ARCH_NO_SG_CHAIN
+#define VIRTIO_BLK_INLINE_SG_CNT	0
+#else
+#define VIRTIO_BLK_INLINE_SG_CNT	2
+#endif
+
 static int major;
 static DEFINE_IDA(vd_index_ida);
 
@@ -77,6 +83,7 @@ struct virtio_blk {
 struct virtblk_req {
 	struct virtio_blk_outhdr out_hdr;
 	u8 status;
+	struct sg_table sg_table;
 	struct scatterlist sg[];
 };
 
@@ -162,12 +169,92 @@ static int virtblk_setup_discard_write_zeroes(struct request *req, bool unmap)
 	return 0;
 }
 
-static inline void virtblk_request_done(struct request *req)
+static void virtblk_unmap_data(struct request *req, struct virtblk_req *vbr)
 {
-	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
+	if (blk_rq_nr_phys_segments(req))
+		sg_free_table_chained(&vbr->sg_table,
+				      VIRTIO_BLK_INLINE_SG_CNT);
+}
+
+static int virtblk_map_data(struct blk_mq_hw_ctx *hctx, struct request *req,
+		struct virtblk_req *vbr)
+{
+	int err;
+
+	if (!blk_rq_nr_phys_segments(req))
+		return 0;
+
+	vbr->sg_table.sgl = vbr->sg;
+	err = sg_alloc_table_chained(&vbr->sg_table,
+				     blk_rq_nr_phys_segments(req),
+				     vbr->sg_table.sgl,
+				     VIRTIO_BLK_INLINE_SG_CNT);
+	if (unlikely(err))
+		return -ENOMEM;
 
+	return blk_rq_map_sg(hctx->queue, req, vbr->sg_table.sgl);
+}
+
+static void virtblk_cleanup_cmd(struct request *req)
+{
 	if (req->rq_flags & RQF_SPECIAL_PAYLOAD)
 		kfree(bvec_virt(&req->special_vec));
+}
+
+static int virtblk_setup_cmd(struct virtio_device *vdev, struct request *req,
+		struct virtblk_req *vbr)
+{
+	bool unmap = false;
+	u32 type;
+
+	vbr->out_hdr.sector = 0;
+
+	switch (req_op(req)) {
+	case REQ_OP_READ:
+		type = VIRTIO_BLK_T_IN;
+		vbr->out_hdr.sector = cpu_to_virtio64(vdev,
+						      blk_rq_pos(req));
+		break;
+	case REQ_OP_WRITE:
+		type = VIRTIO_BLK_T_OUT;
+		vbr->out_hdr.sector = cpu_to_virtio64(vdev,
+						      blk_rq_pos(req));
+		break;
+	case REQ_OP_FLUSH:
+		type = VIRTIO_BLK_T_FLUSH;
+		break;
+	case REQ_OP_DISCARD:
+		type = VIRTIO_BLK_T_DISCARD;
+		break;
+	case REQ_OP_WRITE_ZEROES:
+		type = VIRTIO_BLK_T_WRITE_ZEROES;
+		unmap = !(req->cmd_flags & REQ_NOUNMAP);
+		break;
+	case REQ_OP_DRV_IN:
+		type = VIRTIO_BLK_T_GET_ID;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return BLK_STS_IOERR;
+	}
+
+	vbr->out_hdr.type = cpu_to_virtio32(vdev, type);
+	vbr->out_hdr.ioprio = cpu_to_virtio32(vdev, req_get_ioprio(req));
+
+	if (type == VIRTIO_BLK_T_DISCARD || type == VIRTIO_BLK_T_WRITE_ZEROES) {
+		if (virtblk_setup_discard_write_zeroes(req, unmap))
+			return BLK_STS_RESOURCE;
+	}
+
+	return 0;
+}
+
+static inline void virtblk_request_done(struct request *req)
+{
+	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
+
+	virtblk_unmap_data(req, vbr);
+	virtblk_cleanup_cmd(req);
 	blk_mq_end_request(req, virtblk_result(vbr));
 }
 
@@ -221,61 +308,27 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 	struct request *req = bd->rq;
 	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
 	unsigned long flags;
-	unsigned int num;
+	int num;
 	int qid = hctx->queue_num;
 	int err;
 	bool notify = false;
-	bool unmap = false;
-	u32 type;
 
 	BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems);
 
-	switch (req_op(req)) {
-	case REQ_OP_READ:
-	case REQ_OP_WRITE:
-		type = 0;
-		break;
-	case REQ_OP_FLUSH:
-		type = VIRTIO_BLK_T_FLUSH;
-		break;
-	case REQ_OP_DISCARD:
-		type = VIRTIO_BLK_T_DISCARD;
-		break;
-	case REQ_OP_WRITE_ZEROES:
-		type = VIRTIO_BLK_T_WRITE_ZEROES;
-		unmap = !(req->cmd_flags & REQ_NOUNMAP);
-		break;
-	case REQ_OP_DRV_IN:
-		type = VIRTIO_BLK_T_GET_ID;
-		break;
-	default:
-		WARN_ON_ONCE(1);
-		return BLK_STS_IOERR;
-	}
-
-	vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, type);
-	vbr->out_hdr.sector = type ?
-		0 : cpu_to_virtio64(vblk->vdev, blk_rq_pos(req));
-	vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(req));
+	err = virtblk_setup_cmd(vblk->vdev, req, vbr);
+	if (unlikely(err))
+		return err;
 
 	blk_mq_start_request(req);
 
-	if (type == VIRTIO_BLK_T_DISCARD || type == VIRTIO_BLK_T_WRITE_ZEROES) {
-		err = virtblk_setup_discard_write_zeroes(req, unmap);
-		if (err)
-			return BLK_STS_RESOURCE;
-	}
-
-	num = blk_rq_map_sg(hctx->queue, req, vbr->sg);
-	if (num) {
-		if (rq_data_dir(req) == WRITE)
-			vbr->out_hdr.type |= cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_OUT);
-		else
-			vbr->out_hdr.type |= cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_IN);
+	num = virtblk_map_data(hctx, req, vbr);
+	if (unlikely(num < 0)) {
+		virtblk_cleanup_cmd(req);
+		return BLK_STS_RESOURCE;
 	}
 
 	spin_lock_irqsave(&vblk->vqs[qid].lock, flags);
-	err = virtblk_add_req(vblk->vqs[qid].vq, vbr, vbr->sg, num);
+	err = virtblk_add_req(vblk->vqs[qid].vq, vbr, vbr->sg_table.sgl, num);
 	if (err) {
 		virtqueue_kick(vblk->vqs[qid].vq);
 		/* Don't stop the queue if -ENOMEM: we may have failed to
@@ -284,6 +337,8 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 		if (err == -ENOSPC)
 			blk_mq_stop_hw_queue(hctx);
 		spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags);
+		virtblk_unmap_data(req, vbr);
+		virtblk_cleanup_cmd(req);
 		switch (err) {
 		case -ENOSPC:
 			return BLK_STS_DEV_RESOURCE;
@@ -660,16 +715,6 @@ static const struct attribute_group *virtblk_attr_groups[] = {
 	NULL,
 };
 
-static int virtblk_init_request(struct blk_mq_tag_set *set, struct request *rq,
-		unsigned int hctx_idx, unsigned int numa_node)
-{
-	struct virtio_blk *vblk = set->driver_data;
-	struct virtblk_req *vbr = blk_mq_rq_to_pdu(rq);
-
-	sg_init_table(vbr->sg, vblk->sg_elems);
-	return 0;
-}
-
 static int virtblk_map_queues(struct blk_mq_tag_set *set)
 {
 	struct virtio_blk *vblk = set->driver_data;
@@ -682,7 +727,6 @@ static const struct blk_mq_ops virtio_mq_ops = {
 	.queue_rq	= virtio_queue_rq,
 	.commit_rqs	= virtio_commit_rqs,
 	.complete	= virtblk_request_done,
-	.init_request	= virtblk_init_request,
 	.map_queues	= virtblk_map_queues,
 };
 
@@ -762,7 +806,7 @@ static int virtblk_probe(struct virtio_device *vdev)
 	vblk->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
 	vblk->tag_set.cmd_size =
 		sizeof(struct virtblk_req) +
-		sizeof(struct scatterlist) * sg_elems;
+		sizeof(struct scatterlist) * VIRTIO_BLK_INLINE_SG_CNT;
 	vblk->tag_set.driver_data = vblk;
 	vblk->tag_set.nr_hw_queues = vblk->num_vqs;
 
diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h
index bda5c815e441..a28473470e66 100644
--- a/drivers/block/xen-blkback/common.h
+++ b/drivers/block/xen-blkback/common.h
@@ -226,6 +226,9 @@ struct xen_vbd {
 	sector_t		size;
 	unsigned int		flush_support:1;
 	unsigned int		discard_secure:1;
+	/* Connect-time cached feature_persistent parameter value */
+	unsigned int		feature_gnt_persistent_parm:1;
+	/* Persistent grants feature negotiation result */
 	unsigned int		feature_gnt_persistent:1;
 	unsigned int		overflow_max_grants:1;
 };
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index 33eba3df4dd9..1525e28c5d70 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -156,6 +156,11 @@ static int xen_blkif_alloc_rings(struct xen_blkif *blkif)
 	return 0;
 }
 
+/* Enable the persistent grants feature. */
+static bool feature_persistent = true;
+module_param(feature_persistent, bool, 0644);
+MODULE_PARM_DESC(feature_persistent, "Enables the persistent grants feature");
+
 static struct xen_blkif *xen_blkif_alloc(domid_t domid)
 {
 	struct xen_blkif *blkif;
@@ -471,12 +476,6 @@ static void xen_vbd_free(struct xen_vbd *vbd)
 	vbd->bdev = NULL;
 }
 
-/* Enable the persistent grants feature. */
-static bool feature_persistent = true;
-module_param(feature_persistent, bool, 0644);
-MODULE_PARM_DESC(feature_persistent,
-		"Enables the persistent grants feature");
-
 static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
 			  unsigned major, unsigned minor, int readonly,
 			  int cdrom)
@@ -522,8 +521,6 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
 	if (q && blk_queue_secure_erase(q))
 		vbd->discard_secure = true;
 
-	vbd->feature_gnt_persistent = feature_persistent;
-
 	pr_debug("Successful creation of handle=%04x (dom=%u)\n",
 		handle, blkif->domid);
 	return 0;
@@ -913,7 +910,7 @@ again:
 	xen_blkbk_barrier(xbt, be, be->blkif->vbd.flush_support);
 
 	err = xenbus_printf(xbt, dev->nodename, "feature-persistent", "%u",
-			be->blkif->vbd.feature_gnt_persistent);
+			be->blkif->vbd.feature_gnt_persistent_parm);
 	if (err) {
 		xenbus_dev_fatal(dev, err, "writing %s/feature-persistent",
 				 dev->nodename);
@@ -1090,10 +1087,11 @@ static int connect_ring(struct backend_info *be)
 		xenbus_dev_fatal(dev, err, "unknown fe protocol %s", protocol);
 		return -ENOSYS;
 	}
-	if (blkif->vbd.feature_gnt_persistent)
-		blkif->vbd.feature_gnt_persistent =
-			xenbus_read_unsigned(dev->otherend,
-					"feature-persistent", 0);
+
+	blkif->vbd.feature_gnt_persistent_parm = feature_persistent;
+	blkif->vbd.feature_gnt_persistent =
+		blkif->vbd.feature_gnt_persistent_parm &&
+		xenbus_read_unsigned(dev->otherend, "feature-persistent", 0);
 
 	blkif->vbd.overflow_max_grants = 0;
 
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index d7a9bf43fb32..24a86d829f92 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -152,6 +152,10 @@ static unsigned int xen_blkif_max_ring_order;
 module_param_named(max_ring_page_order, xen_blkif_max_ring_order, int, 0444);
 MODULE_PARM_DESC(max_ring_page_order, "Maximum order of pages to be used for the shared ring");
 
+static bool __read_mostly xen_blkif_trusted = true;
+module_param_named(trusted, xen_blkif_trusted, bool, 0644);
+MODULE_PARM_DESC(trusted, "Is the backend trusted");
+
 #define BLK_RING_SIZE(info)	\
 	__CONST_RING_SIZE(blkif, XEN_PAGE_SIZE * (info)->nr_ring_pages)
 
@@ -208,7 +212,11 @@ struct blkfront_info
 	unsigned int feature_fua:1;
 	unsigned int feature_discard:1;
 	unsigned int feature_secdiscard:1;
+	/* Connect-time cached feature_persistent parameter */
+	unsigned int feature_persistent_parm:1;
+	/* Persistent grants feature negotiation result */
 	unsigned int feature_persistent:1;
+	unsigned int bounce:1;
 	unsigned int discard_granularity;
 	unsigned int discard_alignment;
 	/* Number of 4KB segments handled */
@@ -311,8 +319,8 @@ static int fill_grant_buffer(struct blkfront_ring_info *rinfo, int num)
 		if (!gnt_list_entry)
 			goto out_of_memory;
 
-		if (info->feature_persistent) {
-			granted_page = alloc_page(GFP_NOIO);
+		if (info->bounce) {
+			granted_page = alloc_page(GFP_NOIO | __GFP_ZERO);
 			if (!granted_page) {
 				kfree(gnt_list_entry);
 				goto out_of_memory;
@@ -331,7 +339,7 @@ out_of_memory:
 	list_for_each_entry_safe(gnt_list_entry, n,
 	                         &rinfo->grants, node) {
 		list_del(&gnt_list_entry->node);
-		if (info->feature_persistent)
+		if (info->bounce)
 			__free_page(gnt_list_entry->page);
 		kfree(gnt_list_entry);
 		i--;
@@ -377,7 +385,7 @@ static struct grant *get_grant(grant_ref_t *gref_head,
 	/* Assign a gref to this page */
 	gnt_list_entry->gref = gnttab_claim_grant_reference(gref_head);
 	BUG_ON(gnt_list_entry->gref == -ENOSPC);
-	if (info->feature_persistent)
+	if (info->bounce)
 		grant_foreign_access(gnt_list_entry, info);
 	else {
 		/* Grant access to the GFN passed by the caller */
@@ -401,7 +409,7 @@ static struct grant *get_indirect_grant(grant_ref_t *gref_head,
 	/* Assign a gref to this page */
 	gnt_list_entry->gref = gnttab_claim_grant_reference(gref_head);
 	BUG_ON(gnt_list_entry->gref == -ENOSPC);
-	if (!info->feature_persistent) {
+	if (!info->bounce) {
 		struct page *indirect_page;
 
 		/* Fetch a pre-allocated page to use for indirect grefs */
@@ -703,7 +711,7 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri
 		.grant_idx = 0,
 		.segments = NULL,
 		.rinfo = rinfo,
-		.need_copy = rq_data_dir(req) && info->feature_persistent,
+		.need_copy = rq_data_dir(req) && info->bounce,
 	};
 
 	/*
@@ -981,11 +989,12 @@ static void xlvbd_flush(struct blkfront_info *info)
 {
 	blk_queue_write_cache(info->rq, info->feature_flush ? true : false,
 			      info->feature_fua ? true : false);
-	pr_info("blkfront: %s: %s %s %s %s %s\n",
+	pr_info("blkfront: %s: %s %s %s %s %s %s %s\n",
 		info->gd->disk_name, flush_info(info),
 		"persistent grants:", info->feature_persistent ?
 		"enabled;" : "disabled;", "indirect descriptors:",
-		info->max_indirect_segments ? "enabled;" : "disabled;");
+		info->max_indirect_segments ? "enabled;" : "disabled;",
+		"bounce buffer:", info->bounce ? "enabled" : "disabled;");
 }
 
 static int xen_translate_vdev(int vdevice, int *minor, unsigned int *offset)
@@ -1212,7 +1221,7 @@ static void blkif_free_ring(struct blkfront_ring_info *rinfo)
 	if (!list_empty(&rinfo->indirect_pages)) {
 		struct page *indirect_page, *n;
 
-		BUG_ON(info->feature_persistent);
+		BUG_ON(info->bounce);
 		list_for_each_entry_safe(indirect_page, n, &rinfo->indirect_pages, lru) {
 			list_del(&indirect_page->lru);
 			__free_page(indirect_page);
@@ -1229,7 +1238,7 @@ static void blkif_free_ring(struct blkfront_ring_info *rinfo)
 							  0, 0UL);
 				rinfo->persistent_gnts_c--;
 			}
-			if (info->feature_persistent)
+			if (info->bounce)
 				__free_page(persistent_gnt->page);
 			kfree(persistent_gnt);
 		}
@@ -1250,7 +1259,7 @@ static void blkif_free_ring(struct blkfront_ring_info *rinfo)
 		for (j = 0; j < segs; j++) {
 			persistent_gnt = rinfo->shadow[i].grants_used[j];
 			gnttab_end_foreign_access(persistent_gnt->gref, 0, 0UL);
-			if (info->feature_persistent)
+			if (info->bounce)
 				__free_page(persistent_gnt->page);
 			kfree(persistent_gnt);
 		}
@@ -1440,7 +1449,7 @@ static int blkif_completion(unsigned long *id,
 	data.s = s;
 	num_sg = s->num_sg;
 
-	if (bret->operation == BLKIF_OP_READ && info->feature_persistent) {
+	if (bret->operation == BLKIF_OP_READ && info->bounce) {
 		for_each_sg(s->sg, sg, num_sg, i) {
 			BUG_ON(sg->offset + sg->length > PAGE_SIZE);
 
@@ -1499,7 +1508,7 @@ static int blkif_completion(unsigned long *id,
 				 * Add the used indirect page back to the list of
 				 * available pages for indirect grefs.
 				 */
-				if (!info->feature_persistent) {
+				if (!info->bounce) {
 					indirect_page = s->indirect_grants[i]->page;
 					list_add(&indirect_page->lru, &rinfo->indirect_pages);
 				}
@@ -1692,7 +1701,7 @@ static int setup_blkring(struct xenbus_device *dev,
 	for (i = 0; i < info->nr_ring_pages; i++)
 		rinfo->ring_ref[i] = GRANT_INVALID_REF;
 
-	sring = alloc_pages_exact(ring_size, GFP_NOIO);
+	sring = alloc_pages_exact(ring_size, GFP_NOIO | __GFP_ZERO);
 	if (!sring) {
 		xenbus_dev_fatal(dev, -ENOMEM, "allocating shared ring");
 		return -ENOMEM;
@@ -1776,6 +1785,12 @@ abort_transaction:
 	return err;
 }
 
+/* Enable the persistent grants feature. */
+static bool feature_persistent = true;
+module_param(feature_persistent, bool, 0644);
+MODULE_PARM_DESC(feature_persistent,
+		"Enables the persistent grants feature");
+
 /* Common code used when first setting up, and when resuming. */
 static int talk_to_blkback(struct xenbus_device *dev,
 			   struct blkfront_info *info)
@@ -1790,6 +1805,10 @@ static int talk_to_blkback(struct xenbus_device *dev,
 	if (!info)
 		return -ENODEV;
 
+	/* Check if backend is trusted. */
+	info->bounce = !xen_blkif_trusted ||
+		       !xenbus_read_unsigned(dev->nodename, "trusted", 1);
+
 	max_page_order = xenbus_read_unsigned(info->xbdev->otherend,
 					      "max-ring-page-order", 0);
 	ring_page_order = min(xen_blkif_max_ring_order, max_page_order);
@@ -1863,8 +1882,9 @@ again:
 		message = "writing protocol";
 		goto abort_transaction;
 	}
+	info->feature_persistent_parm = feature_persistent;
 	err = xenbus_printf(xbt, dev->nodename, "feature-persistent", "%u",
-			info->feature_persistent);
+			info->feature_persistent_parm);
 	if (err)
 		dev_warn(&dev->dev,
 			 "writing persistent grants feature to xenbus");
@@ -1932,12 +1952,6 @@ static int negotiate_mq(struct blkfront_info *info)
 	return 0;
 }
 
-/* Enable the persistent grants feature. */
-static bool feature_persistent = true;
-module_param(feature_persistent, bool, 0644);
-MODULE_PARM_DESC(feature_persistent,
-		"Enables the persistent grants feature");
-
 /*
  * Entry point to this code when a new device is created.  Allocate the basic
  * structures and the ring buffer for communication with the backend, and
@@ -2004,8 +2018,6 @@ static int blkfront_probe(struct xenbus_device *dev,
 	info->vdevice = vdevice;
 	info->connected = BLKIF_STATE_DISCONNECTED;
 
-	info->feature_persistent = feature_persistent;
-
 	/* Front end dir is a number, which is used as the id. */
 	info->handle = simple_strtoul(strrchr(dev->nodename, '/')+1, NULL, 0);
 	dev_set_drvdata(&dev->dev, info);
@@ -2199,17 +2211,18 @@ static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo)
 	if (err)
 		goto out_of_memory;
 
-	if (!info->feature_persistent && info->max_indirect_segments) {
+	if (!info->bounce && info->max_indirect_segments) {
 		/*
-		 * We are using indirect descriptors but not persistent
-		 * grants, we need to allocate a set of pages that can be
+		 * We are using indirect descriptors but don't have a bounce
+		 * buffer, we need to allocate a set of pages that can be
 		 * used for mapping indirect grefs
 		 */
 		int num = INDIRECT_GREFS(grants) * BLK_RING_SIZE(info);
 
 		BUG_ON(!list_empty(&rinfo->indirect_pages));
 		for (i = 0; i < num; i++) {
-			struct page *indirect_page = alloc_page(GFP_KERNEL);
+			struct page *indirect_page = alloc_page(GFP_KERNEL |
+			                                        __GFP_ZERO);
 			if (!indirect_page)
 				goto out_of_memory;
 			list_add(&indirect_page->lru, &rinfo->indirect_pages);
@@ -2298,10 +2311,12 @@ static void blkfront_gather_backend_features(struct blkfront_info *info)
 	if (xenbus_read_unsigned(info->xbdev->otherend, "feature-discard", 0))
 		blkfront_setup_discard(info);
 
-	if (info->feature_persistent)
+	if (info->feature_persistent_parm)
 		info->feature_persistent =
 			!!xenbus_read_unsigned(info->xbdev->otherend,
 					       "feature-persistent", 0);
+	if (info->feature_persistent)
+		info->bounce = true;
 
 	indirect_segments = xenbus_read_unsigned(info->xbdev->otherend,
 					"feature-max-indirect-segments", 0);
@@ -2565,6 +2580,13 @@ static void blkfront_delay_work(struct work_struct *work)
 	struct blkfront_info *info;
 	bool need_schedule_work = false;
 
+	/*
+	 * Note that when using bounce buffers but not persistent grants
+	 * there's no need to run blkfront_delay_work because grants are
+	 * revoked in blkif_completion or else an error is reported and the
+	 * connection is closed.
+	 */
+
 	mutex_lock(&blkfront_mutex);
 
 	list_for_each_entry(info, &info_list, info_list) {
diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c
index 052aa3f65514..0916de952e09 100644
--- a/drivers/block/zram/zcomp.c
+++ b/drivers/block/zram/zcomp.c
@@ -63,12 +63,6 @@ static int zcomp_strm_init(struct zcomp_strm *zstrm, struct zcomp *comp)
 
 bool zcomp_available_algorithm(const char *comp)
 {
-	int i;
-
-	i = sysfs_match_string(backends, comp);
-	if (i >= 0)
-		return true;
-
 	/*
 	 * Crypto does not ignore a trailing new line symbol,
 	 * so make sure you don't supply a string containing
@@ -217,6 +211,11 @@ struct zcomp *zcomp_create(const char *compress)
 	struct zcomp *comp;
 	int error;
 
+	/*
+	 * Crypto API will execute /sbin/modprobe if the compression module
+	 * is not loaded yet. We must do it here, otherwise we are about to
+	 * call /sbin/modprobe under CPU hot-plug lock.
+	 */
 	if (!zcomp_available_algorithm(compress))
 		return ERR_PTR(-EINVAL);
 
diff --git a/drivers/bluetooth/btbcm.c b/drivers/bluetooth/btbcm.c
index d9ceca7a7935..a18f289d7346 100644
--- a/drivers/bluetooth/btbcm.c
+++ b/drivers/bluetooth/btbcm.c
@@ -453,6 +453,8 @@ static const struct bcm_subver_table bcm_uart_subver_table[] = {
 	{ 0x6606, "BCM4345C5"	},	/* 003.006.006 */
 	{ 0x230f, "BCM4356A2"	},	/* 001.003.015 */
 	{ 0x220e, "BCM20702A1"  },	/* 001.002.014 */
+	{ 0x420d, "BCM4349B1"	},	/* 002.002.013 */
+	{ 0x420e, "BCM4349B1"	},	/* 002.002.014 */
 	{ 0x4217, "BCM4329B1"   },	/* 002.002.023 */
 	{ 0x6106, "BCM4359C0"	},	/* 003.001.006 */
 	{ 0x4106, "BCM4335A0"	},	/* 002.001.006 */
diff --git a/drivers/bluetooth/btmtksdio.c b/drivers/bluetooth/btmtksdio.c
index ff1f5dfbb6db..d66e4df171d2 100644
--- a/drivers/bluetooth/btmtksdio.c
+++ b/drivers/bluetooth/btmtksdio.c
@@ -331,6 +331,7 @@ static int btmtksdio_recv_event(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct btmtksdio_dev *bdev = hci_get_drvdata(hdev);
 	struct hci_event_hdr *hdr = (void *)skb->data;
+	u8 evt = hdr->evt;
 	int err;
 
 	/* Fix up the vendor event id with 0xff for vendor specific instead
@@ -355,7 +356,7 @@ static int btmtksdio_recv_event(struct hci_dev *hdev, struct sk_buff *skb)
 	if (err < 0)
 		goto err_free_skb;
 
-	if (hdr->evt == HCI_EV_VENDOR) {
+	if (evt == HCI_EV_VENDOR) {
 		if (test_and_clear_bit(BTMTKSDIO_TX_WAIT_VND_EVT,
 				       &bdev->tx_state)) {
 			/* Barrier to sync with other CPUs */
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index a68edbc7be0f..627436329b50 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -420,6 +420,18 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x04ca, 0x4006), .driver_info = BTUSB_REALTEK |
 						     BTUSB_WIDEBAND_SPEECH },
 
+	/* Realtek 8852CE Bluetooth devices */
+	{ USB_DEVICE(0x04ca, 0x4007), .driver_info = BTUSB_REALTEK |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x04c5, 0x1675), .driver_info = BTUSB_REALTEK |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0cb8, 0xc558), .driver_info = BTUSB_REALTEK |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x13d3, 0x3587), .driver_info = BTUSB_REALTEK |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x13d3, 0x3586), .driver_info = BTUSB_REALTEK |
+						     BTUSB_WIDEBAND_SPEECH },
+
 	/* Realtek Bluetooth devices */
 	{ USB_VENDOR_AND_INTERFACE_INFO(0x0bda, 0xe0, 0x01, 0x01),
 	  .driver_info = BTUSB_REALTEK },
@@ -459,6 +471,9 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x0489, 0xe0d9), .driver_info = BTUSB_MEDIATEK |
 						     BTUSB_WIDEBAND_SPEECH |
 						     BTUSB_VALID_LE_STATES },
+	{ USB_DEVICE(0x13d3, 0x3568), .driver_info = BTUSB_MEDIATEK |
+						     BTUSB_WIDEBAND_SPEECH |
+						     BTUSB_VALID_LE_STATES },
 
 	/* Additional Realtek 8723AE Bluetooth devices */
 	{ USB_DEVICE(0x0930, 0x021d), .driver_info = BTUSB_REALTEK },
diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c
index 7abf99f0ee39..cf622e459605 100644
--- a/drivers/bluetooth/hci_bcm.c
+++ b/drivers/bluetooth/hci_bcm.c
@@ -1515,8 +1515,10 @@ static const struct of_device_id bcm_bluetooth_of_match[] = {
 	{ .compatible = "brcm,bcm4345c5" },
 	{ .compatible = "brcm,bcm4330-bt" },
 	{ .compatible = "brcm,bcm43438-bt", .data = &bcm43438_device_data },
+	{ .compatible = "brcm,bcm4349-bt", .data = &bcm43438_device_data },
 	{ .compatible = "brcm,bcm43540-bt", .data = &bcm4354_device_data },
 	{ .compatible = "brcm,bcm4335a0" },
+	{ .compatible = "infineon,cyw55572-bt" },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, bcm_bluetooth_of_match);
diff --git a/drivers/bluetooth/hci_intel.c b/drivers/bluetooth/hci_intel.c
index 7249b91d9b91..78afb9a348e7 100644
--- a/drivers/bluetooth/hci_intel.c
+++ b/drivers/bluetooth/hci_intel.c
@@ -1217,7 +1217,11 @@ static struct platform_driver intel_driver = {
 
 int __init intel_init(void)
 {
-	platform_driver_register(&intel_driver);
+	int err;
+
+	err = platform_driver_register(&intel_driver);
+	if (err)
+		return err;
 
 	return hci_uart_register_proto(&intel_proto);
 }
diff --git a/drivers/bus/hisi_lpc.c b/drivers/bus/hisi_lpc.c
index 378f5d62a991..e7eaa8784fee 100644
--- a/drivers/bus/hisi_lpc.c
+++ b/drivers/bus/hisi_lpc.c
@@ -503,13 +503,13 @@ static int hisi_lpc_acpi_probe(struct device *hostdev)
 {
 	struct acpi_device *adev = ACPI_COMPANION(hostdev);
 	struct acpi_device *child;
+	struct platform_device *pdev;
 	int ret;
 
 	/* Only consider the children of the host */
 	list_for_each_entry(child, &adev->children, node) {
 		const char *hid = acpi_device_hid(child);
 		const struct hisi_lpc_acpi_cell *cell;
-		struct platform_device *pdev;
 		const struct resource *res;
 		bool found = false;
 		int num_res;
@@ -571,22 +571,24 @@ static int hisi_lpc_acpi_probe(struct device *hostdev)
 
 		ret = platform_device_add_resources(pdev, res, num_res);
 		if (ret)
-			goto fail;
+			goto fail_put_device;
 
 		ret = platform_device_add_data(pdev, cell->pdata,
 					       cell->pdata_size);
 		if (ret)
-			goto fail;
+			goto fail_put_device;
 
 		ret = platform_device_add(pdev);
 		if (ret)
-			goto fail;
+			goto fail_put_device;
 
 		acpi_device_set_enumerated(child);
 	}
 
 	return 0;
 
+fail_put_device:
+	platform_device_put(pdev);
 fail:
 	hisi_lpc_acpi_remove(hostdev);
 	return ret;
diff --git a/drivers/bus/mhi/core/init.c b/drivers/bus/mhi/core/init.c
index 4183945fc2c4..d8787aaa176b 100644
--- a/drivers/bus/mhi/core/init.c
+++ b/drivers/bus/mhi/core/init.c
@@ -77,11 +77,14 @@ static const char * const mhi_pm_state_str[] = {
 	[MHI_PM_STATE_LD_ERR_FATAL_DETECT] = "Linkdown or Error Fatal Detect",
 };
 
-const char *to_mhi_pm_state_str(enum mhi_pm_state state)
+const char *to_mhi_pm_state_str(u32 state)
 {
-	int index = find_last_bit((unsigned long *)&state, 32);
+	int index;
 
-	if (index >= ARRAY_SIZE(mhi_pm_state_str))
+	if (state)
+		index = __fls(state);
+
+	if (!state || index >= ARRAY_SIZE(mhi_pm_state_str))
 		return "Invalid State";
 
 	return mhi_pm_state_str[index];
diff --git a/drivers/bus/mhi/core/internal.h b/drivers/bus/mhi/core/internal.h
index c02c4d48b744..71f181402be9 100644
--- a/drivers/bus/mhi/core/internal.h
+++ b/drivers/bus/mhi/core/internal.h
@@ -622,7 +622,7 @@ void mhi_free_bhie_table(struct mhi_controller *mhi_cntrl,
 enum mhi_pm_state __must_check mhi_tryset_pm_state(
 					struct mhi_controller *mhi_cntrl,
 					enum mhi_pm_state state);
-const char *to_mhi_pm_state_str(enum mhi_pm_state state);
+const char *to_mhi_pm_state_str(u32 state);
 int mhi_queue_state_transition(struct mhi_controller *mhi_cntrl,
 			       enum dev_st_transition state);
 void mhi_pm_st_worker(struct work_struct *work);
diff --git a/drivers/bus/mhi/pci_generic.c b/drivers/bus/mhi/pci_generic.c
index 0982642a7907..b780990faf80 100644
--- a/drivers/bus/mhi/pci_generic.c
+++ b/drivers/bus/mhi/pci_generic.c
@@ -406,11 +406,90 @@ static const struct mhi_pci_dev_info mhi_mv31_info = {
 	.mru_default = 32768,
 };
 
+static const struct mhi_channel_config mhi_telit_fn980_hw_v1_channels[] = {
+	MHI_CHANNEL_CONFIG_UL(14, "QMI", 32, 0),
+	MHI_CHANNEL_CONFIG_DL(15, "QMI", 32, 0),
+	MHI_CHANNEL_CONFIG_UL(20, "IPCR", 16, 0),
+	MHI_CHANNEL_CONFIG_DL_AUTOQUEUE(21, "IPCR", 16, 0),
+	MHI_CHANNEL_CONFIG_HW_UL(100, "IP_HW0", 128, 1),
+	MHI_CHANNEL_CONFIG_HW_DL(101, "IP_HW0", 128, 2),
+};
+
+static struct mhi_event_config mhi_telit_fn980_hw_v1_events[] = {
+	MHI_EVENT_CONFIG_CTRL(0, 128),
+	MHI_EVENT_CONFIG_HW_DATA(1, 1024, 100),
+	MHI_EVENT_CONFIG_HW_DATA(2, 2048, 101)
+};
+
+static struct mhi_controller_config modem_telit_fn980_hw_v1_config = {
+	.max_channels = 128,
+	.timeout_ms = 20000,
+	.num_channels = ARRAY_SIZE(mhi_telit_fn980_hw_v1_channels),
+	.ch_cfg = mhi_telit_fn980_hw_v1_channels,
+	.num_events = ARRAY_SIZE(mhi_telit_fn980_hw_v1_events),
+	.event_cfg = mhi_telit_fn980_hw_v1_events,
+};
+
+static const struct mhi_pci_dev_info mhi_telit_fn980_hw_v1_info = {
+	.name = "telit-fn980-hwv1",
+	.fw = "qcom/sdx55m/sbl1.mbn",
+	.edl = "qcom/sdx55m/edl.mbn",
+	.config = &modem_telit_fn980_hw_v1_config,
+	.bar_num = MHI_PCI_DEFAULT_BAR_NUM,
+	.dma_data_width = 32,
+	.mru_default = 32768,
+	.sideband_wake = false,
+};
+
+static const struct mhi_channel_config mhi_telit_fn990_channels[] = {
+	MHI_CHANNEL_CONFIG_UL_SBL(2, "SAHARA", 32, 0),
+	MHI_CHANNEL_CONFIG_DL_SBL(3, "SAHARA", 32, 0),
+	MHI_CHANNEL_CONFIG_UL(4, "DIAG", 64, 1),
+	MHI_CHANNEL_CONFIG_DL(5, "DIAG", 64, 1),
+	MHI_CHANNEL_CONFIG_UL(12, "MBIM", 32, 0),
+	MHI_CHANNEL_CONFIG_DL(13, "MBIM", 32, 0),
+	MHI_CHANNEL_CONFIG_UL(32, "DUN", 32, 0),
+	MHI_CHANNEL_CONFIG_DL(33, "DUN", 32, 0),
+	MHI_CHANNEL_CONFIG_HW_UL(100, "IP_HW0_MBIM", 128, 2),
+	MHI_CHANNEL_CONFIG_HW_DL(101, "IP_HW0_MBIM", 128, 3),
+};
+
+static struct mhi_event_config mhi_telit_fn990_events[] = {
+	MHI_EVENT_CONFIG_CTRL(0, 128),
+	MHI_EVENT_CONFIG_DATA(1, 128),
+	MHI_EVENT_CONFIG_HW_DATA(2, 1024, 100),
+	MHI_EVENT_CONFIG_HW_DATA(3, 2048, 101)
+};
+
+static const struct mhi_controller_config modem_telit_fn990_config = {
+	.max_channels = 128,
+	.timeout_ms = 20000,
+	.num_channels = ARRAY_SIZE(mhi_telit_fn990_channels),
+	.ch_cfg = mhi_telit_fn990_channels,
+	.num_events = ARRAY_SIZE(mhi_telit_fn990_events),
+	.event_cfg = mhi_telit_fn990_events,
+};
+
+static const struct mhi_pci_dev_info mhi_telit_fn990_info = {
+	.name = "telit-fn990",
+	.config = &modem_telit_fn990_config,
+	.bar_num = MHI_PCI_DEFAULT_BAR_NUM,
+	.dma_data_width = 32,
+	.sideband_wake = false,
+	.mru_default = 32768,
+};
+
 static const struct pci_device_id mhi_pci_id_table[] = {
+	/* Telit FN980 hardware revision v1 */
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_QCOM, 0x0306, 0x1C5D, 0x2000),
+		.driver_data = (kernel_ulong_t) &mhi_telit_fn980_hw_v1_info },
 	{ PCI_DEVICE(PCI_VENDOR_ID_QCOM, 0x0306),
 		.driver_data = (kernel_ulong_t) &mhi_qcom_sdx55_info },
 	{ PCI_DEVICE(PCI_VENDOR_ID_QCOM, 0x0304),
 		.driver_data = (kernel_ulong_t) &mhi_qcom_sdx24_info },
+	/* Telit FN990 */
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_QCOM, 0x0308, 0x1c5d, 0x2010),
+		.driver_data = (kernel_ulong_t) &mhi_telit_fn990_info },
 	{ PCI_DEVICE(0x1eac, 0x1001), /* EM120R-GL (sdx24) */
 		.driver_data = (kernel_ulong_t) &mhi_quectel_em1xx_info },
 	{ PCI_DEVICE(0x1eac, 0x1002), /* EM160R-GL (sdx24) */
diff --git a/drivers/clk/bcm/clk-raspberrypi.c b/drivers/clk/bcm/clk-raspberrypi.c
index dd3b71eafabf..56c5166f841a 100644
--- a/drivers/clk/bcm/clk-raspberrypi.c
+++ b/drivers/clk/bcm/clk-raspberrypi.c
@@ -139,7 +139,7 @@ static unsigned long raspberrypi_fw_get_rate(struct clk_hw *hw,
 	ret = raspberrypi_clock_property(rpi->firmware, data,
 					 RPI_FIRMWARE_GET_CLOCK_RATE, &val);
 	if (ret)
-		return ret;
+		return 0;
 
 	return val;
 }
@@ -156,7 +156,7 @@ static int raspberrypi_fw_set_rate(struct clk_hw *hw, unsigned long rate,
 	ret = raspberrypi_clock_property(rpi->firmware, data,
 					 RPI_FIRMWARE_SET_CLOCK_RATE, &_rate);
 	if (ret)
-		dev_err_ratelimited(rpi->dev, "Failed to change %s frequency: %d",
+		dev_err_ratelimited(rpi->dev, "Failed to change %s frequency: %d\n",
 				    clk_hw_get_name(hw), ret);
 
 	return ret;
@@ -208,7 +208,7 @@ static struct clk_hw *raspberrypi_clk_register(struct raspberrypi_clk *rpi,
 					 RPI_FIRMWARE_GET_MIN_CLOCK_RATE,
 					 &min_rate);
 	if (ret) {
-		dev_err(rpi->dev, "Failed to get clock %d min freq: %d",
+		dev_err(rpi->dev, "Failed to get clock %d min freq: %d\n",
 			id, ret);
 		return ERR_PTR(ret);
 	}
@@ -251,8 +251,13 @@ static int raspberrypi_discover_clocks(struct raspberrypi_clk *rpi,
 	struct rpi_firmware_get_clocks_response *clks;
 	int ret;
 
+	/*
+	 * The firmware doesn't guarantee that the last element of
+	 * RPI_FIRMWARE_GET_CLOCKS is zeroed. So allocate an additional
+	 * zero element as sentinel.
+	 */
 	clks = devm_kcalloc(rpi->dev,
-			    sizeof(*clks), RPI_FIRMWARE_NUM_CLK_ID,
+			    RPI_FIRMWARE_NUM_CLK_ID + 1, sizeof(*clks),
 			    GFP_KERNEL);
 	if (!clks)
 		return -ENOMEM;
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 753a6522cf5e..1c9a74efb632 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -846,10 +846,9 @@ static void clk_core_unprepare(struct clk_core *core)
 	if (core->ops->unprepare)
 		core->ops->unprepare(core->hw);
 
-	clk_pm_runtime_put(core);
-
 	trace_clk_unprepare_complete(core);
 	clk_core_unprepare(core->parent);
+	clk_pm_runtime_put(core);
 }
 
 static void clk_core_unprepare_lock(struct clk_core *core)
diff --git a/drivers/clk/mediatek/reset.c b/drivers/clk/mediatek/reset.c
index e562dc3c10a4..d311da574499 100644
--- a/drivers/clk/mediatek/reset.c
+++ b/drivers/clk/mediatek/reset.c
@@ -25,7 +25,7 @@ static int mtk_reset_assert_set_clr(struct reset_controller_dev *rcdev,
 	struct mtk_reset *data = container_of(rcdev, struct mtk_reset, rcdev);
 	unsigned int reg = data->regofs + ((id / 32) << 4);
 
-	return regmap_write(data->regmap, reg, 1);
+	return regmap_write(data->regmap, reg, BIT(id % 32));
 }
 
 static int mtk_reset_deassert_set_clr(struct reset_controller_dev *rcdev,
@@ -34,7 +34,7 @@ static int mtk_reset_deassert_set_clr(struct reset_controller_dev *rcdev,
 	struct mtk_reset *data = container_of(rcdev, struct mtk_reset, rcdev);
 	unsigned int reg = data->regofs + ((id / 32) << 4) + 0x4;
 
-	return regmap_write(data->regmap, reg, 1);
+	return regmap_write(data->regmap, reg, BIT(id % 32));
 }
 
 static int mtk_reset_assert(struct reset_controller_dev *rcdev,
diff --git a/drivers/clk/qcom/camcc-sdm845.c b/drivers/clk/qcom/camcc-sdm845.c
index 1b2cefef7431..a8a2cfa83290 100644
--- a/drivers/clk/qcom/camcc-sdm845.c
+++ b/drivers/clk/qcom/camcc-sdm845.c
@@ -1521,6 +1521,8 @@ static struct clk_branch cam_cc_sys_tmr_clk = {
 	},
 };
 
+static struct gdsc titan_top_gdsc;
+
 static struct gdsc bps_gdsc = {
 	.gdscr = 0x6004,
 	.pd = {
@@ -1554,6 +1556,7 @@ static struct gdsc ife_0_gdsc = {
 		.name = "ife_0_gdsc",
 	},
 	.flags = POLL_CFG_GDSCR,
+	.parent = &titan_top_gdsc.pd,
 	.pwrsts = PWRSTS_OFF_ON,
 };
 
@@ -1563,6 +1566,7 @@ static struct gdsc ife_1_gdsc = {
 		.name = "ife_1_gdsc",
 	},
 	.flags = POLL_CFG_GDSCR,
+	.parent = &titan_top_gdsc.pd,
 	.pwrsts = PWRSTS_OFF_ON,
 };
 
diff --git a/drivers/clk/qcom/camcc-sm8250.c b/drivers/clk/qcom/camcc-sm8250.c
index 439eaafdcc86..9b32c56a5bc5 100644
--- a/drivers/clk/qcom/camcc-sm8250.c
+++ b/drivers/clk/qcom/camcc-sm8250.c
@@ -2205,6 +2205,8 @@ static struct clk_branch cam_cc_sleep_clk = {
 	},
 };
 
+static struct gdsc titan_top_gdsc;
+
 static struct gdsc bps_gdsc = {
 	.gdscr = 0x7004,
 	.pd = {
@@ -2238,6 +2240,7 @@ static struct gdsc ife_0_gdsc = {
 		.name = "ife_0_gdsc",
 	},
 	.flags = POLL_CFG_GDSCR,
+	.parent = &titan_top_gdsc.pd,
 	.pwrsts = PWRSTS_OFF_ON,
 };
 
@@ -2247,6 +2250,7 @@ static struct gdsc ife_1_gdsc = {
 		.name = "ife_1_gdsc",
 	},
 	.flags = POLL_CFG_GDSCR,
+	.parent = &titan_top_gdsc.pd,
 	.pwrsts = PWRSTS_OFF_ON,
 };
 
@@ -2440,17 +2444,7 @@ static struct platform_driver cam_cc_sm8250_driver = {
 	},
 };
 
-static int __init cam_cc_sm8250_init(void)
-{
-	return platform_driver_register(&cam_cc_sm8250_driver);
-}
-subsys_initcall(cam_cc_sm8250_init);
-
-static void __exit cam_cc_sm8250_exit(void)
-{
-	platform_driver_unregister(&cam_cc_sm8250_driver);
-}
-module_exit(cam_cc_sm8250_exit);
+module_platform_driver(cam_cc_sm8250_driver);
 
 MODULE_DESCRIPTION("QTI CAMCC SM8250 Driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/qcom/clk-alpha-pll.c b/drivers/clk/qcom/clk-alpha-pll.c
index 8f65b9bdafce..5e44ceb730ad 100644
--- a/drivers/clk/qcom/clk-alpha-pll.c
+++ b/drivers/clk/qcom/clk-alpha-pll.c
@@ -1420,7 +1420,7 @@ const struct clk_ops clk_alpha_pll_postdiv_fabia_ops = {
 EXPORT_SYMBOL_GPL(clk_alpha_pll_postdiv_fabia_ops);
 
 /**
- * clk_lucid_pll_configure - configure the lucid pll
+ * clk_trion_pll_configure - configure the trion pll
  *
  * @pll: clk alpha pll
  * @regmap: register map
diff --git a/drivers/clk/qcom/clk-krait.c b/drivers/clk/qcom/clk-krait.c
index 59f1af415b58..90046428693c 100644
--- a/drivers/clk/qcom/clk-krait.c
+++ b/drivers/clk/qcom/clk-krait.c
@@ -32,11 +32,16 @@ static void __krait_mux_set_sel(struct krait_mux_clk *mux, int sel)
 		regval |= (sel & mux->mask) << (mux->shift + LPL_SHIFT);
 	}
 	krait_set_l2_indirect_reg(mux->offset, regval);
-	spin_unlock_irqrestore(&krait_clock_reg_lock, flags);
 
 	/* Wait for switch to complete. */
 	mb();
 	udelay(1);
+
+	/*
+	 * Unlock now to make sure the mux register is not
+	 * modified while switching to the new parent.
+	 */
+	spin_unlock_irqrestore(&krait_clock_reg_lock, flags);
 }
 
 static int krait_mux_set_parent(struct clk_hw *hw, u8 index)
diff --git a/drivers/clk/qcom/clk-rcg2.c b/drivers/clk/qcom/clk-rcg2.c
index f675fd969c4d..c3823cc32edc 100644
--- a/drivers/clk/qcom/clk-rcg2.c
+++ b/drivers/clk/qcom/clk-rcg2.c
@@ -13,6 +13,7 @@
 #include <linux/rational.h>
 #include <linux/regmap.h>
 #include <linux/math64.h>
+#include <linux/minmax.h>
 #include <linux/slab.h>
 
 #include <asm/div64.h>
@@ -405,7 +406,7 @@ static int clk_rcg2_get_duty_cycle(struct clk_hw *hw, struct clk_duty *duty)
 static int clk_rcg2_set_duty_cycle(struct clk_hw *hw, struct clk_duty *duty)
 {
 	struct clk_rcg2 *rcg = to_clk_rcg2(hw);
-	u32 notn_m, n, m, d, not2d, mask, duty_per;
+	u32 notn_m, n, m, d, not2d, mask, duty_per, cfg;
 	int ret;
 
 	/* Duty-cycle cannot be modified for non-MND RCGs */
@@ -416,6 +417,11 @@ static int clk_rcg2_set_duty_cycle(struct clk_hw *hw, struct clk_duty *duty)
 
 	regmap_read(rcg->clkr.regmap, RCG_N_OFFSET(rcg), &notn_m);
 	regmap_read(rcg->clkr.regmap, RCG_M_OFFSET(rcg), &m);
+	regmap_read(rcg->clkr.regmap, RCG_CFG_OFFSET(rcg), &cfg);
+
+	/* Duty-cycle cannot be modified if MND divider is in bypass mode. */
+	if (!(cfg & CFG_MODE_MASK))
+		return -EINVAL;
 
 	n = (~(notn_m) + m) & mask;
 
@@ -424,9 +430,11 @@ static int clk_rcg2_set_duty_cycle(struct clk_hw *hw, struct clk_duty *duty)
 	/* Calculate 2d value */
 	d = DIV_ROUND_CLOSEST(n * duty_per * 2, 100);
 
-	 /* Check bit widths of 2d. If D is too big reduce duty cycle. */
-	if (d > mask)
-		d = mask;
+	/*
+	 * Check bit widths of 2d. If D is too big reduce duty cycle.
+	 * Also make sure it is never zero.
+	 */
+	d = clamp_val(d, 1, mask);
 
 	if ((d / 2) > (n - m))
 		d = (n - m) * 2;
diff --git a/drivers/clk/qcom/gcc-ipq8074.c b/drivers/clk/qcom/gcc-ipq8074.c
index 541016db3c4b..d6d5defb82c9 100644
--- a/drivers/clk/qcom/gcc-ipq8074.c
+++ b/drivers/clk/qcom/gcc-ipq8074.c
@@ -662,6 +662,7 @@ static struct clk_branch gcc_sleep_clk_src = {
 			},
 			.num_parents = 1,
 			.ops = &clk_branch2_ops,
+			.flags = CLK_IS_CRITICAL,
 		},
 	},
 };
@@ -1788,8 +1789,10 @@ static struct clk_regmap_div nss_port4_tx_div_clk_src = {
 static const struct freq_tbl ftbl_nss_port5_rx_clk_src[] = {
 	F(19200000, P_XO, 1, 0, 0),
 	F(25000000, P_UNIPHY1_RX, 12.5, 0, 0),
+	F(25000000, P_UNIPHY0_RX, 5, 0, 0),
 	F(78125000, P_UNIPHY1_RX, 4, 0, 0),
 	F(125000000, P_UNIPHY1_RX, 2.5, 0, 0),
+	F(125000000, P_UNIPHY0_RX, 1, 0, 0),
 	F(156250000, P_UNIPHY1_RX, 2, 0, 0),
 	F(312500000, P_UNIPHY1_RX, 1, 0, 0),
 	{ }
@@ -1828,8 +1831,10 @@ static struct clk_regmap_div nss_port5_rx_div_clk_src = {
 static const struct freq_tbl ftbl_nss_port5_tx_clk_src[] = {
 	F(19200000, P_XO, 1, 0, 0),
 	F(25000000, P_UNIPHY1_TX, 12.5, 0, 0),
+	F(25000000, P_UNIPHY0_TX, 5, 0, 0),
 	F(78125000, P_UNIPHY1_TX, 4, 0, 0),
 	F(125000000, P_UNIPHY1_TX, 2.5, 0, 0),
+	F(125000000, P_UNIPHY0_TX, 1, 0, 0),
 	F(156250000, P_UNIPHY1_TX, 2, 0, 0),
 	F(312500000, P_UNIPHY1_TX, 1, 0, 0),
 	{ }
@@ -1867,8 +1872,10 @@ static struct clk_regmap_div nss_port5_tx_div_clk_src = {
 
 static const struct freq_tbl ftbl_nss_port6_rx_clk_src[] = {
 	F(19200000, P_XO, 1, 0, 0),
+	F(25000000, P_UNIPHY2_RX, 5, 0, 0),
 	F(25000000, P_UNIPHY2_RX, 12.5, 0, 0),
 	F(78125000, P_UNIPHY2_RX, 4, 0, 0),
+	F(125000000, P_UNIPHY2_RX, 1, 0, 0),
 	F(125000000, P_UNIPHY2_RX, 2.5, 0, 0),
 	F(156250000, P_UNIPHY2_RX, 2, 0, 0),
 	F(312500000, P_UNIPHY2_RX, 1, 0, 0),
@@ -1907,8 +1914,10 @@ static struct clk_regmap_div nss_port6_rx_div_clk_src = {
 
 static const struct freq_tbl ftbl_nss_port6_tx_clk_src[] = {
 	F(19200000, P_XO, 1, 0, 0),
+	F(25000000, P_UNIPHY2_TX, 5, 0, 0),
 	F(25000000, P_UNIPHY2_TX, 12.5, 0, 0),
 	F(78125000, P_UNIPHY2_TX, 4, 0, 0),
+	F(125000000, P_UNIPHY2_TX, 1, 0, 0),
 	F(125000000, P_UNIPHY2_TX, 2.5, 0, 0),
 	F(156250000, P_UNIPHY2_TX, 2, 0, 0),
 	F(312500000, P_UNIPHY2_TX, 1, 0, 0),
@@ -3346,6 +3355,7 @@ static struct clk_branch gcc_nssnoc_ubi1_ahb_clk = {
 
 static struct clk_branch gcc_ubi0_ahb_clk = {
 	.halt_reg = 0x6820c,
+	.halt_check = BRANCH_HALT_DELAY,
 	.clkr = {
 		.enable_reg = 0x6820c,
 		.enable_mask = BIT(0),
@@ -3363,6 +3373,7 @@ static struct clk_branch gcc_ubi0_ahb_clk = {
 
 static struct clk_branch gcc_ubi0_axi_clk = {
 	.halt_reg = 0x68200,
+	.halt_check = BRANCH_HALT_DELAY,
 	.clkr = {
 		.enable_reg = 0x68200,
 		.enable_mask = BIT(0),
@@ -3380,6 +3391,7 @@ static struct clk_branch gcc_ubi0_axi_clk = {
 
 static struct clk_branch gcc_ubi0_nc_axi_clk = {
 	.halt_reg = 0x68204,
+	.halt_check = BRANCH_HALT_DELAY,
 	.clkr = {
 		.enable_reg = 0x68204,
 		.enable_mask = BIT(0),
@@ -3397,6 +3409,7 @@ static struct clk_branch gcc_ubi0_nc_axi_clk = {
 
 static struct clk_branch gcc_ubi0_core_clk = {
 	.halt_reg = 0x68210,
+	.halt_check = BRANCH_HALT_DELAY,
 	.clkr = {
 		.enable_reg = 0x68210,
 		.enable_mask = BIT(0),
@@ -3414,6 +3427,7 @@ static struct clk_branch gcc_ubi0_core_clk = {
 
 static struct clk_branch gcc_ubi0_mpt_clk = {
 	.halt_reg = 0x68208,
+	.halt_check = BRANCH_HALT_DELAY,
 	.clkr = {
 		.enable_reg = 0x68208,
 		.enable_mask = BIT(0),
@@ -3431,6 +3445,7 @@ static struct clk_branch gcc_ubi0_mpt_clk = {
 
 static struct clk_branch gcc_ubi1_ahb_clk = {
 	.halt_reg = 0x6822c,
+	.halt_check = BRANCH_HALT_DELAY,
 	.clkr = {
 		.enable_reg = 0x6822c,
 		.enable_mask = BIT(0),
@@ -3448,6 +3463,7 @@ static struct clk_branch gcc_ubi1_ahb_clk = {
 
 static struct clk_branch gcc_ubi1_axi_clk = {
 	.halt_reg = 0x68220,
+	.halt_check = BRANCH_HALT_DELAY,
 	.clkr = {
 		.enable_reg = 0x68220,
 		.enable_mask = BIT(0),
@@ -3465,6 +3481,7 @@ static struct clk_branch gcc_ubi1_axi_clk = {
 
 static struct clk_branch gcc_ubi1_nc_axi_clk = {
 	.halt_reg = 0x68224,
+	.halt_check = BRANCH_HALT_DELAY,
 	.clkr = {
 		.enable_reg = 0x68224,
 		.enable_mask = BIT(0),
@@ -3482,6 +3499,7 @@ static struct clk_branch gcc_ubi1_nc_axi_clk = {
 
 static struct clk_branch gcc_ubi1_core_clk = {
 	.halt_reg = 0x68230,
+	.halt_check = BRANCH_HALT_DELAY,
 	.clkr = {
 		.enable_reg = 0x68230,
 		.enable_mask = BIT(0),
@@ -3499,6 +3517,7 @@ static struct clk_branch gcc_ubi1_core_clk = {
 
 static struct clk_branch gcc_ubi1_mpt_clk = {
 	.halt_reg = 0x68228,
+	.halt_check = BRANCH_HALT_DELAY,
 	.clkr = {
 		.enable_reg = 0x68228,
 		.enable_mask = BIT(0),
@@ -4371,6 +4390,33 @@ static struct clk_branch gcc_pcie0_axi_s_bridge_clk = {
 	},
 };
 
+static const struct alpha_pll_config ubi32_pll_config = {
+	.l = 0x4e,
+	.config_ctl_val = 0x200d4aa8,
+	.config_ctl_hi_val = 0x3c2,
+	.main_output_mask = BIT(0),
+	.aux_output_mask = BIT(1),
+	.pre_div_val = 0x0,
+	.pre_div_mask = BIT(12),
+	.post_div_val = 0x0,
+	.post_div_mask = GENMASK(9, 8),
+};
+
+static const struct alpha_pll_config nss_crypto_pll_config = {
+	.l = 0x3e,
+	.alpha = 0x0,
+	.alpha_hi = 0x80,
+	.config_ctl_val = 0x4001055b,
+	.main_output_mask = BIT(0),
+	.pre_div_val = 0x0,
+	.pre_div_mask = GENMASK(14, 12),
+	.post_div_val = 0x1 << 8,
+	.post_div_mask = GENMASK(11, 8),
+	.vco_mask = GENMASK(21, 20),
+	.vco_val = 0x0,
+	.alpha_en_mask = BIT(24),
+};
+
 static struct clk_hw *gcc_ipq8074_hws[] = {
 	&gpll0_out_main_div2.hw,
 	&gpll6_out_main_div2.hw,
@@ -4772,7 +4818,20 @@ static const struct qcom_cc_desc gcc_ipq8074_desc = {
 
 static int gcc_ipq8074_probe(struct platform_device *pdev)
 {
-	return qcom_cc_probe(pdev, &gcc_ipq8074_desc);
+	struct regmap *regmap;
+
+	regmap = qcom_cc_map(pdev, &gcc_ipq8074_desc);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	/* SW Workaround for UBI32 Huayra PLL */
+	regmap_update_bits(regmap, 0x2501c, BIT(26), BIT(26));
+
+	clk_alpha_pll_configure(&ubi32_pll_main, regmap, &ubi32_pll_config);
+	clk_alpha_pll_configure(&nss_crypto_pll_main, regmap,
+				&nss_crypto_pll_config);
+
+	return qcom_cc_really_probe(pdev, &gcc_ipq8074_desc, regmap);
 }
 
 static struct platform_driver gcc_ipq8074_driver = {
diff --git a/drivers/clk/qcom/gcc-msm8939.c b/drivers/clk/qcom/gcc-msm8939.c
index 39ebb443ae3d..de0022e5450d 100644
--- a/drivers/clk/qcom/gcc-msm8939.c
+++ b/drivers/clk/qcom/gcc-msm8939.c
@@ -632,7 +632,7 @@ static struct clk_rcg2 system_noc_bfdcd_clk_src = {
 };
 
 static struct clk_rcg2 bimc_ddr_clk_src = {
-	.cmd_rcgr = 0x32004,
+	.cmd_rcgr = 0x32024,
 	.hid_width = 5,
 	.parent_map = gcc_xo_gpll0_bimc_map,
 	.clkr.hw.init = &(struct clk_init_data){
@@ -644,6 +644,18 @@ static struct clk_rcg2 bimc_ddr_clk_src = {
 	},
 };
 
+static struct clk_rcg2 system_mm_noc_bfdcd_clk_src = {
+	.cmd_rcgr = 0x2600c,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll6a_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "system_mm_noc_bfdcd_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll6a_parent_data,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
 static const struct freq_tbl ftbl_gcc_camss_ahb_clk[] = {
 	F(40000000, P_GPLL0, 10, 1, 2),
 	F(80000000, P_GPLL0, 10, 0, 0),
@@ -1002,7 +1014,7 @@ static struct clk_rcg2 blsp1_uart2_apps_clk_src = {
 };
 
 static const struct freq_tbl ftbl_gcc_camss_cci_clk[] = {
-	F(19200000,	P_XO, 1, 0,	0),
+	F(19200000, P_XO, 1, 0, 0),
 	{ }
 };
 
@@ -2441,7 +2453,7 @@ static struct clk_branch gcc_camss_jpeg_axi_clk = {
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_camss_jpeg_axi_clk",
 			.parent_data = &(const struct clk_parent_data){
-				.hw = &system_noc_bfdcd_clk_src.clkr.hw,
+				.hw = &system_mm_noc_bfdcd_clk_src.clkr.hw,
 			},
 			.num_parents = 1,
 			.flags = CLK_SET_RATE_PARENT,
@@ -2645,7 +2657,7 @@ static struct clk_branch gcc_camss_vfe_axi_clk = {
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_camss_vfe_axi_clk",
 			.parent_data = &(const struct clk_parent_data){
-				.hw = &system_noc_bfdcd_clk_src.clkr.hw,
+				.hw = &system_mm_noc_bfdcd_clk_src.clkr.hw,
 			},
 			.num_parents = 1,
 			.flags = CLK_SET_RATE_PARENT,
@@ -2801,7 +2813,7 @@ static struct clk_branch gcc_mdss_axi_clk = {
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_mdss_axi_clk",
 			.parent_data = &(const struct clk_parent_data){
-				.hw = &system_noc_bfdcd_clk_src.clkr.hw,
+				.hw = &system_mm_noc_bfdcd_clk_src.clkr.hw,
 			},
 			.num_parents = 1,
 			.flags = CLK_SET_RATE_PARENT,
@@ -3193,7 +3205,7 @@ static struct clk_branch gcc_mdp_tbu_clk = {
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_mdp_tbu_clk",
 			.parent_data = &(const struct clk_parent_data){
-				.hw = &system_noc_bfdcd_clk_src.clkr.hw,
+				.hw = &system_mm_noc_bfdcd_clk_src.clkr.hw,
 			},
 			.num_parents = 1,
 			.flags = CLK_SET_RATE_PARENT,
@@ -3211,7 +3223,7 @@ static struct clk_branch gcc_venus_tbu_clk = {
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_venus_tbu_clk",
 			.parent_data = &(const struct clk_parent_data){
-				.hw = &system_noc_bfdcd_clk_src.clkr.hw,
+				.hw = &system_mm_noc_bfdcd_clk_src.clkr.hw,
 			},
 			.num_parents = 1,
 			.flags = CLK_SET_RATE_PARENT,
@@ -3229,7 +3241,7 @@ static struct clk_branch gcc_vfe_tbu_clk = {
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_vfe_tbu_clk",
 			.parent_data = &(const struct clk_parent_data){
-				.hw = &system_noc_bfdcd_clk_src.clkr.hw,
+				.hw = &system_mm_noc_bfdcd_clk_src.clkr.hw,
 			},
 			.num_parents = 1,
 			.flags = CLK_SET_RATE_PARENT,
@@ -3247,7 +3259,7 @@ static struct clk_branch gcc_jpeg_tbu_clk = {
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_jpeg_tbu_clk",
 			.parent_data = &(const struct clk_parent_data){
-				.hw = &system_noc_bfdcd_clk_src.clkr.hw,
+				.hw = &system_mm_noc_bfdcd_clk_src.clkr.hw,
 			},
 			.num_parents = 1,
 			.flags = CLK_SET_RATE_PARENT,
@@ -3484,7 +3496,7 @@ static struct clk_branch gcc_venus0_axi_clk = {
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_venus0_axi_clk",
 			.parent_data = &(const struct clk_parent_data){
-				.hw = &system_noc_bfdcd_clk_src.clkr.hw,
+				.hw = &system_mm_noc_bfdcd_clk_src.clkr.hw,
 			},
 			.num_parents = 1,
 			.flags = CLK_SET_RATE_PARENT,
@@ -3623,6 +3635,7 @@ static struct clk_regmap *gcc_msm8939_clocks[] = {
 	[GPLL2_VOTE] = &gpll2_vote,
 	[PCNOC_BFDCD_CLK_SRC] = &pcnoc_bfdcd_clk_src.clkr,
 	[SYSTEM_NOC_BFDCD_CLK_SRC] = &system_noc_bfdcd_clk_src.clkr,
+	[SYSTEM_MM_NOC_BFDCD_CLK_SRC] = &system_mm_noc_bfdcd_clk_src.clkr,
 	[CAMSS_AHB_CLK_SRC] = &camss_ahb_clk_src.clkr,
 	[APSS_AHB_CLK_SRC] = &apss_ahb_clk_src.clkr,
 	[CSI0_CLK_SRC] = &csi0_clk_src.clkr,
diff --git a/drivers/clk/renesas/r9a06g032-clocks.c b/drivers/clk/renesas/r9a06g032-clocks.c
index c99942f0e4d4..abc0891fd96d 100644
--- a/drivers/clk/renesas/r9a06g032-clocks.c
+++ b/drivers/clk/renesas/r9a06g032-clocks.c
@@ -286,8 +286,8 @@ static const struct r9a06g032_clkdesc r9a06g032_clocks[] = {
 		.name = "uart_group_012",
 		.type = K_BITSEL,
 		.source = 1 + R9A06G032_DIV_UART,
-		/* R9A06G032_SYSCTRL_REG_PWRCTRL_PG1_PR2 */
-		.dual.sel = ((0xec / 4) << 5) | 24,
+		/* R9A06G032_SYSCTRL_REG_PWRCTRL_PG0_0 */
+		.dual.sel = ((0x34 / 4) << 5) | 30,
 		.dual.group = 0,
 	},
 	{
@@ -295,8 +295,8 @@ static const struct r9a06g032_clkdesc r9a06g032_clocks[] = {
 		.name = "uart_group_34567",
 		.type = K_BITSEL,
 		.source = 1 + R9A06G032_DIV_P2_PG,
-		/* R9A06G032_SYSCTRL_REG_PWRCTRL_PG0_0 */
-		.dual.sel = ((0x34 / 4) << 5) | 30,
+		/* R9A06G032_SYSCTRL_REG_PWRCTRL_PG1_PR2 */
+		.dual.sel = ((0xec / 4) << 5) | 24,
 		.dual.group = 1,
 	},
 	D_UGATE(CLK_UART0, "clk_uart0", UART_GROUP_012, 0, 0, 0x1b2, 0x1b3, 0x1b4, 0x1b5),
diff --git a/drivers/clk/renesas/r9a07g044-cpg.c b/drivers/clk/renesas/r9a07g044-cpg.c
index 1490446985e2..61609eddf7d0 100644
--- a/drivers/clk/renesas/r9a07g044-cpg.c
+++ b/drivers/clk/renesas/r9a07g044-cpg.c
@@ -61,8 +61,8 @@ static const struct cpg_core_clk r9a07g044_core_clks[] __initconst = {
 	DEF_FIXED(".osc", R9A07G044_OSCCLK, CLK_EXTAL, 1, 1),
 	DEF_FIXED(".osc_div1000", CLK_OSC_DIV1000, CLK_EXTAL, 1, 1000),
 	DEF_SAMPLL(".pll1", CLK_PLL1, CLK_EXTAL, PLL146_CONF(0)),
-	DEF_FIXED(".pll2", CLK_PLL2, CLK_EXTAL, 133, 2),
-	DEF_FIXED(".pll3", CLK_PLL3, CLK_EXTAL, 133, 2),
+	DEF_FIXED(".pll2", CLK_PLL2, CLK_EXTAL, 200, 3),
+	DEF_FIXED(".pll3", CLK_PLL3, CLK_EXTAL, 200, 3),
 
 	DEF_FIXED(".pll2_div2", CLK_PLL2_DIV2, CLK_PLL2, 1, 2),
 	DEF_FIXED(".pll2_div16", CLK_PLL2_DIV16, CLK_PLL2, 1, 16),
diff --git a/drivers/clk/ti/clk-44xx.c b/drivers/clk/ti/clk-44xx.c
index d078e5d73ed9..868bc7af21b0 100644
--- a/drivers/clk/ti/clk-44xx.c
+++ b/drivers/clk/ti/clk-44xx.c
@@ -56,7 +56,7 @@ static const struct omap_clkctrl_bit_data omap4_aess_bit_data[] __initconst = {
 };
 
 static const char * const omap4_func_dmic_abe_gfclk_parents[] __initconst = {
-	"abe_cm:clk:0018:26",
+	"abe-clkctrl:0018:26",
 	"pad_clks_ck",
 	"slimbus_clk",
 	NULL,
@@ -76,7 +76,7 @@ static const struct omap_clkctrl_bit_data omap4_dmic_bit_data[] __initconst = {
 };
 
 static const char * const omap4_func_mcasp_abe_gfclk_parents[] __initconst = {
-	"abe_cm:clk:0020:26",
+	"abe-clkctrl:0020:26",
 	"pad_clks_ck",
 	"slimbus_clk",
 	NULL,
@@ -89,7 +89,7 @@ static const struct omap_clkctrl_bit_data omap4_mcasp_bit_data[] __initconst = {
 };
 
 static const char * const omap4_func_mcbsp1_gfclk_parents[] __initconst = {
-	"abe_cm:clk:0028:26",
+	"abe-clkctrl:0028:26",
 	"pad_clks_ck",
 	"slimbus_clk",
 	NULL,
@@ -102,7 +102,7 @@ static const struct omap_clkctrl_bit_data omap4_mcbsp1_bit_data[] __initconst =
 };
 
 static const char * const omap4_func_mcbsp2_gfclk_parents[] __initconst = {
-	"abe_cm:clk:0030:26",
+	"abe-clkctrl:0030:26",
 	"pad_clks_ck",
 	"slimbus_clk",
 	NULL,
@@ -115,7 +115,7 @@ static const struct omap_clkctrl_bit_data omap4_mcbsp2_bit_data[] __initconst =
 };
 
 static const char * const omap4_func_mcbsp3_gfclk_parents[] __initconst = {
-	"abe_cm:clk:0038:26",
+	"abe-clkctrl:0038:26",
 	"pad_clks_ck",
 	"slimbus_clk",
 	NULL,
@@ -183,18 +183,18 @@ static const struct omap_clkctrl_bit_data omap4_timer8_bit_data[] __initconst =
 
 static const struct omap_clkctrl_reg_data omap4_abe_clkctrl_regs[] __initconst = {
 	{ OMAP4_L4_ABE_CLKCTRL, NULL, 0, "ocp_abe_iclk" },
-	{ OMAP4_AESS_CLKCTRL, omap4_aess_bit_data, CLKF_SW_SUP, "abe_cm:clk:0008:24" },
+	{ OMAP4_AESS_CLKCTRL, omap4_aess_bit_data, CLKF_SW_SUP, "abe-clkctrl:0008:24" },
 	{ OMAP4_MCPDM_CLKCTRL, NULL, CLKF_SW_SUP, "pad_clks_ck" },
-	{ OMAP4_DMIC_CLKCTRL, omap4_dmic_bit_data, CLKF_SW_SUP, "abe_cm:clk:0018:24" },
-	{ OMAP4_MCASP_CLKCTRL, omap4_mcasp_bit_data, CLKF_SW_SUP, "abe_cm:clk:0020:24" },
-	{ OMAP4_MCBSP1_CLKCTRL, omap4_mcbsp1_bit_data, CLKF_SW_SUP, "abe_cm:clk:0028:24" },
-	{ OMAP4_MCBSP2_CLKCTRL, omap4_mcbsp2_bit_data, CLKF_SW_SUP, "abe_cm:clk:0030:24" },
-	{ OMAP4_MCBSP3_CLKCTRL, omap4_mcbsp3_bit_data, CLKF_SW_SUP, "abe_cm:clk:0038:24" },
-	{ OMAP4_SLIMBUS1_CLKCTRL, omap4_slimbus1_bit_data, CLKF_SW_SUP, "abe_cm:clk:0040:8" },
-	{ OMAP4_TIMER5_CLKCTRL, omap4_timer5_bit_data, CLKF_SW_SUP, "abe_cm:clk:0048:24" },
-	{ OMAP4_TIMER6_CLKCTRL, omap4_timer6_bit_data, CLKF_SW_SUP, "abe_cm:clk:0050:24" },
-	{ OMAP4_TIMER7_CLKCTRL, omap4_timer7_bit_data, CLKF_SW_SUP, "abe_cm:clk:0058:24" },
-	{ OMAP4_TIMER8_CLKCTRL, omap4_timer8_bit_data, CLKF_SW_SUP, "abe_cm:clk:0060:24" },
+	{ OMAP4_DMIC_CLKCTRL, omap4_dmic_bit_data, CLKF_SW_SUP, "abe-clkctrl:0018:24" },
+	{ OMAP4_MCASP_CLKCTRL, omap4_mcasp_bit_data, CLKF_SW_SUP, "abe-clkctrl:0020:24" },
+	{ OMAP4_MCBSP1_CLKCTRL, omap4_mcbsp1_bit_data, CLKF_SW_SUP, "abe-clkctrl:0028:24" },
+	{ OMAP4_MCBSP2_CLKCTRL, omap4_mcbsp2_bit_data, CLKF_SW_SUP, "abe-clkctrl:0030:24" },
+	{ OMAP4_MCBSP3_CLKCTRL, omap4_mcbsp3_bit_data, CLKF_SW_SUP, "abe-clkctrl:0038:24" },
+	{ OMAP4_SLIMBUS1_CLKCTRL, omap4_slimbus1_bit_data, CLKF_SW_SUP, "abe-clkctrl:0040:8" },
+	{ OMAP4_TIMER5_CLKCTRL, omap4_timer5_bit_data, CLKF_SW_SUP, "abe-clkctrl:0048:24" },
+	{ OMAP4_TIMER6_CLKCTRL, omap4_timer6_bit_data, CLKF_SW_SUP, "abe-clkctrl:0050:24" },
+	{ OMAP4_TIMER7_CLKCTRL, omap4_timer7_bit_data, CLKF_SW_SUP, "abe-clkctrl:0058:24" },
+	{ OMAP4_TIMER8_CLKCTRL, omap4_timer8_bit_data, CLKF_SW_SUP, "abe-clkctrl:0060:24" },
 	{ OMAP4_WD_TIMER3_CLKCTRL, NULL, CLKF_SW_SUP, "sys_32k_ck" },
 	{ 0 },
 };
@@ -287,7 +287,7 @@ static const struct omap_clkctrl_bit_data omap4_fdif_bit_data[] __initconst = {
 
 static const struct omap_clkctrl_reg_data omap4_iss_clkctrl_regs[] __initconst = {
 	{ OMAP4_ISS_CLKCTRL, omap4_iss_bit_data, CLKF_SW_SUP, "ducati_clk_mux_ck" },
-	{ OMAP4_FDIF_CLKCTRL, omap4_fdif_bit_data, CLKF_SW_SUP, "iss_cm:clk:0008:24" },
+	{ OMAP4_FDIF_CLKCTRL, omap4_fdif_bit_data, CLKF_SW_SUP, "iss-clkctrl:0008:24" },
 	{ 0 },
 };
 
@@ -320,7 +320,7 @@ static const struct omap_clkctrl_bit_data omap4_dss_core_bit_data[] __initconst
 };
 
 static const struct omap_clkctrl_reg_data omap4_l3_dss_clkctrl_regs[] __initconst = {
-	{ OMAP4_DSS_CORE_CLKCTRL, omap4_dss_core_bit_data, CLKF_SW_SUP, "l3_dss_cm:clk:0000:8" },
+	{ OMAP4_DSS_CORE_CLKCTRL, omap4_dss_core_bit_data, CLKF_SW_SUP, "l3-dss-clkctrl:0000:8" },
 	{ 0 },
 };
 
@@ -336,7 +336,7 @@ static const struct omap_clkctrl_bit_data omap4_gpu_bit_data[] __initconst = {
 };
 
 static const struct omap_clkctrl_reg_data omap4_l3_gfx_clkctrl_regs[] __initconst = {
-	{ OMAP4_GPU_CLKCTRL, omap4_gpu_bit_data, CLKF_SW_SUP, "l3_gfx_cm:clk:0000:24" },
+	{ OMAP4_GPU_CLKCTRL, omap4_gpu_bit_data, CLKF_SW_SUP, "l3-gfx-clkctrl:0000:24" },
 	{ 0 },
 };
 
@@ -372,12 +372,12 @@ static const struct omap_clkctrl_bit_data omap4_hsi_bit_data[] __initconst = {
 };
 
 static const char * const omap4_usb_host_hs_utmi_p1_clk_parents[] __initconst = {
-	"l3_init_cm:clk:0038:24",
+	"l3-init-clkctrl:0038:24",
 	NULL,
 };
 
 static const char * const omap4_usb_host_hs_utmi_p2_clk_parents[] __initconst = {
-	"l3_init_cm:clk:0038:25",
+	"l3-init-clkctrl:0038:25",
 	NULL,
 };
 
@@ -418,7 +418,7 @@ static const struct omap_clkctrl_bit_data omap4_usb_host_hs_bit_data[] __initcon
 };
 
 static const char * const omap4_usb_otg_hs_xclk_parents[] __initconst = {
-	"l3_init_cm:clk:0040:24",
+	"l3-init-clkctrl:0040:24",
 	NULL,
 };
 
@@ -452,14 +452,14 @@ static const struct omap_clkctrl_bit_data omap4_ocp2scp_usb_phy_bit_data[] __ini
 };
 
 static const struct omap_clkctrl_reg_data omap4_l3_init_clkctrl_regs[] __initconst = {
-	{ OMAP4_MMC1_CLKCTRL, omap4_mmc1_bit_data, CLKF_SW_SUP, "l3_init_cm:clk:0008:24" },
-	{ OMAP4_MMC2_CLKCTRL, omap4_mmc2_bit_data, CLKF_SW_SUP, "l3_init_cm:clk:0010:24" },
-	{ OMAP4_HSI_CLKCTRL, omap4_hsi_bit_data, CLKF_HW_SUP, "l3_init_cm:clk:0018:24" },
+	{ OMAP4_MMC1_CLKCTRL, omap4_mmc1_bit_data, CLKF_SW_SUP, "l3-init-clkctrl:0008:24" },
+	{ OMAP4_MMC2_CLKCTRL, omap4_mmc2_bit_data, CLKF_SW_SUP, "l3-init-clkctrl:0010:24" },
+	{ OMAP4_HSI_CLKCTRL, omap4_hsi_bit_data, CLKF_HW_SUP, "l3-init-clkctrl:0018:24" },
 	{ OMAP4_USB_HOST_HS_CLKCTRL, omap4_usb_host_hs_bit_data, CLKF_SW_SUP, "init_60m_fclk" },
 	{ OMAP4_USB_OTG_HS_CLKCTRL, omap4_usb_otg_hs_bit_data, CLKF_HW_SUP, "l3_div_ck" },
 	{ OMAP4_USB_TLL_HS_CLKCTRL, omap4_usb_tll_hs_bit_data, CLKF_HW_SUP, "l4_div_ck" },
 	{ OMAP4_USB_HOST_FS_CLKCTRL, NULL, CLKF_SW_SUP, "func_48mc_fclk" },
-	{ OMAP4_OCP2SCP_USB_PHY_CLKCTRL, omap4_ocp2scp_usb_phy_bit_data, CLKF_HW_SUP, "l3_init_cm:clk:00c0:8" },
+	{ OMAP4_OCP2SCP_USB_PHY_CLKCTRL, omap4_ocp2scp_usb_phy_bit_data, CLKF_HW_SUP, "l3-init-clkctrl:00c0:8" },
 	{ 0 },
 };
 
@@ -530,7 +530,7 @@ static const struct omap_clkctrl_bit_data omap4_gpio6_bit_data[] __initconst = {
 };
 
 static const char * const omap4_per_mcbsp4_gfclk_parents[] __initconst = {
-	"l4_per_cm:clk:00c0:26",
+	"l4-per-clkctrl:00c0:26",
 	"pad_clks_ck",
 	NULL,
 };
@@ -570,12 +570,12 @@ static const struct omap_clkctrl_bit_data omap4_slimbus2_bit_data[] __initconst
 };
 
 static const struct omap_clkctrl_reg_data omap4_l4_per_clkctrl_regs[] __initconst = {
-	{ OMAP4_TIMER10_CLKCTRL, omap4_timer10_bit_data, CLKF_SW_SUP, "l4_per_cm:clk:0008:24" },
-	{ OMAP4_TIMER11_CLKCTRL, omap4_timer11_bit_data, CLKF_SW_SUP, "l4_per_cm:clk:0010:24" },
-	{ OMAP4_TIMER2_CLKCTRL, omap4_timer2_bit_data, CLKF_SW_SUP, "l4_per_cm:clk:0018:24" },
-	{ OMAP4_TIMER3_CLKCTRL, omap4_timer3_bit_data, CLKF_SW_SUP, "l4_per_cm:clk:0020:24" },
-	{ OMAP4_TIMER4_CLKCTRL, omap4_timer4_bit_data, CLKF_SW_SUP, "l4_per_cm:clk:0028:24" },
-	{ OMAP4_TIMER9_CLKCTRL, omap4_timer9_bit_data, CLKF_SW_SUP, "l4_per_cm:clk:0030:24" },
+	{ OMAP4_TIMER10_CLKCTRL, omap4_timer10_bit_data, CLKF_SW_SUP, "l4-per-clkctrl:0008:24" },
+	{ OMAP4_TIMER11_CLKCTRL, omap4_timer11_bit_data, CLKF_SW_SUP, "l4-per-clkctrl:0010:24" },
+	{ OMAP4_TIMER2_CLKCTRL, omap4_timer2_bit_data, CLKF_SW_SUP, "l4-per-clkctrl:0018:24" },
+	{ OMAP4_TIMER3_CLKCTRL, omap4_timer3_bit_data, CLKF_SW_SUP, "l4-per-clkctrl:0020:24" },
+	{ OMAP4_TIMER4_CLKCTRL, omap4_timer4_bit_data, CLKF_SW_SUP, "l4-per-clkctrl:0028:24" },
+	{ OMAP4_TIMER9_CLKCTRL, omap4_timer9_bit_data, CLKF_SW_SUP, "l4-per-clkctrl:0030:24" },
 	{ OMAP4_ELM_CLKCTRL, NULL, 0, "l4_div_ck" },
 	{ OMAP4_GPIO2_CLKCTRL, omap4_gpio2_bit_data, CLKF_HW_SUP, "l4_div_ck" },
 	{ OMAP4_GPIO3_CLKCTRL, omap4_gpio3_bit_data, CLKF_HW_SUP, "l4_div_ck" },
@@ -588,14 +588,14 @@ static const struct omap_clkctrl_reg_data omap4_l4_per_clkctrl_regs[] __initcons
 	{ OMAP4_I2C3_CLKCTRL, NULL, CLKF_SW_SUP, "func_96m_fclk" },
 	{ OMAP4_I2C4_CLKCTRL, NULL, CLKF_SW_SUP, "func_96m_fclk" },
 	{ OMAP4_L4_PER_CLKCTRL, NULL, 0, "l4_div_ck" },
-	{ OMAP4_MCBSP4_CLKCTRL, omap4_mcbsp4_bit_data, CLKF_SW_SUP, "l4_per_cm:clk:00c0:24" },
+	{ OMAP4_MCBSP4_CLKCTRL, omap4_mcbsp4_bit_data, CLKF_SW_SUP, "l4-per-clkctrl:00c0:24" },
 	{ OMAP4_MCSPI1_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
 	{ OMAP4_MCSPI2_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
 	{ OMAP4_MCSPI3_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
 	{ OMAP4_MCSPI4_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
 	{ OMAP4_MMC3_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
 	{ OMAP4_MMC4_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
-	{ OMAP4_SLIMBUS2_CLKCTRL, omap4_slimbus2_bit_data, CLKF_SW_SUP, "l4_per_cm:clk:0118:8" },
+	{ OMAP4_SLIMBUS2_CLKCTRL, omap4_slimbus2_bit_data, CLKF_SW_SUP, "l4-per-clkctrl:0118:8" },
 	{ OMAP4_UART1_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
 	{ OMAP4_UART2_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
 	{ OMAP4_UART3_CLKCTRL, NULL, CLKF_SW_SUP, "func_48m_fclk" },
@@ -630,7 +630,7 @@ static const struct omap_clkctrl_reg_data omap4_l4_wkup_clkctrl_regs[] __initcon
 	{ OMAP4_L4_WKUP_CLKCTRL, NULL, 0, "l4_wkup_clk_mux_ck" },
 	{ OMAP4_WD_TIMER2_CLKCTRL, NULL, CLKF_SW_SUP, "sys_32k_ck" },
 	{ OMAP4_GPIO1_CLKCTRL, omap4_gpio1_bit_data, CLKF_HW_SUP, "l4_wkup_clk_mux_ck" },
-	{ OMAP4_TIMER1_CLKCTRL, omap4_timer1_bit_data, CLKF_SW_SUP, "l4_wkup_cm:clk:0020:24" },
+	{ OMAP4_TIMER1_CLKCTRL, omap4_timer1_bit_data, CLKF_SW_SUP, "l4-wkup-clkctrl:0020:24" },
 	{ OMAP4_COUNTER_32K_CLKCTRL, NULL, 0, "sys_32k_ck" },
 	{ OMAP4_KBD_CLKCTRL, NULL, CLKF_SW_SUP, "sys_32k_ck" },
 	{ 0 },
@@ -644,7 +644,7 @@ static const char * const omap4_pmd_stm_clock_mux_ck_parents[] __initconst = {
 };
 
 static const char * const omap4_trace_clk_div_div_ck_parents[] __initconst = {
-	"emu_sys_cm:clk:0000:22",
+	"emu-sys-clkctrl:0000:22",
 	NULL,
 };
 
@@ -662,7 +662,7 @@ static const struct omap_clkctrl_div_data omap4_trace_clk_div_div_ck_data __init
 };
 
 static const char * const omap4_stm_clk_div_ck_parents[] __initconst = {
-	"emu_sys_cm:clk:0000:20",
+	"emu-sys-clkctrl:0000:20",
 	NULL,
 };
 
@@ -716,73 +716,73 @@ static struct ti_dt_clk omap44xx_clks[] = {
 	 * hwmod support. Once hwmod is removed, these can be removed
 	 * also.
 	 */
-	DT_CLK(NULL, "aess_fclk", "abe_cm:0008:24"),
-	DT_CLK(NULL, "cm2_dm10_mux", "l4_per_cm:0008:24"),
-	DT_CLK(NULL, "cm2_dm11_mux", "l4_per_cm:0010:24"),
-	DT_CLK(NULL, "cm2_dm2_mux", "l4_per_cm:0018:24"),
-	DT_CLK(NULL, "cm2_dm3_mux", "l4_per_cm:0020:24"),
-	DT_CLK(NULL, "cm2_dm4_mux", "l4_per_cm:0028:24"),
-	DT_CLK(NULL, "cm2_dm9_mux", "l4_per_cm:0030:24"),
-	DT_CLK(NULL, "dmic_sync_mux_ck", "abe_cm:0018:26"),
-	DT_CLK(NULL, "dmt1_clk_mux", "l4_wkup_cm:0020:24"),
-	DT_CLK(NULL, "dss_48mhz_clk", "l3_dss_cm:0000:9"),
-	DT_CLK(NULL, "dss_dss_clk", "l3_dss_cm:0000:8"),
-	DT_CLK(NULL, "dss_sys_clk", "l3_dss_cm:0000:10"),
-	DT_CLK(NULL, "dss_tv_clk", "l3_dss_cm:0000:11"),
-	DT_CLK(NULL, "fdif_fck", "iss_cm:0008:24"),
-	DT_CLK(NULL, "func_dmic_abe_gfclk", "abe_cm:0018:24"),
-	DT_CLK(NULL, "func_mcasp_abe_gfclk", "abe_cm:0020:24"),
-	DT_CLK(NULL, "func_mcbsp1_gfclk", "abe_cm:0028:24"),
-	DT_CLK(NULL, "func_mcbsp2_gfclk", "abe_cm:0030:24"),
-	DT_CLK(NULL, "func_mcbsp3_gfclk", "abe_cm:0038:24"),
-	DT_CLK(NULL, "gpio1_dbclk", "l4_wkup_cm:0018:8"),
-	DT_CLK(NULL, "gpio2_dbclk", "l4_per_cm:0040:8"),
-	DT_CLK(NULL, "gpio3_dbclk", "l4_per_cm:0048:8"),
-	DT_CLK(NULL, "gpio4_dbclk", "l4_per_cm:0050:8"),
-	DT_CLK(NULL, "gpio5_dbclk", "l4_per_cm:0058:8"),
-	DT_CLK(NULL, "gpio6_dbclk", "l4_per_cm:0060:8"),
-	DT_CLK(NULL, "hsi_fck", "l3_init_cm:0018:24"),
-	DT_CLK(NULL, "hsmmc1_fclk", "l3_init_cm:0008:24"),
-	DT_CLK(NULL, "hsmmc2_fclk", "l3_init_cm:0010:24"),
-	DT_CLK(NULL, "iss_ctrlclk", "iss_cm:0000:8"),
-	DT_CLK(NULL, "mcasp_sync_mux_ck", "abe_cm:0020:26"),
-	DT_CLK(NULL, "mcbsp1_sync_mux_ck", "abe_cm:0028:26"),
-	DT_CLK(NULL, "mcbsp2_sync_mux_ck", "abe_cm:0030:26"),
-	DT_CLK(NULL, "mcbsp3_sync_mux_ck", "abe_cm:0038:26"),
-	DT_CLK(NULL, "mcbsp4_sync_mux_ck", "l4_per_cm:00c0:26"),
-	DT_CLK(NULL, "ocp2scp_usb_phy_phy_48m", "l3_init_cm:00c0:8"),
-	DT_CLK(NULL, "otg_60m_gfclk", "l3_init_cm:0040:24"),
-	DT_CLK(NULL, "per_mcbsp4_gfclk", "l4_per_cm:00c0:24"),
-	DT_CLK(NULL, "pmd_stm_clock_mux_ck", "emu_sys_cm:0000:20"),
-	DT_CLK(NULL, "pmd_trace_clk_mux_ck", "emu_sys_cm:0000:22"),
-	DT_CLK(NULL, "sgx_clk_mux", "l3_gfx_cm:0000:24"),
-	DT_CLK(NULL, "slimbus1_fclk_0", "abe_cm:0040:8"),
-	DT_CLK(NULL, "slimbus1_fclk_1", "abe_cm:0040:9"),
-	DT_CLK(NULL, "slimbus1_fclk_2", "abe_cm:0040:10"),
-	DT_CLK(NULL, "slimbus1_slimbus_clk", "abe_cm:0040:11"),
-	DT_CLK(NULL, "slimbus2_fclk_0", "l4_per_cm:0118:8"),
-	DT_CLK(NULL, "slimbus2_fclk_1", "l4_per_cm:0118:9"),
-	DT_CLK(NULL, "slimbus2_slimbus_clk", "l4_per_cm:0118:10"),
-	DT_CLK(NULL, "stm_clk_div_ck", "emu_sys_cm:0000:27"),
-	DT_CLK(NULL, "timer5_sync_mux", "abe_cm:0048:24"),
-	DT_CLK(NULL, "timer6_sync_mux", "abe_cm:0050:24"),
-	DT_CLK(NULL, "timer7_sync_mux", "abe_cm:0058:24"),
-	DT_CLK(NULL, "timer8_sync_mux", "abe_cm:0060:24"),
-	DT_CLK(NULL, "trace_clk_div_div_ck", "emu_sys_cm:0000:24"),
-	DT_CLK(NULL, "usb_host_hs_func48mclk", "l3_init_cm:0038:15"),
-	DT_CLK(NULL, "usb_host_hs_hsic480m_p1_clk", "l3_init_cm:0038:13"),
-	DT_CLK(NULL, "usb_host_hs_hsic480m_p2_clk", "l3_init_cm:0038:14"),
-	DT_CLK(NULL, "usb_host_hs_hsic60m_p1_clk", "l3_init_cm:0038:11"),
-	DT_CLK(NULL, "usb_host_hs_hsic60m_p2_clk", "l3_init_cm:0038:12"),
-	DT_CLK(NULL, "usb_host_hs_utmi_p1_clk", "l3_init_cm:0038:8"),
-	DT_CLK(NULL, "usb_host_hs_utmi_p2_clk", "l3_init_cm:0038:9"),
-	DT_CLK(NULL, "usb_host_hs_utmi_p3_clk", "l3_init_cm:0038:10"),
-	DT_CLK(NULL, "usb_otg_hs_xclk", "l3_init_cm:0040:8"),
-	DT_CLK(NULL, "usb_tll_hs_usb_ch0_clk", "l3_init_cm:0048:8"),
-	DT_CLK(NULL, "usb_tll_hs_usb_ch1_clk", "l3_init_cm:0048:9"),
-	DT_CLK(NULL, "usb_tll_hs_usb_ch2_clk", "l3_init_cm:0048:10"),
-	DT_CLK(NULL, "utmi_p1_gfclk", "l3_init_cm:0038:24"),
-	DT_CLK(NULL, "utmi_p2_gfclk", "l3_init_cm:0038:25"),
+	DT_CLK(NULL, "aess_fclk", "abe-clkctrl:0008:24"),
+	DT_CLK(NULL, "cm2_dm10_mux", "l4-per-clkctrl:0008:24"),
+	DT_CLK(NULL, "cm2_dm11_mux", "l4-per-clkctrl:0010:24"),
+	DT_CLK(NULL, "cm2_dm2_mux", "l4-per-clkctrl:0018:24"),
+	DT_CLK(NULL, "cm2_dm3_mux", "l4-per-clkctrl:0020:24"),
+	DT_CLK(NULL, "cm2_dm4_mux", "l4-per-clkctrl:0028:24"),
+	DT_CLK(NULL, "cm2_dm9_mux", "l4-per-clkctrl:0030:24"),
+	DT_CLK(NULL, "dmic_sync_mux_ck", "abe-clkctrl:0018:26"),
+	DT_CLK(NULL, "dmt1_clk_mux", "l4-wkup-clkctrl:0020:24"),
+	DT_CLK(NULL, "dss_48mhz_clk", "l3-dss-clkctrl:0000:9"),
+	DT_CLK(NULL, "dss_dss_clk", "l3-dss-clkctrl:0000:8"),
+	DT_CLK(NULL, "dss_sys_clk", "l3-dss-clkctrl:0000:10"),
+	DT_CLK(NULL, "dss_tv_clk", "l3-dss-clkctrl:0000:11"),
+	DT_CLK(NULL, "fdif_fck", "iss-clkctrl:0008:24"),
+	DT_CLK(NULL, "func_dmic_abe_gfclk", "abe-clkctrl:0018:24"),
+	DT_CLK(NULL, "func_mcasp_abe_gfclk", "abe-clkctrl:0020:24"),
+	DT_CLK(NULL, "func_mcbsp1_gfclk", "abe-clkctrl:0028:24"),
+	DT_CLK(NULL, "func_mcbsp2_gfclk", "abe-clkctrl:0030:24"),
+	DT_CLK(NULL, "func_mcbsp3_gfclk", "abe-clkctrl:0038:24"),
+	DT_CLK(NULL, "gpio1_dbclk", "l4-wkup-clkctrl:0018:8"),
+	DT_CLK(NULL, "gpio2_dbclk", "l4-per-clkctrl:0040:8"),
+	DT_CLK(NULL, "gpio3_dbclk", "l4-per-clkctrl:0048:8"),
+	DT_CLK(NULL, "gpio4_dbclk", "l4-per-clkctrl:0050:8"),
+	DT_CLK(NULL, "gpio5_dbclk", "l4-per-clkctrl:0058:8"),
+	DT_CLK(NULL, "gpio6_dbclk", "l4-per-clkctrl:0060:8"),
+	DT_CLK(NULL, "hsi_fck", "l3-init-clkctrl:0018:24"),
+	DT_CLK(NULL, "hsmmc1_fclk", "l3-init-clkctrl:0008:24"),
+	DT_CLK(NULL, "hsmmc2_fclk", "l3-init-clkctrl:0010:24"),
+	DT_CLK(NULL, "iss_ctrlclk", "iss-clkctrl:0000:8"),
+	DT_CLK(NULL, "mcasp_sync_mux_ck", "abe-clkctrl:0020:26"),
+	DT_CLK(NULL, "mcbsp1_sync_mux_ck", "abe-clkctrl:0028:26"),
+	DT_CLK(NULL, "mcbsp2_sync_mux_ck", "abe-clkctrl:0030:26"),
+	DT_CLK(NULL, "mcbsp3_sync_mux_ck", "abe-clkctrl:0038:26"),
+	DT_CLK(NULL, "mcbsp4_sync_mux_ck", "l4-per-clkctrl:00c0:26"),
+	DT_CLK(NULL, "ocp2scp_usb_phy_phy_48m", "l3-init-clkctrl:00c0:8"),
+	DT_CLK(NULL, "otg_60m_gfclk", "l3-init-clkctrl:0040:24"),
+	DT_CLK(NULL, "per_mcbsp4_gfclk", "l4-per-clkctrl:00c0:24"),
+	DT_CLK(NULL, "pmd_stm_clock_mux_ck", "emu-sys-clkctrl:0000:20"),
+	DT_CLK(NULL, "pmd_trace_clk_mux_ck", "emu-sys-clkctrl:0000:22"),
+	DT_CLK(NULL, "sgx_clk_mux", "l3-gfx-clkctrl:0000:24"),
+	DT_CLK(NULL, "slimbus1_fclk_0", "abe-clkctrl:0040:8"),
+	DT_CLK(NULL, "slimbus1_fclk_1", "abe-clkctrl:0040:9"),
+	DT_CLK(NULL, "slimbus1_fclk_2", "abe-clkctrl:0040:10"),
+	DT_CLK(NULL, "slimbus1_slimbus_clk", "abe-clkctrl:0040:11"),
+	DT_CLK(NULL, "slimbus2_fclk_0", "l4-per-clkctrl:0118:8"),
+	DT_CLK(NULL, "slimbus2_fclk_1", "l4-per-clkctrl:0118:9"),
+	DT_CLK(NULL, "slimbus2_slimbus_clk", "l4-per-clkctrl:0118:10"),
+	DT_CLK(NULL, "stm_clk_div_ck", "emu-sys-clkctrl:0000:27"),
+	DT_CLK(NULL, "timer5_sync_mux", "abe-clkctrl:0048:24"),
+	DT_CLK(NULL, "timer6_sync_mux", "abe-clkctrl:0050:24"),
+	DT_CLK(NULL, "timer7_sync_mux", "abe-clkctrl:0058:24"),
+	DT_CLK(NULL, "timer8_sync_mux", "abe-clkctrl:0060:24"),
+	DT_CLK(NULL, "trace_clk_div_div_ck", "emu-sys-clkctrl:0000:24"),
+	DT_CLK(NULL, "usb_host_hs_func48mclk", "l3-init-clkctrl:0038:15"),
+	DT_CLK(NULL, "usb_host_hs_hsic480m_p1_clk", "l3-init-clkctrl:0038:13"),
+	DT_CLK(NULL, "usb_host_hs_hsic480m_p2_clk", "l3-init-clkctrl:0038:14"),
+	DT_CLK(NULL, "usb_host_hs_hsic60m_p1_clk", "l3-init-clkctrl:0038:11"),
+	DT_CLK(NULL, "usb_host_hs_hsic60m_p2_clk", "l3-init-clkctrl:0038:12"),
+	DT_CLK(NULL, "usb_host_hs_utmi_p1_clk", "l3-init-clkctrl:0038:8"),
+	DT_CLK(NULL, "usb_host_hs_utmi_p2_clk", "l3-init-clkctrl:0038:9"),
+	DT_CLK(NULL, "usb_host_hs_utmi_p3_clk", "l3_init-clkctrl:0038:10"),
+	DT_CLK(NULL, "usb_otg_hs_xclk", "l3-init-clkctrl:0040:8"),
+	DT_CLK(NULL, "usb_tll_hs_usb_ch0_clk", "l3-init-clkctrl:0048:8"),
+	DT_CLK(NULL, "usb_tll_hs_usb_ch1_clk", "l3-init-clkctrl:0048:9"),
+	DT_CLK(NULL, "usb_tll_hs_usb_ch2_clk", "l3-init-clkctrl:0048:10"),
+	DT_CLK(NULL, "utmi_p1_gfclk", "l3-init-clkctrl:0038:24"),
+	DT_CLK(NULL, "utmi_p2_gfclk", "l3-init-clkctrl:0038:25"),
 	{ .node_name = NULL },
 };
 
diff --git a/drivers/clk/ti/clk-54xx.c b/drivers/clk/ti/clk-54xx.c
index 90e0a9ea6351..b4aff76eb373 100644
--- a/drivers/clk/ti/clk-54xx.c
+++ b/drivers/clk/ti/clk-54xx.c
@@ -50,7 +50,7 @@ static const struct omap_clkctrl_bit_data omap5_aess_bit_data[] __initconst = {
 };
 
 static const char * const omap5_dmic_gfclk_parents[] __initconst = {
-	"abe_cm:clk:0018:26",
+	"abe-clkctrl:0018:26",
 	"pad_clks_ck",
 	"slimbus_clk",
 	NULL,
@@ -70,7 +70,7 @@ static const struct omap_clkctrl_bit_data omap5_dmic_bit_data[] __initconst = {
 };
 
 static const char * const omap5_mcbsp1_gfclk_parents[] __initconst = {
-	"abe_cm:clk:0028:26",
+	"abe-clkctrl:0028:26",
 	"pad_clks_ck",
 	"slimbus_clk",
 	NULL,
@@ -83,7 +83,7 @@ static const struct omap_clkctrl_bit_data omap5_mcbsp1_bit_data[] __initconst =
 };
 
 static const char * const omap5_mcbsp2_gfclk_parents[] __initconst = {
-	"abe_cm:clk:0030:26",
+	"abe-clkctrl:0030:26",
 	"pad_clks_ck",
 	"slimbus_clk",
 	NULL,
@@ -96,7 +96,7 @@ static const struct omap_clkctrl_bit_data omap5_mcbsp2_bit_data[] __initconst =
 };
 
 static const char * const omap5_mcbsp3_gfclk_parents[] __initconst = {
-	"abe_cm:clk:0038:26",
+	"abe-clkctrl:0038:26",
 	"pad_clks_ck",
 	"slimbus_clk",
 	NULL,
@@ -136,16 +136,16 @@ static const struct omap_clkctrl_bit_data omap5_timer8_bit_data[] __initconst =
 
 static const struct omap_clkctrl_reg_data omap5_abe_clkctrl_regs[] __initconst = {
 	{ OMAP5_L4_ABE_CLKCTRL, NULL, 0, "abe_iclk" },
-	{ OMAP5_AESS_CLKCTRL, omap5_aess_bit_data, CLKF_SW_SUP, "abe_cm:clk:0008:24" },
+	{ OMAP5_AESS_CLKCTRL, omap5_aess_bit_data, CLKF_SW_SUP, "abe-clkctrl:0008:24" },
 	{ OMAP5_MCPDM_CLKCTRL, NULL, CLKF_SW_SUP, "pad_clks_ck" },
-	{ OMAP5_DMIC_CLKCTRL, omap5_dmic_bit_data, CLKF_SW_SUP, "abe_cm:clk:0018:24" },
-	{ OMAP5_MCBSP1_CLKCTRL, omap5_mcbsp1_bit_data, CLKF_SW_SUP, "abe_cm:clk:0028:24" },
-	{ OMAP5_MCBSP2_CLKCTRL, omap5_mcbsp2_bit_data, CLKF_SW_SUP, "abe_cm:clk:0030:24" },
-	{ OMAP5_MCBSP3_CLKCTRL, omap5_mcbsp3_bit_data, CLKF_SW_SUP, "abe_cm:clk:0038:24" },
-	{ OMAP5_TIMER5_CLKCTRL, omap5_timer5_bit_data, CLKF_SW_SUP, "abe_cm:clk:0048:24" },
-	{ OMAP5_TIMER6_CLKCTRL, omap5_timer6_bit_data, CLKF_SW_SUP, "abe_cm:clk:0050:24" },
-	{ OMAP5_TIMER7_CLKCTRL, omap5_timer7_bit_data, CLKF_SW_SUP, "abe_cm:clk:0058:24" },
-	{ OMAP5_TIMER8_CLKCTRL, omap5_timer8_bit_data, CLKF_SW_SUP, "abe_cm:clk:0060:24" },
+	{ OMAP5_DMIC_CLKCTRL, omap5_dmic_bit_data, CLKF_SW_SUP, "abe-clkctrl:0018:24" },
+	{ OMAP5_MCBSP1_CLKCTRL, omap5_mcbsp1_bit_data, CLKF_SW_SUP, "abe-clkctrl:0028:24" },
+	{ OMAP5_MCBSP2_CLKCTRL, omap5_mcbsp2_bit_data, CLKF_SW_SUP, "abe-clkctrl:0030:24" },
+	{ OMAP5_MCBSP3_CLKCTRL, omap5_mcbsp3_bit_data, CLKF_SW_SUP, "abe-clkctrl:0038:24" },
+	{ OMAP5_TIMER5_CLKCTRL, omap5_timer5_bit_data, CLKF_SW_SUP, "abe-clkctrl:0048:24" },
+	{ OMAP5_TIMER6_CLKCTRL, omap5_timer6_bit_data, CLKF_SW_SUP, "abe-clkctrl:0050:24" },
+	{ OMAP5_TIMER7_CLKCTRL, omap5_timer7_bit_data, CLKF_SW_SUP, "abe-clkctrl:0058:24" },
+	{ OMAP5_TIMER8_CLKCTRL, omap5_timer8_bit_data, CLKF_SW_SUP, "abe-clkctrl:0060:24" },
 	{ 0 },
 };
 
@@ -268,12 +268,12 @@ static const struct omap_clkctrl_bit_data omap5_gpio8_bit_data[] __initconst = {
 };
 
 static const struct omap_clkctrl_reg_data omap5_l4per_clkctrl_regs[] __initconst = {
-	{ OMAP5_TIMER10_CLKCTRL, omap5_timer10_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0008:24" },
-	{ OMAP5_TIMER11_CLKCTRL, omap5_timer11_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0010:24" },
-	{ OMAP5_TIMER2_CLKCTRL, omap5_timer2_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0018:24" },
-	{ OMAP5_TIMER3_CLKCTRL, omap5_timer3_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0020:24" },
-	{ OMAP5_TIMER4_CLKCTRL, omap5_timer4_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0028:24" },
-	{ OMAP5_TIMER9_CLKCTRL, omap5_timer9_bit_data, CLKF_SW_SUP, "l4per_cm:clk:0030:24" },
+	{ OMAP5_TIMER10_CLKCTRL, omap5_timer10_bit_data, CLKF_SW_SUP, "l4per-clkctrl:0008:24" },
+	{ OMAP5_TIMER11_CLKCTRL, omap5_timer11_bit_data, CLKF_SW_SUP, "l4per-clkctrl:0010:24" },
+	{ OMAP5_TIMER2_CLKCTRL, omap5_timer2_bit_data, CLKF_SW_SUP, "l4per-clkctrl:0018:24" },
+	{ OMAP5_TIMER3_CLKCTRL, omap5_timer3_bit_data, CLKF_SW_SUP, "l4per-clkctrl:0020:24" },
+	{ OMAP5_TIMER4_CLKCTRL, omap5_timer4_bit_data, CLKF_SW_SUP, "l4per-clkctrl:0028:24" },
+	{ OMAP5_TIMER9_CLKCTRL, omap5_timer9_bit_data, CLKF_SW_SUP, "l4per-clkctrl:0030:24" },
 	{ OMAP5_GPIO2_CLKCTRL, omap5_gpio2_bit_data, CLKF_HW_SUP, "l4_root_clk_div" },
 	{ OMAP5_GPIO3_CLKCTRL, omap5_gpio3_bit_data, CLKF_HW_SUP, "l4_root_clk_div" },
 	{ OMAP5_GPIO4_CLKCTRL, omap5_gpio4_bit_data, CLKF_HW_SUP, "l4_root_clk_div" },
@@ -345,7 +345,7 @@ static const struct omap_clkctrl_bit_data omap5_dss_core_bit_data[] __initconst
 };
 
 static const struct omap_clkctrl_reg_data omap5_dss_clkctrl_regs[] __initconst = {
-	{ OMAP5_DSS_CORE_CLKCTRL, omap5_dss_core_bit_data, CLKF_SW_SUP, "dss_cm:clk:0000:8" },
+	{ OMAP5_DSS_CORE_CLKCTRL, omap5_dss_core_bit_data, CLKF_SW_SUP, "dss-clkctrl:0000:8" },
 	{ 0 },
 };
 
@@ -378,7 +378,7 @@ static const struct omap_clkctrl_bit_data omap5_gpu_core_bit_data[] __initconst
 };
 
 static const struct omap_clkctrl_reg_data omap5_gpu_clkctrl_regs[] __initconst = {
-	{ OMAP5_GPU_CLKCTRL, omap5_gpu_core_bit_data, CLKF_SW_SUP, "gpu_cm:clk:0000:24" },
+	{ OMAP5_GPU_CLKCTRL, omap5_gpu_core_bit_data, CLKF_SW_SUP, "gpu-clkctrl:0000:24" },
 	{ 0 },
 };
 
@@ -389,7 +389,7 @@ static const char * const omap5_mmc1_fclk_mux_parents[] __initconst = {
 };
 
 static const char * const omap5_mmc1_fclk_parents[] __initconst = {
-	"l3init_cm:clk:0008:24",
+	"l3init-clkctrl:0008:24",
 	NULL,
 };
 
@@ -405,7 +405,7 @@ static const struct omap_clkctrl_bit_data omap5_mmc1_bit_data[] __initconst = {
 };
 
 static const char * const omap5_mmc2_fclk_parents[] __initconst = {
-	"l3init_cm:clk:0010:24",
+	"l3init-clkctrl:0010:24",
 	NULL,
 };
 
@@ -430,12 +430,12 @@ static const char * const omap5_usb_host_hs_hsic480m_p3_clk_parents[] __initcons
 };
 
 static const char * const omap5_usb_host_hs_utmi_p1_clk_parents[] __initconst = {
-	"l3init_cm:clk:0038:24",
+	"l3init-clkctrl:0038:24",
 	NULL,
 };
 
 static const char * const omap5_usb_host_hs_utmi_p2_clk_parents[] __initconst = {
-	"l3init_cm:clk:0038:25",
+	"l3init-clkctrl:0038:25",
 	NULL,
 };
 
@@ -494,8 +494,8 @@ static const struct omap_clkctrl_bit_data omap5_usb_otg_ss_bit_data[] __initcons
 };
 
 static const struct omap_clkctrl_reg_data omap5_l3init_clkctrl_regs[] __initconst = {
-	{ OMAP5_MMC1_CLKCTRL, omap5_mmc1_bit_data, CLKF_SW_SUP, "l3init_cm:clk:0008:25" },
-	{ OMAP5_MMC2_CLKCTRL, omap5_mmc2_bit_data, CLKF_SW_SUP, "l3init_cm:clk:0010:25" },
+	{ OMAP5_MMC1_CLKCTRL, omap5_mmc1_bit_data, CLKF_SW_SUP, "l3init-clkctrl:0008:25" },
+	{ OMAP5_MMC2_CLKCTRL, omap5_mmc2_bit_data, CLKF_SW_SUP, "l3init-clkctrl:0010:25" },
 	{ OMAP5_USB_HOST_HS_CLKCTRL, omap5_usb_host_hs_bit_data, CLKF_SW_SUP, "l3init_60m_fclk" },
 	{ OMAP5_USB_TLL_HS_CLKCTRL, omap5_usb_tll_hs_bit_data, CLKF_HW_SUP, "l4_root_clk_div" },
 	{ OMAP5_SATA_CLKCTRL, omap5_sata_bit_data, CLKF_SW_SUP, "func_48m_fclk" },
@@ -519,7 +519,7 @@ static const struct omap_clkctrl_reg_data omap5_wkupaon_clkctrl_regs[] __initcon
 	{ OMAP5_L4_WKUP_CLKCTRL, NULL, 0, "wkupaon_iclk_mux" },
 	{ OMAP5_WD_TIMER2_CLKCTRL, NULL, CLKF_SW_SUP, "sys_32k_ck" },
 	{ OMAP5_GPIO1_CLKCTRL, omap5_gpio1_bit_data, CLKF_HW_SUP, "wkupaon_iclk_mux" },
-	{ OMAP5_TIMER1_CLKCTRL, omap5_timer1_bit_data, CLKF_SW_SUP, "wkupaon_cm:clk:0020:24" },
+	{ OMAP5_TIMER1_CLKCTRL, omap5_timer1_bit_data, CLKF_SW_SUP, "wkupaon-clkctrl:0020:24" },
 	{ OMAP5_COUNTER_32K_CLKCTRL, NULL, 0, "wkupaon_iclk_mux" },
 	{ OMAP5_KBD_CLKCTRL, NULL, CLKF_SW_SUP, "sys_32k_ck" },
 	{ 0 },
@@ -549,58 +549,58 @@ const struct omap_clkctrl_data omap5_clkctrl_data[] __initconst = {
 static struct ti_dt_clk omap54xx_clks[] = {
 	DT_CLK(NULL, "timer_32k_ck", "sys_32k_ck"),
 	DT_CLK(NULL, "sys_clkin_ck", "sys_clkin"),
-	DT_CLK(NULL, "dmic_gfclk", "abe_cm:0018:24"),
-	DT_CLK(NULL, "dmic_sync_mux_ck", "abe_cm:0018:26"),
-	DT_CLK(NULL, "dss_32khz_clk", "dss_cm:0000:11"),
-	DT_CLK(NULL, "dss_48mhz_clk", "dss_cm:0000:9"),
-	DT_CLK(NULL, "dss_dss_clk", "dss_cm:0000:8"),
-	DT_CLK(NULL, "dss_sys_clk", "dss_cm:0000:10"),
-	DT_CLK(NULL, "gpio1_dbclk", "wkupaon_cm:0018:8"),
-	DT_CLK(NULL, "gpio2_dbclk", "l4per_cm:0040:8"),
-	DT_CLK(NULL, "gpio3_dbclk", "l4per_cm:0048:8"),
-	DT_CLK(NULL, "gpio4_dbclk", "l4per_cm:0050:8"),
-	DT_CLK(NULL, "gpio5_dbclk", "l4per_cm:0058:8"),
-	DT_CLK(NULL, "gpio6_dbclk", "l4per_cm:0060:8"),
-	DT_CLK(NULL, "gpio7_dbclk", "l4per_cm:00f0:8"),
-	DT_CLK(NULL, "gpio8_dbclk", "l4per_cm:00f8:8"),
-	DT_CLK(NULL, "mcbsp1_gfclk", "abe_cm:0028:24"),
-	DT_CLK(NULL, "mcbsp1_sync_mux_ck", "abe_cm:0028:26"),
-	DT_CLK(NULL, "mcbsp2_gfclk", "abe_cm:0030:24"),
-	DT_CLK(NULL, "mcbsp2_sync_mux_ck", "abe_cm:0030:26"),
-	DT_CLK(NULL, "mcbsp3_gfclk", "abe_cm:0038:24"),
-	DT_CLK(NULL, "mcbsp3_sync_mux_ck", "abe_cm:0038:26"),
-	DT_CLK(NULL, "mmc1_32khz_clk", "l3init_cm:0008:8"),
-	DT_CLK(NULL, "mmc1_fclk", "l3init_cm:0008:25"),
-	DT_CLK(NULL, "mmc1_fclk_mux", "l3init_cm:0008:24"),
-	DT_CLK(NULL, "mmc2_fclk", "l3init_cm:0010:25"),
-	DT_CLK(NULL, "mmc2_fclk_mux", "l3init_cm:0010:24"),
-	DT_CLK(NULL, "sata_ref_clk", "l3init_cm:0068:8"),
-	DT_CLK(NULL, "timer10_gfclk_mux", "l4per_cm:0008:24"),
-	DT_CLK(NULL, "timer11_gfclk_mux", "l4per_cm:0010:24"),
-	DT_CLK(NULL, "timer1_gfclk_mux", "wkupaon_cm:0020:24"),
-	DT_CLK(NULL, "timer2_gfclk_mux", "l4per_cm:0018:24"),
-	DT_CLK(NULL, "timer3_gfclk_mux", "l4per_cm:0020:24"),
-	DT_CLK(NULL, "timer4_gfclk_mux", "l4per_cm:0028:24"),
-	DT_CLK(NULL, "timer5_gfclk_mux", "abe_cm:0048:24"),
-	DT_CLK(NULL, "timer6_gfclk_mux", "abe_cm:0050:24"),
-	DT_CLK(NULL, "timer7_gfclk_mux", "abe_cm:0058:24"),
-	DT_CLK(NULL, "timer8_gfclk_mux", "abe_cm:0060:24"),
-	DT_CLK(NULL, "timer9_gfclk_mux", "l4per_cm:0030:24"),
-	DT_CLK(NULL, "usb_host_hs_hsic480m_p1_clk", "l3init_cm:0038:13"),
-	DT_CLK(NULL, "usb_host_hs_hsic480m_p2_clk", "l3init_cm:0038:14"),
-	DT_CLK(NULL, "usb_host_hs_hsic480m_p3_clk", "l3init_cm:0038:7"),
-	DT_CLK(NULL, "usb_host_hs_hsic60m_p1_clk", "l3init_cm:0038:11"),
-	DT_CLK(NULL, "usb_host_hs_hsic60m_p2_clk", "l3init_cm:0038:12"),
-	DT_CLK(NULL, "usb_host_hs_hsic60m_p3_clk", "l3init_cm:0038:6"),
-	DT_CLK(NULL, "usb_host_hs_utmi_p1_clk", "l3init_cm:0038:8"),
-	DT_CLK(NULL, "usb_host_hs_utmi_p2_clk", "l3init_cm:0038:9"),
-	DT_CLK(NULL, "usb_host_hs_utmi_p3_clk", "l3init_cm:0038:10"),
-	DT_CLK(NULL, "usb_otg_ss_refclk960m", "l3init_cm:00d0:8"),
-	DT_CLK(NULL, "usb_tll_hs_usb_ch0_clk", "l3init_cm:0048:8"),
-	DT_CLK(NULL, "usb_tll_hs_usb_ch1_clk", "l3init_cm:0048:9"),
-	DT_CLK(NULL, "usb_tll_hs_usb_ch2_clk", "l3init_cm:0048:10"),
-	DT_CLK(NULL, "utmi_p1_gfclk", "l3init_cm:0038:24"),
-	DT_CLK(NULL, "utmi_p2_gfclk", "l3init_cm:0038:25"),
+	DT_CLK(NULL, "dmic_gfclk", "abe-clkctrl:0018:24"),
+	DT_CLK(NULL, "dmic_sync_mux_ck", "abe-clkctrl:0018:26"),
+	DT_CLK(NULL, "dss_32khz_clk", "dss-clkctrl:0000:11"),
+	DT_CLK(NULL, "dss_48mhz_clk", "dss-clkctrl:0000:9"),
+	DT_CLK(NULL, "dss_dss_clk", "dss-clkctrl:0000:8"),
+	DT_CLK(NULL, "dss_sys_clk", "dss-clkctrl:0000:10"),
+	DT_CLK(NULL, "gpio1_dbclk", "wkupaon-clkctrl:0018:8"),
+	DT_CLK(NULL, "gpio2_dbclk", "l4per-clkctrl:0040:8"),
+	DT_CLK(NULL, "gpio3_dbclk", "l4per-clkctrl:0048:8"),
+	DT_CLK(NULL, "gpio4_dbclk", "l4per-clkctrl:0050:8"),
+	DT_CLK(NULL, "gpio5_dbclk", "l4per-clkctrl:0058:8"),
+	DT_CLK(NULL, "gpio6_dbclk", "l4per-clkctrl:0060:8"),
+	DT_CLK(NULL, "gpio7_dbclk", "l4per-clkctrl:00f0:8"),
+	DT_CLK(NULL, "gpio8_dbclk", "l4per-clkctrl:00f8:8"),
+	DT_CLK(NULL, "mcbsp1_gfclk", "abe-clkctrl:0028:24"),
+	DT_CLK(NULL, "mcbsp1_sync_mux_ck", "abe-clkctrl:0028:26"),
+	DT_CLK(NULL, "mcbsp2_gfclk", "abe-clkctrl:0030:24"),
+	DT_CLK(NULL, "mcbsp2_sync_mux_ck", "abe-clkctrl:0030:26"),
+	DT_CLK(NULL, "mcbsp3_gfclk", "abe-clkctrl:0038:24"),
+	DT_CLK(NULL, "mcbsp3_sync_mux_ck", "abe-clkctrl:0038:26"),
+	DT_CLK(NULL, "mmc1_32khz_clk", "l3init-clkctrl:0008:8"),
+	DT_CLK(NULL, "mmc1_fclk", "l3init-clkctrl:0008:25"),
+	DT_CLK(NULL, "mmc1_fclk_mux", "l3init-clkctrl:0008:24"),
+	DT_CLK(NULL, "mmc2_fclk", "l3init-clkctrl:0010:25"),
+	DT_CLK(NULL, "mmc2_fclk_mux", "l3init-clkctrl:0010:24"),
+	DT_CLK(NULL, "sata_ref_clk", "l3init-clkctrl:0068:8"),
+	DT_CLK(NULL, "timer10_gfclk_mux", "l4per-clkctrl:0008:24"),
+	DT_CLK(NULL, "timer11_gfclk_mux", "l4per-clkctrl:0010:24"),
+	DT_CLK(NULL, "timer1_gfclk_mux", "wkupaon-clkctrl:0020:24"),
+	DT_CLK(NULL, "timer2_gfclk_mux", "l4per-clkctrl:0018:24"),
+	DT_CLK(NULL, "timer3_gfclk_mux", "l4per-clkctrl:0020:24"),
+	DT_CLK(NULL, "timer4_gfclk_mux", "l4per-clkctrl:0028:24"),
+	DT_CLK(NULL, "timer5_gfclk_mux", "abe-clkctrl:0048:24"),
+	DT_CLK(NULL, "timer6_gfclk_mux", "abe-clkctrl:0050:24"),
+	DT_CLK(NULL, "timer7_gfclk_mux", "abe-clkctrl:0058:24"),
+	DT_CLK(NULL, "timer8_gfclk_mux", "abe-clkctrl:0060:24"),
+	DT_CLK(NULL, "timer9_gfclk_mux", "l4per-clkctrl:0030:24"),
+	DT_CLK(NULL, "usb_host_hs_hsic480m_p1_clk", "l3init-clkctrl:0038:13"),
+	DT_CLK(NULL, "usb_host_hs_hsic480m_p2_clk", "l3init-clkctrl:0038:14"),
+	DT_CLK(NULL, "usb_host_hs_hsic480m_p3_clk", "l3init-clkctrl:0038:7"),
+	DT_CLK(NULL, "usb_host_hs_hsic60m_p1_clk", "l3init-clkctrl:0038:11"),
+	DT_CLK(NULL, "usb_host_hs_hsic60m_p2_clk", "l3init-clkctrl:0038:12"),
+	DT_CLK(NULL, "usb_host_hs_hsic60m_p3_clk", "l3init-clkctrl:0038:6"),
+	DT_CLK(NULL, "usb_host_hs_utmi_p1_clk", "l3init-clkctrl:0038:8"),
+	DT_CLK(NULL, "usb_host_hs_utmi_p2_clk", "l3init-clkctrl:0038:9"),
+	DT_CLK(NULL, "usb_host_hs_utmi_p3_clk", "l3init-clkctrl:0038:10"),
+	DT_CLK(NULL, "usb_otg_ss_refclk960m", "l3init-clkctrl:00d0:8"),
+	DT_CLK(NULL, "usb_tll_hs_usb_ch0_clk", "l3init-clkctrl:0048:8"),
+	DT_CLK(NULL, "usb_tll_hs_usb_ch1_clk", "l3init-clkctrl:0048:9"),
+	DT_CLK(NULL, "usb_tll_hs_usb_ch2_clk", "l3init-clkctrl:0048:10"),
+	DT_CLK(NULL, "utmi_p1_gfclk", "l3init-clkctrl:0038:24"),
+	DT_CLK(NULL, "utmi_p2_gfclk", "l3init-clkctrl:0038:25"),
 	{ .node_name = NULL },
 };
 
diff --git a/drivers/clk/ti/clkctrl.c b/drivers/clk/ti/clkctrl.c
index 864c484bde1b..08a85c559f79 100644
--- a/drivers/clk/ti/clkctrl.c
+++ b/drivers/clk/ti/clkctrl.c
@@ -511,10 +511,6 @@ static void __init _ti_omap4_clkctrl_setup(struct device_node *node)
 	char *c;
 	u16 soc_mask = 0;
 
-	if (!(ti_clk_get_features()->flags & TI_CLK_CLKCTRL_COMPAT) &&
-	    of_node_name_eq(node, "clk"))
-		ti_clk_features.flags |= TI_CLK_CLKCTRL_COMPAT;
-
 	addrp = of_get_address(node, 0, NULL, NULL);
 	addr = (u32)of_translate_address(node, addrp);
 
diff --git a/drivers/clocksource/timer-ixp4xx.c b/drivers/clocksource/timer-ixp4xx.c
index cbb184953510..b8e92991c471 100644
--- a/drivers/clocksource/timer-ixp4xx.c
+++ b/drivers/clocksource/timer-ixp4xx.c
@@ -282,7 +282,6 @@ void __init ixp4xx_timer_setup(resource_size_t timerbase,
 	}
 	ixp4xx_timer_register(base, timer_irq, timer_freq);
 }
-EXPORT_SYMBOL_GPL(ixp4xx_timer_setup);
 
 #ifdef CONFIG_OF
 static __init int ixp4xx_of_timer_init(struct device_node *np)
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index cddf7e13c232..799431d287ee 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -532,7 +532,7 @@ static unsigned int __resolve_freq(struct cpufreq_policy *policy,
 
 	target_freq = clamp_val(target_freq, policy->min, policy->max);
 
-	if (!cpufreq_driver->target_index)
+	if (!policy->freq_table)
 		return target_freq;
 
 	idx = cpufreq_frequency_table_target(policy, target_freq, relation);
diff --git a/drivers/cpufreq/pmac32-cpufreq.c b/drivers/cpufreq/pmac32-cpufreq.c
index 4f20c6a9108d..8e41fe9ee870 100644
--- a/drivers/cpufreq/pmac32-cpufreq.c
+++ b/drivers/cpufreq/pmac32-cpufreq.c
@@ -470,6 +470,10 @@ static int pmac_cpufreq_init_MacRISC3(struct device_node *cpunode)
 	if (slew_done_gpio_np)
 		slew_done_gpio = read_gpio(slew_done_gpio_np);
 
+	of_node_put(volt_gpio_np);
+	of_node_put(freq_gpio_np);
+	of_node_put(slew_done_gpio_np);
+
 	/* If we use the frequency GPIOs, calculate the min/max speeds based
 	 * on the bus frequencies
 	 */
diff --git a/drivers/cpufreq/qoriq-cpufreq.c b/drivers/cpufreq/qoriq-cpufreq.c
index 6b6b20da2bcf..573b417e1483 100644
--- a/drivers/cpufreq/qoriq-cpufreq.c
+++ b/drivers/cpufreq/qoriq-cpufreq.c
@@ -275,6 +275,7 @@ static int qoriq_cpufreq_probe(struct platform_device *pdev)
 
 	np = of_find_matching_node(NULL, qoriq_cpufreq_blacklist);
 	if (np) {
+		of_node_put(np);
 		dev_info(&pdev->dev, "Disabling due to erratum A-008083");
 		return -ENODEV;
 	}
diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c
index 70e2e6e37389..3c46ad8c3a1c 100644
--- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c
+++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c
@@ -151,6 +151,7 @@ dma_iv_error:
 	while (i >= 0) {
 		dma_unmap_single(ss->dev, rctx->p_iv[i], ivsize, DMA_TO_DEVICE);
 		memzero_explicit(sf->iv[i], ivsize);
+		i--;
 	}
 	return err;
 }
diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c
index 657530578643..47b5828e35c3 100644
--- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c
+++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c
@@ -476,14 +476,32 @@ static int allocate_flows(struct sun8i_ss_dev *ss)
 
 		ss->flows[i].biv = devm_kmalloc(ss->dev, AES_BLOCK_SIZE,
 						GFP_KERNEL | GFP_DMA);
-		if (!ss->flows[i].biv)
+		if (!ss->flows[i].biv) {
+			err = -ENOMEM;
 			goto error_engine;
+		}
 
 		for (j = 0; j < MAX_SG; j++) {
 			ss->flows[i].iv[j] = devm_kmalloc(ss->dev, AES_BLOCK_SIZE,
 							  GFP_KERNEL | GFP_DMA);
-			if (!ss->flows[i].iv[j])
+			if (!ss->flows[i].iv[j]) {
+				err = -ENOMEM;
 				goto error_engine;
+			}
+		}
+
+		/* the padding could be up to two block. */
+		ss->flows[i].pad = devm_kmalloc(ss->dev, SHA256_BLOCK_SIZE * 2,
+						GFP_KERNEL | GFP_DMA);
+		if (!ss->flows[i].pad) {
+			err = -ENOMEM;
+			goto error_engine;
+		}
+		ss->flows[i].result = devm_kmalloc(ss->dev, SHA256_DIGEST_SIZE,
+						   GFP_KERNEL | GFP_DMA);
+		if (!ss->flows[i].result) {
+			err = -ENOMEM;
+			goto error_engine;
 		}
 
 		ss->flows[i].engine = crypto_engine_alloc_init(ss->dev, true);
diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-hash.c b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-hash.c
index ca4f280af35d..f89a580618aa 100644
--- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-hash.c
+++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-hash.c
@@ -342,18 +342,11 @@ int sun8i_ss_hash_run(struct crypto_engine *engine, void *breq)
 	if (digestsize == SHA224_DIGEST_SIZE)
 		digestsize = SHA256_DIGEST_SIZE;
 
-	/* the padding could be up to two block. */
-	pad = kzalloc(algt->alg.hash.halg.base.cra_blocksize * 2, GFP_KERNEL | GFP_DMA);
-	if (!pad)
-		return -ENOMEM;
+	result = ss->flows[rctx->flow].result;
+	pad = ss->flows[rctx->flow].pad;
+	memset(pad, 0, algt->alg.hash.halg.base.cra_blocksize * 2);
 	bf = (__le32 *)pad;
 
-	result = kzalloc(digestsize, GFP_KERNEL | GFP_DMA);
-	if (!result) {
-		kfree(pad);
-		return -ENOMEM;
-	}
-
 	for (i = 0; i < MAX_SG; i++) {
 		rctx->t_dst[i].addr = 0;
 		rctx->t_dst[i].len = 0;
@@ -449,8 +442,6 @@ int sun8i_ss_hash_run(struct crypto_engine *engine, void *breq)
 
 	memcpy(areq->result, result, algt->alg.hash.halg.digestsize);
 theend:
-	kfree(pad);
-	kfree(result);
 	local_bh_disable();
 	crypto_finalize_hash_request(engine, breq, err);
 	local_bh_enable();
diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss.h b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss.h
index 57ada8653855..eb82ee5345ae 100644
--- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss.h
+++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss.h
@@ -123,6 +123,8 @@ struct sginfo {
  * @stat_req:	number of request done by this flow
  * @iv:		list of IV to use for each step
  * @biv:	buffer which contain the backuped IV
+ * @pad:	padding buffer for hash operations
+ * @result:	buffer for storing the result of hash operations
  */
 struct sun8i_ss_flow {
 	struct crypto_engine *engine;
@@ -130,6 +132,8 @@ struct sun8i_ss_flow {
 	int status;
 	u8 *iv[MAX_SG];
 	u8 *biv;
+	void *pad;
+	void *result;
 #ifdef CONFIG_CRYPTO_DEV_SUN8I_SS_DEBUG
 	unsigned long stat_req;
 #endif
diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c
index 5040726fc119..900727b5edda 100644
--- a/drivers/crypto/ccp/sev-dev.c
+++ b/drivers/crypto/ccp/sev-dev.c
@@ -314,7 +314,7 @@ static int __sev_platform_shutdown_locked(int *error)
 	struct sev_device *sev = psp_master->sev_data;
 	int ret;
 
-	if (sev->state == SEV_STATE_UNINIT)
+	if (!sev || sev->state == SEV_STATE_UNINIT)
 		return 0;
 
 	ret = __sev_do_cmd_locked(SEV_CMD_SHUTDOWN, NULL, error);
@@ -388,6 +388,8 @@ static int sev_ioctl_do_platform_status(struct sev_issue_cmd *argp)
 	struct sev_user_data_status data;
 	int ret;
 
+	memset(&data, 0, sizeof(data));
+
 	ret = __sev_do_cmd_locked(SEV_CMD_PLATFORM_STATUS, &data, &argp->error);
 	if (ret)
 		return ret;
@@ -441,7 +443,7 @@ static int sev_ioctl_do_pek_csr(struct sev_issue_cmd *argp, bool writable)
 	if (input.length > SEV_FW_BLOB_MAX_SIZE)
 		return -EFAULT;
 
-	blob = kmalloc(input.length, GFP_KERNEL);
+	blob = kzalloc(input.length, GFP_KERNEL);
 	if (!blob)
 		return -ENOMEM;
 
@@ -665,7 +667,7 @@ static int sev_ioctl_do_get_id2(struct sev_issue_cmd *argp)
 	input_address = (void __user *)input.address;
 
 	if (input.address && input.length) {
-		id_blob = kmalloc(input.length, GFP_KERNEL);
+		id_blob = kzalloc(input.length, GFP_KERNEL);
 		if (!id_blob)
 			return -ENOMEM;
 
@@ -784,14 +786,14 @@ static int sev_ioctl_do_pdh_export(struct sev_issue_cmd *argp, bool writable)
 	if (input.cert_chain_len > SEV_FW_BLOB_MAX_SIZE)
 		return -EFAULT;
 
-	pdh_blob = kmalloc(input.pdh_cert_len, GFP_KERNEL);
+	pdh_blob = kzalloc(input.pdh_cert_len, GFP_KERNEL);
 	if (!pdh_blob)
 		return -ENOMEM;
 
 	data.pdh_cert_address = __psp_pa(pdh_blob);
 	data.pdh_cert_len = input.pdh_cert_len;
 
-	cert_blob = kmalloc(input.cert_chain_len, GFP_KERNEL);
+	cert_blob = kzalloc(input.cert_chain_len, GFP_KERNEL);
 	if (!cert_blob) {
 		ret = -ENOMEM;
 		goto e_free_pdh;
diff --git a/drivers/crypto/hisilicon/hpre/hpre_crypto.c b/drivers/crypto/hisilicon/hpre/hpre_crypto.c
index 7ba7641723a0..4062251fd1b6 100644
--- a/drivers/crypto/hisilicon/hpre/hpre_crypto.c
+++ b/drivers/crypto/hisilicon/hpre/hpre_crypto.c
@@ -252,7 +252,7 @@ static int hpre_prepare_dma_buf(struct hpre_asym_request *hpre_req,
 	if (unlikely(shift < 0))
 		return -EINVAL;
 
-	ptr = dma_alloc_coherent(dev, ctx->key_sz, tmp, GFP_KERNEL);
+	ptr = dma_alloc_coherent(dev, ctx->key_sz, tmp, GFP_ATOMIC);
 	if (unlikely(!ptr))
 		return -ENOMEM;
 
diff --git a/drivers/crypto/hisilicon/sec/sec_algs.c b/drivers/crypto/hisilicon/sec/sec_algs.c
index 0a3c8f019b02..490e1542305e 100644
--- a/drivers/crypto/hisilicon/sec/sec_algs.c
+++ b/drivers/crypto/hisilicon/sec/sec_algs.c
@@ -449,7 +449,7 @@ static void sec_skcipher_alg_callback(struct sec_bd_info *sec_resp,
 		 */
 	}
 
-	mutex_lock(&ctx->queue->queuelock);
+	spin_lock_bh(&ctx->queue->queuelock);
 	/* Put the IV in place for chained cases */
 	switch (ctx->cipher_alg) {
 	case SEC_C_AES_CBC_128:
@@ -509,7 +509,7 @@ static void sec_skcipher_alg_callback(struct sec_bd_info *sec_resp,
 			list_del(&backlog_req->backlog_head);
 		}
 	}
-	mutex_unlock(&ctx->queue->queuelock);
+	spin_unlock_bh(&ctx->queue->queuelock);
 
 	mutex_lock(&sec_req->lock);
 	list_del(&sec_req_el->head);
@@ -798,7 +798,7 @@ static int sec_alg_skcipher_crypto(struct skcipher_request *skreq,
 	 */
 
 	/* Grab a big lock for a long time to avoid concurrency issues */
-	mutex_lock(&queue->queuelock);
+	spin_lock_bh(&queue->queuelock);
 
 	/*
 	 * Can go on to queue if we have space in either:
@@ -814,15 +814,15 @@ static int sec_alg_skcipher_crypto(struct skcipher_request *skreq,
 		ret = -EBUSY;
 		if ((skreq->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG)) {
 			list_add_tail(&sec_req->backlog_head, &ctx->backlog);
-			mutex_unlock(&queue->queuelock);
+			spin_unlock_bh(&queue->queuelock);
 			goto out;
 		}
 
-		mutex_unlock(&queue->queuelock);
+		spin_unlock_bh(&queue->queuelock);
 		goto err_free_elements;
 	}
 	ret = sec_send_request(sec_req, queue);
-	mutex_unlock(&queue->queuelock);
+	spin_unlock_bh(&queue->queuelock);
 	if (ret)
 		goto err_free_elements;
 
@@ -881,7 +881,7 @@ static int sec_alg_skcipher_init(struct crypto_skcipher *tfm)
 	if (IS_ERR(ctx->queue))
 		return PTR_ERR(ctx->queue);
 
-	mutex_init(&ctx->queue->queuelock);
+	spin_lock_init(&ctx->queue->queuelock);
 	ctx->queue->havesoftqueue = false;
 
 	return 0;
diff --git a/drivers/crypto/hisilicon/sec/sec_drv.h b/drivers/crypto/hisilicon/sec/sec_drv.h
index 179a8250d691..e2a50bf2234b 100644
--- a/drivers/crypto/hisilicon/sec/sec_drv.h
+++ b/drivers/crypto/hisilicon/sec/sec_drv.h
@@ -347,7 +347,7 @@ struct sec_queue {
 	DECLARE_BITMAP(unprocessed, SEC_QUEUE_LEN);
 	DECLARE_KFIFO_PTR(softqueue, typeof(struct sec_request_el *));
 	bool havesoftqueue;
-	struct mutex queuelock;
+	spinlock_t queuelock;
 	void *shadow[SEC_QUEUE_LEN];
 };
 
diff --git a/drivers/crypto/hisilicon/sec2/sec.h b/drivers/crypto/hisilicon/sec2/sec.h
index d97cf02b1df7..cff00fd29765 100644
--- a/drivers/crypto/hisilicon/sec2/sec.h
+++ b/drivers/crypto/hisilicon/sec2/sec.h
@@ -119,7 +119,7 @@ struct sec_qp_ctx {
 	struct idr req_idr;
 	struct sec_alg_res res[QM_Q_DEPTH];
 	struct sec_ctx *ctx;
-	struct mutex req_lock;
+	spinlock_t req_lock;
 	struct list_head backlog;
 	struct hisi_acc_sgl_pool *c_in_pool;
 	struct hisi_acc_sgl_pool *c_out_pool;
diff --git a/drivers/crypto/hisilicon/sec2/sec_crypto.c b/drivers/crypto/hisilicon/sec2/sec_crypto.c
index 090920ed50c8..0d26eda36a52 100644
--- a/drivers/crypto/hisilicon/sec2/sec_crypto.c
+++ b/drivers/crypto/hisilicon/sec2/sec_crypto.c
@@ -124,11 +124,11 @@ static int sec_alloc_req_id(struct sec_req *req, struct sec_qp_ctx *qp_ctx)
 {
 	int req_id;
 
-	mutex_lock(&qp_ctx->req_lock);
+	spin_lock_bh(&qp_ctx->req_lock);
 
 	req_id = idr_alloc_cyclic(&qp_ctx->req_idr, NULL,
 				  0, QM_Q_DEPTH, GFP_ATOMIC);
-	mutex_unlock(&qp_ctx->req_lock);
+	spin_unlock_bh(&qp_ctx->req_lock);
 	if (unlikely(req_id < 0)) {
 		dev_err(req->ctx->dev, "alloc req id fail!\n");
 		return req_id;
@@ -153,9 +153,9 @@ static void sec_free_req_id(struct sec_req *req)
 	qp_ctx->req_list[req_id] = NULL;
 	req->qp_ctx = NULL;
 
-	mutex_lock(&qp_ctx->req_lock);
+	spin_lock_bh(&qp_ctx->req_lock);
 	idr_remove(&qp_ctx->req_idr, req_id);
-	mutex_unlock(&qp_ctx->req_lock);
+	spin_unlock_bh(&qp_ctx->req_lock);
 }
 
 static u8 pre_parse_finished_bd(struct bd_status *status, void *resp)
@@ -270,7 +270,7 @@ static int sec_bd_send(struct sec_ctx *ctx, struct sec_req *req)
 	    !(req->flag & CRYPTO_TFM_REQ_MAY_BACKLOG))
 		return -EBUSY;
 
-	mutex_lock(&qp_ctx->req_lock);
+	spin_lock_bh(&qp_ctx->req_lock);
 	ret = hisi_qp_send(qp_ctx->qp, &req->sec_sqe);
 
 	if (ctx->fake_req_limit <=
@@ -278,10 +278,10 @@ static int sec_bd_send(struct sec_ctx *ctx, struct sec_req *req)
 		list_add_tail(&req->backlog_head, &qp_ctx->backlog);
 		atomic64_inc(&ctx->sec->debug.dfx.send_cnt);
 		atomic64_inc(&ctx->sec->debug.dfx.send_busy_cnt);
-		mutex_unlock(&qp_ctx->req_lock);
+		spin_unlock_bh(&qp_ctx->req_lock);
 		return -EBUSY;
 	}
-	mutex_unlock(&qp_ctx->req_lock);
+	spin_unlock_bh(&qp_ctx->req_lock);
 
 	if (unlikely(ret == -EBUSY))
 		return -ENOBUFS;
@@ -484,7 +484,7 @@ static int sec_create_qp_ctx(struct hisi_qm *qm, struct sec_ctx *ctx,
 
 	qp->req_cb = sec_req_cb;
 
-	mutex_init(&qp_ctx->req_lock);
+	spin_lock_init(&qp_ctx->req_lock);
 	idr_init(&qp_ctx->req_idr);
 	INIT_LIST_HEAD(&qp_ctx->backlog);
 
@@ -617,7 +617,7 @@ static int sec_auth_init(struct sec_ctx *ctx)
 {
 	struct sec_auth_ctx *a_ctx = &ctx->a_ctx;
 
-	a_ctx->a_key = dma_alloc_coherent(ctx->dev, SEC_MAX_KEY_SIZE,
+	a_ctx->a_key = dma_alloc_coherent(ctx->dev, SEC_MAX_AKEY_SIZE,
 					  &a_ctx->a_key_dma, GFP_KERNEL);
 	if (!a_ctx->a_key)
 		return -ENOMEM;
@@ -629,8 +629,8 @@ static void sec_auth_uninit(struct sec_ctx *ctx)
 {
 	struct sec_auth_ctx *a_ctx = &ctx->a_ctx;
 
-	memzero_explicit(a_ctx->a_key, SEC_MAX_KEY_SIZE);
-	dma_free_coherent(ctx->dev, SEC_MAX_KEY_SIZE,
+	memzero_explicit(a_ctx->a_key, SEC_MAX_AKEY_SIZE);
+	dma_free_coherent(ctx->dev, SEC_MAX_AKEY_SIZE,
 			  a_ctx->a_key, a_ctx->a_key_dma);
 }
 
@@ -1373,7 +1373,7 @@ static struct sec_req *sec_back_req_clear(struct sec_ctx *ctx,
 {
 	struct sec_req *backlog_req = NULL;
 
-	mutex_lock(&qp_ctx->req_lock);
+	spin_lock_bh(&qp_ctx->req_lock);
 	if (ctx->fake_req_limit >=
 	    atomic_read(&qp_ctx->qp->qp_status.used) &&
 	    !list_empty(&qp_ctx->backlog)) {
@@ -1381,7 +1381,7 @@ static struct sec_req *sec_back_req_clear(struct sec_ctx *ctx,
 				typeof(*backlog_req), backlog_head);
 		list_del(&backlog_req->backlog_head);
 	}
-	mutex_unlock(&qp_ctx->req_lock);
+	spin_unlock_bh(&qp_ctx->req_lock);
 
 	return backlog_req;
 }
diff --git a/drivers/crypto/hisilicon/sec2/sec_crypto.h b/drivers/crypto/hisilicon/sec2/sec_crypto.h
index 9f71c358a6d3..ee2edaf5058d 100644
--- a/drivers/crypto/hisilicon/sec2/sec_crypto.h
+++ b/drivers/crypto/hisilicon/sec2/sec_crypto.h
@@ -7,6 +7,7 @@
 #define SEC_AIV_SIZE		12
 #define SEC_IV_SIZE		24
 #define SEC_MAX_KEY_SIZE	64
+#define SEC_MAX_AKEY_SIZE	128
 #define SEC_COMM_SCENE		0
 #define SEC_MIN_BLOCK_SZ	1
 
diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index 9ff885d50edf..389a7b51f1f3 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -1831,6 +1831,8 @@ static const struct of_device_id safexcel_of_match_table[] = {
 	{},
 };
 
+MODULE_DEVICE_TABLE(of, safexcel_of_match_table);
+
 static struct platform_driver  crypto_safexcel = {
 	.probe		= safexcel_probe,
 	.remove		= safexcel_remove,
diff --git a/drivers/crypto/qat/qat_4xxx/adf_drv.c b/drivers/crypto/qat/qat_4xxx/adf_drv.c
index 8fd44703115f..359fb7989dfb 100644
--- a/drivers/crypto/qat/qat_4xxx/adf_drv.c
+++ b/drivers/crypto/qat/qat_4xxx/adf_drv.c
@@ -52,13 +52,6 @@ static int adf_crypto_dev_config(struct adf_accel_dev *accel_dev)
 	if (ret)
 		goto err;
 
-	/* Temporarily set the number of crypto instances to zero to avoid
-	 * registering the crypto algorithms.
-	 * This will be removed when the algorithms will support the
-	 * CRYPTO_TFM_REQ_MAY_BACKLOG flag
-	 */
-	instances = 0;
-
 	for (i = 0; i < instances; i++) {
 		val = i;
 		bank = i * 2;
diff --git a/drivers/crypto/qat/qat_common/Makefile b/drivers/crypto/qat/qat_common/Makefile
index 9c57abdf56b7..fc477f016213 100644
--- a/drivers/crypto/qat/qat_common/Makefile
+++ b/drivers/crypto/qat/qat_common/Makefile
@@ -15,6 +15,7 @@ intel_qat-objs := adf_cfg.o \
 	qat_crypto.o \
 	qat_algs.o \
 	qat_asym_algs.o \
+	qat_algs_send.o \
 	qat_uclo.o \
 	qat_hal.o
 
diff --git a/drivers/crypto/qat/qat_common/adf_transport.c b/drivers/crypto/qat/qat_common/adf_transport.c
index 8ba28409fb74..630d0483c4e0 100644
--- a/drivers/crypto/qat/qat_common/adf_transport.c
+++ b/drivers/crypto/qat/qat_common/adf_transport.c
@@ -8,6 +8,9 @@
 #include "adf_cfg.h"
 #include "adf_common_drv.h"
 
+#define ADF_MAX_RING_THRESHOLD		80
+#define ADF_PERCENT(tot, percent)	(((tot) * (percent)) / 100)
+
 static inline u32 adf_modulo(u32 data, u32 shift)
 {
 	u32 div = data >> shift;
@@ -77,6 +80,11 @@ static void adf_disable_ring_irq(struct adf_etr_bank_data *bank, u32 ring)
 				      bank->irq_mask);
 }
 
+bool adf_ring_nearly_full(struct adf_etr_ring_data *ring)
+{
+	return atomic_read(ring->inflights) > ring->threshold;
+}
+
 int adf_send_message(struct adf_etr_ring_data *ring, u32 *msg)
 {
 	struct adf_hw_csr_ops *csr_ops = GET_CSR_OPS(ring->bank->accel_dev);
@@ -217,6 +225,7 @@ int adf_create_ring(struct adf_accel_dev *accel_dev, const char *section,
 	struct adf_etr_bank_data *bank;
 	struct adf_etr_ring_data *ring;
 	char val[ADF_CFG_MAX_VAL_LEN_IN_BYTES];
+	int max_inflights;
 	u32 ring_num;
 	int ret;
 
@@ -263,6 +272,8 @@ int adf_create_ring(struct adf_accel_dev *accel_dev, const char *section,
 	ring->ring_size = adf_verify_ring_size(msg_size, num_msgs);
 	ring->head = 0;
 	ring->tail = 0;
+	max_inflights = ADF_MAX_INFLIGHTS(ring->ring_size, ring->msg_size);
+	ring->threshold = ADF_PERCENT(max_inflights, ADF_MAX_RING_THRESHOLD);
 	atomic_set(ring->inflights, 0);
 	ret = adf_init_ring(ring);
 	if (ret)
diff --git a/drivers/crypto/qat/qat_common/adf_transport.h b/drivers/crypto/qat/qat_common/adf_transport.h
index 2c95f1697c76..e6ef6f9b7691 100644
--- a/drivers/crypto/qat/qat_common/adf_transport.h
+++ b/drivers/crypto/qat/qat_common/adf_transport.h
@@ -14,6 +14,7 @@ int adf_create_ring(struct adf_accel_dev *accel_dev, const char *section,
 		    const char *ring_name, adf_callback_fn callback,
 		    int poll_mode, struct adf_etr_ring_data **ring_ptr);
 
+bool adf_ring_nearly_full(struct adf_etr_ring_data *ring);
 int adf_send_message(struct adf_etr_ring_data *ring, u32 *msg);
 void adf_remove_ring(struct adf_etr_ring_data *ring);
 #endif
diff --git a/drivers/crypto/qat/qat_common/adf_transport_internal.h b/drivers/crypto/qat/qat_common/adf_transport_internal.h
index 501bcf0f1809..8b2c92ba7ca1 100644
--- a/drivers/crypto/qat/qat_common/adf_transport_internal.h
+++ b/drivers/crypto/qat/qat_common/adf_transport_internal.h
@@ -22,6 +22,7 @@ struct adf_etr_ring_data {
 	spinlock_t lock;	/* protects ring data struct */
 	u16 head;
 	u16 tail;
+	u32 threshold;
 	u8 ring_number;
 	u8 ring_size;
 	u8 msg_size;
diff --git a/drivers/crypto/qat/qat_common/qat_algs.c b/drivers/crypto/qat/qat_common/qat_algs.c
index f998ed58457c..873533dc43a7 100644
--- a/drivers/crypto/qat/qat_common/qat_algs.c
+++ b/drivers/crypto/qat/qat_common/qat_algs.c
@@ -17,7 +17,7 @@
 #include <crypto/xts.h>
 #include <linux/dma-mapping.h>
 #include "adf_accel_devices.h"
-#include "adf_transport.h"
+#include "qat_algs_send.h"
 #include "adf_common_drv.h"
 #include "qat_crypto.h"
 #include "icp_qat_hw.h"
@@ -46,19 +46,6 @@
 static DEFINE_MUTEX(algs_lock);
 static unsigned int active_devs;
 
-struct qat_alg_buf {
-	u32 len;
-	u32 resrvd;
-	u64 addr;
-} __packed;
-
-struct qat_alg_buf_list {
-	u64 resrvd;
-	u32 num_bufs;
-	u32 num_mapped_bufs;
-	struct qat_alg_buf bufers[];
-} __packed __aligned(64);
-
 /* Common content descriptor */
 struct qat_alg_cd {
 	union {
@@ -693,7 +680,10 @@ static void qat_alg_free_bufl(struct qat_crypto_instance *inst,
 				 bl->bufers[i].len, DMA_BIDIRECTIONAL);
 
 	dma_unmap_single(dev, blp, sz, DMA_TO_DEVICE);
-	kfree(bl);
+
+	if (!qat_req->buf.sgl_src_valid)
+		kfree(bl);
+
 	if (blp != blpout) {
 		/* If out of place operation dma unmap only data */
 		int bufless = blout->num_bufs - blout->num_mapped_bufs;
@@ -704,7 +694,9 @@ static void qat_alg_free_bufl(struct qat_crypto_instance *inst,
 					 DMA_BIDIRECTIONAL);
 		}
 		dma_unmap_single(dev, blpout, sz_out, DMA_TO_DEVICE);
-		kfree(blout);
+
+		if (!qat_req->buf.sgl_dst_valid)
+			kfree(blout);
 	}
 }
 
@@ -721,15 +713,24 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst,
 	dma_addr_t blp = DMA_MAPPING_ERROR;
 	dma_addr_t bloutp = DMA_MAPPING_ERROR;
 	struct scatterlist *sg;
-	size_t sz_out, sz = struct_size(bufl, bufers, n + 1);
+	size_t sz_out, sz = struct_size(bufl, bufers, n);
+	int node = dev_to_node(&GET_DEV(inst->accel_dev));
 
 	if (unlikely(!n))
 		return -EINVAL;
 
-	bufl = kzalloc_node(sz, GFP_ATOMIC,
-			    dev_to_node(&GET_DEV(inst->accel_dev)));
-	if (unlikely(!bufl))
-		return -ENOMEM;
+	qat_req->buf.sgl_src_valid = false;
+	qat_req->buf.sgl_dst_valid = false;
+
+	if (n > QAT_MAX_BUFF_DESC) {
+		bufl = kzalloc_node(sz, GFP_ATOMIC, node);
+		if (unlikely(!bufl))
+			return -ENOMEM;
+	} else {
+		bufl = &qat_req->buf.sgl_src.sgl_hdr;
+		memset(bufl, 0, sizeof(struct qat_alg_buf_list));
+		qat_req->buf.sgl_src_valid = true;
+	}
 
 	for_each_sg(sgl, sg, n, i)
 		bufl->bufers[i].addr = DMA_MAPPING_ERROR;
@@ -760,12 +761,18 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst,
 		struct qat_alg_buf *bufers;
 
 		n = sg_nents(sglout);
-		sz_out = struct_size(buflout, bufers, n + 1);
+		sz_out = struct_size(buflout, bufers, n);
 		sg_nctr = 0;
-		buflout = kzalloc_node(sz_out, GFP_ATOMIC,
-				       dev_to_node(&GET_DEV(inst->accel_dev)));
-		if (unlikely(!buflout))
-			goto err_in;
+
+		if (n > QAT_MAX_BUFF_DESC) {
+			buflout = kzalloc_node(sz_out, GFP_ATOMIC, node);
+			if (unlikely(!buflout))
+				goto err_in;
+		} else {
+			buflout = &qat_req->buf.sgl_dst.sgl_hdr;
+			memset(buflout, 0, sizeof(struct qat_alg_buf_list));
+			qat_req->buf.sgl_dst_valid = true;
+		}
 
 		bufers = buflout->bufers;
 		for_each_sg(sglout, sg, n, i)
@@ -810,7 +817,9 @@ err_out:
 			dma_unmap_single(dev, buflout->bufers[i].addr,
 					 buflout->bufers[i].len,
 					 DMA_BIDIRECTIONAL);
-	kfree(buflout);
+
+	if (!qat_req->buf.sgl_dst_valid)
+		kfree(buflout);
 
 err_in:
 	if (!dma_mapping_error(dev, blp))
@@ -823,7 +832,8 @@ err_in:
 					 bufl->bufers[i].len,
 					 DMA_BIDIRECTIONAL);
 
-	kfree(bufl);
+	if (!qat_req->buf.sgl_src_valid)
+		kfree(bufl);
 
 	dev_err(dev, "Failed to map buf for dma\n");
 	return -ENOMEM;
@@ -925,8 +935,25 @@ void qat_alg_callback(void *resp)
 	struct icp_qat_fw_la_resp *qat_resp = resp;
 	struct qat_crypto_request *qat_req =
 				(void *)(__force long)qat_resp->opaque_data;
+	struct qat_instance_backlog *backlog = qat_req->alg_req.backlog;
 
 	qat_req->cb(qat_resp, qat_req);
+
+	qat_alg_send_backlog(backlog);
+}
+
+static int qat_alg_send_sym_message(struct qat_crypto_request *qat_req,
+				    struct qat_crypto_instance *inst,
+				    struct crypto_async_request *base)
+{
+	struct qat_alg_req *alg_req = &qat_req->alg_req;
+
+	alg_req->fw_req = (u32 *)&qat_req->req;
+	alg_req->tx_ring = inst->sym_tx;
+	alg_req->base = base;
+	alg_req->backlog = &inst->backlog;
+
+	return qat_alg_send_message(alg_req);
 }
 
 static int qat_alg_aead_dec(struct aead_request *areq)
@@ -939,7 +966,7 @@ static int qat_alg_aead_dec(struct aead_request *areq)
 	struct icp_qat_fw_la_auth_req_params *auth_param;
 	struct icp_qat_fw_la_bulk_req *msg;
 	int digst_size = crypto_aead_authsize(aead_tfm);
-	int ret, ctr = 0;
+	int ret;
 	u32 cipher_len;
 
 	cipher_len = areq->cryptlen - digst_size;
@@ -965,15 +992,12 @@ static int qat_alg_aead_dec(struct aead_request *areq)
 	auth_param = (void *)((u8 *)cipher_param + sizeof(*cipher_param));
 	auth_param->auth_off = 0;
 	auth_param->auth_len = areq->assoclen + cipher_param->cipher_length;
-	do {
-		ret = adf_send_message(ctx->inst->sym_tx, (u32 *)msg);
-	} while (ret == -EAGAIN && ctr++ < 10);
 
-	if (ret == -EAGAIN) {
+	ret = qat_alg_send_sym_message(qat_req, ctx->inst, &areq->base);
+	if (ret == -ENOSPC)
 		qat_alg_free_bufl(ctx->inst, qat_req);
-		return -EBUSY;
-	}
-	return -EINPROGRESS;
+
+	return ret;
 }
 
 static int qat_alg_aead_enc(struct aead_request *areq)
@@ -986,7 +1010,7 @@ static int qat_alg_aead_enc(struct aead_request *areq)
 	struct icp_qat_fw_la_auth_req_params *auth_param;
 	struct icp_qat_fw_la_bulk_req *msg;
 	u8 *iv = areq->iv;
-	int ret, ctr = 0;
+	int ret;
 
 	if (areq->cryptlen % AES_BLOCK_SIZE != 0)
 		return -EINVAL;
@@ -1013,15 +1037,11 @@ static int qat_alg_aead_enc(struct aead_request *areq)
 	auth_param->auth_off = 0;
 	auth_param->auth_len = areq->assoclen + areq->cryptlen;
 
-	do {
-		ret = adf_send_message(ctx->inst->sym_tx, (u32 *)msg);
-	} while (ret == -EAGAIN && ctr++ < 10);
-
-	if (ret == -EAGAIN) {
+	ret = qat_alg_send_sym_message(qat_req, ctx->inst, &areq->base);
+	if (ret == -ENOSPC)
 		qat_alg_free_bufl(ctx->inst, qat_req);
-		return -EBUSY;
-	}
-	return -EINPROGRESS;
+
+	return ret;
 }
 
 static int qat_alg_skcipher_rekey(struct qat_alg_skcipher_ctx *ctx,
@@ -1174,7 +1194,7 @@ static int qat_alg_skcipher_encrypt(struct skcipher_request *req)
 	struct qat_crypto_request *qat_req = skcipher_request_ctx(req);
 	struct icp_qat_fw_la_cipher_req_params *cipher_param;
 	struct icp_qat_fw_la_bulk_req *msg;
-	int ret, ctr = 0;
+	int ret;
 
 	if (req->cryptlen == 0)
 		return 0;
@@ -1198,15 +1218,11 @@ static int qat_alg_skcipher_encrypt(struct skcipher_request *req)
 
 	qat_alg_set_req_iv(qat_req);
 
-	do {
-		ret = adf_send_message(ctx->inst->sym_tx, (u32 *)msg);
-	} while (ret == -EAGAIN && ctr++ < 10);
-
-	if (ret == -EAGAIN) {
+	ret = qat_alg_send_sym_message(qat_req, ctx->inst, &req->base);
+	if (ret == -ENOSPC)
 		qat_alg_free_bufl(ctx->inst, qat_req);
-		return -EBUSY;
-	}
-	return -EINPROGRESS;
+
+	return ret;
 }
 
 static int qat_alg_skcipher_blk_encrypt(struct skcipher_request *req)
@@ -1243,7 +1259,7 @@ static int qat_alg_skcipher_decrypt(struct skcipher_request *req)
 	struct qat_crypto_request *qat_req = skcipher_request_ctx(req);
 	struct icp_qat_fw_la_cipher_req_params *cipher_param;
 	struct icp_qat_fw_la_bulk_req *msg;
-	int ret, ctr = 0;
+	int ret;
 
 	if (req->cryptlen == 0)
 		return 0;
@@ -1268,15 +1284,11 @@ static int qat_alg_skcipher_decrypt(struct skcipher_request *req)
 	qat_alg_set_req_iv(qat_req);
 	qat_alg_update_iv(qat_req);
 
-	do {
-		ret = adf_send_message(ctx->inst->sym_tx, (u32 *)msg);
-	} while (ret == -EAGAIN && ctr++ < 10);
-
-	if (ret == -EAGAIN) {
+	ret = qat_alg_send_sym_message(qat_req, ctx->inst, &req->base);
+	if (ret == -ENOSPC)
 		qat_alg_free_bufl(ctx->inst, qat_req);
-		return -EBUSY;
-	}
-	return -EINPROGRESS;
+
+	return ret;
 }
 
 static int qat_alg_skcipher_blk_decrypt(struct skcipher_request *req)
diff --git a/drivers/crypto/qat/qat_common/qat_algs_send.c b/drivers/crypto/qat/qat_common/qat_algs_send.c
new file mode 100644
index 000000000000..ff5b4347f783
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/qat_algs_send.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: (BSD-3-Clause OR GPL-2.0-only)
+/* Copyright(c) 2022 Intel Corporation */
+#include "adf_transport.h"
+#include "qat_algs_send.h"
+#include "qat_crypto.h"
+
+#define ADF_MAX_RETRIES		20
+
+static int qat_alg_send_message_retry(struct qat_alg_req *req)
+{
+	int ret = 0, ctr = 0;
+
+	do {
+		ret = adf_send_message(req->tx_ring, req->fw_req);
+	} while (ret == -EAGAIN && ctr++ < ADF_MAX_RETRIES);
+
+	if (ret == -EAGAIN)
+		return -ENOSPC;
+
+	return -EINPROGRESS;
+}
+
+void qat_alg_send_backlog(struct qat_instance_backlog *backlog)
+{
+	struct qat_alg_req *req, *tmp;
+
+	spin_lock_bh(&backlog->lock);
+	list_for_each_entry_safe(req, tmp, &backlog->list, list) {
+		if (adf_send_message(req->tx_ring, req->fw_req)) {
+			/* The HW ring is full. Do nothing.
+			 * qat_alg_send_backlog() will be invoked again by
+			 * another callback.
+			 */
+			break;
+		}
+		list_del(&req->list);
+		req->base->complete(req->base, -EINPROGRESS);
+	}
+	spin_unlock_bh(&backlog->lock);
+}
+
+static void qat_alg_backlog_req(struct qat_alg_req *req,
+				struct qat_instance_backlog *backlog)
+{
+	INIT_LIST_HEAD(&req->list);
+
+	spin_lock_bh(&backlog->lock);
+	list_add_tail(&req->list, &backlog->list);
+	spin_unlock_bh(&backlog->lock);
+}
+
+static int qat_alg_send_message_maybacklog(struct qat_alg_req *req)
+{
+	struct qat_instance_backlog *backlog = req->backlog;
+	struct adf_etr_ring_data *tx_ring = req->tx_ring;
+	u32 *fw_req = req->fw_req;
+
+	/* If any request is already backlogged, then add to backlog list */
+	if (!list_empty(&backlog->list))
+		goto enqueue;
+
+	/* If ring is nearly full, then add to backlog list */
+	if (adf_ring_nearly_full(tx_ring))
+		goto enqueue;
+
+	/* If adding request to HW ring fails, then add to backlog list */
+	if (adf_send_message(tx_ring, fw_req))
+		goto enqueue;
+
+	return -EINPROGRESS;
+
+enqueue:
+	qat_alg_backlog_req(req, backlog);
+
+	return -EBUSY;
+}
+
+int qat_alg_send_message(struct qat_alg_req *req)
+{
+	u32 flags = req->base->flags;
+
+	if (flags & CRYPTO_TFM_REQ_MAY_BACKLOG)
+		return qat_alg_send_message_maybacklog(req);
+	else
+		return qat_alg_send_message_retry(req);
+}
diff --git a/drivers/crypto/qat/qat_common/qat_algs_send.h b/drivers/crypto/qat/qat_common/qat_algs_send.h
new file mode 100644
index 000000000000..5ce9f4f69d8f
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/qat_algs_send.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: (BSD-3-Clause OR GPL-2.0-only) */
+/* Copyright(c) 2022 Intel Corporation */
+#ifndef QAT_ALGS_SEND_H
+#define QAT_ALGS_SEND_H
+
+#include "qat_crypto.h"
+
+int qat_alg_send_message(struct qat_alg_req *req);
+void qat_alg_send_backlog(struct qat_instance_backlog *backlog);
+
+#endif
diff --git a/drivers/crypto/qat/qat_common/qat_asym_algs.c b/drivers/crypto/qat/qat_common/qat_asym_algs.c
index b0b78445418b..7173a2a0a484 100644
--- a/drivers/crypto/qat/qat_common/qat_asym_algs.c
+++ b/drivers/crypto/qat/qat_common/qat_asym_algs.c
@@ -12,6 +12,7 @@
 #include <crypto/scatterwalk.h>
 #include "icp_qat_fw_pke.h"
 #include "adf_accel_devices.h"
+#include "qat_algs_send.h"
 #include "adf_transport.h"
 #include "adf_common_drv.h"
 #include "qat_crypto.h"
@@ -135,8 +136,23 @@ struct qat_asym_request {
 	} areq;
 	int err;
 	void (*cb)(struct icp_qat_fw_pke_resp *resp);
+	struct qat_alg_req alg_req;
 } __aligned(64);
 
+static int qat_alg_send_asym_message(struct qat_asym_request *qat_req,
+				     struct qat_crypto_instance *inst,
+				     struct crypto_async_request *base)
+{
+	struct qat_alg_req *alg_req = &qat_req->alg_req;
+
+	alg_req->fw_req = (u32 *)&qat_req->req;
+	alg_req->tx_ring = inst->pke_tx;
+	alg_req->base = base;
+	alg_req->backlog = &inst->backlog;
+
+	return qat_alg_send_message(alg_req);
+}
+
 static void qat_dh_cb(struct icp_qat_fw_pke_resp *resp)
 {
 	struct qat_asym_request *req = (void *)(__force long)resp->opaque;
@@ -148,26 +164,21 @@ static void qat_dh_cb(struct icp_qat_fw_pke_resp *resp)
 	err = (err == ICP_QAT_FW_COMN_STATUS_FLAG_OK) ? 0 : -EINVAL;
 
 	if (areq->src) {
-		if (req->src_align)
-			dma_free_coherent(dev, req->ctx.dh->p_size,
-					  req->src_align, req->in.dh.in.b);
-		else
-			dma_unmap_single(dev, req->in.dh.in.b,
-					 req->ctx.dh->p_size, DMA_TO_DEVICE);
+		dma_unmap_single(dev, req->in.dh.in.b, req->ctx.dh->p_size,
+				 DMA_TO_DEVICE);
+		kfree_sensitive(req->src_align);
 	}
 
 	areq->dst_len = req->ctx.dh->p_size;
 	if (req->dst_align) {
 		scatterwalk_map_and_copy(req->dst_align, areq->dst, 0,
 					 areq->dst_len, 1);
-
-		dma_free_coherent(dev, req->ctx.dh->p_size, req->dst_align,
-				  req->out.dh.r);
-	} else {
-		dma_unmap_single(dev, req->out.dh.r, req->ctx.dh->p_size,
-				 DMA_FROM_DEVICE);
+		kfree_sensitive(req->dst_align);
 	}
 
+	dma_unmap_single(dev, req->out.dh.r, req->ctx.dh->p_size,
+			 DMA_FROM_DEVICE);
+
 	dma_unmap_single(dev, req->phy_in, sizeof(struct qat_dh_input_params),
 			 DMA_TO_DEVICE);
 	dma_unmap_single(dev, req->phy_out,
@@ -213,8 +224,9 @@ static int qat_dh_compute_value(struct kpp_request *req)
 	struct qat_asym_request *qat_req =
 			PTR_ALIGN(kpp_request_ctx(req), 64);
 	struct icp_qat_fw_pke_request *msg = &qat_req->req;
-	int ret, ctr = 0;
+	int ret;
 	int n_input_params = 0;
+	u8 *vaddr;
 
 	if (unlikely(!ctx->xa))
 		return -EINVAL;
@@ -223,6 +235,10 @@ static int qat_dh_compute_value(struct kpp_request *req)
 		req->dst_len = ctx->p_size;
 		return -EOVERFLOW;
 	}
+
+	if (req->src_len > ctx->p_size)
+		return -EINVAL;
+
 	memset(msg, '\0', sizeof(*msg));
 	ICP_QAT_FW_PKE_HDR_VALID_FLAG_SET(msg->pke_hdr,
 					  ICP_QAT_FW_COMN_REQ_FLAG_SET);
@@ -271,27 +287,24 @@ static int qat_dh_compute_value(struct kpp_request *req)
 		 */
 		if (sg_is_last(req->src) && req->src_len == ctx->p_size) {
 			qat_req->src_align = NULL;
-			qat_req->in.dh.in.b = dma_map_single(dev,
-							     sg_virt(req->src),
-							     req->src_len,
-							     DMA_TO_DEVICE);
-			if (unlikely(dma_mapping_error(dev,
-						       qat_req->in.dh.in.b)))
-				return ret;
-
+			vaddr = sg_virt(req->src);
 		} else {
 			int shift = ctx->p_size - req->src_len;
 
-			qat_req->src_align = dma_alloc_coherent(dev,
-								ctx->p_size,
-								&qat_req->in.dh.in.b,
-								GFP_KERNEL);
+			qat_req->src_align = kzalloc(ctx->p_size, GFP_KERNEL);
 			if (unlikely(!qat_req->src_align))
 				return ret;
 
 			scatterwalk_map_and_copy(qat_req->src_align + shift,
 						 req->src, 0, req->src_len, 0);
+
+			vaddr = qat_req->src_align;
 		}
+
+		qat_req->in.dh.in.b = dma_map_single(dev, vaddr, ctx->p_size,
+						     DMA_TO_DEVICE);
+		if (unlikely(dma_mapping_error(dev, qat_req->in.dh.in.b)))
+			goto unmap_src;
 	}
 	/*
 	 * dst can be of any size in valid range, but HW expects it to be the
@@ -302,20 +315,18 @@ static int qat_dh_compute_value(struct kpp_request *req)
 	 */
 	if (sg_is_last(req->dst) && req->dst_len == ctx->p_size) {
 		qat_req->dst_align = NULL;
-		qat_req->out.dh.r = dma_map_single(dev, sg_virt(req->dst),
-						   req->dst_len,
-						   DMA_FROM_DEVICE);
-
-		if (unlikely(dma_mapping_error(dev, qat_req->out.dh.r)))
-			goto unmap_src;
-
+		vaddr = sg_virt(req->dst);
 	} else {
-		qat_req->dst_align = dma_alloc_coherent(dev, ctx->p_size,
-							&qat_req->out.dh.r,
-							GFP_KERNEL);
+		qat_req->dst_align = kzalloc(ctx->p_size, GFP_KERNEL);
 		if (unlikely(!qat_req->dst_align))
 			goto unmap_src;
+
+		vaddr = qat_req->dst_align;
 	}
+	qat_req->out.dh.r = dma_map_single(dev, vaddr, ctx->p_size,
+					   DMA_FROM_DEVICE);
+	if (unlikely(dma_mapping_error(dev, qat_req->out.dh.r)))
+		goto unmap_dst;
 
 	qat_req->in.dh.in_tab[n_input_params] = 0;
 	qat_req->out.dh.out_tab[1] = 0;
@@ -338,13 +349,13 @@ static int qat_dh_compute_value(struct kpp_request *req)
 	msg->input_param_count = n_input_params;
 	msg->output_param_count = 1;
 
-	do {
-		ret = adf_send_message(ctx->inst->pke_tx, (u32 *)msg);
-	} while (ret == -EBUSY && ctr++ < 100);
+	ret = qat_alg_send_asym_message(qat_req, inst, &req->base);
+	if (ret == -ENOSPC)
+		goto unmap_all;
 
-	if (!ret)
-		return -EINPROGRESS;
+	return ret;
 
+unmap_all:
 	if (!dma_mapping_error(dev, qat_req->phy_out))
 		dma_unmap_single(dev, qat_req->phy_out,
 				 sizeof(struct qat_dh_output_params),
@@ -355,23 +366,17 @@ unmap_in_params:
 				 sizeof(struct qat_dh_input_params),
 				 DMA_TO_DEVICE);
 unmap_dst:
-	if (qat_req->dst_align)
-		dma_free_coherent(dev, ctx->p_size, qat_req->dst_align,
-				  qat_req->out.dh.r);
-	else
-		if (!dma_mapping_error(dev, qat_req->out.dh.r))
-			dma_unmap_single(dev, qat_req->out.dh.r, ctx->p_size,
-					 DMA_FROM_DEVICE);
+	if (!dma_mapping_error(dev, qat_req->out.dh.r))
+		dma_unmap_single(dev, qat_req->out.dh.r, ctx->p_size,
+				 DMA_FROM_DEVICE);
+	kfree_sensitive(qat_req->dst_align);
 unmap_src:
 	if (req->src) {
-		if (qat_req->src_align)
-			dma_free_coherent(dev, ctx->p_size, qat_req->src_align,
-					  qat_req->in.dh.in.b);
-		else
-			if (!dma_mapping_error(dev, qat_req->in.dh.in.b))
-				dma_unmap_single(dev, qat_req->in.dh.in.b,
-						 ctx->p_size,
-						 DMA_TO_DEVICE);
+		if (!dma_mapping_error(dev, qat_req->in.dh.in.b))
+			dma_unmap_single(dev, qat_req->in.dh.in.b,
+					 ctx->p_size,
+					 DMA_TO_DEVICE);
+		kfree_sensitive(qat_req->src_align);
 	}
 	return ret;
 }
@@ -420,14 +425,17 @@ static int qat_dh_set_params(struct qat_dh_ctx *ctx, struct dh *params)
 static void qat_dh_clear_ctx(struct device *dev, struct qat_dh_ctx *ctx)
 {
 	if (ctx->g) {
+		memset(ctx->g, 0, ctx->p_size);
 		dma_free_coherent(dev, ctx->p_size, ctx->g, ctx->dma_g);
 		ctx->g = NULL;
 	}
 	if (ctx->xa) {
+		memset(ctx->xa, 0, ctx->p_size);
 		dma_free_coherent(dev, ctx->p_size, ctx->xa, ctx->dma_xa);
 		ctx->xa = NULL;
 	}
 	if (ctx->p) {
+		memset(ctx->p, 0, ctx->p_size);
 		dma_free_coherent(dev, ctx->p_size, ctx->p, ctx->dma_p);
 		ctx->p = NULL;
 	}
@@ -510,25 +518,22 @@ static void qat_rsa_cb(struct icp_qat_fw_pke_resp *resp)
 
 	err = (err == ICP_QAT_FW_COMN_STATUS_FLAG_OK) ? 0 : -EINVAL;
 
-	if (req->src_align)
-		dma_free_coherent(dev, req->ctx.rsa->key_sz, req->src_align,
-				  req->in.rsa.enc.m);
-	else
-		dma_unmap_single(dev, req->in.rsa.enc.m, req->ctx.rsa->key_sz,
-				 DMA_TO_DEVICE);
+	kfree_sensitive(req->src_align);
+
+	dma_unmap_single(dev, req->in.rsa.enc.m, req->ctx.rsa->key_sz,
+			 DMA_TO_DEVICE);
 
 	areq->dst_len = req->ctx.rsa->key_sz;
 	if (req->dst_align) {
 		scatterwalk_map_and_copy(req->dst_align, areq->dst, 0,
 					 areq->dst_len, 1);
 
-		dma_free_coherent(dev, req->ctx.rsa->key_sz, req->dst_align,
-				  req->out.rsa.enc.c);
-	} else {
-		dma_unmap_single(dev, req->out.rsa.enc.c, req->ctx.rsa->key_sz,
-				 DMA_FROM_DEVICE);
+		kfree_sensitive(req->dst_align);
 	}
 
+	dma_unmap_single(dev, req->out.rsa.enc.c, req->ctx.rsa->key_sz,
+			 DMA_FROM_DEVICE);
+
 	dma_unmap_single(dev, req->phy_in, sizeof(struct qat_rsa_input_params),
 			 DMA_TO_DEVICE);
 	dma_unmap_single(dev, req->phy_out,
@@ -542,8 +547,11 @@ void qat_alg_asym_callback(void *_resp)
 {
 	struct icp_qat_fw_pke_resp *resp = _resp;
 	struct qat_asym_request *areq = (void *)(__force long)resp->opaque;
+	struct qat_instance_backlog *backlog = areq->alg_req.backlog;
 
 	areq->cb(resp);
+
+	qat_alg_send_backlog(backlog);
 }
 
 #define PKE_RSA_EP_512 0x1c161b21
@@ -642,7 +650,8 @@ static int qat_rsa_enc(struct akcipher_request *req)
 	struct qat_asym_request *qat_req =
 			PTR_ALIGN(akcipher_request_ctx(req), 64);
 	struct icp_qat_fw_pke_request *msg = &qat_req->req;
-	int ret, ctr = 0;
+	u8 *vaddr;
+	int ret;
 
 	if (unlikely(!ctx->n || !ctx->e))
 		return -EINVAL;
@@ -651,6 +660,10 @@ static int qat_rsa_enc(struct akcipher_request *req)
 		req->dst_len = ctx->key_sz;
 		return -EOVERFLOW;
 	}
+
+	if (req->src_len > ctx->key_sz)
+		return -EINVAL;
+
 	memset(msg, '\0', sizeof(*msg));
 	ICP_QAT_FW_PKE_HDR_VALID_FLAG_SET(msg->pke_hdr,
 					  ICP_QAT_FW_COMN_REQ_FLAG_SET);
@@ -679,40 +692,39 @@ static int qat_rsa_enc(struct akcipher_request *req)
 	 */
 	if (sg_is_last(req->src) && req->src_len == ctx->key_sz) {
 		qat_req->src_align = NULL;
-		qat_req->in.rsa.enc.m = dma_map_single(dev, sg_virt(req->src),
-						   req->src_len, DMA_TO_DEVICE);
-		if (unlikely(dma_mapping_error(dev, qat_req->in.rsa.enc.m)))
-			return ret;
-
+		vaddr = sg_virt(req->src);
 	} else {
 		int shift = ctx->key_sz - req->src_len;
 
-		qat_req->src_align = dma_alloc_coherent(dev, ctx->key_sz,
-							&qat_req->in.rsa.enc.m,
-							GFP_KERNEL);
+		qat_req->src_align = kzalloc(ctx->key_sz, GFP_KERNEL);
 		if (unlikely(!qat_req->src_align))
 			return ret;
 
 		scatterwalk_map_and_copy(qat_req->src_align + shift, req->src,
 					 0, req->src_len, 0);
+		vaddr = qat_req->src_align;
 	}
-	if (sg_is_last(req->dst) && req->dst_len == ctx->key_sz) {
-		qat_req->dst_align = NULL;
-		qat_req->out.rsa.enc.c = dma_map_single(dev, sg_virt(req->dst),
-							req->dst_len,
-							DMA_FROM_DEVICE);
 
-		if (unlikely(dma_mapping_error(dev, qat_req->out.rsa.enc.c)))
-			goto unmap_src;
+	qat_req->in.rsa.enc.m = dma_map_single(dev, vaddr, ctx->key_sz,
+					       DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(dev, qat_req->in.rsa.enc.m)))
+		goto unmap_src;
 
+	if (sg_is_last(req->dst) && req->dst_len == ctx->key_sz) {
+		qat_req->dst_align = NULL;
+		vaddr = sg_virt(req->dst);
 	} else {
-		qat_req->dst_align = dma_alloc_coherent(dev, ctx->key_sz,
-							&qat_req->out.rsa.enc.c,
-							GFP_KERNEL);
+		qat_req->dst_align = kzalloc(ctx->key_sz, GFP_KERNEL);
 		if (unlikely(!qat_req->dst_align))
 			goto unmap_src;
-
+		vaddr = qat_req->dst_align;
 	}
+
+	qat_req->out.rsa.enc.c = dma_map_single(dev, vaddr, ctx->key_sz,
+						DMA_FROM_DEVICE);
+	if (unlikely(dma_mapping_error(dev, qat_req->out.rsa.enc.c)))
+		goto unmap_dst;
+
 	qat_req->in.rsa.in_tab[3] = 0;
 	qat_req->out.rsa.out_tab[1] = 0;
 	qat_req->phy_in = dma_map_single(dev, &qat_req->in.rsa.enc.m,
@@ -732,13 +744,14 @@ static int qat_rsa_enc(struct akcipher_request *req)
 	msg->pke_mid.opaque = (u64)(__force long)qat_req;
 	msg->input_param_count = 3;
 	msg->output_param_count = 1;
-	do {
-		ret = adf_send_message(ctx->inst->pke_tx, (u32 *)msg);
-	} while (ret == -EBUSY && ctr++ < 100);
 
-	if (!ret)
-		return -EINPROGRESS;
+	ret = qat_alg_send_asym_message(qat_req, inst, &req->base);
+	if (ret == -ENOSPC)
+		goto unmap_all;
 
+	return ret;
+
+unmap_all:
 	if (!dma_mapping_error(dev, qat_req->phy_out))
 		dma_unmap_single(dev, qat_req->phy_out,
 				 sizeof(struct qat_rsa_output_params),
@@ -749,21 +762,15 @@ unmap_in_params:
 				 sizeof(struct qat_rsa_input_params),
 				 DMA_TO_DEVICE);
 unmap_dst:
-	if (qat_req->dst_align)
-		dma_free_coherent(dev, ctx->key_sz, qat_req->dst_align,
-				  qat_req->out.rsa.enc.c);
-	else
-		if (!dma_mapping_error(dev, qat_req->out.rsa.enc.c))
-			dma_unmap_single(dev, qat_req->out.rsa.enc.c,
-					 ctx->key_sz, DMA_FROM_DEVICE);
+	if (!dma_mapping_error(dev, qat_req->out.rsa.enc.c))
+		dma_unmap_single(dev, qat_req->out.rsa.enc.c,
+				 ctx->key_sz, DMA_FROM_DEVICE);
+	kfree_sensitive(qat_req->dst_align);
 unmap_src:
-	if (qat_req->src_align)
-		dma_free_coherent(dev, ctx->key_sz, qat_req->src_align,
-				  qat_req->in.rsa.enc.m);
-	else
-		if (!dma_mapping_error(dev, qat_req->in.rsa.enc.m))
-			dma_unmap_single(dev, qat_req->in.rsa.enc.m,
-					 ctx->key_sz, DMA_TO_DEVICE);
+	if (!dma_mapping_error(dev, qat_req->in.rsa.enc.m))
+		dma_unmap_single(dev, qat_req->in.rsa.enc.m, ctx->key_sz,
+				 DMA_TO_DEVICE);
+	kfree_sensitive(qat_req->src_align);
 	return ret;
 }
 
@@ -776,7 +783,8 @@ static int qat_rsa_dec(struct akcipher_request *req)
 	struct qat_asym_request *qat_req =
 			PTR_ALIGN(akcipher_request_ctx(req), 64);
 	struct icp_qat_fw_pke_request *msg = &qat_req->req;
-	int ret, ctr = 0;
+	u8 *vaddr;
+	int ret;
 
 	if (unlikely(!ctx->n || !ctx->d))
 		return -EINVAL;
@@ -785,6 +793,10 @@ static int qat_rsa_dec(struct akcipher_request *req)
 		req->dst_len = ctx->key_sz;
 		return -EOVERFLOW;
 	}
+
+	if (req->src_len > ctx->key_sz)
+		return -EINVAL;
+
 	memset(msg, '\0', sizeof(*msg));
 	ICP_QAT_FW_PKE_HDR_VALID_FLAG_SET(msg->pke_hdr,
 					  ICP_QAT_FW_COMN_REQ_FLAG_SET);
@@ -823,40 +835,37 @@ static int qat_rsa_dec(struct akcipher_request *req)
 	 */
 	if (sg_is_last(req->src) && req->src_len == ctx->key_sz) {
 		qat_req->src_align = NULL;
-		qat_req->in.rsa.dec.c = dma_map_single(dev, sg_virt(req->src),
-						   req->dst_len, DMA_TO_DEVICE);
-		if (unlikely(dma_mapping_error(dev, qat_req->in.rsa.dec.c)))
-			return ret;
-
+		vaddr = sg_virt(req->src);
 	} else {
 		int shift = ctx->key_sz - req->src_len;
 
-		qat_req->src_align = dma_alloc_coherent(dev, ctx->key_sz,
-							&qat_req->in.rsa.dec.c,
-							GFP_KERNEL);
+		qat_req->src_align = kzalloc(ctx->key_sz, GFP_KERNEL);
 		if (unlikely(!qat_req->src_align))
 			return ret;
 
 		scatterwalk_map_and_copy(qat_req->src_align + shift, req->src,
 					 0, req->src_len, 0);
+		vaddr = qat_req->src_align;
 	}
-	if (sg_is_last(req->dst) && req->dst_len == ctx->key_sz) {
-		qat_req->dst_align = NULL;
-		qat_req->out.rsa.dec.m = dma_map_single(dev, sg_virt(req->dst),
-						    req->dst_len,
-						    DMA_FROM_DEVICE);
 
-		if (unlikely(dma_mapping_error(dev, qat_req->out.rsa.dec.m)))
-			goto unmap_src;
+	qat_req->in.rsa.dec.c = dma_map_single(dev, vaddr, ctx->key_sz,
+					       DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(dev, qat_req->in.rsa.dec.c)))
+		goto unmap_src;
 
+	if (sg_is_last(req->dst) && req->dst_len == ctx->key_sz) {
+		qat_req->dst_align = NULL;
+		vaddr = sg_virt(req->dst);
 	} else {
-		qat_req->dst_align = dma_alloc_coherent(dev, ctx->key_sz,
-							&qat_req->out.rsa.dec.m,
-							GFP_KERNEL);
+		qat_req->dst_align = kzalloc(ctx->key_sz, GFP_KERNEL);
 		if (unlikely(!qat_req->dst_align))
 			goto unmap_src;
-
+		vaddr = qat_req->dst_align;
 	}
+	qat_req->out.rsa.dec.m = dma_map_single(dev, vaddr, ctx->key_sz,
+						DMA_FROM_DEVICE);
+	if (unlikely(dma_mapping_error(dev, qat_req->out.rsa.dec.m)))
+		goto unmap_dst;
 
 	if (ctx->crt_mode)
 		qat_req->in.rsa.in_tab[6] = 0;
@@ -884,13 +893,14 @@ static int qat_rsa_dec(struct akcipher_request *req)
 		msg->input_param_count = 3;
 
 	msg->output_param_count = 1;
-	do {
-		ret = adf_send_message(ctx->inst->pke_tx, (u32 *)msg);
-	} while (ret == -EBUSY && ctr++ < 100);
 
-	if (!ret)
-		return -EINPROGRESS;
+	ret = qat_alg_send_asym_message(qat_req, inst, &req->base);
+	if (ret == -ENOSPC)
+		goto unmap_all;
+
+	return ret;
 
+unmap_all:
 	if (!dma_mapping_error(dev, qat_req->phy_out))
 		dma_unmap_single(dev, qat_req->phy_out,
 				 sizeof(struct qat_rsa_output_params),
@@ -901,21 +911,15 @@ unmap_in_params:
 				 sizeof(struct qat_rsa_input_params),
 				 DMA_TO_DEVICE);
 unmap_dst:
-	if (qat_req->dst_align)
-		dma_free_coherent(dev, ctx->key_sz, qat_req->dst_align,
-				  qat_req->out.rsa.dec.m);
-	else
-		if (!dma_mapping_error(dev, qat_req->out.rsa.dec.m))
-			dma_unmap_single(dev, qat_req->out.rsa.dec.m,
-					 ctx->key_sz, DMA_FROM_DEVICE);
+	if (!dma_mapping_error(dev, qat_req->out.rsa.dec.m))
+		dma_unmap_single(dev, qat_req->out.rsa.dec.m,
+				 ctx->key_sz, DMA_FROM_DEVICE);
+	kfree_sensitive(qat_req->dst_align);
 unmap_src:
-	if (qat_req->src_align)
-		dma_free_coherent(dev, ctx->key_sz, qat_req->src_align,
-				  qat_req->in.rsa.dec.c);
-	else
-		if (!dma_mapping_error(dev, qat_req->in.rsa.dec.c))
-			dma_unmap_single(dev, qat_req->in.rsa.dec.c,
-					 ctx->key_sz, DMA_TO_DEVICE);
+	if (!dma_mapping_error(dev, qat_req->in.rsa.dec.c))
+		dma_unmap_single(dev, qat_req->in.rsa.dec.c, ctx->key_sz,
+				 DMA_TO_DEVICE);
+	kfree_sensitive(qat_req->src_align);
 	return ret;
 }
 
@@ -1233,18 +1237,8 @@ static void qat_rsa_exit_tfm(struct crypto_akcipher *tfm)
 	struct qat_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
 	struct device *dev = &GET_DEV(ctx->inst->accel_dev);
 
-	if (ctx->n)
-		dma_free_coherent(dev, ctx->key_sz, ctx->n, ctx->dma_n);
-	if (ctx->e)
-		dma_free_coherent(dev, ctx->key_sz, ctx->e, ctx->dma_e);
-	if (ctx->d) {
-		memset(ctx->d, '\0', ctx->key_sz);
-		dma_free_coherent(dev, ctx->key_sz, ctx->d, ctx->dma_d);
-	}
+	qat_rsa_clear_ctx(dev, ctx);
 	qat_crypto_put_instance(ctx->inst);
-	ctx->n = NULL;
-	ctx->e = NULL;
-	ctx->d = NULL;
 }
 
 static struct akcipher_alg rsa = {
diff --git a/drivers/crypto/qat/qat_common/qat_crypto.c b/drivers/crypto/qat/qat_common/qat_crypto.c
index 3efbb3883601..994e43fab0a4 100644
--- a/drivers/crypto/qat/qat_common/qat_crypto.c
+++ b/drivers/crypto/qat/qat_common/qat_crypto.c
@@ -136,13 +136,6 @@ int qat_crypto_dev_config(struct adf_accel_dev *accel_dev)
 	if (ret)
 		goto err;
 
-	/* Temporarily set the number of crypto instances to zero to avoid
-	 * registering the crypto algorithms.
-	 * This will be removed when the algorithms will support the
-	 * CRYPTO_TFM_REQ_MAY_BACKLOG flag
-	 */
-	instances = 0;
-
 	for (i = 0; i < instances; i++) {
 		val = i;
 		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_BANK_NUM, i);
@@ -328,6 +321,9 @@ static int qat_crypto_create_instances(struct adf_accel_dev *accel_dev)
 				      &inst->pke_rx);
 		if (ret)
 			goto err;
+
+		INIT_LIST_HEAD(&inst->backlog.list);
+		spin_lock_init(&inst->backlog.lock);
 	}
 	return 0;
 err:
diff --git a/drivers/crypto/qat/qat_common/qat_crypto.h b/drivers/crypto/qat/qat_common/qat_crypto.h
index b6a4c95ae003..245b6d9a3650 100644
--- a/drivers/crypto/qat/qat_common/qat_crypto.h
+++ b/drivers/crypto/qat/qat_common/qat_crypto.h
@@ -9,6 +9,19 @@
 #include "adf_accel_devices.h"
 #include "icp_qat_fw_la.h"
 
+struct qat_instance_backlog {
+	struct list_head list;
+	spinlock_t lock; /* protects backlog list */
+};
+
+struct qat_alg_req {
+	u32 *fw_req;
+	struct adf_etr_ring_data *tx_ring;
+	struct crypto_async_request *base;
+	struct list_head list;
+	struct qat_instance_backlog *backlog;
+};
+
 struct qat_crypto_instance {
 	struct adf_etr_ring_data *sym_tx;
 	struct adf_etr_ring_data *sym_rx;
@@ -19,8 +32,29 @@ struct qat_crypto_instance {
 	unsigned long state;
 	int id;
 	atomic_t refctr;
+	struct qat_instance_backlog backlog;
 };
 
+#define QAT_MAX_BUFF_DESC	4
+
+struct qat_alg_buf {
+	u32 len;
+	u32 resrvd;
+	u64 addr;
+} __packed;
+
+struct qat_alg_buf_list {
+	u64 resrvd;
+	u32 num_bufs;
+	u32 num_mapped_bufs;
+	struct qat_alg_buf bufers[];
+} __packed;
+
+struct qat_alg_fixed_buf_list {
+	struct qat_alg_buf_list sgl_hdr;
+	struct qat_alg_buf descriptors[QAT_MAX_BUFF_DESC];
+} __packed __aligned(64);
+
 struct qat_crypto_request_buffs {
 	struct qat_alg_buf_list *bl;
 	dma_addr_t blp;
@@ -28,6 +62,10 @@ struct qat_crypto_request_buffs {
 	dma_addr_t bloutp;
 	size_t sz;
 	size_t sz_out;
+	bool sgl_src_valid;
+	bool sgl_dst_valid;
+	struct qat_alg_fixed_buf_list sgl_src;
+	struct qat_alg_fixed_buf_list sgl_dst;
 };
 
 struct qat_crypto_request;
@@ -53,6 +91,7 @@ struct qat_crypto_request {
 		u8 iv[AES_BLOCK_SIZE];
 	};
 	bool encryption;
+	struct qat_alg_req alg_req;
 };
 
 static inline bool adf_hw_dev_has_crypto(struct adf_accel_dev *accel_dev)
diff --git a/drivers/cxl/core/bus.c b/drivers/cxl/core/bus.c
index 267d8042bec2..0987a6423ee0 100644
--- a/drivers/cxl/core/bus.c
+++ b/drivers/cxl/core/bus.c
@@ -182,6 +182,7 @@ static void cxl_decoder_release(struct device *dev)
 
 	ida_free(&port->decoder_ida, cxld->id);
 	kfree(cxld);
+	put_device(&port->dev);
 }
 
 static const struct device_type cxl_decoder_switch_type = {
@@ -481,6 +482,9 @@ cxl_decoder_alloc(struct cxl_port *port, int nr_targets, resource_size_t base,
 	if (rc < 0)
 		goto err;
 
+	/* need parent to stick around to release the id */
+	get_device(&port->dev);
+
 	*cxld = (struct cxl_decoder) {
 		.id = rc,
 		.range = {
diff --git a/drivers/devfreq/event/exynos-ppmu.c b/drivers/devfreq/event/exynos-ppmu.c
index 17ed980d9099..d6da9c3e3106 100644
--- a/drivers/devfreq/event/exynos-ppmu.c
+++ b/drivers/devfreq/event/exynos-ppmu.c
@@ -514,15 +514,19 @@ static int of_get_devfreq_events(struct device_node *np,
 
 	count = of_get_child_count(events_np);
 	desc = devm_kcalloc(dev, count, sizeof(*desc), GFP_KERNEL);
-	if (!desc)
+	if (!desc) {
+		of_node_put(events_np);
 		return -ENOMEM;
+	}
 	info->num_events = count;
 
 	of_id = of_match_device(exynos_ppmu_id_match, dev);
 	if (of_id)
 		info->ppmu_type = (enum exynos_ppmu_type)of_id->data;
-	else
+	else {
+		of_node_put(events_np);
 		return -EINVAL;
+	}
 
 	j = 0;
 	for_each_child_of_node(events_np, node) {
diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 91bdcc1441fb..c56280ee6579 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -69,12 +69,9 @@ static void dma_buf_release(struct dentry *dentry)
 	BUG_ON(dmabuf->vmapping_counter);
 
 	/*
-	 * Any fences that a dma-buf poll can wait on should be signaled
-	 * before releasing dma-buf. This is the responsibility of each
-	 * driver that uses the reservation objects.
-	 *
-	 * If you hit this BUG() it means someone dropped their ref to the
-	 * dma-buf while still having pending operation to the buffer.
+	 * If you hit this BUG() it could mean:
+	 * * There's a file reference imbalance in dma_buf_poll / dma_buf_poll_cb or somewhere else
+	 * * dmabuf->cb_in/out.active are non-0 despite no pending fence callback
 	 */
 	BUG_ON(dmabuf->cb_in.active || dmabuf->cb_out.active);
 
@@ -202,6 +199,7 @@ static loff_t dma_buf_llseek(struct file *file, loff_t offset, int whence)
 static void dma_buf_poll_cb(struct dma_fence *fence, struct dma_fence_cb *cb)
 {
 	struct dma_buf_poll_cb_t *dcb = (struct dma_buf_poll_cb_t *)cb;
+	struct dma_buf *dmabuf = container_of(dcb->poll, struct dma_buf, poll);
 	unsigned long flags;
 
 	spin_lock_irqsave(&dcb->poll->lock, flags);
@@ -209,6 +207,8 @@ static void dma_buf_poll_cb(struct dma_fence *fence, struct dma_fence_cb *cb)
 	dcb->active = 0;
 	spin_unlock_irqrestore(&dcb->poll->lock, flags);
 	dma_fence_put(fence);
+	/* Paired with get_file in dma_buf_poll */
+	fput(dmabuf->file);
 }
 
 static bool dma_buf_poll_shared(struct dma_resv *resv,
@@ -284,8 +284,12 @@ static __poll_t dma_buf_poll(struct file *file, poll_table *poll)
 		spin_unlock_irq(&dmabuf->poll.lock);
 
 		if (events & EPOLLOUT) {
+			/* Paired with fput in dma_buf_poll_cb */
+			get_file(dmabuf->file);
+
 			if (!dma_buf_poll_shared(resv, dcb) &&
 			    !dma_buf_poll_excl(resv, dcb))
+
 				/* No callback queued, wake up any other waiters */
 				dma_buf_poll_cb(NULL, &dcb->cb);
 			else
@@ -305,6 +309,9 @@ static __poll_t dma_buf_poll(struct file *file, poll_table *poll)
 		spin_unlock_irq(&dmabuf->poll.lock);
 
 		if (events & EPOLLIN) {
+			/* Paired with fput in dma_buf_poll_cb */
+			get_file(dmabuf->file);
+
 			if (!dma_buf_poll_excl(resv, dcb))
 				/* No callback queued, wake up any other waiters */
 				dma_buf_poll_cb(NULL, &dcb->cb);
diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c
index 9631f2fd2faf..38e8767ec371 100644
--- a/drivers/dma-buf/udmabuf.c
+++ b/drivers/dma-buf/udmabuf.c
@@ -368,7 +368,23 @@ static struct miscdevice udmabuf_misc = {
 
 static int __init udmabuf_dev_init(void)
 {
-	return misc_register(&udmabuf_misc);
+	int ret;
+
+	ret = misc_register(&udmabuf_misc);
+	if (ret < 0) {
+		pr_err("Could not initialize udmabuf device\n");
+		return ret;
+	}
+
+	ret = dma_coerce_mask_and_coherent(udmabuf_misc.this_device,
+					   DMA_BIT_MASK(64));
+	if (ret < 0) {
+		pr_err("Could not setup DMA mask for udmabuf device\n");
+		misc_deregister(&udmabuf_misc);
+		return ret;
+	}
+
+	return 0;
 }
 
 static void __exit udmabuf_dev_exit(void)
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index 177a537971a1..c5638afe9436 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -1898,6 +1898,11 @@ static int at_xdmac_alloc_chan_resources(struct dma_chan *chan)
 	for (i = 0; i < init_nr_desc_per_channel; i++) {
 		desc = at_xdmac_alloc_desc(chan, GFP_KERNEL);
 		if (!desc) {
+			if (i == 0) {
+				dev_warn(chan2dev(chan),
+					 "can't allocate any descriptors\n");
+				return -EIO;
+			}
 			dev_warn(chan2dev(chan),
 				"only %d descriptors have been allocated\n", i);
 			break;
diff --git a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c
index 35993ab92154..48de8d2b32f2 100644
--- a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c
+++ b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c
@@ -944,6 +944,11 @@ static int dw_axi_dma_chan_slave_config(struct dma_chan *dchan,
 static void axi_chan_dump_lli(struct axi_dma_chan *chan,
 			      struct axi_dma_hw_desc *desc)
 {
+	if (!desc->lli) {
+		dev_err(dchan2dev(&chan->vc.chan), "NULL LLI\n");
+		return;
+	}
+
 	dev_err(dchan2dev(&chan->vc.chan),
 		"SAR: 0x%llx DAR: 0x%llx LLP: 0x%llx BTS 0x%x CTL: 0x%x:%08x",
 		le64_to_cpu(desc->lli->sar),
@@ -1011,6 +1016,11 @@ static void axi_chan_block_xfer_complete(struct axi_dma_chan *chan)
 
 	/* The completed descriptor currently is in the head of vc list */
 	vd = vchan_next_desc(&chan->vc);
+	if (!vd) {
+		dev_err(chan2dev(chan), "BUG: %s, IRQ with no descriptors\n",
+			axi_chan_name(chan));
+		goto out;
+	}
 
 	if (chan->cyclic) {
 		desc = vd_to_axi_desc(vd);
@@ -1040,6 +1050,7 @@ static void axi_chan_block_xfer_complete(struct axi_dma_chan *chan)
 		axi_chan_start_first_queued(chan);
 	}
 
+out:
 	spin_unlock_irqrestore(&chan->vc.lock, flags);
 }
 
diff --git a/drivers/dma/dw-edma/dw-edma-core.c b/drivers/dma/dw-edma/dw-edma-core.c
index 53289927dd0d..36b3fe1b6b0f 100644
--- a/drivers/dma/dw-edma/dw-edma-core.c
+++ b/drivers/dma/dw-edma/dw-edma-core.c
@@ -424,7 +424,7 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 		chunk->ll_region.sz += burst->sz;
 		desc->alloc_sz += burst->sz;
 
-		if (chan->dir == EDMA_DIR_WRITE) {
+		if (dir == DMA_DEV_TO_MEM) {
 			burst->sar = src_addr;
 			if (xfer->type == EDMA_XFER_CYCLIC) {
 				burst->dar = xfer->xfer.cyclic.paddr;
diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index e622245c9380..11d3f2aede71 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -720,10 +720,7 @@ static void idxd_device_wqs_clear_state(struct idxd_device *idxd)
 	for (i = 0; i < idxd->max_wqs; i++) {
 		struct idxd_wq *wq = idxd->wqs[i];
 
-		if (wq->state == IDXD_WQ_ENABLED) {
-			idxd_wq_disable_cleanup(wq);
-			wq->state = IDXD_WQ_DISABLED;
-		}
+		idxd_wq_disable_cleanup(wq);
 		idxd_wq_device_reset_cleanup(wq);
 	}
 }
diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c
index 2ddc31e64db0..da31e73d24d4 100644
--- a/drivers/dma/imx-dma.c
+++ b/drivers/dma/imx-dma.c
@@ -1047,7 +1047,7 @@ static int __init imxdma_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	imxdma->dev = &pdev->dev;
-	imxdma->devtype = (enum imx_dma_type)of_device_get_match_data(&pdev->dev);
+	imxdma->devtype = (uintptr_t)of_device_get_match_data(&pdev->dev);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	imxdma->base = devm_ioremap_resource(&pdev->dev, res);
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 0294019c5489..52e20bfe6fee 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -2763,7 +2763,7 @@ MODULE_DESCRIPTION("i.MX SDMA driver");
 #if IS_ENABLED(CONFIG_SOC_IMX6Q)
 MODULE_FIRMWARE("imx/sdma/sdma-imx6q.bin");
 #endif
-#if IS_ENABLED(CONFIG_SOC_IMX7D)
+#if IS_ENABLED(CONFIG_SOC_IMX7D) || IS_ENABLED(CONFIG_SOC_IMX8M)
 MODULE_FIRMWARE("imx/sdma/sdma-imx7d.bin");
 #endif
 MODULE_LICENSE("GPL");
diff --git a/drivers/dma/lgm/lgm-dma.c b/drivers/dma/lgm/lgm-dma.c
index efe8bd3a0e2a..9b9184f964be 100644
--- a/drivers/dma/lgm/lgm-dma.c
+++ b/drivers/dma/lgm/lgm-dma.c
@@ -1593,11 +1593,12 @@ static int intel_ldma_probe(struct platform_device *pdev)
 	d->core_clk = devm_clk_get_optional(dev, NULL);
 	if (IS_ERR(d->core_clk))
 		return PTR_ERR(d->core_clk);
-	clk_prepare_enable(d->core_clk);
 
 	d->rst = devm_reset_control_get_optional(dev, NULL);
 	if (IS_ERR(d->rst))
 		return PTR_ERR(d->rst);
+
+	clk_prepare_enable(d->core_clk);
 	reset_control_deassert(d->rst);
 
 	ret = devm_add_action_or_reset(dev, ldma_clk_disable, d);
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index 110de8a60058..4ef68ddff75b 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -2589,7 +2589,7 @@ static struct dma_pl330_desc *pl330_get_desc(struct dma_pl330_chan *pch)
 
 	/* If the DMAC pool is empty, alloc new */
 	if (!desc) {
-		DEFINE_SPINLOCK(lock);
+		static DEFINE_SPINLOCK(lock);
 		LIST_HEAD(pool);
 
 		if (!add_desc(&pool, &lock, GFP_ATOMIC, 1))
diff --git a/drivers/dma/qcom/bam_dma.c b/drivers/dma/qcom/bam_dma.c
index c8a77b428b52..ca8c862c9747 100644
--- a/drivers/dma/qcom/bam_dma.c
+++ b/drivers/dma/qcom/bam_dma.c
@@ -515,14 +515,6 @@ static int bam_alloc_chan(struct dma_chan *chan)
 	return 0;
 }
 
-static int bam_pm_runtime_get_sync(struct device *dev)
-{
-	if (pm_runtime_enabled(dev))
-		return pm_runtime_get_sync(dev);
-
-	return 0;
-}
-
 /**
  * bam_free_chan - Frees dma resources associated with specific channel
  * @chan: specified channel
@@ -538,7 +530,7 @@ static void bam_free_chan(struct dma_chan *chan)
 	unsigned long flags;
 	int ret;
 
-	ret = bam_pm_runtime_get_sync(bdev->dev);
+	ret = pm_runtime_get_sync(bdev->dev);
 	if (ret < 0)
 		return;
 
@@ -734,7 +726,7 @@ static int bam_pause(struct dma_chan *chan)
 	unsigned long flag;
 	int ret;
 
-	ret = bam_pm_runtime_get_sync(bdev->dev);
+	ret = pm_runtime_get_sync(bdev->dev);
 	if (ret < 0)
 		return ret;
 
@@ -760,7 +752,7 @@ static int bam_resume(struct dma_chan *chan)
 	unsigned long flag;
 	int ret;
 
-	ret = bam_pm_runtime_get_sync(bdev->dev);
+	ret = pm_runtime_get_sync(bdev->dev);
 	if (ret < 0)
 		return ret;
 
@@ -869,7 +861,7 @@ static irqreturn_t bam_dma_irq(int irq, void *data)
 	if (srcs & P_IRQ)
 		tasklet_schedule(&bdev->task);
 
-	ret = bam_pm_runtime_get_sync(bdev->dev);
+	ret = pm_runtime_get_sync(bdev->dev);
 	if (ret < 0)
 		return IRQ_NONE;
 
@@ -987,7 +979,7 @@ static void bam_start_dma(struct bam_chan *bchan)
 	if (!vd)
 		return;
 
-	ret = bam_pm_runtime_get_sync(bdev->dev);
+	ret = pm_runtime_get_sync(bdev->dev);
 	if (ret < 0)
 		return;
 
@@ -1350,11 +1342,6 @@ static int bam_dma_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_unregister_dma;
 
-	if (!bdev->bamclk) {
-		pm_runtime_disable(&pdev->dev);
-		return 0;
-	}
-
 	pm_runtime_irq_safe(&pdev->dev);
 	pm_runtime_set_autosuspend_delay(&pdev->dev, BAM_DMA_AUTOSUSPEND_DELAY);
 	pm_runtime_use_autosuspend(&pdev->dev);
@@ -1438,10 +1425,8 @@ static int __maybe_unused bam_dma_suspend(struct device *dev)
 {
 	struct bam_device *bdev = dev_get_drvdata(dev);
 
-	if (bdev->bamclk) {
-		pm_runtime_force_suspend(dev);
-		clk_unprepare(bdev->bamclk);
-	}
+	pm_runtime_force_suspend(dev);
+	clk_unprepare(bdev->bamclk);
 
 	return 0;
 }
@@ -1451,13 +1436,11 @@ static int __maybe_unused bam_dma_resume(struct device *dev)
 	struct bam_device *bdev = dev_get_drvdata(dev);
 	int ret;
 
-	if (bdev->bamclk) {
-		ret = clk_prepare(bdev->bamclk);
-		if (ret)
-			return ret;
+	ret = clk_prepare(bdev->bamclk);
+	if (ret)
+		return ret;
 
-		pm_runtime_force_resume(dev);
-	}
+	pm_runtime_force_resume(dev);
 
 	return 0;
 }
diff --git a/drivers/dma/sf-pdma/sf-pdma.c b/drivers/dma/sf-pdma/sf-pdma.c
index f12606aeff87..ab0ad7a2f201 100644
--- a/drivers/dma/sf-pdma/sf-pdma.c
+++ b/drivers/dma/sf-pdma/sf-pdma.c
@@ -52,16 +52,6 @@ static inline struct sf_pdma_desc *to_sf_pdma_desc(struct virt_dma_desc *vd)
 static struct sf_pdma_desc *sf_pdma_alloc_desc(struct sf_pdma_chan *chan)
 {
 	struct sf_pdma_desc *desc;
-	unsigned long flags;
-
-	spin_lock_irqsave(&chan->lock, flags);
-
-	if (chan->desc && !chan->desc->in_use) {
-		spin_unlock_irqrestore(&chan->lock, flags);
-		return chan->desc;
-	}
-
-	spin_unlock_irqrestore(&chan->lock, flags);
 
 	desc = kzalloc(sizeof(*desc), GFP_NOWAIT);
 	if (!desc)
@@ -111,7 +101,6 @@ sf_pdma_prep_dma_memcpy(struct dma_chan *dchan,	dma_addr_t dest, dma_addr_t src,
 	desc->async_tx = vchan_tx_prep(&chan->vchan, &desc->vdesc, flags);
 
 	spin_lock_irqsave(&chan->vchan.lock, iflags);
-	chan->desc = desc;
 	sf_pdma_fill_desc(desc, dest, src, len);
 	spin_unlock_irqrestore(&chan->vchan.lock, iflags);
 
@@ -170,11 +159,17 @@ static size_t sf_pdma_desc_residue(struct sf_pdma_chan *chan,
 	unsigned long flags;
 	u64 residue = 0;
 	struct sf_pdma_desc *desc;
-	struct dma_async_tx_descriptor *tx;
+	struct dma_async_tx_descriptor *tx = NULL;
 
 	spin_lock_irqsave(&chan->vchan.lock, flags);
 
-	tx = &chan->desc->vdesc.tx;
+	list_for_each_entry(vd, &chan->vchan.desc_submitted, node)
+		if (vd->tx.cookie == cookie)
+			tx = &vd->tx;
+
+	if (!tx)
+		goto out;
+
 	if (cookie == tx->chan->completed_cookie)
 		goto out;
 
@@ -241,6 +236,19 @@ static void sf_pdma_enable_request(struct sf_pdma_chan *chan)
 	writel(v, regs->ctrl);
 }
 
+static struct sf_pdma_desc *sf_pdma_get_first_pending_desc(struct sf_pdma_chan *chan)
+{
+	struct virt_dma_chan *vchan = &chan->vchan;
+	struct virt_dma_desc *vdesc;
+
+	if (list_empty(&vchan->desc_issued))
+		return NULL;
+
+	vdesc = list_first_entry(&vchan->desc_issued, struct virt_dma_desc, node);
+
+	return container_of(vdesc, struct sf_pdma_desc, vdesc);
+}
+
 static void sf_pdma_xfer_desc(struct sf_pdma_chan *chan)
 {
 	struct sf_pdma_desc *desc = chan->desc;
@@ -268,8 +276,11 @@ static void sf_pdma_issue_pending(struct dma_chan *dchan)
 
 	spin_lock_irqsave(&chan->vchan.lock, flags);
 
-	if (vchan_issue_pending(&chan->vchan) && chan->desc)
+	if (!chan->desc && vchan_issue_pending(&chan->vchan)) {
+		/* vchan_issue_pending has made a check that desc in not NULL */
+		chan->desc = sf_pdma_get_first_pending_desc(chan);
 		sf_pdma_xfer_desc(chan);
+	}
 
 	spin_unlock_irqrestore(&chan->vchan.lock, flags);
 }
@@ -298,6 +309,11 @@ static void sf_pdma_donebh_tasklet(struct tasklet_struct *t)
 	spin_lock_irqsave(&chan->vchan.lock, flags);
 	list_del(&chan->desc->vdesc.node);
 	vchan_cookie_complete(&chan->desc->vdesc);
+
+	chan->desc = sf_pdma_get_first_pending_desc(chan);
+	if (chan->desc)
+		sf_pdma_xfer_desc(chan);
+
 	spin_unlock_irqrestore(&chan->vchan.lock, flags);
 }
 
diff --git a/drivers/dma/sprd-dma.c b/drivers/dma/sprd-dma.c
index 4357d2395e6b..60115d8d4083 100644
--- a/drivers/dma/sprd-dma.c
+++ b/drivers/dma/sprd-dma.c
@@ -1236,11 +1236,8 @@ static int sprd_dma_remove(struct platform_device *pdev)
 {
 	struct sprd_dma_dev *sdev = platform_get_drvdata(pdev);
 	struct sprd_dma_chn *c, *cn;
-	int ret;
 
-	ret = pm_runtime_get_sync(&pdev->dev);
-	if (ret < 0)
-		return ret;
+	pm_runtime_get_sync(&pdev->dev);
 
 	/* explicitly free the irq */
 	if (sdev->irq > 0)
diff --git a/drivers/dma/ti/dma-crossbar.c b/drivers/dma/ti/dma-crossbar.c
index 71d24fc07c00..f744ddbbbad7 100644
--- a/drivers/dma/ti/dma-crossbar.c
+++ b/drivers/dma/ti/dma-crossbar.c
@@ -245,6 +245,7 @@ static void *ti_dra7_xbar_route_allocate(struct of_phandle_args *dma_spec,
 	if (dma_spec->args[0] >= xbar->xbar_requests) {
 		dev_err(&pdev->dev, "Invalid XBAR request number: %d\n",
 			dma_spec->args[0]);
+		put_device(&pdev->dev);
 		return ERR_PTR(-EINVAL);
 	}
 
@@ -252,12 +253,14 @@ static void *ti_dra7_xbar_route_allocate(struct of_phandle_args *dma_spec,
 	dma_spec->np = of_parse_phandle(ofdma->of_node, "dma-masters", 0);
 	if (!dma_spec->np) {
 		dev_err(&pdev->dev, "Can't get DMA master\n");
+		put_device(&pdev->dev);
 		return ERR_PTR(-EINVAL);
 	}
 
 	map = kzalloc(sizeof(*map), GFP_KERNEL);
 	if (!map) {
 		of_node_put(dma_spec->np);
+		put_device(&pdev->dev);
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -268,6 +271,8 @@ static void *ti_dra7_xbar_route_allocate(struct of_phandle_args *dma_spec,
 		mutex_unlock(&xbar->mutex);
 		dev_err(&pdev->dev, "Run out of free DMA requests\n");
 		kfree(map);
+		of_node_put(dma_spec->np);
+		put_device(&pdev->dev);
 		return ERR_PTR(-ENOMEM);
 	}
 	set_bit(map->xbar_out, xbar->dma_inuse);
diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c
index 6d1ddecbf0da..d0a9ccf640c4 100644
--- a/drivers/edac/ghes_edac.c
+++ b/drivers/edac/ghes_edac.c
@@ -101,9 +101,14 @@ static void dimm_setup_label(struct dimm_info *dimm, u16 handle)
 
 	dmi_memdev_name(handle, &bank, &device);
 
-	/* both strings must be non-zero */
-	if (bank && *bank && device && *device)
-		snprintf(dimm->label, sizeof(dimm->label), "%s %s", bank, device);
+	/*
+	 * Set to a NULL string when both bank and device are zero. In this case,
+	 * the label assigned by default will be preserved.
+	 */
+	snprintf(dimm->label, sizeof(dimm->label), "%s%s%s",
+		 (bank && *bank) ? bank : "",
+		 (bank && *bank && device && *device) ? " " : "",
+		 (device && *device) ? device : "");
 }
 
 static void assign_dmi_dimm_info(struct dimm_info *dimm, struct memdev_dmi_entry *entry)
diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig
index cda7d7162cbb..97ce31e667fc 100644
--- a/drivers/firmware/Kconfig
+++ b/drivers/firmware/Kconfig
@@ -40,6 +40,7 @@ config ARM_SCPI_POWER_DOMAIN
 config ARM_SDE_INTERFACE
 	bool "ARM Software Delegated Exception Interface (SDEI)"
 	depends on ARM64
+	depends on ACPI_APEI_GHES
 	help
 	  The Software Delegated Exception Interface (SDEI) is an ARM
 	  standard for registering callbacks from the platform firmware
diff --git a/drivers/firmware/arm_scpi.c b/drivers/firmware/arm_scpi.c
index ddf0b9ff9e15..435d0e2658a4 100644
--- a/drivers/firmware/arm_scpi.c
+++ b/drivers/firmware/arm_scpi.c
@@ -815,7 +815,7 @@ static int scpi_init_versions(struct scpi_drvinfo *info)
 		info->firmware_version = le32_to_cpu(caps.platform_version);
 	}
 	/* Ignore error if not implemented */
-	if (scpi_info->is_legacy && ret == -EOPNOTSUPP)
+	if (info->is_legacy && ret == -EOPNOTSUPP)
 		return 0;
 
 	return ret;
@@ -913,13 +913,14 @@ static int scpi_probe(struct platform_device *pdev)
 	struct resource res;
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev->of_node;
+	struct scpi_drvinfo *scpi_drvinfo;
 
-	scpi_info = devm_kzalloc(dev, sizeof(*scpi_info), GFP_KERNEL);
-	if (!scpi_info)
+	scpi_drvinfo = devm_kzalloc(dev, sizeof(*scpi_drvinfo), GFP_KERNEL);
+	if (!scpi_drvinfo)
 		return -ENOMEM;
 
 	if (of_match_device(legacy_scpi_of_match, &pdev->dev))
-		scpi_info->is_legacy = true;
+		scpi_drvinfo->is_legacy = true;
 
 	count = of_count_phandle_with_args(np, "mboxes", "#mbox-cells");
 	if (count < 0) {
@@ -927,19 +928,19 @@ static int scpi_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
-	scpi_info->channels = devm_kcalloc(dev, count, sizeof(struct scpi_chan),
-					   GFP_KERNEL);
-	if (!scpi_info->channels)
+	scpi_drvinfo->channels =
+		devm_kcalloc(dev, count, sizeof(struct scpi_chan), GFP_KERNEL);
+	if (!scpi_drvinfo->channels)
 		return -ENOMEM;
 
-	ret = devm_add_action(dev, scpi_free_channels, scpi_info);
+	ret = devm_add_action(dev, scpi_free_channels, scpi_drvinfo);
 	if (ret)
 		return ret;
 
-	for (; scpi_info->num_chans < count; scpi_info->num_chans++) {
+	for (; scpi_drvinfo->num_chans < count; scpi_drvinfo->num_chans++) {
 		resource_size_t size;
-		int idx = scpi_info->num_chans;
-		struct scpi_chan *pchan = scpi_info->channels + idx;
+		int idx = scpi_drvinfo->num_chans;
+		struct scpi_chan *pchan = scpi_drvinfo->channels + idx;
 		struct mbox_client *cl = &pchan->cl;
 		struct device_node *shmem = of_parse_phandle(np, "shmem", idx);
 
@@ -986,45 +987,53 @@ static int scpi_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	scpi_info->commands = scpi_std_commands;
+	scpi_drvinfo->commands = scpi_std_commands;
 
-	platform_set_drvdata(pdev, scpi_info);
+	platform_set_drvdata(pdev, scpi_drvinfo);
 
-	if (scpi_info->is_legacy) {
+	if (scpi_drvinfo->is_legacy) {
 		/* Replace with legacy variants */
 		scpi_ops.clk_set_val = legacy_scpi_clk_set_val;
-		scpi_info->commands = scpi_legacy_commands;
+		scpi_drvinfo->commands = scpi_legacy_commands;
 
 		/* Fill priority bitmap */
 		for (idx = 0; idx < ARRAY_SIZE(legacy_hpriority_cmds); idx++)
 			set_bit(legacy_hpriority_cmds[idx],
-				scpi_info->cmd_priority);
+				scpi_drvinfo->cmd_priority);
 	}
 
-	ret = scpi_init_versions(scpi_info);
+	scpi_info = scpi_drvinfo;
+
+	ret = scpi_init_versions(scpi_drvinfo);
 	if (ret) {
 		dev_err(dev, "incorrect or no SCP firmware found\n");
+		scpi_info = NULL;
 		return ret;
 	}
 
-	if (scpi_info->is_legacy && !scpi_info->protocol_version &&
-	    !scpi_info->firmware_version)
+	if (scpi_drvinfo->is_legacy && !scpi_drvinfo->protocol_version &&
+	    !scpi_drvinfo->firmware_version)
 		dev_info(dev, "SCP Protocol legacy pre-1.0 firmware\n");
 	else
 		dev_info(dev, "SCP Protocol %lu.%lu Firmware %lu.%lu.%lu version\n",
 			 FIELD_GET(PROTO_REV_MAJOR_MASK,
-				   scpi_info->protocol_version),
+				   scpi_drvinfo->protocol_version),
 			 FIELD_GET(PROTO_REV_MINOR_MASK,
-				   scpi_info->protocol_version),
+				   scpi_drvinfo->protocol_version),
 			 FIELD_GET(FW_REV_MAJOR_MASK,
-				   scpi_info->firmware_version),
+				   scpi_drvinfo->firmware_version),
 			 FIELD_GET(FW_REV_MINOR_MASK,
-				   scpi_info->firmware_version),
+				   scpi_drvinfo->firmware_version),
 			 FIELD_GET(FW_REV_PATCH_MASK,
-				   scpi_info->firmware_version));
-	scpi_info->scpi_ops = &scpi_ops;
+				   scpi_drvinfo->firmware_version));
+
+	scpi_drvinfo->scpi_ops = &scpi_ops;
 
-	return devm_of_platform_populate(dev);
+	ret = devm_of_platform_populate(dev);
+	if (ret)
+		scpi_info = NULL;
+
+	return ret;
 }
 
 static const struct of_device_id scpi_of_match[] = {
diff --git a/drivers/firmware/arm_sdei.c b/drivers/firmware/arm_sdei.c
index a7e762c352f9..1e1a51510e83 100644
--- a/drivers/firmware/arm_sdei.c
+++ b/drivers/firmware/arm_sdei.c
@@ -1059,14 +1059,14 @@ static bool __init sdei_present_acpi(void)
 	return true;
 }
 
-static int __init sdei_init(void)
+void __init sdei_init(void)
 {
 	struct platform_device *pdev;
 	int ret;
 
 	ret = platform_driver_register(&sdei_driver);
 	if (ret || !sdei_present_acpi())
-		return ret;
+		return;
 
 	pdev = platform_device_register_simple(sdei_driver.driver.name,
 					       0, NULL, 0);
@@ -1076,17 +1076,8 @@ static int __init sdei_init(void)
 		pr_info("Failed to register ACPI:SDEI platform device %d\n",
 			ret);
 	}
-
-	return ret;
 }
 
-/*
- * On an ACPI system SDEI needs to be ready before HEST:GHES tries to register
- * its events. ACPI is initialised from a subsys_initcall(), GHES is initialised
- * by device_initcall(). We want to be called in the middle.
- */
-subsys_initcall_sync(sdei_init);
-
 int sdei_event_handler(struct pt_regs *regs,
 		       struct sdei_registered_event *arg)
 {
diff --git a/drivers/firmware/efi/capsule-loader.c b/drivers/firmware/efi/capsule-loader.c
index 4dde8edd53b6..3e8d4b51a814 100644
--- a/drivers/firmware/efi/capsule-loader.c
+++ b/drivers/firmware/efi/capsule-loader.c
@@ -243,29 +243,6 @@ failed:
 }
 
 /**
- * efi_capsule_flush - called by file close or file flush
- * @file: file pointer
- * @id: not used
- *
- *	If a capsule is being partially uploaded then calling this function
- *	will be treated as upload termination and will free those completed
- *	buffer pages and -ECANCELED will be returned.
- **/
-static int efi_capsule_flush(struct file *file, fl_owner_t id)
-{
-	int ret = 0;
-	struct capsule_info *cap_info = file->private_data;
-
-	if (cap_info->index > 0) {
-		pr_err("capsule upload not complete\n");
-		efi_free_all_buff_pages(cap_info);
-		ret = -ECANCELED;
-	}
-
-	return ret;
-}
-
-/**
  * efi_capsule_release - called by file close
  * @inode: not used
  * @file: file pointer
@@ -277,6 +254,13 @@ static int efi_capsule_release(struct inode *inode, struct file *file)
 {
 	struct capsule_info *cap_info = file->private_data;
 
+	if (cap_info->index > 0 &&
+	    (cap_info->header.headersize == 0 ||
+	     cap_info->count < cap_info->total_size)) {
+		pr_err("capsule upload not complete\n");
+		efi_free_all_buff_pages(cap_info);
+	}
+
 	kfree(cap_info->pages);
 	kfree(cap_info->phys);
 	kfree(file->private_data);
@@ -324,7 +308,6 @@ static const struct file_operations efi_capsule_fops = {
 	.owner = THIS_MODULE,
 	.open = efi_capsule_open,
 	.write = efi_capsule_write,
-	.flush = efi_capsule_flush,
 	.release = efi_capsule_release,
 	.llseek = no_llseek,
 };
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index d0537573501e..2c67f71f2375 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -37,6 +37,13 @@ KBUILD_CFLAGS			:= $(cflags-y) -Os -DDISABLE_BRANCH_PROFILING \
 				   $(call cc-option,-fno-addrsig) \
 				   -D__DISABLE_EXPORTS
 
+#
+# struct randomization only makes sense for Linux internal types, which the EFI
+# stub code never touches, so let's turn off struct randomization for the stub
+# altogether
+#
+KBUILD_CFLAGS := $(filter-out $(RANDSTRUCT_CFLAGS), $(KBUILD_CFLAGS))
+
 # remove SCS flags from all objects in this directory
 KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_SCS), $(KBUILD_CFLAGS))
 # disable LTO
diff --git a/drivers/firmware/sysfb.c b/drivers/firmware/sysfb.c
index 2bfbb05f7d89..1f276f108cc9 100644
--- a/drivers/firmware/sysfb.c
+++ b/drivers/firmware/sysfb.c
@@ -34,21 +34,59 @@
 #include <linux/screen_info.h>
 #include <linux/sysfb.h>
 
+static struct platform_device *pd;
+static DEFINE_MUTEX(disable_lock);
+static bool disabled;
+
+static bool sysfb_unregister(void)
+{
+	if (IS_ERR_OR_NULL(pd))
+		return false;
+
+	platform_device_unregister(pd);
+	pd = NULL;
+
+	return true;
+}
+
+/**
+ * sysfb_disable() - disable the Generic System Framebuffers support
+ *
+ * This disables the registration of system framebuffer devices that match the
+ * generic drivers that make use of the system framebuffer set up by firmware.
+ *
+ * It also unregisters a device if this was already registered by sysfb_init().
+ *
+ * Context: The function can sleep. A @disable_lock mutex is acquired to serialize
+ *          against sysfb_init(), that registers a system framebuffer device.
+ */
+void sysfb_disable(void)
+{
+	mutex_lock(&disable_lock);
+	sysfb_unregister();
+	disabled = true;
+	mutex_unlock(&disable_lock);
+}
+EXPORT_SYMBOL_GPL(sysfb_disable);
+
 static __init int sysfb_init(void)
 {
 	struct screen_info *si = &screen_info;
 	struct simplefb_platform_data mode;
-	struct platform_device *pd;
 	const char *name;
 	bool compatible;
-	int ret;
+	int ret = 0;
+
+	mutex_lock(&disable_lock);
+	if (disabled)
+		goto unlock_mutex;
 
 	/* try to create a simple-framebuffer device */
 	compatible = sysfb_parse_mode(si, &mode);
 	if (compatible) {
-		ret = sysfb_create_simplefb(si, &mode);
-		if (!ret)
-			return 0;
+		pd = sysfb_create_simplefb(si, &mode);
+		if (!IS_ERR(pd))
+			goto unlock_mutex;
 	}
 
 	/* if the FB is incompatible, create a legacy framebuffer device */
@@ -60,8 +98,10 @@ static __init int sysfb_init(void)
 		name = "platform-framebuffer";
 
 	pd = platform_device_alloc(name, 0);
-	if (!pd)
-		return -ENOMEM;
+	if (!pd) {
+		ret = -ENOMEM;
+		goto unlock_mutex;
+	}
 
 	sysfb_apply_efi_quirks(pd);
 
@@ -73,9 +113,11 @@ static __init int sysfb_init(void)
 	if (ret)
 		goto err;
 
-	return 0;
+	goto unlock_mutex;
 err:
 	platform_device_put(pd);
+unlock_mutex:
+	mutex_unlock(&disable_lock);
 	return ret;
 }
 
diff --git a/drivers/firmware/sysfb_simplefb.c b/drivers/firmware/sysfb_simplefb.c
index 757cc8b9f3de..eac51c2a27ba 100644
--- a/drivers/firmware/sysfb_simplefb.c
+++ b/drivers/firmware/sysfb_simplefb.c
@@ -57,8 +57,8 @@ __init bool sysfb_parse_mode(const struct screen_info *si,
 	return false;
 }
 
-__init int sysfb_create_simplefb(const struct screen_info *si,
-				 const struct simplefb_platform_data *mode)
+__init struct platform_device *sysfb_create_simplefb(const struct screen_info *si,
+						     const struct simplefb_platform_data *mode)
 {
 	struct platform_device *pd;
 	struct resource res;
@@ -76,7 +76,7 @@ __init int sysfb_create_simplefb(const struct screen_info *si,
 		base |= (u64)si->ext_lfb_base << 32;
 	if (!base || (u64)(resource_size_t)base != base) {
 		printk(KERN_DEBUG "sysfb: inaccessible VRAM base\n");
-		return -EINVAL;
+		return ERR_PTR(-EINVAL);
 	}
 
 	/*
@@ -93,7 +93,7 @@ __init int sysfb_create_simplefb(const struct screen_info *si,
 	length = mode->height * mode->stride;
 	if (length > size) {
 		printk(KERN_WARNING "sysfb: VRAM smaller than advertised\n");
-		return -EINVAL;
+		return ERR_PTR(-EINVAL);
 	}
 	length = PAGE_ALIGN(length);
 
@@ -104,11 +104,11 @@ __init int sysfb_create_simplefb(const struct screen_info *si,
 	res.start = base;
 	res.end = res.start + length - 1;
 	if (res.end <= res.start)
-		return -EINVAL;
+		return ERR_PTR(-EINVAL);
 
 	pd = platform_device_alloc("simple-framebuffer", 0);
 	if (!pd)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	sysfb_apply_efi_quirks(pd);
 
@@ -124,10 +124,10 @@ __init int sysfb_create_simplefb(const struct screen_info *si,
 	if (ret)
 		goto err_put_device;
 
-	return 0;
+	return pd;
 
 err_put_device:
 	platform_device_put(pd);
 
-	return ret;
+	return ERR_PTR(ret);
 }
diff --git a/drivers/firmware/tegra/bpmp-debugfs.c b/drivers/firmware/tegra/bpmp-debugfs.c
index 3e9fa4b54358..1ed881a567d5 100644
--- a/drivers/firmware/tegra/bpmp-debugfs.c
+++ b/drivers/firmware/tegra/bpmp-debugfs.c
@@ -465,7 +465,7 @@ static int bpmp_populate_debugfs_inband(struct tegra_bpmp *bpmp,
 			mode |= attrs & DEBUGFS_S_IWUSR ? 0200 : 0;
 			dentry = debugfs_create_file(name, mode, parent, bpmp,
 						     &bpmp_debug_fops);
-			if (!dentry) {
+			if (IS_ERR(dentry)) {
 				err = -ENOMEM;
 				goto out;
 			}
@@ -716,7 +716,7 @@ static int bpmp_populate_dir(struct tegra_bpmp *bpmp, struct seqbuf *seqbuf,
 
 		if (t & DEBUGFS_S_ISDIR) {
 			dentry = debugfs_create_dir(name, parent);
-			if (!dentry)
+			if (IS_ERR(dentry))
 				return -ENOMEM;
 			err = bpmp_populate_dir(bpmp, seqbuf, dentry, depth+1);
 			if (err < 0)
@@ -729,7 +729,7 @@ static int bpmp_populate_dir(struct tegra_bpmp *bpmp, struct seqbuf *seqbuf,
 			dentry = debugfs_create_file(name, mode,
 						     parent, bpmp,
 						     &debugfs_fops);
-			if (!dentry)
+			if (IS_ERR(dentry))
 				return -ENOMEM;
 		}
 	}
@@ -779,11 +779,11 @@ int tegra_bpmp_init_debugfs(struct tegra_bpmp *bpmp)
 		return 0;
 
 	root = debugfs_create_dir("bpmp", NULL);
-	if (!root)
+	if (IS_ERR(root))
 		return -ENOMEM;
 
 	bpmp->debugfs_mirror = debugfs_create_dir("debug", root);
-	if (!bpmp->debugfs_mirror) {
+	if (IS_ERR(bpmp->debugfs_mirror)) {
 		err = -ENOMEM;
 		goto out;
 	}
diff --git a/drivers/firmware/tegra/bpmp.c b/drivers/firmware/tegra/bpmp.c
index 5654c5e9862b..037db21de510 100644
--- a/drivers/firmware/tegra/bpmp.c
+++ b/drivers/firmware/tegra/bpmp.c
@@ -201,7 +201,7 @@ static ssize_t __tegra_bpmp_channel_read(struct tegra_bpmp_channel *channel,
 	int err;
 
 	if (data && size > 0)
-		memcpy(data, channel->ib->data, size);
+		memcpy_fromio(data, channel->ib->data, size);
 
 	err = tegra_bpmp_ack_response(channel);
 	if (err < 0)
@@ -245,7 +245,7 @@ static ssize_t __tegra_bpmp_channel_write(struct tegra_bpmp_channel *channel,
 	channel->ob->flags = flags;
 
 	if (data && size > 0)
-		memcpy(channel->ob->data, data, size);
+		memcpy_toio(channel->ob->data, data, size);
 
 	return tegra_bpmp_post_request(channel);
 }
@@ -420,7 +420,7 @@ void tegra_bpmp_mrq_return(struct tegra_bpmp_channel *channel, int code,
 	channel->ob->code = code;
 
 	if (data && size > 0)
-		memcpy(channel->ob->data, data, size);
+		memcpy_toio(channel->ob->data, data, size);
 
 	err = tegra_bpmp_post_response(channel);
 	if (WARN_ON(err < 0))
diff --git a/drivers/fpga/altera-pr-ip-core.c b/drivers/fpga/altera-pr-ip-core.c
index dfdf21ed34c4..c24b6fb2d7c3 100644
--- a/drivers/fpga/altera-pr-ip-core.c
+++ b/drivers/fpga/altera-pr-ip-core.c
@@ -108,7 +108,7 @@ static int alt_pr_fpga_write(struct fpga_manager *mgr, const char *buf,
 	u32 *buffer_32 = (u32 *)buf;
 	size_t i = 0;
 
-	if (count <= 0)
+	if (!count)
 		return -EINVAL;
 
 	/* Write out the complete 32-bit chunks */
diff --git a/drivers/fsi/fsi-occ.c b/drivers/fsi/fsi-occ.c
index b223f0ef337b..ecf738411fe2 100644
--- a/drivers/fsi/fsi-occ.c
+++ b/drivers/fsi/fsi-occ.c
@@ -50,6 +50,7 @@ struct occ {
 	struct device *sbefifo;
 	char name[32];
 	int idx;
+	u8 sequence_number;
 	enum versions version;
 	struct miscdevice mdev;
 	struct mutex occ_lock;
@@ -141,8 +142,7 @@ static ssize_t occ_write(struct file *file, const char __user *buf,
 {
 	struct occ_client *client = file->private_data;
 	size_t rlen, data_length;
-	u16 checksum = 0;
-	ssize_t rc, i;
+	ssize_t rc;
 	u8 *cmd;
 
 	if (!client)
@@ -156,9 +156,6 @@ static ssize_t occ_write(struct file *file, const char __user *buf,
 	/* Construct the command */
 	cmd = client->buffer;
 
-	/* Sequence number (we could increment and compare with response) */
-	cmd[0] = 1;
-
 	/*
 	 * Copy the user command (assume user data follows the occ command
 	 * format)
@@ -178,14 +175,7 @@ static ssize_t occ_write(struct file *file, const char __user *buf,
 		goto done;
 	}
 
-	/* Calculate checksum */
-	for (i = 0; i < data_length + 4; ++i)
-		checksum += cmd[i];
-
-	cmd[data_length + 4] = checksum >> 8;
-	cmd[data_length + 5] = checksum & 0xFF;
-
-	/* Submit command */
+	/* Submit command; 4 bytes before the data and 2 bytes after */
 	rlen = PAGE_SIZE;
 	rc = fsi_occ_submit(client->occ->dev, cmd, data_length + 6, cmd,
 			    &rlen);
@@ -314,11 +304,13 @@ free:
 	return rc;
 }
 
-static int occ_putsram(struct occ *occ, const void *data, ssize_t len)
+static int occ_putsram(struct occ *occ, const void *data, ssize_t len,
+		       u8 seq_no, u16 checksum)
 {
 	size_t cmd_len, buf_len, resp_len, resp_data_len;
 	u32 data_len = ((len + 7) / 8) * 8;	/* must be multiples of 8 B */
 	__be32 *buf;
+	u8 *byte_buf;
 	int idx = 0, rc;
 
 	cmd_len = (occ->version == occ_p10) ? 6 : 5;
@@ -358,6 +350,15 @@ static int occ_putsram(struct occ *occ, const void *data, ssize_t len)
 	buf[4 + idx] = cpu_to_be32(data_len);
 	memcpy(&buf[5 + idx], data, len);
 
+	byte_buf = (u8 *)&buf[5 + idx];
+	/*
+	 * Overwrite the first byte with our sequence number and the last two
+	 * bytes with the checksum.
+	 */
+	byte_buf[0] = seq_no;
+	byte_buf[len - 2] = checksum >> 8;
+	byte_buf[len - 1] = checksum & 0xff;
+
 	rc = sbefifo_submit(occ->sbefifo, buf, cmd_len, buf, &resp_len);
 	if (rc)
 		goto free;
@@ -467,9 +468,12 @@ int fsi_occ_submit(struct device *dev, const void *request, size_t req_len,
 	struct occ *occ = dev_get_drvdata(dev);
 	struct occ_response *resp = response;
 	u8 seq_no;
+	u16 checksum = 0;
 	u16 resp_data_length;
+	const u8 *byte_request = (const u8 *)request;
 	unsigned long start;
 	int rc;
+	size_t i;
 
 	if (!occ)
 		return -ENODEV;
@@ -479,11 +483,26 @@ int fsi_occ_submit(struct device *dev, const void *request, size_t req_len,
 		return -EINVAL;
 	}
 
+	/* Checksum the request, ignoring first byte (sequence number). */
+	for (i = 1; i < req_len - 2; ++i)
+		checksum += byte_request[i];
+
 	mutex_lock(&occ->occ_lock);
 
-	/* Extract the seq_no from the command (first byte) */
-	seq_no = *(const u8 *)request;
-	rc = occ_putsram(occ, request, req_len);
+	/*
+	 * Get a sequence number and update the counter. Avoid a sequence
+	 * number of 0 which would pass the response check below even if the
+	 * OCC response is uninitialized. Any sequence number the user is
+	 * trying to send is overwritten since this function is the only common
+	 * interface to the OCC and therefore the only place we can guarantee
+	 * unique sequence numbers.
+	 */
+	seq_no = occ->sequence_number++;
+	if (!occ->sequence_number)
+		occ->sequence_number = 1;
+	checksum += seq_no;
+
+	rc = occ_putsram(occ, request, req_len, seq_no, checksum);
 	if (rc)
 		goto done;
 
@@ -574,6 +593,7 @@ static int occ_probe(struct platform_device *pdev)
 	occ->version = (uintptr_t)of_device_get_match_data(dev);
 	occ->dev = dev;
 	occ->sbefifo = dev->parent;
+	occ->sequence_number = 1;
 	mutex_init(&occ->occ_lock);
 
 	if (dev->of_node) {
diff --git a/drivers/gpio/gpio-mockup.c b/drivers/gpio/gpio-mockup.c
index d26bff29157b..369a832d9620 100644
--- a/drivers/gpio/gpio-mockup.c
+++ b/drivers/gpio/gpio-mockup.c
@@ -373,6 +373,13 @@ static void gpio_mockup_debugfs_setup(struct device *dev,
 	}
 }
 
+static void gpio_mockup_debugfs_cleanup(void *data)
+{
+	struct gpio_mockup_chip *chip = data;
+
+	debugfs_remove_recursive(chip->dbg_dir);
+}
+
 static void gpio_mockup_dispose_mappings(void *data)
 {
 	struct gpio_mockup_chip *chip = data;
@@ -455,7 +462,7 @@ static int gpio_mockup_probe(struct platform_device *pdev)
 
 	gpio_mockup_debugfs_setup(dev, chip);
 
-	return 0;
+	return devm_add_action_or_reset(dev, gpio_mockup_debugfs_cleanup, chip);
 }
 
 static const struct of_device_id gpio_mockup_of_match[] = {
diff --git a/drivers/gpio/gpio-mpc8xxx.c b/drivers/gpio/gpio-mpc8xxx.c
index 85e5fd8851ce..d6c2dc127b85 100644
--- a/drivers/gpio/gpio-mpc8xxx.c
+++ b/drivers/gpio/gpio-mpc8xxx.c
@@ -172,6 +172,7 @@ static int mpc8xxx_irq_set_type(struct irq_data *d, unsigned int flow_type)
 
 	switch (flow_type) {
 	case IRQ_TYPE_EDGE_FALLING:
+	case IRQ_TYPE_LEVEL_LOW:
 		raw_spin_lock_irqsave(&mpc8xxx_gc->lock, flags);
 		gc->write_reg(mpc8xxx_gc->regs + GPIO_ICR,
 			gc->read_reg(mpc8xxx_gc->regs + GPIO_ICR)
diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c
index c4cbdf19227c..ac848ebe0b73 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -1168,7 +1168,9 @@ static int pca953x_suspend(struct device *dev)
 {
 	struct pca953x_chip *chip = dev_get_drvdata(dev);
 
+	mutex_lock(&chip->i2c_lock);
 	regcache_cache_only(chip->regmap, true);
+	mutex_unlock(&chip->i2c_lock);
 
 	if (atomic_read(&chip->wakeup_path))
 		device_set_wakeup_path(dev);
@@ -1191,13 +1193,17 @@ static int pca953x_resume(struct device *dev)
 		}
 	}
 
+	mutex_lock(&chip->i2c_lock);
 	regcache_cache_only(chip->regmap, false);
 	regcache_mark_dirty(chip->regmap);
 	ret = pca953x_regcache_sync(dev);
-	if (ret)
+	if (ret) {
+		mutex_unlock(&chip->i2c_lock);
 		return ret;
+	}
 
 	ret = regcache_sync(chip->regmap);
+	mutex_unlock(&chip->i2c_lock);
 	if (ret) {
 		dev_err(dev, "Failed to restore register map: %d\n", ret);
 		return ret;
diff --git a/drivers/gpio/gpio-rockchip.c b/drivers/gpio/gpio-rockchip.c
index 22b8f0aa80f1..f31b0947eaaa 100644
--- a/drivers/gpio/gpio-rockchip.c
+++ b/drivers/gpio/gpio-rockchip.c
@@ -418,11 +418,11 @@ static int rockchip_irq_set_type(struct irq_data *d, unsigned int type)
 			goto out;
 		} else {
 			bank->toggle_edge_mode |= mask;
-			level |= mask;
+			level &= ~mask;
 
 			/*
 			 * Determine gpio state. If 1 next interrupt should be
-			 * falling otherwise rising.
+			 * low otherwise high.
 			 */
 			data = readl(bank->reg_base + bank->gpio_regs->ext_port);
 			if (data & mask)
diff --git a/drivers/gpio/gpio-xilinx.c b/drivers/gpio/gpio-xilinx.c
index a1b66338d077..db616ae560a3 100644
--- a/drivers/gpio/gpio-xilinx.c
+++ b/drivers/gpio/gpio-xilinx.c
@@ -99,7 +99,7 @@ static inline void xgpio_set_value32(unsigned long *map, int bit, u32 v)
 	const unsigned long offset = (bit % BITS_PER_LONG) & BIT(5);
 
 	map[index] &= ~(0xFFFFFFFFul << offset);
-	map[index] |= v << offset;
+	map[index] |= (unsigned long)v << offset;
 }
 
 static inline int xgpio_regoffset(struct xgpio_instance *chip, int ch)
diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index 66e434f59f60..7a96eb626a08 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -863,7 +863,8 @@ int of_mm_gpiochip_add_data(struct device_node *np,
 	if (mm_gc->save_regs)
 		mm_gc->save_regs(mm_gc);
 
-	mm_gc->gc.of_node = np;
+	of_node_put(mm_gc->gc.of_node);
+	mm_gc->gc.of_node = of_node_get(np);
 
 	ret = gpiochip_add_data(gc, data);
 	if (ret)
@@ -871,6 +872,7 @@ int of_mm_gpiochip_add_data(struct device_node *np,
 
 	return 0;
 err2:
+	of_node_put(np);
 	iounmap(mm_gc->regs);
 err1:
 	kfree(gc->label);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 2eebefd26fa8..4f62f422bcb7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -312,7 +312,7 @@ enum amdgpu_kiq_irq {
 	AMDGPU_CP_KIQ_IRQ_DRIVER0 = 0,
 	AMDGPU_CP_KIQ_IRQ_LAST
 };
-
+#define SRIOV_USEC_TIMEOUT  1200000 /* wait 12 * 100ms for SRIOV */
 #define MAX_KIQ_REG_WAIT       5000 /* in usecs, 5ms */
 #define MAX_KIQ_REG_BAILOUT_INTERVAL   5 /* in msecs, 5ms */
 #define MAX_KIQ_REG_TRY 1000
@@ -1285,6 +1285,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 void amdgpu_device_pci_config_reset(struct amdgpu_device *adev);
 int amdgpu_device_pci_reset(struct amdgpu_device *adev);
 bool amdgpu_device_need_post(struct amdgpu_device *adev);
+bool amdgpu_device_should_use_aspm(struct amdgpu_device *adev);
 
 void amdgpu_cs_report_moved_bytes(struct amdgpu_device *adev, u64 num_bytes,
 				  u64 num_vis_bytes);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 1d41c2c00623..5690cb6d27fe 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -768,7 +768,8 @@ int amdgpu_amdkfd_flush_gpu_tlb_pasid(struct kgd_dev *kgd, uint16_t pasid,
 	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
 	bool all_hub = false;
 
-	if (adev->family == AMDGPU_FAMILY_AI)
+	if (adev->family == AMDGPU_FAMILY_AI ||
+	    adev->family == AMDGPU_FAMILY_RV)
 		all_hub = true;
 
 	return amdgpu_gmc_flush_gpu_tlb_pasid(adev, pasid, flush_type, all_hub);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 21c02f817a84..c904269b3e14 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1318,16 +1318,10 @@ void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev,
 				    struct amdgpu_vm *vm)
 {
 	struct amdkfd_process_info *process_info = vm->process_info;
-	struct amdgpu_bo *pd = vm->root.bo;
 
 	if (!process_info)
 		return;
 
-	/* Release eviction fence from PD */
-	amdgpu_bo_reserve(pd, false);
-	amdgpu_bo_fence(pd, NULL, false);
-	amdgpu_bo_unreserve(pd);
-
 	/* Update process info */
 	mutex_lock(&process_info->lock);
 	process_info->n_vms--;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index a926b5ebbfdf..d1af709cc7dc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1309,6 +1309,31 @@ bool amdgpu_device_need_post(struct amdgpu_device *adev)
 	return true;
 }
 
+/**
+ * amdgpu_device_should_use_aspm - check if the device should program ASPM
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Confirm whether the module parameter and pcie bridge agree that ASPM should
+ * be set for this device.
+ *
+ * Returns true if it should be used or false if not.
+ */
+bool amdgpu_device_should_use_aspm(struct amdgpu_device *adev)
+{
+	switch (amdgpu_aspm) {
+	case -1:
+		break;
+	case 0:
+		return false;
+	case 1:
+		return true;
+	default:
+		return false;
+	}
+	return pcie_aspm_enabled(adev->pdev);
+}
+
 /* if we get transitioned to only one device, take VGA back */
 /**
  * amdgpu_device_vga_set_decode - enable/disable vga decode
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
index cd0acbea75da..d58ab9deb028 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
@@ -341,7 +341,8 @@ int amdgpu_fbdev_init(struct amdgpu_device *adev)
 	}
 
 	/* disable all the possible outputs/crtcs before entering KMS mode */
-	if (!amdgpu_device_has_dc_support(adev) && !amdgpu_virtual_display)
+	if (!amdgpu_device_has_dc_support(adev) && !amdgpu_virtual_display &&
+	    !amdgpu_sriov_vf(adev))
 		drm_helper_disable_unused_functions(adev_to_drm(adev));
 
 	drm_fb_helper_initial_config(&rfbdev->helper, bpp_sel);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
index 4f3c62adccbd..cc2e0c9cfe0a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
@@ -333,6 +333,7 @@ int amdgpu_irq_init(struct amdgpu_device *adev)
 	if (!amdgpu_device_has_dc_support(adev)) {
 		if (!adev->enable_virtual_display)
 			/* Disable vblank IRQs aggressively for power-saving */
+			/* XXX: can this be enabled for DC? */
 			adev_to_drm(adev)->vblank_disable_immediate = true;
 
 		r = drm_vblank_init(adev_to_drm(adev), adev->mode_info.num_crtc);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 41d0b3a7b65d..a0b1bf17cb74 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -912,6 +912,10 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 	if (WARN_ON_ONCE(min_offset > max_offset))
 		return -EINVAL;
 
+	/* Check domain to be pinned to against preferred domains */
+	if (bo->preferred_domains & domain)
+		domain = bo->preferred_domains & domain;
+
 	/* A shared bo cannot be migrated to VRAM */
 	if (bo->tbo.base.import_attach) {
 		if (domain & AMDGPU_GEM_DOMAIN_GTT)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 57e9932d8a04..65744c3bd364 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -2505,7 +2505,7 @@ static int psp_load_smu_fw(struct psp_context *psp)
 static bool fw_load_skip_check(struct psp_context *psp,
 			       struct amdgpu_firmware_info *ucode)
 {
-	if (!ucode->fw)
+	if (!ucode->fw || !ucode->ucode_size)
 		return true;
 
 	if (ucode->ucode_id == AMDGPU_UCODE_ID_SMC &&
@@ -2729,6 +2729,9 @@ static int psp_hw_fini(void *handle)
 		psp_rap_terminate(psp);
 		psp_dtm_terminate(psp);
 		psp_hdcp_terminate(psp);
+
+		if (adev->gmc.xgmi.num_physical_nodes > 1)
+			psp_xgmi_terminate(psp);
 	}
 
 	psp_asd_unload(psp);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index a799e0b1ff73..ce0b9cb61f58 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -723,7 +723,7 @@ int amdgpu_xgmi_remove_device(struct amdgpu_device *adev)
 		amdgpu_put_xgmi_hive(hive);
 	}
 
-	return psp_xgmi_terminate(&adev->psp);
+	return 0;
 }
 
 static int amdgpu_xgmi_ras_late_init(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index f10ce740a29c..de6d10390ab2 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -1719,7 +1719,7 @@ static void cik_program_aspm(struct amdgpu_device *adev)
 	bool disable_l0s = false, disable_l1 = false, disable_plloff_in_l1 = false;
 	bool disable_clkreq = false;
 
-	if (amdgpu_aspm == 0)
+	if (!amdgpu_device_should_use_aspm(adev))
 		return;
 
 	if (pci_is_root_bus(adev->pdev->bus))
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index db27fcf87cd0..16cbae04078a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -2624,7 +2624,8 @@ static void gfx_v9_0_constants_init(struct amdgpu_device *adev)
 
 	gfx_v9_0_tiling_mode_table_init(adev);
 
-	gfx_v9_0_setup_rb(adev);
+	if (adev->gfx.num_gfx_rings)
+		gfx_v9_0_setup_rb(adev);
 	gfx_v9_0_get_cu_info(adev, &adev->gfx.cu_info);
 	adev->gfx.config.db_debug2 = RREG32_SOC15(GC, 0, mmDB_DEBUG2);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 93a4da4284ed..9c07ec8b9732 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -414,6 +414,7 @@ static int gmc_v10_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
 	uint32_t seq;
 	uint16_t queried_pasid;
 	bool ret;
+	u32 usec_timeout = amdgpu_sriov_vf(adev) ? SRIOV_USEC_TIMEOUT : adev->usec_timeout;
 	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
 	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
 
@@ -432,7 +433,7 @@ static int gmc_v10_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
 
 		amdgpu_ring_commit(ring);
 		spin_unlock(&adev->gfx.kiq.ring_lock);
-		r = amdgpu_fence_wait_polling(ring, seq, adev->usec_timeout);
+		r = amdgpu_fence_wait_polling(ring, seq, usec_timeout);
 		if (r < 1) {
 			dev_err(adev->dev, "wait for kiq fence error: %ld.\n", r);
 			return -ETIME;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 0e731016921b..70d24b522df8 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -863,6 +863,7 @@ static int gmc_v9_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
 	uint32_t seq;
 	uint16_t queried_pasid;
 	bool ret;
+	u32 usec_timeout = amdgpu_sriov_vf(adev) ? SRIOV_USEC_TIMEOUT : adev->usec_timeout;
 	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
 	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
 
@@ -902,7 +903,7 @@ static int gmc_v9_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
 
 		amdgpu_ring_commit(ring);
 		spin_unlock(&adev->gfx.kiq.ring_lock);
-		r = amdgpu_fence_wait_polling(ring, seq, adev->usec_timeout);
+		r = amdgpu_fence_wait_polling(ring, seq, usec_timeout);
 		if (r < 1) {
 			dev_err(adev->dev, "wait for kiq fence error: %ld.\n", r);
 			up_read(&adev->reset_sem);
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
index b3bede1dc41d..4259f623a9d7 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
@@ -176,6 +176,7 @@ static void mmhub_v1_0_init_cache_regs(struct amdgpu_device *adev)
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL2, INVALIDATE_L2_CACHE, 1);
 	WREG32_SOC15(MMHUB, 0, mmVM_L2_CNTL2, tmp);
 
+	tmp = mmVM_L2_CNTL3_DEFAULT;
 	if (adev->gmc.translate_further) {
 		tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, BANK_SELECT, 12);
 		tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3,
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
index b184b656b9b6..6f21154d4891 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
@@ -366,6 +366,7 @@ static void nbio_v2_3_enable_aspm(struct amdgpu_device *adev,
 		WREG32_PCIE(smnPCIE_LC_CNTL, data);
 }
 
+#ifdef CONFIG_PCIEASPM
 static void nbio_v2_3_program_ltr(struct amdgpu_device *adev)
 {
 	uint32_t def, data;
@@ -387,9 +388,11 @@ static void nbio_v2_3_program_ltr(struct amdgpu_device *adev)
 	if (def != data)
 		WREG32_PCIE(smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2, data);
 }
+#endif
 
 static void nbio_v2_3_program_aspm(struct amdgpu_device *adev)
 {
+#ifdef CONFIG_PCIEASPM
 	uint32_t def, data;
 
 	def = data = RREG32_PCIE(smnPCIE_LC_CNTL);
@@ -445,7 +448,10 @@ static void nbio_v2_3_program_aspm(struct amdgpu_device *adev)
 	if (def != data)
 		WREG32_PCIE(smnPCIE_LC_CNTL6, data);
 
-	nbio_v2_3_program_ltr(adev);
+	/* Don't bother about LTR if LTR is not enabled
+	 * in the path */
+	if (adev->pdev->ltr_path)
+		nbio_v2_3_program_ltr(adev);
 
 	def = data = RREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP3);
 	data |= 0x5DE0 << RCC_BIF_STRAP3__STRAP_VLINK_ASPM_IDLE_TIMER__SHIFT;
@@ -469,6 +475,7 @@ static void nbio_v2_3_program_aspm(struct amdgpu_device *adev)
 	data &= ~PCIE_LC_CNTL3__LC_DSC_DONT_ENTER_L23_AFTER_PME_ACK_MASK;
 	if (def != data)
 		WREG32_PCIE(smnPCIE_LC_CNTL3, data);
+#endif
 }
 
 static void nbio_v2_3_apply_lc_spc_mode_wa(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c
index 0d2d629e2d6a..be3f6c52c3ff 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c
@@ -278,6 +278,7 @@ static void nbio_v6_1_init_registers(struct amdgpu_device *adev)
 		WREG32_PCIE(smnPCIE_CI_CNTL, data);
 }
 
+#ifdef CONFIG_PCIEASPM
 static void nbio_v6_1_program_ltr(struct amdgpu_device *adev)
 {
 	uint32_t def, data;
@@ -299,9 +300,11 @@ static void nbio_v6_1_program_ltr(struct amdgpu_device *adev)
 	if (def != data)
 		WREG32_PCIE(smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2, data);
 }
+#endif
 
 static void nbio_v6_1_program_aspm(struct amdgpu_device *adev)
 {
+#ifdef CONFIG_PCIEASPM
 	uint32_t def, data;
 
 	def = data = RREG32_PCIE(smnPCIE_LC_CNTL);
@@ -357,7 +360,10 @@ static void nbio_v6_1_program_aspm(struct amdgpu_device *adev)
 	if (def != data)
 		WREG32_PCIE(smnPCIE_LC_CNTL6, data);
 
-	nbio_v6_1_program_ltr(adev);
+	/* Don't bother about LTR if LTR is not enabled
+	 * in the path */
+	if (adev->pdev->ltr_path)
+		nbio_v6_1_program_ltr(adev);
 
 	def = data = RREG32_PCIE(smnRCC_BIF_STRAP3);
 	data |= 0x5DE0 << RCC_BIF_STRAP3__STRAP_VLINK_ASPM_IDLE_TIMER__SHIFT;
@@ -381,6 +387,7 @@ static void nbio_v6_1_program_aspm(struct amdgpu_device *adev)
 	data &= ~PCIE_LC_CNTL3__LC_DSC_DONT_ENTER_L23_AFTER_PME_ACK_MASK;
 	if (def != data)
 		WREG32_PCIE(smnPCIE_LC_CNTL3, data);
+#endif
 }
 
 const struct amdgpu_nbio_funcs nbio_v6_1_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
index f50045cebd44..74cd7543729b 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
@@ -630,6 +630,7 @@ const struct amdgpu_nbio_ras_funcs nbio_v7_4_ras_funcs = {
 	.ras_fini = amdgpu_nbio_ras_fini,
 };
 
+#ifdef CONFIG_PCIEASPM
 static void nbio_v7_4_program_ltr(struct amdgpu_device *adev)
 {
 	uint32_t def, data;
@@ -651,9 +652,11 @@ static void nbio_v7_4_program_ltr(struct amdgpu_device *adev)
 	if (def != data)
 		WREG32_PCIE(smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2, data);
 }
+#endif
 
 static void nbio_v7_4_program_aspm(struct amdgpu_device *adev)
 {
+#ifdef CONFIG_PCIEASPM
 	uint32_t def, data;
 
 	def = data = RREG32_PCIE(smnPCIE_LC_CNTL);
@@ -709,7 +712,10 @@ static void nbio_v7_4_program_aspm(struct amdgpu_device *adev)
 	if (def != data)
 		WREG32_PCIE(smnPCIE_LC_CNTL6, data);
 
-	nbio_v7_4_program_ltr(adev);
+	/* Don't bother about LTR if LTR is not enabled
+	 * in the path */
+	if (adev->pdev->ltr_path)
+		nbio_v7_4_program_ltr(adev);
 
 	def = data = RREG32_PCIE(smnRCC_BIF_STRAP3);
 	data |= 0x5DE0 << RCC_BIF_STRAP3__STRAP_VLINK_ASPM_IDLE_TIMER__SHIFT;
@@ -733,6 +739,7 @@ static void nbio_v7_4_program_aspm(struct amdgpu_device *adev)
 	data &= ~PCIE_LC_CNTL3__LC_DSC_DONT_ENTER_L23_AFTER_PME_ACK_MASK;
 	if (def != data)
 		WREG32_PCIE(smnPCIE_LC_CNTL3, data);
+#endif
 }
 
 const struct amdgpu_nbio_funcs nbio_v7_4_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 9cbed9a8f1c0..6e277236b44f 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -584,7 +584,7 @@ static void nv_pcie_gen3_enable(struct amdgpu_device *adev)
 
 static void nv_program_aspm(struct amdgpu_device *adev)
 {
-	if (!amdgpu_aspm)
+	if (!amdgpu_device_should_use_aspm(adev))
 		return;
 
 	if (!(adev->flags & AMD_IS_APU) &&
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 9014f71d52dd..8b20326c4c05 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -1507,6 +1507,11 @@ static int sdma_v4_0_start(struct amdgpu_device *adev)
 		WREG32_SDMA(i, mmSDMA0_CNTL, temp);
 
 		if (!amdgpu_sriov_vf(adev)) {
+			ring = &adev->sdma.instance[i].ring;
+			adev->nbio.funcs->sdma_doorbell_range(adev, i,
+				ring->use_doorbell, ring->doorbell_index,
+				adev->doorbell_index.sdma_doorbell_range);
+
 			/* unhalt engine */
 			temp = RREG32_SDMA(i, mmSDMA0_F32_CNTL);
 			temp = REG_SET_FIELD(temp, SDMA0_F32_CNTL, HALT, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/si.c b/drivers/gpu/drm/amd/amdgpu/si.c
index e6d2f74a7976..7f99e130acd0 100644
--- a/drivers/gpu/drm/amd/amdgpu/si.c
+++ b/drivers/gpu/drm/amd/amdgpu/si.c
@@ -2453,7 +2453,7 @@ static void si_program_aspm(struct amdgpu_device *adev)
 	bool disable_l0s = false, disable_l1 = false, disable_plloff_in_l1 = false;
 	bool disable_clkreq = false;
 
-	if (amdgpu_aspm == 0)
+	if (!amdgpu_device_should_use_aspm(adev))
 		return;
 
 	if (adev->flags & AMD_IS_APU)
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 6439d5c3d8d8..7d5ff50435e5 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -689,7 +689,7 @@ static void soc15_pcie_gen3_enable(struct amdgpu_device *adev)
 
 static void soc15_program_aspm(struct amdgpu_device *adev)
 {
-	if (!amdgpu_aspm)
+	if (!amdgpu_device_should_use_aspm(adev))
 		return;
 
 	if (!(adev->flags & AMD_IS_APU) &&
@@ -1416,25 +1416,6 @@ static int soc15_common_sw_fini(void *handle)
 	return 0;
 }
 
-static void soc15_doorbell_range_init(struct amdgpu_device *adev)
-{
-	int i;
-	struct amdgpu_ring *ring;
-
-	/* sdma/ih doorbell range are programed by hypervisor */
-	if (!amdgpu_sriov_vf(adev)) {
-		for (i = 0; i < adev->sdma.num_instances; i++) {
-			ring = &adev->sdma.instance[i].ring;
-			adev->nbio.funcs->sdma_doorbell_range(adev, i,
-				ring->use_doorbell, ring->doorbell_index,
-				adev->doorbell_index.sdma_doorbell_range);
-		}
-
-		adev->nbio.funcs->ih_doorbell_range(adev, adev->irq.ih.use_doorbell,
-						adev->irq.ih.doorbell_index);
-	}
-}
-
 static int soc15_common_hw_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -1454,12 +1435,6 @@ static int soc15_common_hw_init(void *handle)
 
 	/* enable the doorbell aperture */
 	soc15_enable_doorbell_aperture(adev, true);
-	/* HW doorbell routing policy: doorbell writing not
-	 * in SDMA/IH/MM/ACV range will be routed to CP. So
-	 * we need to init SDMA/IH/MM/ACV doorbell range prior
-	 * to CP ip block init and ring test.
-	 */
-	soc15_doorbell_range_init(adev);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
index 6e56bef4fdf8..1310617f030f 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -1511,7 +1511,7 @@ static int vcn_v3_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
 	struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__UNPAUSE};
 	uint32_t tmp;
 
-	vcn_v3_0_pause_dpg_mode(adev, 0, &state);
+	vcn_v3_0_pause_dpg_mode(adev, inst_idx, &state);
 
 	/* Wait for power status to be 1 */
 	SOC15_WAIT_ON_RREG(VCN, inst_idx, mmUVD_POWER_STATUS, 1,
diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
index a9ca6988009e..73728fa85997 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
@@ -289,6 +289,10 @@ static int vega10_ih_irq_init(struct amdgpu_device *adev)
 		}
 	}
 
+	if (!amdgpu_sriov_vf(adev))
+		adev->nbio.funcs->ih_doorbell_range(adev, adev->irq.ih.use_doorbell,
+						    adev->irq.ih.doorbell_index);
+
 	pci_set_master(adev->pdev);
 
 	/* enable interrupts */
diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
index f51dfc38ac65..ac34af4cb178 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
@@ -340,6 +340,10 @@ static int vega20_ih_irq_init(struct amdgpu_device *adev)
 		}
 	}
 
+	if (!amdgpu_sriov_vf(adev))
+		adev->nbio.funcs->ih_doorbell_range(adev, adev->irq.ih.use_doorbell,
+						    adev->irq.ih.doorbell_index);
+
 	pci_set_master(adev->pdev);
 
 	/* enable interrupts */
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 6645ebbd2696..45f0188c4273 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -81,6 +81,10 @@
 #include "mxgpu_vi.h"
 #include "amdgpu_dm.h"
 
+#if IS_ENABLED(CONFIG_X86)
+#include <asm/intel-family.h>
+#endif
+
 #define ixPCIE_LC_L1_PM_SUBSTATE	0x100100C6
 #define PCIE_LC_L1_PM_SUBSTATE__LC_L1_SUBSTATES_OVERRIDE_EN_MASK	0x00000001L
 #define PCIE_LC_L1_PM_SUBSTATE__LC_PCI_PM_L1_2_OVERRIDE_MASK	0x00000002L
@@ -1134,13 +1138,24 @@ static void vi_enable_aspm(struct amdgpu_device *adev)
 		WREG32_PCIE(ixPCIE_LC_CNTL, data);
 }
 
+static bool aspm_support_quirk_check(void)
+{
+#if IS_ENABLED(CONFIG_X86)
+	struct cpuinfo_x86 *c = &cpu_data(0);
+
+	return !(c->x86 == 6 && c->x86_model == INTEL_FAM6_ALDERLAKE);
+#else
+	return true;
+#endif
+}
+
 static void vi_program_aspm(struct amdgpu_device *adev)
 {
 	u32 data, data1, orig;
 	bool bL1SS = false;
 	bool bClkReqSupport = true;
 
-	if (!amdgpu_aspm)
+	if (!amdgpu_device_should_use_aspm(adev) || !aspm_support_quirk_check())
 		return;
 
 	if (adev->flags & AMD_IS_APU ||
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index d2aecf7bf66b..e3dfea3d44a4 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -70,6 +70,7 @@
 #include <linux/pci.h>
 #include <linux/firmware.h>
 #include <linux/component.h>
+#include <linux/dmi.h>
 
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_uapi.h>
@@ -215,6 +216,8 @@ static void handle_cursor_update(struct drm_plane *plane,
 static const struct drm_format_info *
 amd_get_format_info(const struct drm_mode_fb_cmd2 *cmd);
 
+static void handle_hpd_irq_helper(struct amdgpu_dm_connector *aconnector);
+
 static bool
 is_timing_unchanged_for_freesync(struct drm_crtc_state *old_crtc_state,
 				 struct drm_crtc_state *new_crtc_state);
@@ -618,6 +621,113 @@ static void dm_dcn_vertical_interrupt0_high_irq(void *interrupt_params)
 }
 #endif
 
+/**
+ * dmub_aux_setconfig_reply_callback - Callback for AUX or SET_CONFIG command.
+ * @adev: amdgpu_device pointer
+ * @notify: dmub notification structure
+ *
+ * Dmub AUX or SET_CONFIG command completion processing callback
+ * Copies dmub notification to DM which is to be read by AUX command.
+ * issuing thread and also signals the event to wake up the thread.
+ */
+void dmub_aux_setconfig_callback(struct amdgpu_device *adev, struct dmub_notification *notify)
+{
+	if (adev->dm.dmub_notify)
+		memcpy(adev->dm.dmub_notify, notify, sizeof(struct dmub_notification));
+	if (notify->type == DMUB_NOTIFICATION_AUX_REPLY)
+		complete(&adev->dm.dmub_aux_transfer_done);
+}
+
+/**
+ * dmub_hpd_callback - DMUB HPD interrupt processing callback.
+ * @adev: amdgpu_device pointer
+ * @notify: dmub notification structure
+ *
+ * Dmub Hpd interrupt processing callback. Gets displayindex through the
+ * ink index and calls helper to do the processing.
+ */
+void dmub_hpd_callback(struct amdgpu_device *adev, struct dmub_notification *notify)
+{
+	struct amdgpu_dm_connector *aconnector;
+	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
+	struct dc_link *link;
+	uint8_t link_index = 0;
+	struct drm_device *dev;
+
+	if (adev == NULL)
+		return;
+
+	if (notify == NULL) {
+		DRM_ERROR("DMUB HPD callback notification was NULL");
+		return;
+	}
+
+	if (notify->link_index > adev->dm.dc->link_count) {
+		DRM_ERROR("DMUB HPD index (%u)is abnormal", notify->link_index);
+		return;
+	}
+
+	link_index = notify->link_index;
+	link = adev->dm.dc->links[link_index];
+	dev = adev->dm.ddev;
+
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
+		aconnector = to_amdgpu_dm_connector(connector);
+		if (link && aconnector->dc_link == link) {
+			DRM_INFO("DMUB HPD callback: link_index=%u\n", link_index);
+			handle_hpd_irq_helper(aconnector);
+			break;
+		}
+	}
+	drm_connector_list_iter_end(&iter);
+
+}
+
+/**
+ * register_dmub_notify_callback - Sets callback for DMUB notify
+ * @adev: amdgpu_device pointer
+ * @type: Type of dmub notification
+ * @callback: Dmub interrupt callback function
+ * @dmub_int_thread_offload: offload indicator
+ *
+ * API to register a dmub callback handler for a dmub notification
+ * Also sets indicator whether callback processing to be offloaded.
+ * to dmub interrupt handling thread
+ * Return: true if successfully registered, false if there is existing registration
+ */
+bool register_dmub_notify_callback(struct amdgpu_device *adev, enum dmub_notification_type type,
+dmub_notify_interrupt_callback_t callback, bool dmub_int_thread_offload)
+{
+	if (callback != NULL && type < ARRAY_SIZE(adev->dm.dmub_thread_offload)) {
+		adev->dm.dmub_callback[type] = callback;
+		adev->dm.dmub_thread_offload[type] = dmub_int_thread_offload;
+	} else
+		return false;
+
+	return true;
+}
+
+static void dm_handle_hpd_work(struct work_struct *work)
+{
+	struct dmub_hpd_work *dmub_hpd_wrk;
+
+	dmub_hpd_wrk = container_of(work, struct dmub_hpd_work, handle_hpd_work);
+
+	if (!dmub_hpd_wrk->dmub_notify) {
+		DRM_ERROR("dmub_hpd_wrk dmub_notify is NULL");
+		return;
+	}
+
+	if (dmub_hpd_wrk->dmub_notify->type < ARRAY_SIZE(dmub_hpd_wrk->adev->dm.dmub_callback)) {
+		dmub_hpd_wrk->adev->dm.dmub_callback[dmub_hpd_wrk->dmub_notify->type](dmub_hpd_wrk->adev,
+		dmub_hpd_wrk->dmub_notify);
+	}
+	kfree(dmub_hpd_wrk);
+
+}
+
 #define DMUB_TRACE_MAX_READ 64
 /**
  * dm_dmub_outbox1_low_irq() - Handles Outbox interrupt
@@ -634,18 +744,33 @@ static void dm_dmub_outbox1_low_irq(void *interrupt_params)
 	struct amdgpu_display_manager *dm = &adev->dm;
 	struct dmcub_trace_buf_entry entry = { 0 };
 	uint32_t count = 0;
+	struct dmub_hpd_work *dmub_hpd_wrk;
 
 	if (dc_enable_dmub_notifications(adev->dm.dc)) {
+		dmub_hpd_wrk = kzalloc(sizeof(*dmub_hpd_wrk), GFP_ATOMIC);
+		if (!dmub_hpd_wrk) {
+			DRM_ERROR("Failed to allocate dmub_hpd_wrk");
+			return;
+		}
+		INIT_WORK(&dmub_hpd_wrk->handle_hpd_work, dm_handle_hpd_work);
+
 		if (irq_params->irq_src == DC_IRQ_SOURCE_DMCUB_OUTBOX) {
 			do {
 				dc_stat_get_dmub_notification(adev->dm.dc, &notify);
-			} while (notify.pending_notification);
+				if (notify.type >= ARRAY_SIZE(dm->dmub_thread_offload)) {
+					DRM_ERROR("DM: notify type %d larger than the array size %zu!", notify.type,
+					ARRAY_SIZE(dm->dmub_thread_offload));
+					continue;
+				}
+				if (dm->dmub_thread_offload[notify.type] == true) {
+					dmub_hpd_wrk->dmub_notify = &notify;
+					dmub_hpd_wrk->adev = adev;
+					queue_work(adev->dm.delayed_hpd_wq, &dmub_hpd_wrk->handle_hpd_work);
+				} else {
+					dm->dmub_callback[notify.type](adev, &notify);
+				}
 
-			if (adev->dm.dmub_notify)
-				memcpy(adev->dm.dmub_notify, &notify, sizeof(struct dmub_notification));
-			if (notify.type == DMUB_NOTIFICATION_AUX_REPLY)
-				complete(&adev->dm.dmub_aux_transfer_done);
-			// TODO : HPD Implementation
+			} while (notify.pending_notification);
 
 		} else {
 			DRM_ERROR("DM: Failed to receive correct outbox IRQ !");
@@ -900,6 +1025,11 @@ static int dm_dmub_hw_init(struct amdgpu_device *adev)
 		return 0;
 	}
 
+	/* Reset DMCUB if it was previously running - before we overwrite its memory. */
+	status = dmub_srv_hw_reset(dmub_srv);
+	if (status != DMUB_STATUS_OK)
+		DRM_WARN("Error resetting DMUB HW: %d\n", status);
+
 	hdr = (const struct dmcub_firmware_header_v1_0 *)dmub_fw->data;
 
 	fw_inst_const = dmub_fw->data +
@@ -1109,6 +1239,149 @@ static void vblank_control_worker(struct work_struct *work)
 }
 
 #endif
+
+static void dm_handle_hpd_rx_offload_work(struct work_struct *work)
+{
+	struct hpd_rx_irq_offload_work *offload_work;
+	struct amdgpu_dm_connector *aconnector;
+	struct dc_link *dc_link;
+	struct amdgpu_device *adev;
+	enum dc_connection_type new_connection_type = dc_connection_none;
+	unsigned long flags;
+
+	offload_work = container_of(work, struct hpd_rx_irq_offload_work, work);
+	aconnector = offload_work->offload_wq->aconnector;
+
+	if (!aconnector) {
+		DRM_ERROR("Can't retrieve aconnector in hpd_rx_irq_offload_work");
+		goto skip;
+	}
+
+	adev = drm_to_adev(aconnector->base.dev);
+	dc_link = aconnector->dc_link;
+
+	mutex_lock(&aconnector->hpd_lock);
+	if (!dc_link_detect_sink(dc_link, &new_connection_type))
+		DRM_ERROR("KMS: Failed to detect connector\n");
+	mutex_unlock(&aconnector->hpd_lock);
+
+	if (new_connection_type == dc_connection_none)
+		goto skip;
+
+	if (amdgpu_in_reset(adev))
+		goto skip;
+
+	mutex_lock(&adev->dm.dc_lock);
+	if (offload_work->data.bytes.device_service_irq.bits.AUTOMATED_TEST)
+		dc_link_dp_handle_automated_test(dc_link);
+	else if ((dc_link->connector_signal != SIGNAL_TYPE_EDP) &&
+			hpd_rx_irq_check_link_loss_status(dc_link, &offload_work->data) &&
+			dc_link_dp_allow_hpd_rx_irq(dc_link)) {
+		dc_link_dp_handle_link_loss(dc_link);
+		spin_lock_irqsave(&offload_work->offload_wq->offload_lock, flags);
+		offload_work->offload_wq->is_handling_link_loss = false;
+		spin_unlock_irqrestore(&offload_work->offload_wq->offload_lock, flags);
+	}
+	mutex_unlock(&adev->dm.dc_lock);
+
+skip:
+	kfree(offload_work);
+
+}
+
+static struct hpd_rx_irq_offload_work_queue *hpd_rx_irq_create_workqueue(struct dc *dc)
+{
+	int max_caps = dc->caps.max_links;
+	int i = 0;
+	struct hpd_rx_irq_offload_work_queue *hpd_rx_offload_wq = NULL;
+
+	hpd_rx_offload_wq = kcalloc(max_caps, sizeof(*hpd_rx_offload_wq), GFP_KERNEL);
+
+	if (!hpd_rx_offload_wq)
+		return NULL;
+
+
+	for (i = 0; i < max_caps; i++) {
+		hpd_rx_offload_wq[i].wq =
+				    create_singlethread_workqueue("amdgpu_dm_hpd_rx_offload_wq");
+
+		if (hpd_rx_offload_wq[i].wq == NULL) {
+			DRM_ERROR("create amdgpu_dm_hpd_rx_offload_wq fail!");
+			return NULL;
+		}
+
+		spin_lock_init(&hpd_rx_offload_wq[i].offload_lock);
+	}
+
+	return hpd_rx_offload_wq;
+}
+
+struct amdgpu_stutter_quirk {
+	u16 chip_vendor;
+	u16 chip_device;
+	u16 subsys_vendor;
+	u16 subsys_device;
+	u8 revision;
+};
+
+static const struct amdgpu_stutter_quirk amdgpu_stutter_quirk_list[] = {
+	/* https://bugzilla.kernel.org/show_bug.cgi?id=214417 */
+	{ 0x1002, 0x15dd, 0x1002, 0x15dd, 0xc8 },
+	{ 0, 0, 0, 0, 0 },
+};
+
+static bool dm_should_disable_stutter(struct pci_dev *pdev)
+{
+	const struct amdgpu_stutter_quirk *p = amdgpu_stutter_quirk_list;
+
+	while (p && p->chip_device != 0) {
+		if (pdev->vendor == p->chip_vendor &&
+		    pdev->device == p->chip_device &&
+		    pdev->subsystem_vendor == p->subsys_vendor &&
+		    pdev->subsystem_device == p->subsys_device &&
+		    pdev->revision == p->revision) {
+			return true;
+		}
+		++p;
+	}
+	return false;
+}
+
+static const struct dmi_system_id hpd_disconnect_quirk_table[] = {
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3660"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3260"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3460"),
+		},
+	},
+	{}
+};
+
+static void retrieve_dmi_info(struct amdgpu_display_manager *dm)
+{
+	const struct dmi_system_id *dmi_id;
+
+	dm->aux_hpd_discon_quirk = false;
+
+	dmi_id = dmi_first_match(hpd_disconnect_quirk_table);
+	if (dmi_id) {
+		dm->aux_hpd_discon_quirk = true;
+		DRM_INFO("aux_hpd_discon_quirk attached\n");
+	}
+}
+
 static int amdgpu_dm_init(struct amdgpu_device *adev)
 {
 	struct dc_init_data init_data;
@@ -1200,6 +1473,9 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 	init_data.flags.power_down_display_on_boot = true;
 
 	INIT_LIST_HEAD(&adev->dm.da_list);
+
+	retrieve_dmi_info(&adev->dm);
+
 	/* Display Core create. */
 	adev->dm.dc = dc_create(&init_data);
 
@@ -1217,6 +1493,8 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 
 	if (adev->asic_type != CHIP_CARRIZO && adev->asic_type != CHIP_STONEY)
 		adev->dm.dc->debug.disable_stutter = amdgpu_pp_feature_mask & PP_STUTTER_MODE ? false : true;
+	if (dm_should_disable_stutter(adev->pdev))
+		adev->dm.dc->debug.disable_stutter = true;
 
 	if (amdgpu_dc_debug_mask & DC_DISABLE_STUTTER)
 		adev->dm.dc->debug.disable_stutter = true;
@@ -1235,6 +1513,12 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 
 	dc_hardware_init(adev->dm.dc);
 
+	adev->dm.hpd_rx_offload_wq = hpd_rx_irq_create_workqueue(adev->dm.dc);
+	if (!adev->dm.hpd_rx_offload_wq) {
+		DRM_ERROR("amdgpu: failed to create hpd rx offload workqueue.\n");
+		goto error;
+	}
+
 #if defined(CONFIG_DRM_AMD_DC_DCN)
 	if ((adev->flags & AMD_IS_APU) && (adev->asic_type >= CHIP_CARRIZO)) {
 		struct dc_phy_addr_space_config pa_config;
@@ -1287,7 +1571,25 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 			DRM_INFO("amdgpu: fail to allocate adev->dm.dmub_notify");
 			goto error;
 		}
+
+		adev->dm.delayed_hpd_wq = create_singlethread_workqueue("amdgpu_dm_hpd_wq");
+		if (!adev->dm.delayed_hpd_wq) {
+			DRM_ERROR("amdgpu: failed to create hpd offload workqueue.\n");
+			goto error;
+		}
+
 		amdgpu_dm_outbox_init(adev);
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+		if (!register_dmub_notify_callback(adev, DMUB_NOTIFICATION_AUX_REPLY,
+			dmub_aux_setconfig_callback, false)) {
+			DRM_ERROR("amdgpu: fail to register dmub aux callback");
+			goto error;
+		}
+		if (!register_dmub_notify_callback(adev, DMUB_NOTIFICATION_HPD, dmub_hpd_callback, true)) {
+			DRM_ERROR("amdgpu: fail to register dmub hpd callback");
+			goto error;
+		}
+#endif
 	}
 
 	if (amdgpu_dm_initialize_drm_device(adev)) {
@@ -1369,6 +1671,8 @@ static void amdgpu_dm_fini(struct amdgpu_device *adev)
 	if (dc_enable_dmub_notifications(adev->dm.dc)) {
 		kfree(adev->dm.dmub_notify);
 		adev->dm.dmub_notify = NULL;
+		destroy_workqueue(adev->dm.delayed_hpd_wq);
+		adev->dm.delayed_hpd_wq = NULL;
 	}
 
 	if (adev->dm.dmub_bo)
@@ -1394,6 +1698,18 @@ static void amdgpu_dm_fini(struct amdgpu_device *adev)
 		adev->dm.freesync_module = NULL;
 	}
 
+	if (adev->dm.hpd_rx_offload_wq) {
+		for (i = 0; i < adev->dm.dc->caps.max_links; i++) {
+			if (adev->dm.hpd_rx_offload_wq[i].wq) {
+				destroy_workqueue(adev->dm.hpd_rx_offload_wq[i].wq);
+				adev->dm.hpd_rx_offload_wq[i].wq = NULL;
+			}
+		}
+
+		kfree(adev->dm.hpd_rx_offload_wq);
+		adev->dm.hpd_rx_offload_wq = NULL;
+	}
+
 	mutex_destroy(&adev->dm.audio_lock);
 	mutex_destroy(&adev->dm.dc_lock);
 
@@ -2013,6 +2329,16 @@ context_alloc_fail:
 	return res;
 }
 
+static void hpd_rx_irq_work_suspend(struct amdgpu_display_manager *dm)
+{
+	int i;
+
+	if (dm->hpd_rx_offload_wq) {
+		for (i = 0; i < dm->dc->caps.max_links; i++)
+			flush_workqueue(dm->hpd_rx_offload_wq[i].wq);
+	}
+}
+
 static int dm_suspend(void *handle)
 {
 	struct amdgpu_device *adev = handle;
@@ -2034,6 +2360,8 @@ static int dm_suspend(void *handle)
 
 		amdgpu_dm_irq_suspend(adev);
 
+		hpd_rx_irq_work_suspend(dm);
+
 		return ret;
 	}
 
@@ -2044,6 +2372,8 @@ static int dm_suspend(void *handle)
 
 	amdgpu_dm_irq_suspend(adev);
 
+	hpd_rx_irq_work_suspend(dm);
+
 	dc_set_power_state(dm->dc, DC_ACPI_CM_POWER_STATE_D3);
 
 	return 0;
@@ -2654,9 +2984,8 @@ void amdgpu_dm_update_connector_after_detect(
 		dc_sink_release(sink);
 }
 
-static void handle_hpd_irq(void *param)
+static void handle_hpd_irq_helper(struct amdgpu_dm_connector *aconnector)
 {
-	struct amdgpu_dm_connector *aconnector = (struct amdgpu_dm_connector *)param;
 	struct drm_connector *connector = &aconnector->base;
 	struct drm_device *dev = connector->dev;
 	enum dc_connection_type new_connection_type = dc_connection_none;
@@ -2715,7 +3044,15 @@ static void handle_hpd_irq(void *param)
 
 }
 
-static void dm_handle_hpd_rx_irq(struct amdgpu_dm_connector *aconnector)
+static void handle_hpd_irq(void *param)
+{
+	struct amdgpu_dm_connector *aconnector = (struct amdgpu_dm_connector *)param;
+
+	handle_hpd_irq_helper(aconnector);
+
+}
+
+static void dm_handle_mst_sideband_msg(struct amdgpu_dm_connector *aconnector)
 {
 	uint8_t esi[DP_PSR_ERROR_STATUS - DP_SINK_COUNT_ESI] = { 0 };
 	uint8_t dret;
@@ -2793,6 +3130,25 @@ static void dm_handle_hpd_rx_irq(struct amdgpu_dm_connector *aconnector)
 		DRM_DEBUG_DRIVER("Loop exceeded max iterations\n");
 }
 
+static void schedule_hpd_rx_offload_work(struct hpd_rx_irq_offload_work_queue *offload_wq,
+							union hpd_irq_data hpd_irq_data)
+{
+	struct hpd_rx_irq_offload_work *offload_work =
+				kzalloc(sizeof(*offload_work), GFP_KERNEL);
+
+	if (!offload_work) {
+		DRM_ERROR("Failed to allocate hpd_rx_irq_offload_work.\n");
+		return;
+	}
+
+	INIT_WORK(&offload_work->work, dm_handle_hpd_rx_offload_work);
+	offload_work->data = hpd_irq_data;
+	offload_work->offload_wq = offload_wq;
+
+	queue_work(offload_wq->wq, &offload_work->work);
+	DRM_DEBUG_KMS("queue work to handle hpd_rx offload work");
+}
+
 static void handle_hpd_rx_irq(void *param)
 {
 	struct amdgpu_dm_connector *aconnector = (struct amdgpu_dm_connector *)param;
@@ -2804,14 +3160,16 @@ static void handle_hpd_rx_irq(void *param)
 	enum dc_connection_type new_connection_type = dc_connection_none;
 	struct amdgpu_device *adev = drm_to_adev(dev);
 	union hpd_irq_data hpd_irq_data;
-	bool lock_flag = 0;
+	bool link_loss = false;
+	bool has_left_work = false;
+	int idx = aconnector->base.index;
+	struct hpd_rx_irq_offload_work_queue *offload_wq = &adev->dm.hpd_rx_offload_wq[idx];
 
 	memset(&hpd_irq_data, 0, sizeof(hpd_irq_data));
 
 	if (adev->dm.disable_hpd_irq)
 		return;
 
-
 	/*
 	 * TODO:Temporary add mutex to protect hpd interrupt not have a gpio
 	 * conflict, after implement i2c helper, this mutex should be
@@ -2819,43 +3177,41 @@ static void handle_hpd_rx_irq(void *param)
 	 */
 	mutex_lock(&aconnector->hpd_lock);
 
-	read_hpd_rx_irq_data(dc_link, &hpd_irq_data);
+	result = dc_link_handle_hpd_rx_irq(dc_link, &hpd_irq_data,
+						&link_loss, true, &has_left_work);
 
-	if ((dc_link->cur_link_settings.lane_count != LANE_COUNT_UNKNOWN) ||
-		(dc_link->type == dc_connection_mst_branch)) {
-		if (hpd_irq_data.bytes.device_service_irq.bits.UP_REQ_MSG_RDY) {
-			result = true;
-			dm_handle_hpd_rx_irq(aconnector);
-			goto out;
-		} else if (hpd_irq_data.bytes.device_service_irq.bits.DOWN_REP_MSG_RDY) {
-			result = false;
-			dm_handle_hpd_rx_irq(aconnector);
+	if (!has_left_work)
+		goto out;
+
+	if (hpd_irq_data.bytes.device_service_irq.bits.AUTOMATED_TEST) {
+		schedule_hpd_rx_offload_work(offload_wq, hpd_irq_data);
+		goto out;
+	}
+
+	if (dc_link_dp_allow_hpd_rx_irq(dc_link)) {
+		if (hpd_irq_data.bytes.device_service_irq.bits.UP_REQ_MSG_RDY ||
+			hpd_irq_data.bytes.device_service_irq.bits.DOWN_REP_MSG_RDY) {
+			dm_handle_mst_sideband_msg(aconnector);
 			goto out;
 		}
-	}
 
-	/*
-	 * TODO: We need the lock to avoid touching DC state while it's being
-	 * modified during automated compliance testing, or when link loss
-	 * happens. While this should be split into subhandlers and proper
-	 * interfaces to avoid having to conditionally lock like this in the
-	 * outer layer, we need this workaround temporarily to allow MST
-	 * lightup in some scenarios to avoid timeout.
-	 */
-	if (!amdgpu_in_reset(adev) &&
-	    (hpd_rx_irq_check_link_loss_status(dc_link, &hpd_irq_data) ||
-	     hpd_irq_data.bytes.device_service_irq.bits.AUTOMATED_TEST)) {
-		mutex_lock(&adev->dm.dc_lock);
-		lock_flag = 1;
-	}
+		if (link_loss) {
+			bool skip = false;
 
-#ifdef CONFIG_DRM_AMD_DC_HDCP
-	result = dc_link_handle_hpd_rx_irq(dc_link, &hpd_irq_data, NULL);
-#else
-	result = dc_link_handle_hpd_rx_irq(dc_link, NULL, NULL);
-#endif
-	if (!amdgpu_in_reset(adev) && lock_flag)
-		mutex_unlock(&adev->dm.dc_lock);
+			spin_lock(&offload_wq->offload_lock);
+			skip = offload_wq->is_handling_link_loss;
+
+			if (!skip)
+				offload_wq->is_handling_link_loss = true;
+
+			spin_unlock(&offload_wq->offload_lock);
+
+			if (!skip)
+				schedule_hpd_rx_offload_work(offload_wq, hpd_irq_data);
+
+			goto out;
+		}
+	}
 
 out:
 	if (result && !is_mst_root_connector) {
@@ -2940,6 +3296,10 @@ static void register_hpd_handlers(struct amdgpu_device *adev)
 			amdgpu_dm_irq_register_interrupt(adev, &int_params,
 					handle_hpd_rx_irq,
 					(void *) aconnector);
+
+			if (adev->dm.hpd_rx_offload_wq)
+				adev->dm.hpd_rx_offload_wq[connector->index].aconnector =
+					aconnector;
 		}
 	}
 }
@@ -3838,9 +4198,6 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 	}
 #endif
 
-	/* Disable vblank IRQs aggressively for power-saving. */
-	adev_to_drm(adev)->vblank_disable_immediate = true;
-
 	/* loops over all connectors on the board */
 	for (i = 0; i < link_cnt; i++) {
 		struct dc_link *link = NULL;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index 46d6e65f6bd4..f9c3e5a41713 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -47,6 +47,8 @@
 #define AMDGPU_DM_MAX_CRTC 6
 
 #define AMDGPU_DM_MAX_NUM_EDP 2
+
+#define AMDGPU_DMUB_NOTIFICATION_MAX 5
 /*
 #include "include/amdgpu_dal_power_if.h"
 #include "amdgpu_dm_irq.h"
@@ -86,6 +88,21 @@ struct dm_compressor_info {
 	uint64_t gpu_addr;
 };
 
+typedef void (*dmub_notify_interrupt_callback_t)(struct amdgpu_device *adev, struct dmub_notification *notify);
+
+/**
+ * struct dmub_hpd_work - Handle time consuming work in low priority outbox IRQ
+ *
+ * @handle_hpd_work: Work to be executed in a separate thread to handle hpd_low_irq
+ * @dmub_notify:  notification for callback function
+ * @adev: amdgpu_device pointer
+ */
+struct dmub_hpd_work {
+	struct work_struct handle_hpd_work;
+	struct dmub_notification *dmub_notify;
+	struct amdgpu_device *adev;
+};
+
 /**
  * struct vblank_control_work - Work data for vblank control
  * @work: Kernel work data for the work event
@@ -155,6 +172,48 @@ struct dal_allocation {
 };
 
 /**
+ * struct hpd_rx_irq_offload_work_queue - Work queue to handle hpd_rx_irq
+ * offload work
+ */
+struct hpd_rx_irq_offload_work_queue {
+	/**
+	 * @wq: workqueue structure to queue offload work.
+	 */
+	struct workqueue_struct *wq;
+	/**
+	 * @offload_lock: To protect fields of offload work queue.
+	 */
+	spinlock_t offload_lock;
+	/**
+	 * @is_handling_link_loss: Used to prevent inserting link loss event when
+	 * we're handling link loss
+	 */
+	bool is_handling_link_loss;
+	/**
+	 * @aconnector: The aconnector that this work queue is attached to
+	 */
+	struct amdgpu_dm_connector *aconnector;
+};
+
+/**
+ * struct hpd_rx_irq_offload_work - hpd_rx_irq offload work structure
+ */
+struct hpd_rx_irq_offload_work {
+	/**
+	 * @work: offload work
+	 */
+	struct work_struct work;
+	/**
+	 * @data: reference irq data which is used while handling offload work
+	 */
+	union hpd_irq_data data;
+	/**
+	 * @offload_wq: offload work queue that this work is queued to
+	 */
+	struct hpd_rx_irq_offload_work_queue *offload_wq;
+};
+
+/**
  * struct amdgpu_display_manager - Central amdgpu display manager device
  *
  * @dc: Display Core control structure
@@ -190,9 +249,31 @@ struct amdgpu_display_manager {
 	 */
 	struct dmub_srv *dmub_srv;
 
+	/**
+	 * @dmub_notify:
+	 *
+	 * Notification from DMUB.
+	 */
+
 	struct dmub_notification *dmub_notify;
 
 	/**
+	 * @dmub_callback:
+	 *
+	 * Callback functions to handle notification from DMUB.
+	 */
+
+	dmub_notify_interrupt_callback_t dmub_callback[AMDGPU_DMUB_NOTIFICATION_MAX];
+
+	/**
+	 * @dmub_thread_offload:
+	 *
+	 * Flag to indicate if callback is offload.
+	 */
+
+	bool dmub_thread_offload[AMDGPU_DMUB_NOTIFICATION_MAX];
+
+	/**
 	 * @dmub_fb_info:
 	 *
 	 * Framebuffer regions for the DMUB.
@@ -422,7 +503,12 @@ struct amdgpu_display_manager {
 	 */
 	struct crc_rd_work *crc_rd_wrk;
 #endif
-
+	/**
+	 * @hpd_rx_offload_wq:
+	 *
+	 * Work queue to offload works of hpd_rx_irq
+	 */
+	struct hpd_rx_irq_offload_work_queue *hpd_rx_offload_wq;
 	/**
 	 * @mst_encoders:
 	 *
@@ -439,6 +525,7 @@ struct amdgpu_display_manager {
 	 */
 	struct list_head da_list;
 	struct completion dmub_aux_transfer_done;
+	struct workqueue_struct *delayed_hpd_wq;
 
 	/**
 	 * @brightness:
@@ -452,6 +539,14 @@ struct amdgpu_display_manager {
 	 * last successfully applied backlight values.
 	 */
 	u32 actual_brightness[AMDGPU_DM_MAX_NUM_EDP];
+
+	/**
+	 * @aux_hpd_discon_quirk:
+	 *
+	 * quirk for hpd discon while aux is on-going.
+	 * occurred on certain intel platform
+	 */
+	bool aux_hpd_discon_quirk;
 };
 
 enum dsc_clock_force_state {
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index 5c9f5214bc4e..6d694cea2420 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -3007,7 +3007,7 @@ void crtc_debugfs_init(struct drm_crtc *crtc)
 				   &crc_win_y_end_fops);
 	debugfs_create_file_unsafe("crc_win_update", 0644, dir, crtc,
 				   &crc_win_update_fops);
-
+	dput(dir);
 }
 #endif
 /*
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 74885ff77f96..652cf108b3c2 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -55,6 +55,8 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 	ssize_t result = 0;
 	struct aux_payload payload;
 	enum aux_return_code_type operation_result;
+	struct amdgpu_device *adev;
+	struct ddc_service *ddc;
 
 	if (WARN_ON(msg->size > 16))
 		return -E2BIG;
@@ -71,6 +73,21 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 	result = dc_link_aux_transfer_raw(TO_DM_AUX(aux)->ddc_service, &payload,
 				      &operation_result);
 
+	/*
+	 * w/a on certain intel platform where hpd is unexpected to pull low during
+	 * 1st sideband message transaction by return AUX_RET_ERROR_HPD_DISCON
+	 * aux transaction is succuess in such case, therefore bypass the error
+	 */
+	ddc = TO_DM_AUX(aux)->ddc_service;
+	adev = ddc->ctx->driver_context;
+	if (adev->dm.aux_hpd_discon_quirk) {
+		if (msg->address == DP_SIDEBAND_MSG_DOWN_REQ_BASE &&
+			operation_result == AUX_RET_ERROR_HPD_DISCON) {
+			result = 0;
+			operation_result = AUX_RET_SUCCESS;
+		}
+	}
+
 	if (payload.write && result >= 0)
 		result = msg->size;
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index b37c4d2e7a1e..1bde9d4e82d4 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -1788,6 +1788,11 @@ void dc_post_update_surfaces_to_stream(struct dc *dc)
 
 	post_surface_trace(dc);
 
+	if (dc->ctx->dce_version >= DCE_VERSION_MAX)
+		TRACE_DCN_CLOCK_STATE(&context->bw_ctx.bw.dcn.clk);
+	else
+		TRACE_DCE_CLOCK_STATE(&context->bw_ctx.bw.dce);
+
 	if (is_flip_pending_in_pipes(dc, context))
 		return;
 
@@ -2974,6 +2979,14 @@ void dc_commit_updates_for_stream(struct dc *dc,
 			if (new_pipe->plane_state && new_pipe->plane_state != old_pipe->plane_state)
 				new_pipe->plane_state->force_full_update = true;
 		}
+	} else if (update_type == UPDATE_TYPE_FAST && dc_ctx->dce_version >= DCE_VERSION_MAX) {
+		/*
+		 * Previous frame finished and HW is ready for optimization.
+		 *
+		 * Only relevant for DCN behavior where we can guarantee the optimization
+		 * is safe to apply - retain the legacy behavior for DCE.
+		 */
+		dc_post_update_surfaces_to_stream(dc);
 	}
 
 
@@ -3030,14 +3043,11 @@ void dc_commit_updates_for_stream(struct dc *dc,
 				pipe_ctx->plane_state->force_full_update = false;
 		}
 	}
-	/*let's use current_state to update watermark etc*/
-	if (update_type >= UPDATE_TYPE_FULL) {
-		dc_post_update_surfaces_to_stream(dc);
 
-		if (dc_ctx->dce_version >= DCE_VERSION_MAX)
-			TRACE_DCN_CLOCK_STATE(&context->bw_ctx.bw.dcn.clk);
-		else
-			TRACE_DCE_CLOCK_STATE(&context->bw_ctx.bw.dce);
+	/* Legacy optimization path for DCE. */
+	if (update_type >= UPDATE_TYPE_FULL && dc_ctx->dce_version < DCE_VERSION_MAX) {
+		dc_post_update_surfaces_to_stream(dc);
+		TRACE_DCE_CLOCK_STATE(&context->bw_ctx.bw.dce);
 	}
 
 	return;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 05f81d44aa6c..6d5dc5ab3d8c 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -2075,7 +2075,7 @@ static struct dc_link_settings get_max_link_cap(struct dc_link *link)
 	return max_link_cap;
 }
 
-enum dc_status read_hpd_rx_irq_data(
+static enum dc_status read_hpd_rx_irq_data(
 	struct dc_link *link,
 	union hpd_irq_data *irq_data)
 {
@@ -2743,7 +2743,7 @@ void decide_link_settings(struct dc_stream_state *stream,
 }
 
 /*************************Short Pulse IRQ***************************/
-static bool allow_hpd_rx_irq(const struct dc_link *link)
+bool dc_link_dp_allow_hpd_rx_irq(const struct dc_link *link)
 {
 	/*
 	 * Don't handle RX IRQ unless one of following is met:
@@ -3177,7 +3177,7 @@ static void dp_test_get_audio_test_data(struct dc_link *link, bool disable_video
 	}
 }
 
-static void handle_automated_test(struct dc_link *link)
+void dc_link_dp_handle_automated_test(struct dc_link *link)
 {
 	union test_request test_request;
 	union test_response test_response;
@@ -3226,17 +3226,50 @@ static void handle_automated_test(struct dc_link *link)
 			sizeof(test_response));
 }
 
-bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd_irq_dpcd_data, bool *out_link_loss)
+void dc_link_dp_handle_link_loss(struct dc_link *link)
+{
+	int i;
+	struct pipe_ctx *pipe_ctx;
+
+	for (i = 0; i < MAX_PIPES; i++) {
+		pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i];
+		if (pipe_ctx && pipe_ctx->stream && pipe_ctx->stream->link == link)
+			break;
+	}
+
+	if (pipe_ctx == NULL || pipe_ctx->stream == NULL)
+		return;
+
+	for (i = 0; i < MAX_PIPES; i++) {
+		pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i];
+		if (pipe_ctx && pipe_ctx->stream && !pipe_ctx->stream->dpms_off &&
+				pipe_ctx->stream->link == link && !pipe_ctx->prev_odm_pipe) {
+			core_link_disable_stream(pipe_ctx);
+		}
+	}
+
+	for (i = 0; i < MAX_PIPES; i++) {
+		pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i];
+		if (pipe_ctx && pipe_ctx->stream && !pipe_ctx->stream->dpms_off &&
+				pipe_ctx->stream->link == link && !pipe_ctx->prev_odm_pipe) {
+			core_link_enable_stream(link->dc->current_state, pipe_ctx);
+		}
+	}
+}
+
+bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd_irq_dpcd_data, bool *out_link_loss,
+							bool defer_handling, bool *has_left_work)
 {
 	union hpd_irq_data hpd_irq_dpcd_data = { { { {0} } } };
 	union device_service_irq device_service_clear = { { 0 } };
 	enum dc_status result;
 	bool status = false;
-	struct pipe_ctx *pipe_ctx;
-	int i;
 
 	if (out_link_loss)
 		*out_link_loss = false;
+
+	if (has_left_work)
+		*has_left_work = false;
 	/* For use cases related to down stream connection status change,
 	 * PSR and device auto test, refer to function handle_sst_hpd_irq
 	 * in DAL2.1*/
@@ -3268,11 +3301,14 @@ bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd
 			&device_service_clear.raw,
 			sizeof(device_service_clear.raw));
 		device_service_clear.raw = 0;
-		handle_automated_test(link);
+		if (defer_handling && has_left_work)
+			*has_left_work = true;
+		else
+			dc_link_dp_handle_automated_test(link);
 		return false;
 	}
 
-	if (!allow_hpd_rx_irq(link)) {
+	if (!dc_link_dp_allow_hpd_rx_irq(link)) {
 		DC_LOG_HW_HPD_IRQ("%s: skipping HPD handling on %d\n",
 			__func__, link->link_index);
 		return false;
@@ -3286,12 +3322,18 @@ bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd
 	 * so do not handle as a normal sink status change interrupt.
 	 */
 
-	if (hpd_irq_dpcd_data.bytes.device_service_irq.bits.UP_REQ_MSG_RDY)
+	if (hpd_irq_dpcd_data.bytes.device_service_irq.bits.UP_REQ_MSG_RDY) {
+		if (defer_handling && has_left_work)
+			*has_left_work = true;
 		return true;
+	}
 
 	/* check if we have MST msg and return since we poll for it */
-	if (hpd_irq_dpcd_data.bytes.device_service_irq.bits.DOWN_REP_MSG_RDY)
+	if (hpd_irq_dpcd_data.bytes.device_service_irq.bits.DOWN_REP_MSG_RDY) {
+		if (defer_handling && has_left_work)
+			*has_left_work = true;
 		return false;
+	}
 
 	/* For now we only handle 'Downstream port status' case.
 	 * If we got sink count changed it means
@@ -3308,29 +3350,10 @@ bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd
 					sizeof(hpd_irq_dpcd_data),
 					"Status: ");
 
-		for (i = 0; i < MAX_PIPES; i++) {
-			pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i];
-			if (pipe_ctx && pipe_ctx->stream && pipe_ctx->stream->link == link)
-				break;
-		}
-
-		if (pipe_ctx == NULL || pipe_ctx->stream == NULL)
-			return false;
-
-
-		for (i = 0; i < MAX_PIPES; i++) {
-			pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i];
-			if (pipe_ctx && pipe_ctx->stream && !pipe_ctx->stream->dpms_off &&
-					pipe_ctx->stream->link == link && !pipe_ctx->prev_odm_pipe)
-				core_link_disable_stream(pipe_ctx);
-		}
-
-		for (i = 0; i < MAX_PIPES; i++) {
-			pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i];
-			if (pipe_ctx && pipe_ctx->stream && !pipe_ctx->stream->dpms_off &&
-					pipe_ctx->stream->link == link && !pipe_ctx->prev_odm_pipe)
-				core_link_enable_stream(link->dc->current_state, pipe_ctx);
-		}
+		if (defer_handling && has_left_work)
+			*has_left_work = true;
+		else
+			dc_link_dp_handle_link_loss(link);
 
 		status = false;
 		if (out_link_loss)
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index 82f1f27baaf3..188556e41b9d 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -1062,12 +1062,13 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 	 * on certain displays, such as the Sharp 4k. 36bpp is needed
 	 * to support SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616 and
 	 * SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616 with actual > 10 bpc
-	 * precision on at least DCN display engines. However, at least
-	 * Carrizo with DCE_VERSION_11_0 does not like 36 bpp lb depth,
-	 * so use only 30 bpp on DCE_VERSION_11_0. Testing with DCE 11.2 and 8.3
-	 * did not show such problems, so this seems to be the exception.
+	 * precision on DCN display engines, but apparently not for DCE, as
+	 * far as testing on DCE-11.2 and DCE-8 showed. Various DCE parts have
+	 * problems: Carrizo with DCE_VERSION_11_0 does not like 36 bpp lb depth,
+	 * neither do DCE-8 at 4k resolution, or DCE-11.2 (broken identify pixel
+	 * passthrough). Therefore only use 36 bpp on DCN where it is actually needed.
 	 */
-	if (plane_state->ctx->dce_version > DCE_VERSION_11_0)
+	if (plane_state->ctx->dce_version > DCE_VERSION_MAX)
 		pipe_ctx->plane_res.scl_data.lb_params.depth = LB_PIXEL_DEPTH_36BPP;
 	else
 		pipe_ctx->plane_res.scl_data.lb_params.depth = LB_PIXEL_DEPTH_30BPP;
diff --git a/drivers/gpu/drm/amd/display/dc/dc_link.h b/drivers/gpu/drm/amd/display/dc/dc_link.h
index 83845d006c54..9b7c32f7fd86 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_link.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_link.h
@@ -296,7 +296,8 @@ enum dc_status dc_link_allocate_mst_payload(struct pipe_ctx *pipe_ctx);
  * false - no change in Downstream port status. No further action required
  * from DM. */
 bool dc_link_handle_hpd_rx_irq(struct dc_link *dc_link,
-		union hpd_irq_data *hpd_irq_dpcd_data, bool *out_link_loss);
+		union hpd_irq_data *hpd_irq_dpcd_data, bool *out_link_loss,
+		bool defer_handling, bool *has_left_work);
 
 /*
  * On eDP links this function call will stall until T12 has elapsed.
@@ -305,9 +306,9 @@ bool dc_link_handle_hpd_rx_irq(struct dc_link *dc_link,
  */
 bool dc_link_wait_for_t12(struct dc_link *link);
 
-enum dc_status read_hpd_rx_irq_data(
-	struct dc_link *link,
-	union hpd_irq_data *irq_data);
+void dc_link_dp_handle_automated_test(struct dc_link *link);
+void dc_link_dp_handle_link_loss(struct dc_link *link);
+bool dc_link_dp_allow_hpd_rx_irq(const struct dc_link *link);
 
 struct dc_sink_init_data;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
index 054823d12403..5f1b735da506 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
@@ -545,9 +545,11 @@ static void dce112_get_pix_clk_dividers_helper (
 		switch (pix_clk_params->color_depth) {
 		case COLOR_DEPTH_101010:
 			actual_pixel_clock_100hz = (actual_pixel_clock_100hz * 5) >> 2;
+			actual_pixel_clock_100hz -= actual_pixel_clock_100hz % 10;
 			break;
 		case COLOR_DEPTH_121212:
 			actual_pixel_clock_100hz = (actual_pixel_clock_100hz * 6) >> 2;
+			actual_pixel_clock_100hz -= actual_pixel_clock_100hz % 10;
 			break;
 		case COLOR_DEPTH_161616:
 			actual_pixel_clock_100hz = actual_pixel_clock_100hz * 2;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
index 11019c2c62cc..8192f1967e92 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
@@ -126,6 +126,12 @@ struct mpcc *mpc1_get_mpcc_for_dpp(struct mpc_tree *tree, int dpp_id)
 	while (tmp_mpcc != NULL) {
 		if (tmp_mpcc->dpp_id == dpp_id)
 			return tmp_mpcc;
+
+		/* avoid circular linked list */
+		ASSERT(tmp_mpcc != tmp_mpcc->mpcc_bot);
+		if (tmp_mpcc == tmp_mpcc->mpcc_bot)
+			break;
+
 		tmp_mpcc = tmp_mpcc->mpcc_bot;
 	}
 	return NULL;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
index 37848f4577b1..92fee47278e5 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
@@ -480,6 +480,11 @@ void optc1_enable_optc_clock(struct timing_generator *optc, bool enable)
 				OTG_CLOCK_ON, 1,
 				1, 1000);
 	} else  {
+
+		//last chance to clear underflow, otherwise, it will always there due to clock is off.
+		if (optc->funcs->is_optc_underflow_occurred(optc) == true)
+			optc->funcs->clear_optc_underflow(optc);
+
 		REG_UPDATE_2(OTG_CLOCK_CONTROL,
 				OTG_CLOCK_GATE_DIS, 0,
 				OTG_CLOCK_EN, 0);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c
index 947eb0df3f12..142fc0a3a536 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c
@@ -532,6 +532,12 @@ struct mpcc *mpc2_get_mpcc_for_dpp(struct mpc_tree *tree, int dpp_id)
 	while (tmp_mpcc != NULL) {
 		if (tmp_mpcc->dpp_id == 0xf || tmp_mpcc->dpp_id == dpp_id)
 			return tmp_mpcc;
+
+		/* avoid circular linked list */
+		ASSERT(tmp_mpcc != tmp_mpcc->mpcc_bot);
+		if (tmp_mpcc == tmp_mpcc->mpcc_bot)
+			break;
+
 		tmp_mpcc = tmp_mpcc->mpcc_bot;
 	}
 	return NULL;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c
index 36044cb8ec83..1c0f56d8ba8b 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c
@@ -67,9 +67,15 @@ static uint32_t convert_and_clamp(
 void dcn21_dchvm_init(struct hubbub *hubbub)
 {
 	struct dcn20_hubbub *hubbub1 = TO_DCN20_HUBBUB(hubbub);
-	uint32_t riommu_active;
+	uint32_t riommu_active, prefetch_done;
 	int i;
 
+	REG_GET(DCHVM_RIOMMU_STAT0, HOSTVM_PREFETCH_DONE, &prefetch_done);
+
+	if (prefetch_done) {
+		hubbub->riommu_active = true;
+		return;
+	}
 	//Init DCHVM block
 	REG_UPDATE(DCHVM_CTRL0, HOSTVM_INIT_REQ, 1);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c
index f24612523248..33c2337c4edf 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c
@@ -86,7 +86,7 @@ bool hubp3_program_surface_flip_and_addr(
 			VMID, address->vmid);
 
 	if (address->type == PLN_ADDR_TYPE_GRPH_STEREO) {
-		REG_UPDATE(DCSURF_FLIP_CONTROL, SURFACE_FLIP_MODE_FOR_STEREOSYNC, 0x1);
+		REG_UPDATE(DCSURF_FLIP_CONTROL, SURFACE_FLIP_MODE_FOR_STEREOSYNC, 0);
 		REG_UPDATE(DCSURF_FLIP_CONTROL, SURFACE_FLIP_IN_STEREOSYNC, 0x1);
 
 	} else {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
index 0294d0cc4759..735c92a5aa36 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
@@ -1856,7 +1856,7 @@ static struct pipe_ctx *dcn30_find_split_pipe(
 	return pipe;
 }
 
-static noinline bool dcn30_internal_validate_bw(
+noinline bool dcn30_internal_validate_bw(
 		struct dc *dc,
 		struct dc_state *context,
 		display_e2e_pipe_params_st *pipes,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.h
index b754b89beadf..b92e4cc0232f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.h
@@ -55,6 +55,13 @@ unsigned int dcn30_calc_max_scaled_time(
 
 bool dcn30_validate_bandwidth(struct dc *dc, struct dc_state *context,
 		bool fast_validate);
+bool dcn30_internal_validate_bw(
+		struct dc *dc,
+		struct dc_state *context,
+		display_e2e_pipe_params_st *pipes,
+		int *pipe_cnt_out,
+		int *vlevel_out,
+		bool fast_validate);
 void dcn30_calculate_wm_and_dlg(
 		struct dc *dc, struct dc_state *context,
 		display_e2e_pipe_params_st *pipes,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c
index 589ddab61c2a..7aad0340f794 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c
@@ -500,7 +500,7 @@ static struct stream_encoder *dcn303_stream_encoder_create(enum engine_id eng_id
 	int afmt_inst;
 
 	/* Mapping of VPG, AFMT, DME register blocks to DIO block instance */
-	if (eng_id <= ENGINE_ID_DIGE) {
+	if (eng_id <= ENGINE_ID_DIGB) {
 		vpg_inst = eng_id;
 		afmt_inst = eng_id;
 	} else
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
index b60ab3cc0f11..e224c5213258 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
@@ -1664,6 +1664,15 @@ static void dcn31_calculate_wm_and_dlg_fp(
 	if (context->bw_ctx.dml.soc.min_dcfclk > dcfclk)
 		dcfclk = context->bw_ctx.dml.soc.min_dcfclk;
 
+	/* We don't recalculate clocks for 0 pipe configs, which can block
+	 * S0i3 as high clocks will block low power states
+	 * Override any clocks that can block S0i3 to min here
+	 */
+	if (pipe_cnt == 0) {
+		context->bw_ctx.bw.dcn.clk.dcfclk_khz = dcfclk; // always should be vlevel 0
+		return;
+	}
+
 	pipes[0].clks_cfg.voltage = vlevel;
 	pipes[0].clks_cfg.dcfclk_mhz = dcfclk;
 	pipes[0].clks_cfg.socclk_mhz = context->bw_ctx.dml.soc.clock_limits[vlevel].socclk_mhz;
@@ -1789,6 +1798,60 @@ static void dcn31_calculate_wm_and_dlg(
 	DC_FP_END();
 }
 
+bool dcn31_validate_bandwidth(struct dc *dc,
+		struct dc_state *context,
+		bool fast_validate)
+{
+	bool out = false;
+
+	BW_VAL_TRACE_SETUP();
+
+	int vlevel = 0;
+	int pipe_cnt = 0;
+	display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_KERNEL);
+	DC_LOGGER_INIT(dc->ctx->logger);
+
+	BW_VAL_TRACE_COUNT();
+
+	DC_FP_START();
+	out = dcn30_internal_validate_bw(dc, context, pipes, &pipe_cnt, &vlevel, fast_validate);
+	DC_FP_END();
+
+	// Disable fast_validate to set min dcfclk in alculate_wm_and_dlg
+	if (pipe_cnt == 0)
+		fast_validate = false;
+
+	if (!out)
+		goto validate_fail;
+
+	BW_VAL_TRACE_END_VOLTAGE_LEVEL();
+
+	if (fast_validate) {
+		BW_VAL_TRACE_SKIP(fast);
+		goto validate_out;
+	}
+
+	dc->res_pool->funcs->calculate_wm_and_dlg(dc, context, pipes, pipe_cnt, vlevel);
+
+	BW_VAL_TRACE_END_WATERMARKS();
+
+	goto validate_out;
+
+validate_fail:
+	DC_LOG_WARNING("Mode Validation Warning: %s failed alidation.\n",
+		dml_get_status_message(context->bw_ctx.dml.vba.ValidationStatus[context->bw_ctx.dml.vba.soc.num_states]));
+
+	BW_VAL_TRACE_SKIP(fail);
+	out = false;
+
+validate_out:
+	kfree(pipes);
+
+	BW_VAL_TRACE_FINISH();
+
+	return out;
+}
+
 static struct dc_cap_funcs cap_funcs = {
 	.get_dcc_compression_cap = dcn20_get_dcc_compression_cap
 };
@@ -1871,7 +1934,7 @@ static struct resource_funcs dcn31_res_pool_funcs = {
 	.link_encs_assign = link_enc_cfg_link_encs_assign,
 	.link_enc_unassign = link_enc_cfg_link_enc_unassign,
 	.panel_cntl_create = dcn31_panel_cntl_create,
-	.validate_bandwidth = dcn30_validate_bandwidth,
+	.validate_bandwidth = dcn31_validate_bandwidth,
 	.calculate_wm_and_dlg = dcn31_calculate_wm_and_dlg,
 	.update_soc_for_wm_a = dcn31_update_soc_for_wm_a,
 	.populate_dml_pipes = dcn31_populate_dml_pipes_from_context,
diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
index b99aa232bd8b..4bee6d018bfa 100644
--- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
+++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
@@ -567,10 +567,6 @@ static void build_vrr_infopacket_data_v1(const struct mod_vrr_params *vrr,
 	 * Note: We should never go above the field rate of the mode timing set.
 	 */
 	infopacket->sb[8] = (unsigned char)((vrr->max_refresh_in_uhz + 500000) / 1000000);
-
-	/* FreeSync HDR */
-	infopacket->sb[9] = 0;
-	infopacket->sb[10] = 0;
 }
 
 static void build_vrr_infopacket_data_v3(const struct mod_vrr_params *vrr,
@@ -638,10 +634,6 @@ static void build_vrr_infopacket_data_v3(const struct mod_vrr_params *vrr,
 
 	/* PB16 : Reserved bits 7:1, FixedRate bit 0 */
 	infopacket->sb[16] = (vrr->state == VRR_STATE_ACTIVE_FIXED) ? 1 : 0;
-
-	//FreeSync HDR
-	infopacket->sb[9] = 0;
-	infopacket->sb[10] = 0;
 }
 
 static void build_vrr_infopacket_fs2_data(enum color_transfer_func app_tf,
@@ -726,8 +718,7 @@ static void build_vrr_infopacket_header_v2(enum signal_type signal,
 		/* HB2  = [Bits 7:5 = 0] [Bits 4:0 = Length = 0x09] */
 		infopacket->hb2 = 0x09;
 
-		*payload_size = 0x0A;
-
+		*payload_size = 0x09;
 	} else if (dc_is_dp_signal(signal)) {
 
 		/* HEADER */
@@ -776,9 +767,9 @@ static void build_vrr_infopacket_header_v3(enum signal_type signal,
 		infopacket->hb1 = version;
 
 		/* HB2  = [Bits 7:5 = 0] [Bits 4:0 = Length] */
-		*payload_size = 0x10;
-		infopacket->hb2 = *payload_size - 1; //-1 for checksum
+		infopacket->hb2 = 0x10;
 
+		*payload_size = 0x10;
 	} else if (dc_is_dp_signal(signal)) {
 
 		/* HEADER */
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
index 574a9d7f7a5e..79976921dc46 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
@@ -338,7 +338,7 @@ sienna_cichlid_get_allowed_feature_mask(struct smu_context *smu,
 	if (smu->dc_controlled_by_gpio)
        *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_ACDC_BIT);
 
-	if (amdgpu_aspm)
+	if (amdgpu_device_should_use_aspm(adev))
 		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DS_LCLK_BIT);
 
 	return 0;
@@ -3915,6 +3915,7 @@ static const struct pptable_funcs sienna_cichlid_ppt_funcs = {
 	.dump_pptable = sienna_cichlid_dump_pptable,
 	.init_microcode = smu_v11_0_init_microcode,
 	.load_microcode = smu_v11_0_load_microcode,
+	.fini_microcode = smu_v11_0_fini_microcode,
 	.init_smc_tables = sienna_cichlid_init_smc_tables,
 	.fini_smc_tables = smu_v11_0_fini_smc_tables,
 	.init_power = smu_v11_0_init_power,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
index e6c93396434f..614c3d049514 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
@@ -1235,6 +1235,8 @@ int smu_v11_0_set_fan_speed_rpm(struct smu_context *smu,
 	uint32_t crystal_clock_freq = 2500;
 	uint32_t tach_period;
 
+	if (speed == 0)
+		return -EINVAL;
 	/*
 	 * To prevent from possible overheat, some ASICs may have requirement
 	 * for minimum fan speed:
diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
index 66737d15a436..b0e9534fd562 100644
--- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
+++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
@@ -1142,6 +1142,10 @@ static int adv7511_init_cec_regmap(struct adv7511 *adv)
 						adv->addr_cec);
 	if (IS_ERR(adv->i2c_cec))
 		return PTR_ERR(adv->i2c_cec);
+
+	regmap_write(adv->regmap, ADV7511_REG_CEC_I2C_ADDR,
+		     adv->i2c_cec->addr << 1);
+
 	i2c_set_clientdata(adv->i2c_cec, adv);
 
 	adv->regmap_cec = devm_regmap_init_i2c(adv->i2c_cec,
@@ -1509,10 +1513,21 @@ static struct i2c_driver adv7511_driver = {
 
 static int __init adv7511_init(void)
 {
-	if (IS_ENABLED(CONFIG_DRM_MIPI_DSI))
-		mipi_dsi_driver_register(&adv7533_dsi_driver);
+	int ret;
+
+	if (IS_ENABLED(CONFIG_DRM_MIPI_DSI)) {
+		ret = mipi_dsi_driver_register(&adv7533_dsi_driver);
+		if (ret)
+			return ret;
+	}
+
+	ret = i2c_add_driver(&adv7511_driver);
+	if (ret) {
+		if (IS_ENABLED(CONFIG_DRM_MIPI_DSI))
+			mipi_dsi_driver_unregister(&adv7533_dsi_driver);
+	}
 
-	return i2c_add_driver(&adv7511_driver);
+	return ret;
 }
 module_init(adv7511_init);
 
diff --git a/drivers/gpu/drm/bridge/display-connector.c b/drivers/gpu/drm/bridge/display-connector.c
index 847a0dce7f1d..d24f5b90feab 100644
--- a/drivers/gpu/drm/bridge/display-connector.c
+++ b/drivers/gpu/drm/bridge/display-connector.c
@@ -13,6 +13,7 @@
 #include <linux/platform_device.h>
 #include <linux/regulator/consumer.h>
 
+#include <drm/drm_atomic_helper.h>
 #include <drm/drm_bridge.h>
 #include <drm/drm_edid.h>
 
@@ -87,10 +88,95 @@ static struct edid *display_connector_get_edid(struct drm_bridge *bridge,
 	return drm_get_edid(connector, conn->bridge.ddc);
 }
 
+/*
+ * Since this bridge is tied to the connector, it acts like a passthrough,
+ * so concerning the output bus formats, either pass the bus formats from the
+ * previous bridge or return fallback data like done in the bridge function:
+ * drm_atomic_bridge_chain_select_bus_fmts().
+ * This supports negotiation if the bridge chain has all bits in place.
+ */
+static u32 *display_connector_get_output_bus_fmts(struct drm_bridge *bridge,
+					struct drm_bridge_state *bridge_state,
+					struct drm_crtc_state *crtc_state,
+					struct drm_connector_state *conn_state,
+					unsigned int *num_output_fmts)
+{
+	struct drm_bridge *prev_bridge = drm_bridge_get_prev_bridge(bridge);
+	struct drm_bridge_state *prev_bridge_state;
+
+	if (!prev_bridge || !prev_bridge->funcs->atomic_get_output_bus_fmts) {
+		struct drm_connector *conn = conn_state->connector;
+		u32 *out_bus_fmts;
+
+		*num_output_fmts = 1;
+		out_bus_fmts = kmalloc(sizeof(*out_bus_fmts), GFP_KERNEL);
+		if (!out_bus_fmts)
+			return NULL;
+
+		if (conn->display_info.num_bus_formats &&
+		    conn->display_info.bus_formats)
+			out_bus_fmts[0] = conn->display_info.bus_formats[0];
+		else
+			out_bus_fmts[0] = MEDIA_BUS_FMT_FIXED;
+
+		return out_bus_fmts;
+	}
+
+	prev_bridge_state = drm_atomic_get_new_bridge_state(crtc_state->state,
+							    prev_bridge);
+
+	return prev_bridge->funcs->atomic_get_output_bus_fmts(prev_bridge, prev_bridge_state,
+							      crtc_state, conn_state,
+							      num_output_fmts);
+}
+
+/*
+ * Since this bridge is tied to the connector, it acts like a passthrough,
+ * so concerning the input bus formats, either pass the bus formats from the
+ * previous bridge or MEDIA_BUS_FMT_FIXED (like select_bus_fmt_recursive())
+ * when atomic_get_input_bus_fmts is not supported.
+ * This supports negotiation if the bridge chain has all bits in place.
+ */
+static u32 *display_connector_get_input_bus_fmts(struct drm_bridge *bridge,
+					struct drm_bridge_state *bridge_state,
+					struct drm_crtc_state *crtc_state,
+					struct drm_connector_state *conn_state,
+					u32 output_fmt,
+					unsigned int *num_input_fmts)
+{
+	struct drm_bridge *prev_bridge = drm_bridge_get_prev_bridge(bridge);
+	struct drm_bridge_state *prev_bridge_state;
+
+	if (!prev_bridge || !prev_bridge->funcs->atomic_get_input_bus_fmts) {
+		u32 *in_bus_fmts;
+
+		*num_input_fmts = 1;
+		in_bus_fmts = kmalloc(sizeof(*in_bus_fmts), GFP_KERNEL);
+		if (!in_bus_fmts)
+			return NULL;
+
+		in_bus_fmts[0] = MEDIA_BUS_FMT_FIXED;
+
+		return in_bus_fmts;
+	}
+
+	prev_bridge_state = drm_atomic_get_new_bridge_state(crtc_state->state,
+							    prev_bridge);
+
+	return prev_bridge->funcs->atomic_get_input_bus_fmts(prev_bridge, prev_bridge_state,
+							     crtc_state, conn_state, output_fmt,
+							     num_input_fmts);
+}
+
 static const struct drm_bridge_funcs display_connector_bridge_funcs = {
 	.attach = display_connector_attach,
 	.detect = display_connector_detect,
 	.get_edid = display_connector_get_edid,
+	.atomic_get_output_bus_fmts = display_connector_get_output_bus_fmts,
+	.atomic_get_input_bus_fmts = display_connector_get_input_bus_fmts,
+	.atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_bridge_destroy_state,
+	.atomic_reset = drm_atomic_helper_bridge_reset,
 };
 
 static irqreturn_t display_connector_hpd_irq(int irq, void *arg)
diff --git a/drivers/gpu/drm/bridge/lontium-lt9611uxc.c b/drivers/gpu/drm/bridge/lontium-lt9611uxc.c
index 010657ea7af7..c4454d0f6cad 100644
--- a/drivers/gpu/drm/bridge/lontium-lt9611uxc.c
+++ b/drivers/gpu/drm/bridge/lontium-lt9611uxc.c
@@ -997,7 +997,7 @@ static int lt9611uxc_remove(struct i2c_client *client)
 	struct lt9611uxc *lt9611uxc = i2c_get_clientdata(client);
 
 	disable_irq(client->irq);
-	flush_scheduled_work();
+	cancel_work_sync(&lt9611uxc->work);
 	lt9611uxc_audio_exit(lt9611uxc);
 	drm_bridge_remove(&lt9611uxc->bridge);
 
diff --git a/drivers/gpu/drm/bridge/panel.c b/drivers/gpu/drm/bridge/panel.c
index c916f4b8907e..b32295abd9e7 100644
--- a/drivers/gpu/drm/bridge/panel.c
+++ b/drivers/gpu/drm/bridge/panel.c
@@ -9,6 +9,7 @@
 #include <drm/drm_connector.h>
 #include <drm/drm_encoder.h>
 #include <drm/drm_modeset_helper_vtables.h>
+#include <drm/drm_of.h>
 #include <drm/drm_panel.h>
 #include <drm/drm_print.h>
 #include <drm/drm_probe_helper.h>
@@ -332,3 +333,39 @@ struct drm_connector *drm_panel_bridge_connector(struct drm_bridge *bridge)
 	return &panel_bridge->connector;
 }
 EXPORT_SYMBOL(drm_panel_bridge_connector);
+
+#ifdef CONFIG_OF
+/**
+ * devm_drm_of_get_bridge - Return next bridge in the chain
+ * @dev: device to tie the bridge lifetime to
+ * @np: device tree node containing encoder output ports
+ * @port: port in the device tree node
+ * @endpoint: endpoint in the device tree node
+ *
+ * Given a DT node's port and endpoint number, finds the connected node
+ * and returns the associated bridge if any, or creates and returns a
+ * drm panel bridge instance if a panel is connected.
+ *
+ * Returns a pointer to the bridge if successful, or an error pointer
+ * otherwise.
+ */
+struct drm_bridge *devm_drm_of_get_bridge(struct device *dev,
+					  struct device_node *np,
+					  u32 port, u32 endpoint)
+{
+	struct drm_bridge *bridge;
+	struct drm_panel *panel;
+	int ret;
+
+	ret = drm_of_find_panel_or_bridge(np, port, endpoint,
+					  &panel, &bridge);
+	if (ret)
+		return ERR_PTR(ret);
+
+	if (panel)
+		bridge = devm_drm_panel_bridge_add(dev, panel);
+
+	return bridge;
+}
+EXPORT_SYMBOL(devm_drm_of_get_bridge);
+#endif
diff --git a/drivers/gpu/drm/bridge/sil-sii8620.c b/drivers/gpu/drm/bridge/sil-sii8620.c
index ec7745c31da0..ab0bce4a988c 100644
--- a/drivers/gpu/drm/bridge/sil-sii8620.c
+++ b/drivers/gpu/drm/bridge/sil-sii8620.c
@@ -605,7 +605,7 @@ static void *sii8620_burst_get_tx_buf(struct sii8620 *ctx, int len)
 	u8 *buf = &ctx->burst.tx_buf[ctx->burst.tx_count];
 	int size = len + 2;
 
-	if (ctx->burst.tx_count + size > ARRAY_SIZE(ctx->burst.tx_buf)) {
+	if (ctx->burst.tx_count + size >= ARRAY_SIZE(ctx->burst.tx_buf)) {
 		dev_err(ctx->dev, "TX-BLK buffer exhausted\n");
 		ctx->error = -EINVAL;
 		return NULL;
@@ -622,7 +622,7 @@ static u8 *sii8620_burst_get_rx_buf(struct sii8620 *ctx, int len)
 	u8 *buf = &ctx->burst.rx_buf[ctx->burst.rx_count];
 	int size = len + 1;
 
-	if (ctx->burst.tx_count + size > ARRAY_SIZE(ctx->burst.tx_buf)) {
+	if (ctx->burst.rx_count + size >= ARRAY_SIZE(ctx->burst.rx_buf)) {
 		dev_err(ctx->dev, "RX-BLK buffer exhausted\n");
 		ctx->error = -EINVAL;
 		return NULL;
diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c
index 23a6f90b694b..14d671742963 100644
--- a/drivers/gpu/drm/bridge/tc358767.c
+++ b/drivers/gpu/drm/bridge/tc358767.c
@@ -1549,19 +1549,12 @@ static irqreturn_t tc_irq_handler(int irq, void *arg)
 	return IRQ_HANDLED;
 }
 
-static int tc_probe(struct i2c_client *client, const struct i2c_device_id *id)
+static int tc_probe_edp_bridge_endpoint(struct tc_data *tc)
 {
-	struct device *dev = &client->dev;
+	struct device *dev = tc->dev;
 	struct drm_panel *panel;
-	struct tc_data *tc;
 	int ret;
 
-	tc = devm_kzalloc(dev, sizeof(*tc), GFP_KERNEL);
-	if (!tc)
-		return -ENOMEM;
-
-	tc->dev = dev;
-
 	/* port@2 is the output port */
 	ret = drm_of_find_panel_or_bridge(dev->of_node, 2, 0, &panel, NULL);
 	if (ret && ret != -ENODEV)
@@ -1580,6 +1573,25 @@ static int tc_probe(struct i2c_client *client, const struct i2c_device_id *id)
 		tc->bridge.type = DRM_MODE_CONNECTOR_DisplayPort;
 	}
 
+	return 0;
+}
+
+static int tc_probe(struct i2c_client *client, const struct i2c_device_id *id)
+{
+	struct device *dev = &client->dev;
+	struct tc_data *tc;
+	int ret;
+
+	tc = devm_kzalloc(dev, sizeof(*tc), GFP_KERNEL);
+	if (!tc)
+		return -ENOMEM;
+
+	tc->dev = dev;
+
+	ret = tc_probe_edp_bridge_endpoint(tc);
+	if (ret)
+		return ret;
+
 	/* Shut down GPIO is optional */
 	tc->sd_gpio = devm_gpiod_get_optional(dev, "shutdown", GPIOD_OUT_HIGH);
 	if (IS_ERR(tc->sd_gpio))
diff --git a/drivers/gpu/drm/drm_aperture.c b/drivers/gpu/drm/drm_aperture.c
index 74bd4a76b253..059fd71424f6 100644
--- a/drivers/gpu/drm/drm_aperture.c
+++ b/drivers/gpu/drm/drm_aperture.c
@@ -329,7 +329,20 @@ int drm_aperture_remove_conflicting_pci_framebuffers(struct pci_dev *pdev,
 						     const struct drm_driver *req_driver)
 {
 	resource_size_t base, size;
-	int bar, ret = 0;
+	int bar, ret;
+
+	/*
+	 * WARNING: Apparently we must kick fbdev drivers before vgacon,
+	 * otherwise the vga fbdev driver falls over.
+	 */
+#if IS_REACHABLE(CONFIG_FB)
+	ret = remove_conflicting_pci_framebuffers(pdev, req_driver->name);
+	if (ret)
+		return ret;
+#endif
+	ret = vga_remove_vgacon(pdev);
+	if (ret)
+		return ret;
 
 	for (bar = 0; bar < PCI_STD_NUM_BARS; ++bar) {
 		if (!(pci_resource_flags(pdev, bar) & IORESOURCE_MEM))
@@ -339,15 +352,6 @@ int drm_aperture_remove_conflicting_pci_framebuffers(struct pci_dev *pdev,
 		drm_aperture_detach_drivers(base, size);
 	}
 
-	/*
-	 * WARNING: Apparently we must kick fbdev drivers before vgacon,
-	 * otherwise the vga fbdev driver falls over.
-	 */
-#if IS_REACHABLE(CONFIG_FB)
-	ret = remove_conflicting_pci_framebuffers(pdev, req_driver->name);
-#endif
-	if (ret == 0)
-		ret = vga_remove_vgacon(pdev);
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL(drm_aperture_remove_conflicting_pci_framebuffers);
diff --git a/drivers/gpu/drm/drm_bridge.c b/drivers/gpu/drm/drm_bridge.c
index a8ed66751c2d..7ee29f073857 100644
--- a/drivers/gpu/drm/drm_bridge.c
+++ b/drivers/gpu/drm/drm_bridge.c
@@ -28,6 +28,7 @@
 #include <drm/drm_atomic_state_helper.h>
 #include <drm/drm_bridge.h>
 #include <drm/drm_encoder.h>
+#include <drm/drm_of.h>
 #include <drm/drm_print.h>
 
 #include "drm_crtc_internal.h"
@@ -51,10 +52,8 @@
  *
  * Display drivers are responsible for linking encoders with the first bridge
  * in the chains. This is done by acquiring the appropriate bridge with
- * of_drm_find_bridge() or drm_of_find_panel_or_bridge(), or creating it for a
- * panel with drm_panel_bridge_add_typed() (or the managed version
- * devm_drm_panel_bridge_add_typed()). Once acquired, the bridge shall be
- * attached to the encoder with a call to drm_bridge_attach().
+ * devm_drm_of_get_bridge(). Once acquired, the bridge shall be attached to the
+ * encoder with a call to drm_bridge_attach().
  *
  * Bridges are responsible for linking themselves with the next bridge in the
  * chain, if any. This is done the same way as for encoders, with the call to
diff --git a/drivers/gpu/drm/drm_dp_aux_bus.c b/drivers/gpu/drm/drm_dp_aux_bus.c
index 298ea7a49591..f7c03ad5a15a 100644
--- a/drivers/gpu/drm/drm_dp_aux_bus.c
+++ b/drivers/gpu/drm/drm_dp_aux_bus.c
@@ -66,7 +66,6 @@ static int dp_aux_ep_probe(struct device *dev)
  * @dev: The device to remove.
  *
  * Calls through to the endpoint driver remove.
- *
  */
 static void dp_aux_ep_remove(struct device *dev)
 {
@@ -120,8 +119,6 @@ ATTRIBUTE_GROUPS(dp_aux_ep_dev);
 /**
  * dp_aux_ep_dev_release() - Free memory for the dp_aux_ep device
  * @dev: The device to free.
- *
- * Return: 0 if no error or negative error code.
  */
 static void dp_aux_ep_dev_release(struct device *dev)
 {
@@ -256,6 +253,7 @@ int of_dp_aux_populate_ep_devices(struct drm_dp_aux *aux)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(of_dp_aux_populate_ep_devices);
 
 static void of_dp_aux_depopulate_ep_devices_void(void *data)
 {
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index b3e3babe18c0..2a586e6489da 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -3860,9 +3860,7 @@ int drm_dp_mst_topology_mgr_resume(struct drm_dp_mst_topology_mgr *mgr,
 	if (!mgr->mst_primary)
 		goto out_fail;
 
-	ret = drm_dp_dpcd_read(mgr->aux, DP_DPCD_REV, mgr->dpcd,
-			       DP_RECEIVER_CAP_SIZE);
-	if (ret != DP_RECEIVER_CAP_SIZE) {
+	if (drm_dp_read_dpcd_caps(mgr->aux, mgr->dpcd) < 0) {
 		drm_dbg_kms(mgr->dev, "dpcd read failed - undocked during suspend?\n");
 		goto out_fail;
 	}
@@ -4894,8 +4892,7 @@ void drm_dp_mst_dump_topology(struct seq_file *m,
 		u8 buf[DP_PAYLOAD_TABLE_SIZE];
 		int ret;
 
-		ret = drm_dp_dpcd_read(mgr->aux, DP_DPCD_REV, buf, DP_RECEIVER_CAP_SIZE);
-		if (ret) {
+		if (drm_dp_read_dpcd_caps(mgr->aux, buf) < 0) {
 			seq_printf(m, "dpcd read failed\n");
 			goto out;
 		}
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index 09c820045859..dbd19a34b517 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -167,21 +167,6 @@ void drm_gem_private_object_init(struct drm_device *dev,
 }
 EXPORT_SYMBOL(drm_gem_private_object_init);
 
-static void
-drm_gem_remove_prime_handles(struct drm_gem_object *obj, struct drm_file *filp)
-{
-	/*
-	 * Note: obj->dma_buf can't disappear as long as we still hold a
-	 * handle reference in obj->handle_count.
-	 */
-	mutex_lock(&filp->prime.lock);
-	if (obj->dma_buf) {
-		drm_prime_remove_buf_handle_locked(&filp->prime,
-						   obj->dma_buf);
-	}
-	mutex_unlock(&filp->prime.lock);
-}
-
 /**
  * drm_gem_object_handle_free - release resources bound to userspace handles
  * @obj: GEM object to clean up.
@@ -252,7 +237,7 @@ drm_gem_object_release_handle(int id, void *ptr, void *data)
 	if (obj->funcs->close)
 		obj->funcs->close(obj, file_priv);
 
-	drm_gem_remove_prime_handles(obj, file_priv);
+	drm_prime_remove_buf_handle(&file_priv->prime, id);
 	drm_vma_node_revoke(&obj->vma_node, file_priv);
 
 	drm_gem_object_handle_put_unlocked(obj);
@@ -1224,7 +1209,7 @@ retry:
 		ret = dma_resv_lock_slow_interruptible(obj->resv,
 								 acquire_ctx);
 		if (ret) {
-			ww_acquire_done(acquire_ctx);
+			ww_acquire_fini(acquire_ctx);
 			return ret;
 		}
 	}
@@ -1249,7 +1234,7 @@ retry:
 				goto retry;
 			}
 
-			ww_acquire_done(acquire_ctx);
+			ww_acquire_fini(acquire_ctx);
 			return ret;
 		}
 	}
diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c
index a61946374c82..a30ffc07470c 100644
--- a/drivers/gpu/drm/drm_gem_shmem_helper.c
+++ b/drivers/gpu/drm/drm_gem_shmem_helper.c
@@ -22,17 +22,22 @@
  *
  * This library provides helpers for GEM objects backed by shmem buffers
  * allocated using anonymous pageable memory.
+ *
+ * Functions that operate on the GEM object receive struct &drm_gem_shmem_object.
+ * For GEM callback helpers in struct &drm_gem_object functions, see likewise
+ * named functions with an _object_ infix (e.g., drm_gem_shmem_object_vmap() wraps
+ * drm_gem_shmem_vmap()). These helpers perform the necessary type conversion.
  */
 
 static const struct drm_gem_object_funcs drm_gem_shmem_funcs = {
-	.free = drm_gem_shmem_free_object,
-	.print_info = drm_gem_shmem_print_info,
-	.pin = drm_gem_shmem_pin,
-	.unpin = drm_gem_shmem_unpin,
-	.get_sg_table = drm_gem_shmem_get_sg_table,
-	.vmap = drm_gem_shmem_vmap,
-	.vunmap = drm_gem_shmem_vunmap,
-	.mmap = drm_gem_shmem_mmap,
+	.free = drm_gem_shmem_object_free,
+	.print_info = drm_gem_shmem_object_print_info,
+	.pin = drm_gem_shmem_object_pin,
+	.unpin = drm_gem_shmem_object_unpin,
+	.get_sg_table = drm_gem_shmem_object_get_sg_table,
+	.vmap = drm_gem_shmem_object_vmap,
+	.vunmap = drm_gem_shmem_object_vunmap,
+	.mmap = drm_gem_shmem_object_mmap,
 };
 
 static struct drm_gem_shmem_object *
@@ -112,16 +117,15 @@ struct drm_gem_shmem_object *drm_gem_shmem_create(struct drm_device *dev, size_t
 EXPORT_SYMBOL_GPL(drm_gem_shmem_create);
 
 /**
- * drm_gem_shmem_free_object - Free resources associated with a shmem GEM object
- * @obj: GEM object to free
+ * drm_gem_shmem_free - Free resources associated with a shmem GEM object
+ * @shmem: shmem GEM object to free
  *
  * This function cleans up the GEM object state and frees the memory used to
- * store the object itself. It should be used to implement
- * &drm_gem_object_funcs.free.
+ * store the object itself.
  */
-void drm_gem_shmem_free_object(struct drm_gem_object *obj)
+void drm_gem_shmem_free(struct drm_gem_shmem_object *shmem)
 {
-	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
+	struct drm_gem_object *obj = &shmem->base;
 
 	WARN_ON(shmem->vmap_use_count);
 
@@ -145,7 +149,7 @@ void drm_gem_shmem_free_object(struct drm_gem_object *obj)
 	mutex_destroy(&shmem->vmap_lock);
 	kfree(shmem);
 }
-EXPORT_SYMBOL_GPL(drm_gem_shmem_free_object);
+EXPORT_SYMBOL_GPL(drm_gem_shmem_free);
 
 static int drm_gem_shmem_get_pages_locked(struct drm_gem_shmem_object *shmem)
 {
@@ -225,19 +229,16 @@ EXPORT_SYMBOL(drm_gem_shmem_put_pages);
 
 /**
  * drm_gem_shmem_pin - Pin backing pages for a shmem GEM object
- * @obj: GEM object
+ * @shmem: shmem GEM object
  *
  * This function makes sure the backing pages are pinned in memory while the
- * buffer is exported. It should only be used to implement
- * &drm_gem_object_funcs.pin.
+ * buffer is exported.
  *
  * Returns:
  * 0 on success or a negative error code on failure.
  */
-int drm_gem_shmem_pin(struct drm_gem_object *obj)
+int drm_gem_shmem_pin(struct drm_gem_shmem_object *shmem)
 {
-	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
-
 	WARN_ON(shmem->base.import_attach);
 
 	return drm_gem_shmem_get_pages(shmem);
@@ -246,15 +247,13 @@ EXPORT_SYMBOL(drm_gem_shmem_pin);
 
 /**
  * drm_gem_shmem_unpin - Unpin backing pages for a shmem GEM object
- * @obj: GEM object
+ * @shmem: shmem GEM object
  *
  * This function removes the requirement that the backing pages are pinned in
- * memory. It should only be used to implement &drm_gem_object_funcs.unpin.
+ * memory.
  */
-void drm_gem_shmem_unpin(struct drm_gem_object *obj)
+void drm_gem_shmem_unpin(struct drm_gem_shmem_object *shmem)
 {
-	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
-
 	WARN_ON(shmem->base.import_attach);
 
 	drm_gem_shmem_put_pages(shmem);
@@ -275,6 +274,7 @@ static int drm_gem_shmem_vmap_locked(struct drm_gem_shmem_object *shmem, struct
 		ret = dma_buf_vmap(obj->import_attach->dmabuf, map);
 		if (!ret) {
 			if (WARN_ON(map->is_iomem)) {
+				dma_buf_vunmap(obj->import_attach->dmabuf, map);
 				ret = -EIO;
 				goto err_put_pages;
 			}
@@ -320,20 +320,16 @@ err_zero_use:
  *       store.
  *
  * This function makes sure that a contiguous kernel virtual address mapping
- * exists for the buffer backing the shmem GEM object.
- *
- * This function can be used to implement &drm_gem_object_funcs.vmap. But it can
- * also be called by drivers directly, in which case it will hide the
- * differences between dma-buf imported and natively allocated objects.
+ * exists for the buffer backing the shmem GEM object. It hides the differences
+ * between dma-buf imported and natively allocated objects.
  *
  * Acquired mappings should be cleaned up by calling drm_gem_shmem_vunmap().
  *
  * Returns:
  * 0 on success or a negative error code on failure.
  */
-int drm_gem_shmem_vmap(struct drm_gem_object *obj, struct dma_buf_map *map)
+int drm_gem_shmem_vmap(struct drm_gem_shmem_object *shmem, struct dma_buf_map *map)
 {
-	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
 	int ret;
 
 	ret = mutex_lock_interruptible(&shmem->vmap_lock);
@@ -376,21 +372,18 @@ static void drm_gem_shmem_vunmap_locked(struct drm_gem_shmem_object *shmem,
  * drm_gem_shmem_vmap(). The mapping is only removed when the use count drops to
  * zero.
  *
- * This function can be used to implement &drm_gem_object_funcs.vmap. But it can
- * also be called by drivers directly, in which case it will hide the
- * differences between dma-buf imported and natively allocated objects.
+ * This function hides the differences between dma-buf imported and natively
+ * allocated objects.
  */
-void drm_gem_shmem_vunmap(struct drm_gem_object *obj, struct dma_buf_map *map)
+void drm_gem_shmem_vunmap(struct drm_gem_shmem_object *shmem, struct dma_buf_map *map)
 {
-	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
-
 	mutex_lock(&shmem->vmap_lock);
 	drm_gem_shmem_vunmap_locked(shmem, map);
 	mutex_unlock(&shmem->vmap_lock);
 }
 EXPORT_SYMBOL(drm_gem_shmem_vunmap);
 
-struct drm_gem_shmem_object *
+static struct drm_gem_shmem_object *
 drm_gem_shmem_create_with_handle(struct drm_file *file_priv,
 				 struct drm_device *dev, size_t size,
 				 uint32_t *handle)
@@ -414,15 +407,12 @@ drm_gem_shmem_create_with_handle(struct drm_file *file_priv,
 
 	return shmem;
 }
-EXPORT_SYMBOL(drm_gem_shmem_create_with_handle);
 
 /* Update madvise status, returns true if not purged, else
  * false or -errno.
  */
-int drm_gem_shmem_madvise(struct drm_gem_object *obj, int madv)
+int drm_gem_shmem_madvise(struct drm_gem_shmem_object *shmem, int madv)
 {
-	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
-
 	mutex_lock(&shmem->pages_lock);
 
 	if (shmem->madv >= 0)
@@ -436,14 +426,14 @@ int drm_gem_shmem_madvise(struct drm_gem_object *obj, int madv)
 }
 EXPORT_SYMBOL(drm_gem_shmem_madvise);
 
-void drm_gem_shmem_purge_locked(struct drm_gem_object *obj)
+void drm_gem_shmem_purge_locked(struct drm_gem_shmem_object *shmem)
 {
+	struct drm_gem_object *obj = &shmem->base;
 	struct drm_device *dev = obj->dev;
-	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
 
 	WARN_ON(!drm_gem_shmem_is_purgeable(shmem));
 
-	dma_unmap_sgtable(obj->dev->dev, shmem->sgt, DMA_BIDIRECTIONAL, 0);
+	dma_unmap_sgtable(dev->dev, shmem->sgt, DMA_BIDIRECTIONAL, 0);
 	sg_free_table(shmem->sgt);
 	kfree(shmem->sgt);
 	shmem->sgt = NULL;
@@ -462,18 +452,15 @@ void drm_gem_shmem_purge_locked(struct drm_gem_object *obj)
 	 */
 	shmem_truncate_range(file_inode(obj->filp), 0, (loff_t)-1);
 
-	invalidate_mapping_pages(file_inode(obj->filp)->i_mapping,
-			0, (loff_t)-1);
+	invalidate_mapping_pages(file_inode(obj->filp)->i_mapping, 0, (loff_t)-1);
 }
 EXPORT_SYMBOL(drm_gem_shmem_purge_locked);
 
-bool drm_gem_shmem_purge(struct drm_gem_object *obj)
+bool drm_gem_shmem_purge(struct drm_gem_shmem_object *shmem)
 {
-	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
-
 	if (!mutex_trylock(&shmem->pages_lock))
 		return false;
-	drm_gem_shmem_purge_locked(obj);
+	drm_gem_shmem_purge_locked(shmem);
 	mutex_unlock(&shmem->pages_lock);
 
 	return true;
@@ -581,19 +568,18 @@ static const struct vm_operations_struct drm_gem_shmem_vm_ops = {
 
 /**
  * drm_gem_shmem_mmap - Memory-map a shmem GEM object
- * @obj: gem object
+ * @shmem: shmem GEM object
  * @vma: VMA for the area to be mapped
  *
  * This function implements an augmented version of the GEM DRM file mmap
- * operation for shmem objects. Drivers which employ the shmem helpers should
- * use this function as their &drm_gem_object_funcs.mmap handler.
+ * operation for shmem objects.
  *
  * Returns:
  * 0 on success or a negative error code on failure.
  */
-int drm_gem_shmem_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
+int drm_gem_shmem_mmap(struct drm_gem_shmem_object *shmem, struct vm_area_struct *vma)
 {
-	struct drm_gem_shmem_object *shmem;
+	struct drm_gem_object *obj = &shmem->base;
 	int ret;
 
 	if (obj->import_attach) {
@@ -604,8 +590,6 @@ int drm_gem_shmem_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
 		return dma_buf_mmap(obj->dma_buf, vma, 0);
 	}
 
-	shmem = to_drm_gem_shmem_obj(obj);
-
 	ret = drm_gem_shmem_get_pages(shmem);
 	if (ret) {
 		drm_gem_vm_close(vma);
@@ -624,17 +608,13 @@ EXPORT_SYMBOL_GPL(drm_gem_shmem_mmap);
 
 /**
  * drm_gem_shmem_print_info() - Print &drm_gem_shmem_object info for debugfs
+ * @shmem: shmem GEM object
  * @p: DRM printer
  * @indent: Tab indentation level
- * @obj: GEM object
- *
- * This implements the &drm_gem_object_funcs.info callback.
  */
-void drm_gem_shmem_print_info(struct drm_printer *p, unsigned int indent,
-			      const struct drm_gem_object *obj)
+void drm_gem_shmem_print_info(const struct drm_gem_shmem_object *shmem,
+			      struct drm_printer *p, unsigned int indent)
 {
-	const struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
-
 	drm_printf_indent(p, indent, "pages_use_count=%u\n", shmem->pages_use_count);
 	drm_printf_indent(p, indent, "vmap_use_count=%u\n", shmem->vmap_use_count);
 	drm_printf_indent(p, indent, "vaddr=%p\n", shmem->vaddr);
@@ -644,12 +624,10 @@ EXPORT_SYMBOL(drm_gem_shmem_print_info);
 /**
  * drm_gem_shmem_get_sg_table - Provide a scatter/gather table of pinned
  *                              pages for a shmem GEM object
- * @obj: GEM object
+ * @shmem: shmem GEM object
  *
  * This function exports a scatter/gather table suitable for PRIME usage by
- * calling the standard DMA mapping API. Drivers should not call this function
- * directly, instead it should only be used as an implementation for
- * &drm_gem_object_funcs.get_sg_table.
+ * calling the standard DMA mapping API.
  *
  * Drivers who need to acquire an scatter/gather table for objects need to call
  * drm_gem_shmem_get_pages_sgt() instead.
@@ -657,9 +635,9 @@ EXPORT_SYMBOL(drm_gem_shmem_print_info);
  * Returns:
  * A pointer to the scatter/gather table of pinned pages or NULL on failure.
  */
-struct sg_table *drm_gem_shmem_get_sg_table(struct drm_gem_object *obj)
+struct sg_table *drm_gem_shmem_get_sg_table(struct drm_gem_shmem_object *shmem)
 {
-	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
+	struct drm_gem_object *obj = &shmem->base;
 
 	WARN_ON(shmem->base.import_attach);
 
@@ -670,7 +648,7 @@ EXPORT_SYMBOL_GPL(drm_gem_shmem_get_sg_table);
 /**
  * drm_gem_shmem_get_pages_sgt - Pin pages, dma map them, and return a
  *				 scatter/gather table for a shmem GEM object.
- * @obj: GEM object
+ * @shmem: shmem GEM object
  *
  * This function returns a scatter/gather table suitable for driver usage. If
  * the sg table doesn't exist, the pages are pinned, dma-mapped, and a sg
@@ -683,10 +661,10 @@ EXPORT_SYMBOL_GPL(drm_gem_shmem_get_sg_table);
  * Returns:
  * A pointer to the scatter/gather table of pinned pages or errno on failure.
  */
-struct sg_table *drm_gem_shmem_get_pages_sgt(struct drm_gem_object *obj)
+struct sg_table *drm_gem_shmem_get_pages_sgt(struct drm_gem_shmem_object *shmem)
 {
+	struct drm_gem_object *obj = &shmem->base;
 	int ret;
-	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
 	struct sg_table *sgt;
 
 	if (shmem->sgt)
@@ -698,7 +676,7 @@ struct sg_table *drm_gem_shmem_get_pages_sgt(struct drm_gem_object *obj)
 	if (ret)
 		return ERR_PTR(ret);
 
-	sgt = drm_gem_shmem_get_sg_table(&shmem->base);
+	sgt = drm_gem_shmem_get_sg_table(shmem);
 	if (IS_ERR(sgt)) {
 		ret = PTR_ERR(sgt);
 		goto err_put_pages;
diff --git a/drivers/gpu/drm/drm_gem_ttm_helper.c b/drivers/gpu/drm/drm_gem_ttm_helper.c
index ecf3d2a54a98..759c65bfd284 100644
--- a/drivers/gpu/drm/drm_gem_ttm_helper.c
+++ b/drivers/gpu/drm/drm_gem_ttm_helper.c
@@ -64,8 +64,13 @@ int drm_gem_ttm_vmap(struct drm_gem_object *gem,
 		     struct dma_buf_map *map)
 {
 	struct ttm_buffer_object *bo = drm_gem_ttm_of_gem(gem);
+	int ret;
+
+	dma_resv_lock(gem->resv, NULL);
+	ret = ttm_bo_vmap(bo, map);
+	dma_resv_unlock(gem->resv);
 
-	return ttm_bo_vmap(bo, map);
+	return ret;
 }
 EXPORT_SYMBOL(drm_gem_ttm_vmap);
 
@@ -82,7 +87,9 @@ void drm_gem_ttm_vunmap(struct drm_gem_object *gem,
 {
 	struct ttm_buffer_object *bo = drm_gem_ttm_of_gem(gem);
 
+	dma_resv_lock(gem->resv, NULL);
 	ttm_bo_vunmap(bo, map);
+	dma_resv_unlock(gem->resv);
 }
 EXPORT_SYMBOL(drm_gem_ttm_vunmap);
 
diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h
index 17f3548c8ed2..d05e6a5b6687 100644
--- a/drivers/gpu/drm/drm_internal.h
+++ b/drivers/gpu/drm/drm_internal.h
@@ -74,8 +74,8 @@ int drm_prime_fd_to_handle_ioctl(struct drm_device *dev, void *data,
 
 void drm_prime_init_file_private(struct drm_prime_file_private *prime_fpriv);
 void drm_prime_destroy_file_private(struct drm_prime_file_private *prime_fpriv);
-void drm_prime_remove_buf_handle_locked(struct drm_prime_file_private *prime_fpriv,
-					struct dma_buf *dma_buf);
+void drm_prime_remove_buf_handle(struct drm_prime_file_private *prime_fpriv,
+				 uint32_t handle);
 
 /* drm_drv.c */
 struct drm_minor *drm_minor_acquire(unsigned int minor_id);
diff --git a/drivers/gpu/drm/drm_mipi_dbi.c b/drivers/gpu/drm/drm_mipi_dbi.c
index 71b646c4131f..00d470ff071d 100644
--- a/drivers/gpu/drm/drm_mipi_dbi.c
+++ b/drivers/gpu/drm/drm_mipi_dbi.c
@@ -1183,6 +1183,13 @@ int mipi_dbi_spi_transfer(struct spi_device *spi, u32 speed_hz,
 	size_t chunk;
 	int ret;
 
+	/* In __spi_validate, there's a validation that no partial transfers
+	 * are accepted (xfer->len % w_size must be zero).
+	 * Here we align max_chunk to multiple of 2 (16bits),
+	 * to prevent transfers from being rejected.
+	 */
+	max_chunk = ALIGN_DOWN(max_chunk, 2);
+
 	spi_message_init_with_transfers(&m, &tr, 1);
 
 	while (len) {
diff --git a/drivers/gpu/drm/drm_of.c b/drivers/gpu/drm/drm_of.c
index cd34c9d48b46..ac56279bfb71 100644
--- a/drivers/gpu/drm/drm_of.c
+++ b/drivers/gpu/drm/drm_of.c
@@ -256,6 +256,9 @@ EXPORT_SYMBOL_GPL(drm_of_encoder_active_endpoint);
  * return either the associated struct drm_panel or drm_bridge device. Either
  * @panel or @bridge must not be NULL.
  *
+ * This function is deprecated and should not be used in new drivers. Use
+ * devm_drm_of_get_bridge() instead.
+ *
  * Returns zero if successful, or one of the standard error codes if it fails.
  */
 int drm_of_find_panel_or_bridge(const struct device_node *np,
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index d6c7f4f9a7a2..a350310b65d8 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -187,29 +187,33 @@ static int drm_prime_lookup_buf_handle(struct drm_prime_file_private *prime_fpri
 	return -ENOENT;
 }
 
-void drm_prime_remove_buf_handle_locked(struct drm_prime_file_private *prime_fpriv,
-					struct dma_buf *dma_buf)
+void drm_prime_remove_buf_handle(struct drm_prime_file_private *prime_fpriv,
+				 uint32_t handle)
 {
 	struct rb_node *rb;
 
-	rb = prime_fpriv->dmabufs.rb_node;
+	mutex_lock(&prime_fpriv->lock);
+
+	rb = prime_fpriv->handles.rb_node;
 	while (rb) {
 		struct drm_prime_member *member;
 
-		member = rb_entry(rb, struct drm_prime_member, dmabuf_rb);
-		if (member->dma_buf == dma_buf) {
+		member = rb_entry(rb, struct drm_prime_member, handle_rb);
+		if (member->handle == handle) {
 			rb_erase(&member->handle_rb, &prime_fpriv->handles);
 			rb_erase(&member->dmabuf_rb, &prime_fpriv->dmabufs);
 
-			dma_buf_put(dma_buf);
+			dma_buf_put(member->dma_buf);
 			kfree(member);
-			return;
-		} else if (member->dma_buf < dma_buf) {
+			break;
+		} else if (member->handle < handle) {
 			rb = rb->rb_right;
 		} else {
 			rb = rb->rb_left;
 		}
 	}
+
+	mutex_unlock(&prime_fpriv->lock);
 }
 
 void drm_prime_init_file_private(struct drm_prime_file_private *prime_fpriv)
diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
index 12571ac45540..12989a47eb66 100644
--- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
@@ -806,31 +806,40 @@ static int exynos7_decon_resume(struct device *dev)
 	if (ret < 0) {
 		DRM_DEV_ERROR(dev, "Failed to prepare_enable the pclk [%d]\n",
 			      ret);
-		return ret;
+		goto err_pclk_enable;
 	}
 
 	ret = clk_prepare_enable(ctx->aclk);
 	if (ret < 0) {
 		DRM_DEV_ERROR(dev, "Failed to prepare_enable the aclk [%d]\n",
 			      ret);
-		return ret;
+		goto err_aclk_enable;
 	}
 
 	ret = clk_prepare_enable(ctx->eclk);
 	if  (ret < 0) {
 		DRM_DEV_ERROR(dev, "Failed to prepare_enable the eclk [%d]\n",
 			      ret);
-		return ret;
+		goto err_eclk_enable;
 	}
 
 	ret = clk_prepare_enable(ctx->vclk);
 	if  (ret < 0) {
 		DRM_DEV_ERROR(dev, "Failed to prepare_enable the vclk [%d]\n",
 			      ret);
-		return ret;
+		goto err_vclk_enable;
 	}
 
 	return 0;
+
+err_vclk_enable:
+	clk_disable_unprepare(ctx->eclk);
+err_eclk_enable:
+	clk_disable_unprepare(ctx->aclk);
+err_aclk_enable:
+	clk_disable_unprepare(ctx->pclk);
+err_pclk_enable:
+	return ret;
 }
 #endif
 
diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_modeset.c b/drivers/gpu/drm/hyperv/hyperv_drm_modeset.c
index 8c97a20dfe23..22bebeb9c3ac 100644
--- a/drivers/gpu/drm/hyperv/hyperv_drm_modeset.c
+++ b/drivers/gpu/drm/hyperv/hyperv_drm_modeset.c
@@ -7,9 +7,11 @@
 
 #include <drm/drm_damage_helper.h>
 #include <drm/drm_drv.h>
+#include <drm/drm_edid.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_format_helper.h>
 #include <drm/drm_fourcc.h>
+#include <drm/drm_framebuffer.h>
 #include <drm/drm_gem_atomic_helper.h>
 #include <drm/drm_gem_framebuffer_helper.h>
 #include <drm/drm_gem_shmem_helper.h>
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 26cf75422945..9d371be7dc5c 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -249,6 +249,7 @@ i915-y += \
 	display/g4x_dp.o \
 	display/g4x_hdmi.o \
 	display/icl_dsi.o \
+	display/intel_backlight.o \
 	display/intel_crt.o \
 	display/intel_ddi.o \
 	display/intel_ddi_buf_trans.o \
diff --git a/drivers/gpu/drm/i915/display/g4x_dp.c b/drivers/gpu/drm/i915/display/g4x_dp.c
index de0f358184aa..29c0eca647e3 100644
--- a/drivers/gpu/drm/i915/display/g4x_dp.c
+++ b/drivers/gpu/drm/i915/display/g4x_dp.c
@@ -7,6 +7,7 @@
 
 #include "g4x_dp.h"
 #include "intel_audio.h"
+#include "intel_backlight.h"
 #include "intel_connector.h"
 #include "intel_de.h"
 #include "intel_display_types.h"
@@ -16,7 +17,6 @@
 #include "intel_fifo_underrun.h"
 #include "intel_hdmi.h"
 #include "intel_hotplug.h"
-#include "intel_panel.h"
 #include "intel_pps.h"
 #include "intel_sideband.h"
 
diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c
index 638a00b2dc2d..2601873e1546 100644
--- a/drivers/gpu/drm/i915/display/icl_dsi.c
+++ b/drivers/gpu/drm/i915/display/icl_dsi.c
@@ -29,6 +29,7 @@
 #include <drm/drm_mipi_dsi.h>
 
 #include "intel_atomic.h"
+#include "intel_backlight.h"
 #include "intel_combo_phy.h"
 #include "intel_connector.h"
 #include "intel_crtc.h"
diff --git a/drivers/gpu/drm/i915/display/intel_backlight.c b/drivers/gpu/drm/i915/display/intel_backlight.c
new file mode 100644
index 000000000000..60f91ac7d142
--- /dev/null
+++ b/drivers/gpu/drm/i915/display/intel_backlight.c
@@ -0,0 +1,1776 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#include <linux/kernel.h>
+#include <linux/pwm.h>
+
+#include "intel_backlight.h"
+#include "intel_connector.h"
+#include "intel_de.h"
+#include "intel_display_types.h"
+#include "intel_dp_aux_backlight.h"
+#include "intel_dsi_dcs_backlight.h"
+#include "intel_panel.h"
+
+/**
+ * scale - scale values from one range to another
+ * @source_val: value in range [@source_min..@source_max]
+ * @source_min: minimum legal value for @source_val
+ * @source_max: maximum legal value for @source_val
+ * @target_min: corresponding target value for @source_min
+ * @target_max: corresponding target value for @source_max
+ *
+ * Return @source_val in range [@source_min..@source_max] scaled to range
+ * [@target_min..@target_max].
+ */
+static u32 scale(u32 source_val,
+		 u32 source_min, u32 source_max,
+		 u32 target_min, u32 target_max)
+{
+	u64 target_val;
+
+	WARN_ON(source_min > source_max);
+	WARN_ON(target_min > target_max);
+
+	/* defensive */
+	source_val = clamp(source_val, source_min, source_max);
+
+	/* avoid overflows */
+	target_val = mul_u32_u32(source_val - source_min,
+				 target_max - target_min);
+	target_val = DIV_ROUND_CLOSEST_ULL(target_val, source_max - source_min);
+	target_val += target_min;
+
+	return target_val;
+}
+
+/*
+ * Scale user_level in range [0..user_max] to [0..hw_max], clamping the result
+ * to [hw_min..hw_max].
+ */
+static u32 clamp_user_to_hw(struct intel_connector *connector,
+			    u32 user_level, u32 user_max)
+{
+	struct intel_panel *panel = &connector->panel;
+	u32 hw_level;
+
+	hw_level = scale(user_level, 0, user_max, 0, panel->backlight.max);
+	hw_level = clamp(hw_level, panel->backlight.min, panel->backlight.max);
+
+	return hw_level;
+}
+
+/* Scale hw_level in range [hw_min..hw_max] to [0..user_max]. */
+static u32 scale_hw_to_user(struct intel_connector *connector,
+			    u32 hw_level, u32 user_max)
+{
+	struct intel_panel *panel = &connector->panel;
+
+	return scale(hw_level, panel->backlight.min, panel->backlight.max,
+		     0, user_max);
+}
+
+u32 intel_panel_invert_pwm_level(struct intel_connector *connector, u32 val)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+
+	drm_WARN_ON(&dev_priv->drm, panel->backlight.pwm_level_max == 0);
+
+	if (dev_priv->params.invert_brightness < 0)
+		return val;
+
+	if (dev_priv->params.invert_brightness > 0 ||
+	    dev_priv->quirks & QUIRK_INVERT_BRIGHTNESS) {
+		return panel->backlight.pwm_level_max - val + panel->backlight.pwm_level_min;
+	}
+
+	return val;
+}
+
+void intel_panel_set_pwm_level(const struct drm_connector_state *conn_state, u32 val)
+{
+	struct intel_connector *connector = to_intel_connector(conn_state->connector);
+	struct drm_i915_private *i915 = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+
+	drm_dbg_kms(&i915->drm, "set backlight PWM = %d\n", val);
+	panel->backlight.pwm_funcs->set(conn_state, val);
+}
+
+u32 intel_panel_backlight_level_to_pwm(struct intel_connector *connector, u32 val)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+
+	drm_WARN_ON_ONCE(&dev_priv->drm,
+			 panel->backlight.max == 0 || panel->backlight.pwm_level_max == 0);
+
+	val = scale(val, panel->backlight.min, panel->backlight.max,
+		    panel->backlight.pwm_level_min, panel->backlight.pwm_level_max);
+
+	return intel_panel_invert_pwm_level(connector, val);
+}
+
+u32 intel_panel_backlight_level_from_pwm(struct intel_connector *connector, u32 val)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+
+	drm_WARN_ON_ONCE(&dev_priv->drm,
+			 panel->backlight.max == 0 || panel->backlight.pwm_level_max == 0);
+
+	if (dev_priv->params.invert_brightness > 0 ||
+	    (dev_priv->params.invert_brightness == 0 && dev_priv->quirks & QUIRK_INVERT_BRIGHTNESS))
+		val = panel->backlight.pwm_level_max - (val - panel->backlight.pwm_level_min);
+
+	return scale(val, panel->backlight.pwm_level_min, panel->backlight.pwm_level_max,
+		     panel->backlight.min, panel->backlight.max);
+}
+
+static u32 lpt_get_backlight(struct intel_connector *connector, enum pipe unused)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+
+	return intel_de_read(dev_priv, BLC_PWM_PCH_CTL2) & BACKLIGHT_DUTY_CYCLE_MASK;
+}
+
+static u32 pch_get_backlight(struct intel_connector *connector, enum pipe unused)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+
+	return intel_de_read(dev_priv, BLC_PWM_CPU_CTL) & BACKLIGHT_DUTY_CYCLE_MASK;
+}
+
+static u32 i9xx_get_backlight(struct intel_connector *connector, enum pipe unused)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+	u32 val;
+
+	val = intel_de_read(dev_priv, BLC_PWM_CTL) & BACKLIGHT_DUTY_CYCLE_MASK;
+	if (DISPLAY_VER(dev_priv) < 4)
+		val >>= 1;
+
+	if (panel->backlight.combination_mode) {
+		u8 lbpc;
+
+		pci_read_config_byte(to_pci_dev(dev_priv->drm.dev), LBPC, &lbpc);
+		val *= lbpc;
+	}
+
+	return val;
+}
+
+static u32 vlv_get_backlight(struct intel_connector *connector, enum pipe pipe)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+
+	if (drm_WARN_ON(&dev_priv->drm, pipe != PIPE_A && pipe != PIPE_B))
+		return 0;
+
+	return intel_de_read(dev_priv, VLV_BLC_PWM_CTL(pipe)) & BACKLIGHT_DUTY_CYCLE_MASK;
+}
+
+static u32 bxt_get_backlight(struct intel_connector *connector, enum pipe unused)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+
+	return intel_de_read(dev_priv,
+			     BXT_BLC_PWM_DUTY(panel->backlight.controller));
+}
+
+static u32 ext_pwm_get_backlight(struct intel_connector *connector, enum pipe unused)
+{
+	struct intel_panel *panel = &connector->panel;
+	struct pwm_state state;
+
+	pwm_get_state(panel->backlight.pwm, &state);
+	return pwm_get_relative_duty_cycle(&state, 100);
+}
+
+static void lpt_set_backlight(const struct drm_connector_state *conn_state, u32 level)
+{
+	struct intel_connector *connector = to_intel_connector(conn_state->connector);
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+
+	u32 val = intel_de_read(dev_priv, BLC_PWM_PCH_CTL2) & ~BACKLIGHT_DUTY_CYCLE_MASK;
+	intel_de_write(dev_priv, BLC_PWM_PCH_CTL2, val | level);
+}
+
+static void pch_set_backlight(const struct drm_connector_state *conn_state, u32 level)
+{
+	struct intel_connector *connector = to_intel_connector(conn_state->connector);
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	u32 tmp;
+
+	tmp = intel_de_read(dev_priv, BLC_PWM_CPU_CTL) & ~BACKLIGHT_DUTY_CYCLE_MASK;
+	intel_de_write(dev_priv, BLC_PWM_CPU_CTL, tmp | level);
+}
+
+static void i9xx_set_backlight(const struct drm_connector_state *conn_state, u32 level)
+{
+	struct intel_connector *connector = to_intel_connector(conn_state->connector);
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+	u32 tmp, mask;
+
+	drm_WARN_ON(&dev_priv->drm, panel->backlight.pwm_level_max == 0);
+
+	if (panel->backlight.combination_mode) {
+		u8 lbpc;
+
+		lbpc = level * 0xfe / panel->backlight.pwm_level_max + 1;
+		level /= lbpc;
+		pci_write_config_byte(to_pci_dev(dev_priv->drm.dev), LBPC, lbpc);
+	}
+
+	if (DISPLAY_VER(dev_priv) == 4) {
+		mask = BACKLIGHT_DUTY_CYCLE_MASK;
+	} else {
+		level <<= 1;
+		mask = BACKLIGHT_DUTY_CYCLE_MASK_PNV;
+	}
+
+	tmp = intel_de_read(dev_priv, BLC_PWM_CTL) & ~mask;
+	intel_de_write(dev_priv, BLC_PWM_CTL, tmp | level);
+}
+
+static void vlv_set_backlight(const struct drm_connector_state *conn_state, u32 level)
+{
+	struct intel_connector *connector = to_intel_connector(conn_state->connector);
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	enum pipe pipe = to_intel_crtc(conn_state->crtc)->pipe;
+	u32 tmp;
+
+	tmp = intel_de_read(dev_priv, VLV_BLC_PWM_CTL(pipe)) & ~BACKLIGHT_DUTY_CYCLE_MASK;
+	intel_de_write(dev_priv, VLV_BLC_PWM_CTL(pipe), tmp | level);
+}
+
+static void bxt_set_backlight(const struct drm_connector_state *conn_state, u32 level)
+{
+	struct intel_connector *connector = to_intel_connector(conn_state->connector);
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+
+	intel_de_write(dev_priv,
+		       BXT_BLC_PWM_DUTY(panel->backlight.controller), level);
+}
+
+static void ext_pwm_set_backlight(const struct drm_connector_state *conn_state, u32 level)
+{
+	struct intel_panel *panel = &to_intel_connector(conn_state->connector)->panel;
+
+	pwm_set_relative_duty_cycle(&panel->backlight.pwm_state, level, 100);
+	pwm_apply_state(panel->backlight.pwm, &panel->backlight.pwm_state);
+}
+
+static void
+intel_panel_actually_set_backlight(const struct drm_connector_state *conn_state, u32 level)
+{
+	struct intel_connector *connector = to_intel_connector(conn_state->connector);
+	struct drm_i915_private *i915 = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+
+	drm_dbg_kms(&i915->drm, "set backlight level = %d\n", level);
+
+	panel->backlight.funcs->set(conn_state, level);
+}
+
+/* set backlight brightness to level in range [0..max], assuming hw min is
+ * respected.
+ */
+void intel_panel_set_backlight_acpi(const struct drm_connector_state *conn_state,
+				    u32 user_level, u32 user_max)
+{
+	struct intel_connector *connector = to_intel_connector(conn_state->connector);
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+	u32 hw_level;
+
+	/*
+	 * Lack of crtc may occur during driver init because
+	 * connection_mutex isn't held across the entire backlight
+	 * setup + modeset readout, and the BIOS can issue the
+	 * requests at any time.
+	 */
+	if (!panel->backlight.present || !conn_state->crtc)
+		return;
+
+	mutex_lock(&dev_priv->backlight_lock);
+
+	drm_WARN_ON(&dev_priv->drm, panel->backlight.max == 0);
+
+	hw_level = clamp_user_to_hw(connector, user_level, user_max);
+	panel->backlight.level = hw_level;
+
+	if (panel->backlight.device)
+		panel->backlight.device->props.brightness =
+			scale_hw_to_user(connector,
+					 panel->backlight.level,
+					 panel->backlight.device->props.max_brightness);
+
+	if (panel->backlight.enabled)
+		intel_panel_actually_set_backlight(conn_state, hw_level);
+
+	mutex_unlock(&dev_priv->backlight_lock);
+}
+
+static void lpt_disable_backlight(const struct drm_connector_state *old_conn_state, u32 level)
+{
+	struct intel_connector *connector = to_intel_connector(old_conn_state->connector);
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	u32 tmp;
+
+	intel_panel_set_pwm_level(old_conn_state, level);
+
+	/*
+	 * Although we don't support or enable CPU PWM with LPT/SPT based
+	 * systems, it may have been enabled prior to loading the
+	 * driver. Disable to avoid warnings on LCPLL disable.
+	 *
+	 * This needs rework if we need to add support for CPU PWM on PCH split
+	 * platforms.
+	 */
+	tmp = intel_de_read(dev_priv, BLC_PWM_CPU_CTL2);
+	if (tmp & BLM_PWM_ENABLE) {
+		drm_dbg_kms(&dev_priv->drm,
+			    "cpu backlight was enabled, disabling\n");
+		intel_de_write(dev_priv, BLC_PWM_CPU_CTL2,
+			       tmp & ~BLM_PWM_ENABLE);
+	}
+
+	tmp = intel_de_read(dev_priv, BLC_PWM_PCH_CTL1);
+	intel_de_write(dev_priv, BLC_PWM_PCH_CTL1, tmp & ~BLM_PCH_PWM_ENABLE);
+}
+
+static void pch_disable_backlight(const struct drm_connector_state *old_conn_state, u32 val)
+{
+	struct intel_connector *connector = to_intel_connector(old_conn_state->connector);
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	u32 tmp;
+
+	intel_panel_set_pwm_level(old_conn_state, val);
+
+	tmp = intel_de_read(dev_priv, BLC_PWM_CPU_CTL2);
+	intel_de_write(dev_priv, BLC_PWM_CPU_CTL2, tmp & ~BLM_PWM_ENABLE);
+
+	tmp = intel_de_read(dev_priv, BLC_PWM_PCH_CTL1);
+	intel_de_write(dev_priv, BLC_PWM_PCH_CTL1, tmp & ~BLM_PCH_PWM_ENABLE);
+}
+
+static void i9xx_disable_backlight(const struct drm_connector_state *old_conn_state, u32 val)
+{
+	intel_panel_set_pwm_level(old_conn_state, val);
+}
+
+static void i965_disable_backlight(const struct drm_connector_state *old_conn_state, u32 val)
+{
+	struct drm_i915_private *dev_priv = to_i915(old_conn_state->connector->dev);
+	u32 tmp;
+
+	intel_panel_set_pwm_level(old_conn_state, val);
+
+	tmp = intel_de_read(dev_priv, BLC_PWM_CTL2);
+	intel_de_write(dev_priv, BLC_PWM_CTL2, tmp & ~BLM_PWM_ENABLE);
+}
+
+static void vlv_disable_backlight(const struct drm_connector_state *old_conn_state, u32 val)
+{
+	struct intel_connector *connector = to_intel_connector(old_conn_state->connector);
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	enum pipe pipe = to_intel_crtc(old_conn_state->crtc)->pipe;
+	u32 tmp;
+
+	intel_panel_set_pwm_level(old_conn_state, val);
+
+	tmp = intel_de_read(dev_priv, VLV_BLC_PWM_CTL2(pipe));
+	intel_de_write(dev_priv, VLV_BLC_PWM_CTL2(pipe),
+		       tmp & ~BLM_PWM_ENABLE);
+}
+
+static void bxt_disable_backlight(const struct drm_connector_state *old_conn_state, u32 val)
+{
+	struct intel_connector *connector = to_intel_connector(old_conn_state->connector);
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+	u32 tmp;
+
+	intel_panel_set_pwm_level(old_conn_state, val);
+
+	tmp = intel_de_read(dev_priv,
+			    BXT_BLC_PWM_CTL(panel->backlight.controller));
+	intel_de_write(dev_priv, BXT_BLC_PWM_CTL(panel->backlight.controller),
+		       tmp & ~BXT_BLC_PWM_ENABLE);
+
+	if (panel->backlight.controller == 1) {
+		val = intel_de_read(dev_priv, UTIL_PIN_CTL);
+		val &= ~UTIL_PIN_ENABLE;
+		intel_de_write(dev_priv, UTIL_PIN_CTL, val);
+	}
+}
+
+static void cnp_disable_backlight(const struct drm_connector_state *old_conn_state, u32 val)
+{
+	struct intel_connector *connector = to_intel_connector(old_conn_state->connector);
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+	u32 tmp;
+
+	intel_panel_set_pwm_level(old_conn_state, val);
+
+	tmp = intel_de_read(dev_priv,
+			    BXT_BLC_PWM_CTL(panel->backlight.controller));
+	intel_de_write(dev_priv, BXT_BLC_PWM_CTL(panel->backlight.controller),
+		       tmp & ~BXT_BLC_PWM_ENABLE);
+}
+
+static void ext_pwm_disable_backlight(const struct drm_connector_state *old_conn_state, u32 level)
+{
+	struct intel_connector *connector = to_intel_connector(old_conn_state->connector);
+	struct intel_panel *panel = &connector->panel;
+
+	panel->backlight.pwm_state.enabled = false;
+	pwm_apply_state(panel->backlight.pwm, &panel->backlight.pwm_state);
+}
+
+void intel_panel_disable_backlight(const struct drm_connector_state *old_conn_state)
+{
+	struct intel_connector *connector = to_intel_connector(old_conn_state->connector);
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+
+	if (!panel->backlight.present)
+		return;
+
+	/*
+	 * Do not disable backlight on the vga_switcheroo path. When switching
+	 * away from i915, the other client may depend on i915 to handle the
+	 * backlight. This will leave the backlight on unnecessarily when
+	 * another client is not activated.
+	 */
+	if (dev_priv->drm.switch_power_state == DRM_SWITCH_POWER_CHANGING) {
+		drm_dbg_kms(&dev_priv->drm,
+			    "Skipping backlight disable on vga switch\n");
+		return;
+	}
+
+	mutex_lock(&dev_priv->backlight_lock);
+
+	if (panel->backlight.device)
+		panel->backlight.device->props.power = FB_BLANK_POWERDOWN;
+	panel->backlight.enabled = false;
+	panel->backlight.funcs->disable(old_conn_state, 0);
+
+	mutex_unlock(&dev_priv->backlight_lock);
+}
+
+static void lpt_enable_backlight(const struct intel_crtc_state *crtc_state,
+				 const struct drm_connector_state *conn_state, u32 level)
+{
+	struct intel_connector *connector = to_intel_connector(conn_state->connector);
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+	u32 pch_ctl1, pch_ctl2, schicken;
+
+	pch_ctl1 = intel_de_read(dev_priv, BLC_PWM_PCH_CTL1);
+	if (pch_ctl1 & BLM_PCH_PWM_ENABLE) {
+		drm_dbg_kms(&dev_priv->drm, "pch backlight already enabled\n");
+		pch_ctl1 &= ~BLM_PCH_PWM_ENABLE;
+		intel_de_write(dev_priv, BLC_PWM_PCH_CTL1, pch_ctl1);
+	}
+
+	if (HAS_PCH_LPT(dev_priv)) {
+		schicken = intel_de_read(dev_priv, SOUTH_CHICKEN2);
+		if (panel->backlight.alternate_pwm_increment)
+			schicken |= LPT_PWM_GRANULARITY;
+		else
+			schicken &= ~LPT_PWM_GRANULARITY;
+		intel_de_write(dev_priv, SOUTH_CHICKEN2, schicken);
+	} else {
+		schicken = intel_de_read(dev_priv, SOUTH_CHICKEN1);
+		if (panel->backlight.alternate_pwm_increment)
+			schicken |= SPT_PWM_GRANULARITY;
+		else
+			schicken &= ~SPT_PWM_GRANULARITY;
+		intel_de_write(dev_priv, SOUTH_CHICKEN1, schicken);
+	}
+
+	pch_ctl2 = panel->backlight.pwm_level_max << 16;
+	intel_de_write(dev_priv, BLC_PWM_PCH_CTL2, pch_ctl2);
+
+	pch_ctl1 = 0;
+	if (panel->backlight.active_low_pwm)
+		pch_ctl1 |= BLM_PCH_POLARITY;
+
+	/* After LPT, override is the default. */
+	if (HAS_PCH_LPT(dev_priv))
+		pch_ctl1 |= BLM_PCH_OVERRIDE_ENABLE;
+
+	intel_de_write(dev_priv, BLC_PWM_PCH_CTL1, pch_ctl1);
+	intel_de_posting_read(dev_priv, BLC_PWM_PCH_CTL1);
+	intel_de_write(dev_priv, BLC_PWM_PCH_CTL1,
+		       pch_ctl1 | BLM_PCH_PWM_ENABLE);
+
+	/* This won't stick until the above enable. */
+	intel_panel_set_pwm_level(conn_state, level);
+}
+
+static void pch_enable_backlight(const struct intel_crtc_state *crtc_state,
+				 const struct drm_connector_state *conn_state, u32 level)
+{
+	struct intel_connector *connector = to_intel_connector(conn_state->connector);
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
+	u32 cpu_ctl2, pch_ctl1, pch_ctl2;
+
+	cpu_ctl2 = intel_de_read(dev_priv, BLC_PWM_CPU_CTL2);
+	if (cpu_ctl2 & BLM_PWM_ENABLE) {
+		drm_dbg_kms(&dev_priv->drm, "cpu backlight already enabled\n");
+		cpu_ctl2 &= ~BLM_PWM_ENABLE;
+		intel_de_write(dev_priv, BLC_PWM_CPU_CTL2, cpu_ctl2);
+	}
+
+	pch_ctl1 = intel_de_read(dev_priv, BLC_PWM_PCH_CTL1);
+	if (pch_ctl1 & BLM_PCH_PWM_ENABLE) {
+		drm_dbg_kms(&dev_priv->drm, "pch backlight already enabled\n");
+		pch_ctl1 &= ~BLM_PCH_PWM_ENABLE;
+		intel_de_write(dev_priv, BLC_PWM_PCH_CTL1, pch_ctl1);
+	}
+
+	if (cpu_transcoder == TRANSCODER_EDP)
+		cpu_ctl2 = BLM_TRANSCODER_EDP;
+	else
+		cpu_ctl2 = BLM_PIPE(cpu_transcoder);
+	intel_de_write(dev_priv, BLC_PWM_CPU_CTL2, cpu_ctl2);
+	intel_de_posting_read(dev_priv, BLC_PWM_CPU_CTL2);
+	intel_de_write(dev_priv, BLC_PWM_CPU_CTL2, cpu_ctl2 | BLM_PWM_ENABLE);
+
+	/* This won't stick until the above enable. */
+	intel_panel_set_pwm_level(conn_state, level);
+
+	pch_ctl2 = panel->backlight.pwm_level_max << 16;
+	intel_de_write(dev_priv, BLC_PWM_PCH_CTL2, pch_ctl2);
+
+	pch_ctl1 = 0;
+	if (panel->backlight.active_low_pwm)
+		pch_ctl1 |= BLM_PCH_POLARITY;
+
+	intel_de_write(dev_priv, BLC_PWM_PCH_CTL1, pch_ctl1);
+	intel_de_posting_read(dev_priv, BLC_PWM_PCH_CTL1);
+	intel_de_write(dev_priv, BLC_PWM_PCH_CTL1,
+		       pch_ctl1 | BLM_PCH_PWM_ENABLE);
+}
+
+static void i9xx_enable_backlight(const struct intel_crtc_state *crtc_state,
+				  const struct drm_connector_state *conn_state, u32 level)
+{
+	struct intel_connector *connector = to_intel_connector(conn_state->connector);
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+	u32 ctl, freq;
+
+	ctl = intel_de_read(dev_priv, BLC_PWM_CTL);
+	if (ctl & BACKLIGHT_DUTY_CYCLE_MASK_PNV) {
+		drm_dbg_kms(&dev_priv->drm, "backlight already enabled\n");
+		intel_de_write(dev_priv, BLC_PWM_CTL, 0);
+	}
+
+	freq = panel->backlight.pwm_level_max;
+	if (panel->backlight.combination_mode)
+		freq /= 0xff;
+
+	ctl = freq << 17;
+	if (panel->backlight.combination_mode)
+		ctl |= BLM_LEGACY_MODE;
+	if (IS_PINEVIEW(dev_priv) && panel->backlight.active_low_pwm)
+		ctl |= BLM_POLARITY_PNV;
+
+	intel_de_write(dev_priv, BLC_PWM_CTL, ctl);
+	intel_de_posting_read(dev_priv, BLC_PWM_CTL);
+
+	/* XXX: combine this into above write? */
+	intel_panel_set_pwm_level(conn_state, level);
+
+	/*
+	 * Needed to enable backlight on some 855gm models. BLC_HIST_CTL is
+	 * 855gm only, but checking for gen2 is safe, as 855gm is the only gen2
+	 * that has backlight.
+	 */
+	if (DISPLAY_VER(dev_priv) == 2)
+		intel_de_write(dev_priv, BLC_HIST_CTL, BLM_HISTOGRAM_ENABLE);
+}
+
+static void i965_enable_backlight(const struct intel_crtc_state *crtc_state,
+				  const struct drm_connector_state *conn_state, u32 level)
+{
+	struct intel_connector *connector = to_intel_connector(conn_state->connector);
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+	enum pipe pipe = to_intel_crtc(conn_state->crtc)->pipe;
+	u32 ctl, ctl2, freq;
+
+	ctl2 = intel_de_read(dev_priv, BLC_PWM_CTL2);
+	if (ctl2 & BLM_PWM_ENABLE) {
+		drm_dbg_kms(&dev_priv->drm, "backlight already enabled\n");
+		ctl2 &= ~BLM_PWM_ENABLE;
+		intel_de_write(dev_priv, BLC_PWM_CTL2, ctl2);
+	}
+
+	freq = panel->backlight.pwm_level_max;
+	if (panel->backlight.combination_mode)
+		freq /= 0xff;
+
+	ctl = freq << 16;
+	intel_de_write(dev_priv, BLC_PWM_CTL, ctl);
+
+	ctl2 = BLM_PIPE(pipe);
+	if (panel->backlight.combination_mode)
+		ctl2 |= BLM_COMBINATION_MODE;
+	if (panel->backlight.active_low_pwm)
+		ctl2 |= BLM_POLARITY_I965;
+	intel_de_write(dev_priv, BLC_PWM_CTL2, ctl2);
+	intel_de_posting_read(dev_priv, BLC_PWM_CTL2);
+	intel_de_write(dev_priv, BLC_PWM_CTL2, ctl2 | BLM_PWM_ENABLE);
+
+	intel_panel_set_pwm_level(conn_state, level);
+}
+
+static void vlv_enable_backlight(const struct intel_crtc_state *crtc_state,
+				 const struct drm_connector_state *conn_state, u32 level)
+{
+	struct intel_connector *connector = to_intel_connector(conn_state->connector);
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+	enum pipe pipe = to_intel_crtc(crtc_state->uapi.crtc)->pipe;
+	u32 ctl, ctl2;
+
+	ctl2 = intel_de_read(dev_priv, VLV_BLC_PWM_CTL2(pipe));
+	if (ctl2 & BLM_PWM_ENABLE) {
+		drm_dbg_kms(&dev_priv->drm, "backlight already enabled\n");
+		ctl2 &= ~BLM_PWM_ENABLE;
+		intel_de_write(dev_priv, VLV_BLC_PWM_CTL2(pipe), ctl2);
+	}
+
+	ctl = panel->backlight.pwm_level_max << 16;
+	intel_de_write(dev_priv, VLV_BLC_PWM_CTL(pipe), ctl);
+
+	/* XXX: combine this into above write? */
+	intel_panel_set_pwm_level(conn_state, level);
+
+	ctl2 = 0;
+	if (panel->backlight.active_low_pwm)
+		ctl2 |= BLM_POLARITY_I965;
+	intel_de_write(dev_priv, VLV_BLC_PWM_CTL2(pipe), ctl2);
+	intel_de_posting_read(dev_priv, VLV_BLC_PWM_CTL2(pipe));
+	intel_de_write(dev_priv, VLV_BLC_PWM_CTL2(pipe),
+		       ctl2 | BLM_PWM_ENABLE);
+}
+
+static void bxt_enable_backlight(const struct intel_crtc_state *crtc_state,
+				 const struct drm_connector_state *conn_state, u32 level)
+{
+	struct intel_connector *connector = to_intel_connector(conn_state->connector);
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+	enum pipe pipe = to_intel_crtc(crtc_state->uapi.crtc)->pipe;
+	u32 pwm_ctl, val;
+
+	/* Controller 1 uses the utility pin. */
+	if (panel->backlight.controller == 1) {
+		val = intel_de_read(dev_priv, UTIL_PIN_CTL);
+		if (val & UTIL_PIN_ENABLE) {
+			drm_dbg_kms(&dev_priv->drm,
+				    "util pin already enabled\n");
+			val &= ~UTIL_PIN_ENABLE;
+			intel_de_write(dev_priv, UTIL_PIN_CTL, val);
+		}
+
+		val = 0;
+		if (panel->backlight.util_pin_active_low)
+			val |= UTIL_PIN_POLARITY;
+		intel_de_write(dev_priv, UTIL_PIN_CTL,
+			       val | UTIL_PIN_PIPE(pipe) | UTIL_PIN_MODE_PWM | UTIL_PIN_ENABLE);
+	}
+
+	pwm_ctl = intel_de_read(dev_priv,
+				BXT_BLC_PWM_CTL(panel->backlight.controller));
+	if (pwm_ctl & BXT_BLC_PWM_ENABLE) {
+		drm_dbg_kms(&dev_priv->drm, "backlight already enabled\n");
+		pwm_ctl &= ~BXT_BLC_PWM_ENABLE;
+		intel_de_write(dev_priv,
+			       BXT_BLC_PWM_CTL(panel->backlight.controller),
+			       pwm_ctl);
+	}
+
+	intel_de_write(dev_priv,
+		       BXT_BLC_PWM_FREQ(panel->backlight.controller),
+		       panel->backlight.pwm_level_max);
+
+	intel_panel_set_pwm_level(conn_state, level);
+
+	pwm_ctl = 0;
+	if (panel->backlight.active_low_pwm)
+		pwm_ctl |= BXT_BLC_PWM_POLARITY;
+
+	intel_de_write(dev_priv, BXT_BLC_PWM_CTL(panel->backlight.controller),
+		       pwm_ctl);
+	intel_de_posting_read(dev_priv,
+			      BXT_BLC_PWM_CTL(panel->backlight.controller));
+	intel_de_write(dev_priv, BXT_BLC_PWM_CTL(panel->backlight.controller),
+		       pwm_ctl | BXT_BLC_PWM_ENABLE);
+}
+
+static void cnp_enable_backlight(const struct intel_crtc_state *crtc_state,
+				 const struct drm_connector_state *conn_state, u32 level)
+{
+	struct intel_connector *connector = to_intel_connector(conn_state->connector);
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+	u32 pwm_ctl;
+
+	pwm_ctl = intel_de_read(dev_priv,
+				BXT_BLC_PWM_CTL(panel->backlight.controller));
+	if (pwm_ctl & BXT_BLC_PWM_ENABLE) {
+		drm_dbg_kms(&dev_priv->drm, "backlight already enabled\n");
+		pwm_ctl &= ~BXT_BLC_PWM_ENABLE;
+		intel_de_write(dev_priv,
+			       BXT_BLC_PWM_CTL(panel->backlight.controller),
+			       pwm_ctl);
+	}
+
+	intel_de_write(dev_priv,
+		       BXT_BLC_PWM_FREQ(panel->backlight.controller),
+		       panel->backlight.pwm_level_max);
+
+	intel_panel_set_pwm_level(conn_state, level);
+
+	pwm_ctl = 0;
+	if (panel->backlight.active_low_pwm)
+		pwm_ctl |= BXT_BLC_PWM_POLARITY;
+
+	intel_de_write(dev_priv, BXT_BLC_PWM_CTL(panel->backlight.controller),
+		       pwm_ctl);
+	intel_de_posting_read(dev_priv,
+			      BXT_BLC_PWM_CTL(panel->backlight.controller));
+	intel_de_write(dev_priv, BXT_BLC_PWM_CTL(panel->backlight.controller),
+		       pwm_ctl | BXT_BLC_PWM_ENABLE);
+}
+
+static void ext_pwm_enable_backlight(const struct intel_crtc_state *crtc_state,
+				     const struct drm_connector_state *conn_state, u32 level)
+{
+	struct intel_connector *connector = to_intel_connector(conn_state->connector);
+	struct intel_panel *panel = &connector->panel;
+
+	pwm_set_relative_duty_cycle(&panel->backlight.pwm_state, level, 100);
+	panel->backlight.pwm_state.enabled = true;
+	pwm_apply_state(panel->backlight.pwm, &panel->backlight.pwm_state);
+}
+
+static void __intel_panel_enable_backlight(const struct intel_crtc_state *crtc_state,
+					   const struct drm_connector_state *conn_state)
+{
+	struct intel_connector *connector = to_intel_connector(conn_state->connector);
+	struct intel_panel *panel = &connector->panel;
+
+	WARN_ON(panel->backlight.max == 0);
+
+	if (panel->backlight.level <= panel->backlight.min) {
+		panel->backlight.level = panel->backlight.max;
+		if (panel->backlight.device)
+			panel->backlight.device->props.brightness =
+				scale_hw_to_user(connector,
+						 panel->backlight.level,
+						 panel->backlight.device->props.max_brightness);
+	}
+
+	panel->backlight.funcs->enable(crtc_state, conn_state, panel->backlight.level);
+	panel->backlight.enabled = true;
+	if (panel->backlight.device)
+		panel->backlight.device->props.power = FB_BLANK_UNBLANK;
+}
+
+void intel_panel_enable_backlight(const struct intel_crtc_state *crtc_state,
+				  const struct drm_connector_state *conn_state)
+{
+	struct intel_connector *connector = to_intel_connector(conn_state->connector);
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+	enum pipe pipe = to_intel_crtc(crtc_state->uapi.crtc)->pipe;
+
+	if (!panel->backlight.present)
+		return;
+
+	drm_dbg_kms(&dev_priv->drm, "pipe %c\n", pipe_name(pipe));
+
+	mutex_lock(&dev_priv->backlight_lock);
+
+	__intel_panel_enable_backlight(crtc_state, conn_state);
+
+	mutex_unlock(&dev_priv->backlight_lock);
+}
+
+#if IS_ENABLED(CONFIG_BACKLIGHT_CLASS_DEVICE)
+static u32 intel_panel_get_backlight(struct intel_connector *connector)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+	u32 val = 0;
+
+	mutex_lock(&dev_priv->backlight_lock);
+
+	if (panel->backlight.enabled)
+		val = panel->backlight.funcs->get(connector, intel_connector_get_pipe(connector));
+
+	mutex_unlock(&dev_priv->backlight_lock);
+
+	drm_dbg_kms(&dev_priv->drm, "get backlight PWM = %d\n", val);
+	return val;
+}
+
+/* Scale user_level in range [0..user_max] to [hw_min..hw_max]. */
+static u32 scale_user_to_hw(struct intel_connector *connector,
+			    u32 user_level, u32 user_max)
+{
+	struct intel_panel *panel = &connector->panel;
+
+	return scale(user_level, 0, user_max,
+		     panel->backlight.min, panel->backlight.max);
+}
+
+/* set backlight brightness to level in range [0..max], scaling wrt hw min */
+static void intel_panel_set_backlight(const struct drm_connector_state *conn_state,
+				      u32 user_level, u32 user_max)
+{
+	struct intel_connector *connector = to_intel_connector(conn_state->connector);
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+	u32 hw_level;
+
+	if (!panel->backlight.present)
+		return;
+
+	mutex_lock(&dev_priv->backlight_lock);
+
+	drm_WARN_ON(&dev_priv->drm, panel->backlight.max == 0);
+
+	hw_level = scale_user_to_hw(connector, user_level, user_max);
+	panel->backlight.level = hw_level;
+
+	if (panel->backlight.enabled)
+		intel_panel_actually_set_backlight(conn_state, hw_level);
+
+	mutex_unlock(&dev_priv->backlight_lock);
+}
+
+static int intel_backlight_device_update_status(struct backlight_device *bd)
+{
+	struct intel_connector *connector = bl_get_data(bd);
+	struct intel_panel *panel = &connector->panel;
+	struct drm_device *dev = connector->base.dev;
+
+	drm_modeset_lock(&dev->mode_config.connection_mutex, NULL);
+	DRM_DEBUG_KMS("updating intel_backlight, brightness=%d/%d\n",
+		      bd->props.brightness, bd->props.max_brightness);
+	intel_panel_set_backlight(connector->base.state, bd->props.brightness,
+				  bd->props.max_brightness);
+
+	/*
+	 * Allow flipping bl_power as a sub-state of enabled. Sadly the
+	 * backlight class device does not make it easy to differentiate
+	 * between callbacks for brightness and bl_power, so our backlight_power
+	 * callback needs to take this into account.
+	 */
+	if (panel->backlight.enabled) {
+		if (panel->backlight.power) {
+			bool enable = bd->props.power == FB_BLANK_UNBLANK &&
+				bd->props.brightness != 0;
+			panel->backlight.power(connector, enable);
+		}
+	} else {
+		bd->props.power = FB_BLANK_POWERDOWN;
+	}
+
+	drm_modeset_unlock(&dev->mode_config.connection_mutex);
+	return 0;
+}
+
+static int intel_backlight_device_get_brightness(struct backlight_device *bd)
+{
+	struct intel_connector *connector = bl_get_data(bd);
+	struct drm_device *dev = connector->base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	intel_wakeref_t wakeref;
+	int ret = 0;
+
+	with_intel_runtime_pm(&dev_priv->runtime_pm, wakeref) {
+		u32 hw_level;
+
+		drm_modeset_lock(&dev->mode_config.connection_mutex, NULL);
+
+		hw_level = intel_panel_get_backlight(connector);
+		ret = scale_hw_to_user(connector,
+				       hw_level, bd->props.max_brightness);
+
+		drm_modeset_unlock(&dev->mode_config.connection_mutex);
+	}
+
+	return ret;
+}
+
+static const struct backlight_ops intel_backlight_device_ops = {
+	.update_status = intel_backlight_device_update_status,
+	.get_brightness = intel_backlight_device_get_brightness,
+};
+
+int intel_backlight_device_register(struct intel_connector *connector)
+{
+	struct drm_i915_private *i915 = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+	struct backlight_properties props;
+	struct backlight_device *bd;
+	const char *name;
+	int ret = 0;
+
+	if (WARN_ON(panel->backlight.device))
+		return -ENODEV;
+
+	if (!panel->backlight.present)
+		return 0;
+
+	WARN_ON(panel->backlight.max == 0);
+
+	memset(&props, 0, sizeof(props));
+	props.type = BACKLIGHT_RAW;
+
+	/*
+	 * Note: Everything should work even if the backlight device max
+	 * presented to the userspace is arbitrarily chosen.
+	 */
+	props.max_brightness = panel->backlight.max;
+	props.brightness = scale_hw_to_user(connector,
+					    panel->backlight.level,
+					    props.max_brightness);
+
+	if (panel->backlight.enabled)
+		props.power = FB_BLANK_UNBLANK;
+	else
+		props.power = FB_BLANK_POWERDOWN;
+
+	name = kstrdup("intel_backlight", GFP_KERNEL);
+	if (!name)
+		return -ENOMEM;
+
+	bd = backlight_device_get_by_name(name);
+	if (bd) {
+		put_device(&bd->dev);
+		/*
+		 * Using the same name independent of the drm device or connector
+		 * prevents registration of multiple backlight devices in the
+		 * driver. However, we need to use the default name for backward
+		 * compatibility. Use unique names for subsequent backlight devices as a
+		 * fallback when the default name already exists.
+		 */
+		kfree(name);
+		name = kasprintf(GFP_KERNEL, "card%d-%s-backlight",
+				 i915->drm.primary->index, connector->base.name);
+		if (!name)
+			return -ENOMEM;
+	}
+	bd = backlight_device_register(name, connector->base.kdev, connector,
+				       &intel_backlight_device_ops, &props);
+
+	if (IS_ERR(bd)) {
+		drm_err(&i915->drm,
+			"[CONNECTOR:%d:%s] backlight device %s register failed: %ld\n",
+			connector->base.base.id, connector->base.name, name, PTR_ERR(bd));
+		ret = PTR_ERR(bd);
+		goto out;
+	}
+
+	panel->backlight.device = bd;
+
+	drm_dbg_kms(&i915->drm,
+		    "[CONNECTOR:%d:%s] backlight device %s registered\n",
+		    connector->base.base.id, connector->base.name, name);
+
+out:
+	kfree(name);
+
+	return ret;
+}
+
+void intel_backlight_device_unregister(struct intel_connector *connector)
+{
+	struct intel_panel *panel = &connector->panel;
+
+	if (panel->backlight.device) {
+		backlight_device_unregister(panel->backlight.device);
+		panel->backlight.device = NULL;
+	}
+}
+#endif /* CONFIG_BACKLIGHT_CLASS_DEVICE */
+
+/*
+ * CNP: PWM clock frequency is 19.2 MHz or 24 MHz.
+ *      PWM increment = 1
+ */
+static u32 cnp_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+
+	return DIV_ROUND_CLOSEST(KHz(RUNTIME_INFO(dev_priv)->rawclk_freq),
+				 pwm_freq_hz);
+}
+
+/*
+ * BXT: PWM clock frequency = 19.2 MHz.
+ */
+static u32 bxt_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz)
+{
+	return DIV_ROUND_CLOSEST(KHz(19200), pwm_freq_hz);
+}
+
+/*
+ * SPT: This value represents the period of the PWM stream in clock periods
+ * multiplied by 16 (default increment) or 128 (alternate increment selected in
+ * SCHICKEN_1 bit 0). PWM clock is 24 MHz.
+ */
+static u32 spt_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz)
+{
+	struct intel_panel *panel = &connector->panel;
+	u32 mul;
+
+	if (panel->backlight.alternate_pwm_increment)
+		mul = 128;
+	else
+		mul = 16;
+
+	return DIV_ROUND_CLOSEST(MHz(24), pwm_freq_hz * mul);
+}
+
+/*
+ * LPT: This value represents the period of the PWM stream in clock periods
+ * multiplied by 128 (default increment) or 16 (alternate increment, selected in
+ * LPT SOUTH_CHICKEN2 register bit 5).
+ */
+static u32 lpt_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+	u32 mul, clock;
+
+	if (panel->backlight.alternate_pwm_increment)
+		mul = 16;
+	else
+		mul = 128;
+
+	if (HAS_PCH_LPT_H(dev_priv))
+		clock = MHz(135); /* LPT:H */
+	else
+		clock = MHz(24); /* LPT:LP */
+
+	return DIV_ROUND_CLOSEST(clock, pwm_freq_hz * mul);
+}
+
+/*
+ * ILK/SNB/IVB: This value represents the period of the PWM stream in PCH
+ * display raw clocks multiplied by 128.
+ */
+static u32 pch_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+
+	return DIV_ROUND_CLOSEST(KHz(RUNTIME_INFO(dev_priv)->rawclk_freq),
+				 pwm_freq_hz * 128);
+}
+
+/*
+ * Gen2: This field determines the number of time base events (display core
+ * clock frequency/32) in total for a complete cycle of modulated backlight
+ * control.
+ *
+ * Gen3: A time base event equals the display core clock ([DevPNV] HRAW clock)
+ * divided by 32.
+ */
+static u32 i9xx_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	int clock;
+
+	if (IS_PINEVIEW(dev_priv))
+		clock = KHz(RUNTIME_INFO(dev_priv)->rawclk_freq);
+	else
+		clock = KHz(dev_priv->cdclk.hw.cdclk);
+
+	return DIV_ROUND_CLOSEST(clock, pwm_freq_hz * 32);
+}
+
+/*
+ * Gen4: This value represents the period of the PWM stream in display core
+ * clocks ([DevCTG] HRAW clocks) multiplied by 128.
+ *
+ */
+static u32 i965_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	int clock;
+
+	if (IS_G4X(dev_priv))
+		clock = KHz(RUNTIME_INFO(dev_priv)->rawclk_freq);
+	else
+		clock = KHz(dev_priv->cdclk.hw.cdclk);
+
+	return DIV_ROUND_CLOSEST(clock, pwm_freq_hz * 128);
+}
+
+/*
+ * VLV: This value represents the period of the PWM stream in display core
+ * clocks ([DevCTG] 200MHz HRAW clocks) multiplied by 128 or 25MHz S0IX clocks
+ * multiplied by 16. CHV uses a 19.2MHz S0IX clock.
+ */
+static u32 vlv_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	int mul, clock;
+
+	if ((intel_de_read(dev_priv, CBR1_VLV) & CBR_PWM_CLOCK_MUX_SELECT) == 0) {
+		if (IS_CHERRYVIEW(dev_priv))
+			clock = KHz(19200);
+		else
+			clock = MHz(25);
+		mul = 16;
+	} else {
+		clock = KHz(RUNTIME_INFO(dev_priv)->rawclk_freq);
+		mul = 128;
+	}
+
+	return DIV_ROUND_CLOSEST(clock, pwm_freq_hz * mul);
+}
+
+static u16 get_vbt_pwm_freq(struct drm_i915_private *dev_priv)
+{
+	u16 pwm_freq_hz = dev_priv->vbt.backlight.pwm_freq_hz;
+
+	if (pwm_freq_hz) {
+		drm_dbg_kms(&dev_priv->drm,
+			    "VBT defined backlight frequency %u Hz\n",
+			    pwm_freq_hz);
+	} else {
+		pwm_freq_hz = 200;
+		drm_dbg_kms(&dev_priv->drm,
+			    "default backlight frequency %u Hz\n",
+			    pwm_freq_hz);
+	}
+
+	return pwm_freq_hz;
+}
+
+static u32 get_backlight_max_vbt(struct intel_connector *connector)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+	u16 pwm_freq_hz = get_vbt_pwm_freq(dev_priv);
+	u32 pwm;
+
+	if (!panel->backlight.pwm_funcs->hz_to_pwm) {
+		drm_dbg_kms(&dev_priv->drm,
+			    "backlight frequency conversion not supported\n");
+		return 0;
+	}
+
+	pwm = panel->backlight.pwm_funcs->hz_to_pwm(connector, pwm_freq_hz);
+	if (!pwm) {
+		drm_dbg_kms(&dev_priv->drm,
+			    "backlight frequency conversion failed\n");
+		return 0;
+	}
+
+	return pwm;
+}
+
+/*
+ * Note: The setup hooks can't assume pipe is set!
+ */
+static u32 get_backlight_min_vbt(struct intel_connector *connector)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+	int min;
+
+	drm_WARN_ON(&dev_priv->drm, panel->backlight.pwm_level_max == 0);
+
+	/*
+	 * XXX: If the vbt value is 255, it makes min equal to max, which leads
+	 * to problems. There are such machines out there. Either our
+	 * interpretation is wrong or the vbt has bogus data. Or both. Safeguard
+	 * against this by letting the minimum be at most (arbitrarily chosen)
+	 * 25% of the max.
+	 */
+	min = clamp_t(int, dev_priv->vbt.backlight.min_brightness, 0, 64);
+	if (min != dev_priv->vbt.backlight.min_brightness) {
+		drm_dbg_kms(&dev_priv->drm,
+			    "clamping VBT min backlight %d/255 to %d/255\n",
+			    dev_priv->vbt.backlight.min_brightness, min);
+	}
+
+	/* vbt value is a coefficient in range [0..255] */
+	return scale(min, 0, 255, 0, panel->backlight.pwm_level_max);
+}
+
+static int lpt_setup_backlight(struct intel_connector *connector, enum pipe unused)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+	u32 cpu_ctl2, pch_ctl1, pch_ctl2, val;
+	bool alt, cpu_mode;
+
+	if (HAS_PCH_LPT(dev_priv))
+		alt = intel_de_read(dev_priv, SOUTH_CHICKEN2) & LPT_PWM_GRANULARITY;
+	else
+		alt = intel_de_read(dev_priv, SOUTH_CHICKEN1) & SPT_PWM_GRANULARITY;
+	panel->backlight.alternate_pwm_increment = alt;
+
+	pch_ctl1 = intel_de_read(dev_priv, BLC_PWM_PCH_CTL1);
+	panel->backlight.active_low_pwm = pch_ctl1 & BLM_PCH_POLARITY;
+
+	pch_ctl2 = intel_de_read(dev_priv, BLC_PWM_PCH_CTL2);
+	panel->backlight.pwm_level_max = pch_ctl2 >> 16;
+
+	cpu_ctl2 = intel_de_read(dev_priv, BLC_PWM_CPU_CTL2);
+
+	if (!panel->backlight.pwm_level_max)
+		panel->backlight.pwm_level_max = get_backlight_max_vbt(connector);
+
+	if (!panel->backlight.pwm_level_max)
+		return -ENODEV;
+
+	panel->backlight.pwm_level_min = get_backlight_min_vbt(connector);
+
+	panel->backlight.pwm_enabled = pch_ctl1 & BLM_PCH_PWM_ENABLE;
+
+	cpu_mode = panel->backlight.pwm_enabled && HAS_PCH_LPT(dev_priv) &&
+		   !(pch_ctl1 & BLM_PCH_OVERRIDE_ENABLE) &&
+		   (cpu_ctl2 & BLM_PWM_ENABLE);
+
+	if (cpu_mode) {
+		val = pch_get_backlight(connector, unused);
+
+		drm_dbg_kms(&dev_priv->drm,
+			    "CPU backlight register was enabled, switching to PCH override\n");
+
+		/* Write converted CPU PWM value to PCH override register */
+		lpt_set_backlight(connector->base.state, val);
+		intel_de_write(dev_priv, BLC_PWM_PCH_CTL1,
+			       pch_ctl1 | BLM_PCH_OVERRIDE_ENABLE);
+
+		intel_de_write(dev_priv, BLC_PWM_CPU_CTL2,
+			       cpu_ctl2 & ~BLM_PWM_ENABLE);
+	}
+
+	return 0;
+}
+
+static int pch_setup_backlight(struct intel_connector *connector, enum pipe unused)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+	u32 cpu_ctl2, pch_ctl1, pch_ctl2;
+
+	pch_ctl1 = intel_de_read(dev_priv, BLC_PWM_PCH_CTL1);
+	panel->backlight.active_low_pwm = pch_ctl1 & BLM_PCH_POLARITY;
+
+	pch_ctl2 = intel_de_read(dev_priv, BLC_PWM_PCH_CTL2);
+	panel->backlight.pwm_level_max = pch_ctl2 >> 16;
+
+	if (!panel->backlight.pwm_level_max)
+		panel->backlight.pwm_level_max = get_backlight_max_vbt(connector);
+
+	if (!panel->backlight.pwm_level_max)
+		return -ENODEV;
+
+	panel->backlight.pwm_level_min = get_backlight_min_vbt(connector);
+
+	cpu_ctl2 = intel_de_read(dev_priv, BLC_PWM_CPU_CTL2);
+	panel->backlight.pwm_enabled = (cpu_ctl2 & BLM_PWM_ENABLE) &&
+		(pch_ctl1 & BLM_PCH_PWM_ENABLE);
+
+	return 0;
+}
+
+static int i9xx_setup_backlight(struct intel_connector *connector, enum pipe unused)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+	u32 ctl, val;
+
+	ctl = intel_de_read(dev_priv, BLC_PWM_CTL);
+
+	if (DISPLAY_VER(dev_priv) == 2 || IS_I915GM(dev_priv) || IS_I945GM(dev_priv))
+		panel->backlight.combination_mode = ctl & BLM_LEGACY_MODE;
+
+	if (IS_PINEVIEW(dev_priv))
+		panel->backlight.active_low_pwm = ctl & BLM_POLARITY_PNV;
+
+	panel->backlight.pwm_level_max = ctl >> 17;
+
+	if (!panel->backlight.pwm_level_max) {
+		panel->backlight.pwm_level_max = get_backlight_max_vbt(connector);
+		panel->backlight.pwm_level_max >>= 1;
+	}
+
+	if (!panel->backlight.pwm_level_max)
+		return -ENODEV;
+
+	if (panel->backlight.combination_mode)
+		panel->backlight.pwm_level_max *= 0xff;
+
+	panel->backlight.pwm_level_min = get_backlight_min_vbt(connector);
+
+	val = i9xx_get_backlight(connector, unused);
+	val = intel_panel_invert_pwm_level(connector, val);
+	val = clamp(val, panel->backlight.pwm_level_min, panel->backlight.pwm_level_max);
+
+	panel->backlight.pwm_enabled = val != 0;
+
+	return 0;
+}
+
+static int i965_setup_backlight(struct intel_connector *connector, enum pipe unused)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+	u32 ctl, ctl2;
+
+	ctl2 = intel_de_read(dev_priv, BLC_PWM_CTL2);
+	panel->backlight.combination_mode = ctl2 & BLM_COMBINATION_MODE;
+	panel->backlight.active_low_pwm = ctl2 & BLM_POLARITY_I965;
+
+	ctl = intel_de_read(dev_priv, BLC_PWM_CTL);
+	panel->backlight.pwm_level_max = ctl >> 16;
+
+	if (!panel->backlight.pwm_level_max)
+		panel->backlight.pwm_level_max = get_backlight_max_vbt(connector);
+
+	if (!panel->backlight.pwm_level_max)
+		return -ENODEV;
+
+	if (panel->backlight.combination_mode)
+		panel->backlight.pwm_level_max *= 0xff;
+
+	panel->backlight.pwm_level_min = get_backlight_min_vbt(connector);
+
+	panel->backlight.pwm_enabled = ctl2 & BLM_PWM_ENABLE;
+
+	return 0;
+}
+
+static int vlv_setup_backlight(struct intel_connector *connector, enum pipe pipe)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+	u32 ctl, ctl2;
+
+	if (drm_WARN_ON(&dev_priv->drm, pipe != PIPE_A && pipe != PIPE_B))
+		return -ENODEV;
+
+	ctl2 = intel_de_read(dev_priv, VLV_BLC_PWM_CTL2(pipe));
+	panel->backlight.active_low_pwm = ctl2 & BLM_POLARITY_I965;
+
+	ctl = intel_de_read(dev_priv, VLV_BLC_PWM_CTL(pipe));
+	panel->backlight.pwm_level_max = ctl >> 16;
+
+	if (!panel->backlight.pwm_level_max)
+		panel->backlight.pwm_level_max = get_backlight_max_vbt(connector);
+
+	if (!panel->backlight.pwm_level_max)
+		return -ENODEV;
+
+	panel->backlight.pwm_level_min = get_backlight_min_vbt(connector);
+
+	panel->backlight.pwm_enabled = ctl2 & BLM_PWM_ENABLE;
+
+	return 0;
+}
+
+static int
+bxt_setup_backlight(struct intel_connector *connector, enum pipe unused)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+	u32 pwm_ctl, val;
+
+	panel->backlight.controller = dev_priv->vbt.backlight.controller;
+
+	pwm_ctl = intel_de_read(dev_priv,
+				BXT_BLC_PWM_CTL(panel->backlight.controller));
+
+	/* Controller 1 uses the utility pin. */
+	if (panel->backlight.controller == 1) {
+		val = intel_de_read(dev_priv, UTIL_PIN_CTL);
+		panel->backlight.util_pin_active_low =
+					val & UTIL_PIN_POLARITY;
+	}
+
+	panel->backlight.active_low_pwm = pwm_ctl & BXT_BLC_PWM_POLARITY;
+	panel->backlight.pwm_level_max =
+		intel_de_read(dev_priv, BXT_BLC_PWM_FREQ(panel->backlight.controller));
+
+	if (!panel->backlight.pwm_level_max)
+		panel->backlight.pwm_level_max = get_backlight_max_vbt(connector);
+
+	if (!panel->backlight.pwm_level_max)
+		return -ENODEV;
+
+	panel->backlight.pwm_level_min = get_backlight_min_vbt(connector);
+
+	panel->backlight.pwm_enabled = pwm_ctl & BXT_BLC_PWM_ENABLE;
+
+	return 0;
+}
+
+static int
+cnp_setup_backlight(struct intel_connector *connector, enum pipe unused)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+	u32 pwm_ctl;
+
+	/*
+	 * CNP has the BXT implementation of backlight, but with only one
+	 * controller. TODO: ICP has multiple controllers but we only use
+	 * controller 0 for now.
+	 */
+	panel->backlight.controller = 0;
+
+	pwm_ctl = intel_de_read(dev_priv,
+				BXT_BLC_PWM_CTL(panel->backlight.controller));
+
+	panel->backlight.active_low_pwm = pwm_ctl & BXT_BLC_PWM_POLARITY;
+	panel->backlight.pwm_level_max =
+		intel_de_read(dev_priv, BXT_BLC_PWM_FREQ(panel->backlight.controller));
+
+	if (!panel->backlight.pwm_level_max)
+		panel->backlight.pwm_level_max = get_backlight_max_vbt(connector);
+
+	if (!panel->backlight.pwm_level_max)
+		return -ENODEV;
+
+	panel->backlight.pwm_level_min = get_backlight_min_vbt(connector);
+
+	panel->backlight.pwm_enabled = pwm_ctl & BXT_BLC_PWM_ENABLE;
+
+	return 0;
+}
+
+static int ext_pwm_setup_backlight(struct intel_connector *connector,
+				   enum pipe pipe)
+{
+	struct drm_device *dev = connector->base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct intel_panel *panel = &connector->panel;
+	const char *desc;
+	u32 level;
+
+	/* Get the right PWM chip for DSI backlight according to VBT */
+	if (dev_priv->vbt.dsi.config->pwm_blc == PPS_BLC_PMIC) {
+		panel->backlight.pwm = pwm_get(dev->dev, "pwm_pmic_backlight");
+		desc = "PMIC";
+	} else {
+		panel->backlight.pwm = pwm_get(dev->dev, "pwm_soc_backlight");
+		desc = "SoC";
+	}
+
+	if (IS_ERR(panel->backlight.pwm)) {
+		drm_err(&dev_priv->drm, "Failed to get the %s PWM chip\n",
+			desc);
+		panel->backlight.pwm = NULL;
+		return -ENODEV;
+	}
+
+	panel->backlight.pwm_level_max = 100; /* 100% */
+	panel->backlight.pwm_level_min = get_backlight_min_vbt(connector);
+
+	if (pwm_is_enabled(panel->backlight.pwm)) {
+		/* PWM is already enabled, use existing settings */
+		pwm_get_state(panel->backlight.pwm, &panel->backlight.pwm_state);
+
+		level = pwm_get_relative_duty_cycle(&panel->backlight.pwm_state,
+						    100);
+		level = intel_panel_invert_pwm_level(connector, level);
+		panel->backlight.pwm_enabled = true;
+
+		drm_dbg_kms(&dev_priv->drm, "PWM already enabled at freq %ld, VBT freq %d, level %d\n",
+			    NSEC_PER_SEC / (unsigned long)panel->backlight.pwm_state.period,
+			    get_vbt_pwm_freq(dev_priv), level);
+	} else {
+		/* Set period from VBT frequency, leave other settings at 0. */
+		panel->backlight.pwm_state.period =
+			NSEC_PER_SEC / get_vbt_pwm_freq(dev_priv);
+	}
+
+	drm_info(&dev_priv->drm, "Using %s PWM for LCD backlight control\n",
+		 desc);
+	return 0;
+}
+
+static void intel_pwm_set_backlight(const struct drm_connector_state *conn_state, u32 level)
+{
+	struct intel_connector *connector = to_intel_connector(conn_state->connector);
+	struct intel_panel *panel = &connector->panel;
+
+	panel->backlight.pwm_funcs->set(conn_state,
+				       intel_panel_invert_pwm_level(connector, level));
+}
+
+static u32 intel_pwm_get_backlight(struct intel_connector *connector, enum pipe pipe)
+{
+	struct intel_panel *panel = &connector->panel;
+
+	return intel_panel_invert_pwm_level(connector,
+					    panel->backlight.pwm_funcs->get(connector, pipe));
+}
+
+static void intel_pwm_enable_backlight(const struct intel_crtc_state *crtc_state,
+				       const struct drm_connector_state *conn_state, u32 level)
+{
+	struct intel_connector *connector = to_intel_connector(conn_state->connector);
+	struct intel_panel *panel = &connector->panel;
+
+	panel->backlight.pwm_funcs->enable(crtc_state, conn_state,
+					   intel_panel_invert_pwm_level(connector, level));
+}
+
+static void intel_pwm_disable_backlight(const struct drm_connector_state *conn_state, u32 level)
+{
+	struct intel_connector *connector = to_intel_connector(conn_state->connector);
+	struct intel_panel *panel = &connector->panel;
+
+	panel->backlight.pwm_funcs->disable(conn_state,
+					    intel_panel_invert_pwm_level(connector, level));
+}
+
+static int intel_pwm_setup_backlight(struct intel_connector *connector, enum pipe pipe)
+{
+	struct intel_panel *panel = &connector->panel;
+	int ret = panel->backlight.pwm_funcs->setup(connector, pipe);
+
+	if (ret < 0)
+		return ret;
+
+	panel->backlight.min = panel->backlight.pwm_level_min;
+	panel->backlight.max = panel->backlight.pwm_level_max;
+	panel->backlight.level = intel_pwm_get_backlight(connector, pipe);
+	panel->backlight.enabled = panel->backlight.pwm_enabled;
+
+	return 0;
+}
+
+void intel_panel_update_backlight(struct intel_atomic_state *state,
+				  struct intel_encoder *encoder,
+				  const struct intel_crtc_state *crtc_state,
+				  const struct drm_connector_state *conn_state)
+{
+	struct intel_connector *connector = to_intel_connector(conn_state->connector);
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_panel *panel = &connector->panel;
+
+	if (!panel->backlight.present)
+		return;
+
+	mutex_lock(&dev_priv->backlight_lock);
+	if (!panel->backlight.enabled)
+		__intel_panel_enable_backlight(crtc_state, conn_state);
+
+	mutex_unlock(&dev_priv->backlight_lock);
+}
+
+int intel_panel_setup_backlight(struct drm_connector *connector, enum pipe pipe)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->dev);
+	struct intel_connector *intel_connector = to_intel_connector(connector);
+	struct intel_panel *panel = &intel_connector->panel;
+	int ret;
+
+	if (!dev_priv->vbt.backlight.present) {
+		if (dev_priv->quirks & QUIRK_BACKLIGHT_PRESENT) {
+			drm_dbg_kms(&dev_priv->drm,
+				    "no backlight present per VBT, but present per quirk\n");
+		} else {
+			drm_dbg_kms(&dev_priv->drm,
+				    "no backlight present per VBT\n");
+			return 0;
+		}
+	}
+
+	/* ensure intel_panel has been initialized first */
+	if (drm_WARN_ON(&dev_priv->drm, !panel->backlight.funcs))
+		return -ENODEV;
+
+	/* set level and max in panel struct */
+	mutex_lock(&dev_priv->backlight_lock);
+	ret = panel->backlight.funcs->setup(intel_connector, pipe);
+	mutex_unlock(&dev_priv->backlight_lock);
+
+	if (ret) {
+		drm_dbg_kms(&dev_priv->drm,
+			    "failed to setup backlight for connector %s\n",
+			    connector->name);
+		return ret;
+	}
+
+	panel->backlight.present = true;
+
+	drm_dbg_kms(&dev_priv->drm,
+		    "Connector %s backlight initialized, %s, brightness %u/%u\n",
+		    connector->name,
+		    enableddisabled(panel->backlight.enabled),
+		    panel->backlight.level, panel->backlight.max);
+
+	return 0;
+}
+
+void intel_panel_destroy_backlight(struct intel_panel *panel)
+{
+	/* dispose of the pwm */
+	if (panel->backlight.pwm)
+		pwm_put(panel->backlight.pwm);
+
+	panel->backlight.present = false;
+}
+
+static const struct intel_panel_bl_funcs bxt_pwm_funcs = {
+	.setup = bxt_setup_backlight,
+	.enable = bxt_enable_backlight,
+	.disable = bxt_disable_backlight,
+	.set = bxt_set_backlight,
+	.get = bxt_get_backlight,
+	.hz_to_pwm = bxt_hz_to_pwm,
+};
+
+static const struct intel_panel_bl_funcs cnp_pwm_funcs = {
+	.setup = cnp_setup_backlight,
+	.enable = cnp_enable_backlight,
+	.disable = cnp_disable_backlight,
+	.set = bxt_set_backlight,
+	.get = bxt_get_backlight,
+	.hz_to_pwm = cnp_hz_to_pwm,
+};
+
+static const struct intel_panel_bl_funcs lpt_pwm_funcs = {
+	.setup = lpt_setup_backlight,
+	.enable = lpt_enable_backlight,
+	.disable = lpt_disable_backlight,
+	.set = lpt_set_backlight,
+	.get = lpt_get_backlight,
+	.hz_to_pwm = lpt_hz_to_pwm,
+};
+
+static const struct intel_panel_bl_funcs spt_pwm_funcs = {
+	.setup = lpt_setup_backlight,
+	.enable = lpt_enable_backlight,
+	.disable = lpt_disable_backlight,
+	.set = lpt_set_backlight,
+	.get = lpt_get_backlight,
+	.hz_to_pwm = spt_hz_to_pwm,
+};
+
+static const struct intel_panel_bl_funcs pch_pwm_funcs = {
+	.setup = pch_setup_backlight,
+	.enable = pch_enable_backlight,
+	.disable = pch_disable_backlight,
+	.set = pch_set_backlight,
+	.get = pch_get_backlight,
+	.hz_to_pwm = pch_hz_to_pwm,
+};
+
+static const struct intel_panel_bl_funcs ext_pwm_funcs = {
+	.setup = ext_pwm_setup_backlight,
+	.enable = ext_pwm_enable_backlight,
+	.disable = ext_pwm_disable_backlight,
+	.set = ext_pwm_set_backlight,
+	.get = ext_pwm_get_backlight,
+};
+
+static const struct intel_panel_bl_funcs vlv_pwm_funcs = {
+	.setup = vlv_setup_backlight,
+	.enable = vlv_enable_backlight,
+	.disable = vlv_disable_backlight,
+	.set = vlv_set_backlight,
+	.get = vlv_get_backlight,
+	.hz_to_pwm = vlv_hz_to_pwm,
+};
+
+static const struct intel_panel_bl_funcs i965_pwm_funcs = {
+	.setup = i965_setup_backlight,
+	.enable = i965_enable_backlight,
+	.disable = i965_disable_backlight,
+	.set = i9xx_set_backlight,
+	.get = i9xx_get_backlight,
+	.hz_to_pwm = i965_hz_to_pwm,
+};
+
+static const struct intel_panel_bl_funcs i9xx_pwm_funcs = {
+	.setup = i9xx_setup_backlight,
+	.enable = i9xx_enable_backlight,
+	.disable = i9xx_disable_backlight,
+	.set = i9xx_set_backlight,
+	.get = i9xx_get_backlight,
+	.hz_to_pwm = i9xx_hz_to_pwm,
+};
+
+static const struct intel_panel_bl_funcs pwm_bl_funcs = {
+	.setup = intel_pwm_setup_backlight,
+	.enable = intel_pwm_enable_backlight,
+	.disable = intel_pwm_disable_backlight,
+	.set = intel_pwm_set_backlight,
+	.get = intel_pwm_get_backlight,
+};
+
+/* Set up chip specific backlight functions */
+void
+intel_panel_init_backlight_funcs(struct intel_panel *panel)
+{
+	struct intel_connector *connector =
+		container_of(panel, struct intel_connector, panel);
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+
+	if (connector->base.connector_type == DRM_MODE_CONNECTOR_DSI &&
+	    intel_dsi_dcs_init_backlight_funcs(connector) == 0)
+		return;
+
+	if (IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv)) {
+		panel->backlight.pwm_funcs = &bxt_pwm_funcs;
+	} else if (INTEL_PCH_TYPE(dev_priv) >= PCH_CNP) {
+		panel->backlight.pwm_funcs = &cnp_pwm_funcs;
+	} else if (INTEL_PCH_TYPE(dev_priv) >= PCH_LPT) {
+		if (HAS_PCH_LPT(dev_priv))
+			panel->backlight.pwm_funcs = &lpt_pwm_funcs;
+		else
+			panel->backlight.pwm_funcs = &spt_pwm_funcs;
+	} else if (HAS_PCH_SPLIT(dev_priv)) {
+		panel->backlight.pwm_funcs = &pch_pwm_funcs;
+	} else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
+		if (connector->base.connector_type == DRM_MODE_CONNECTOR_DSI) {
+			panel->backlight.pwm_funcs = &ext_pwm_funcs;
+		} else {
+			panel->backlight.pwm_funcs = &vlv_pwm_funcs;
+		}
+	} else if (DISPLAY_VER(dev_priv) == 4) {
+		panel->backlight.pwm_funcs = &i965_pwm_funcs;
+	} else {
+		panel->backlight.pwm_funcs = &i9xx_pwm_funcs;
+	}
+
+	if (connector->base.connector_type == DRM_MODE_CONNECTOR_eDP &&
+	    intel_dp_aux_init_backlight_funcs(connector) == 0)
+		return;
+
+	/* We're using a standard PWM backlight interface */
+	panel->backlight.funcs = &pwm_bl_funcs;
+}
diff --git a/drivers/gpu/drm/i915/display/intel_backlight.h b/drivers/gpu/drm/i915/display/intel_backlight.h
new file mode 100644
index 000000000000..282020cb47d5
--- /dev/null
+++ b/drivers/gpu/drm/i915/display/intel_backlight.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#ifndef __INTEL_BACKLIGHT_H__
+#define __INTEL_BACKLIGHT_H__
+
+#include <linux/types.h>
+
+struct drm_connector;
+struct drm_connector_state;
+struct intel_atomic_state;
+struct intel_connector;
+struct intel_crtc_state;
+struct intel_encoder;
+struct intel_panel;
+enum pipe;
+
+void intel_panel_init_backlight_funcs(struct intel_panel *panel);
+void intel_panel_destroy_backlight(struct intel_panel *panel);
+void intel_panel_set_backlight_acpi(const struct drm_connector_state *conn_state,
+				    u32 level, u32 max);
+int intel_panel_setup_backlight(struct drm_connector *connector,
+				enum pipe pipe);
+void intel_panel_enable_backlight(const struct intel_crtc_state *crtc_state,
+				  const struct drm_connector_state *conn_state);
+void intel_panel_update_backlight(struct intel_atomic_state *state,
+				  struct intel_encoder *encoder,
+				  const struct intel_crtc_state *crtc_state,
+				  const struct drm_connector_state *conn_state);
+void intel_panel_disable_backlight(const struct drm_connector_state *old_conn_state);
+void intel_panel_set_pwm_level(const struct drm_connector_state *conn_state, u32 level);
+u32 intel_panel_invert_pwm_level(struct intel_connector *connector, u32 level);
+u32 intel_panel_backlight_level_to_pwm(struct intel_connector *connector, u32 level);
+u32 intel_panel_backlight_level_from_pwm(struct intel_connector *connector, u32 val);
+
+#if IS_ENABLED(CONFIG_BACKLIGHT_CLASS_DEVICE)
+int intel_backlight_device_register(struct intel_connector *connector);
+void intel_backlight_device_unregister(struct intel_connector *connector);
+#else /* CONFIG_BACKLIGHT_CLASS_DEVICE */
+static inline int intel_backlight_device_register(struct intel_connector *connector)
+{
+	return 0;
+}
+static inline void intel_backlight_device_unregister(struct intel_connector *connector)
+{
+}
+#endif /* CONFIG_BACKLIGHT_CLASS_DEVICE */
+
+#endif /* __INTEL_BACKLIGHT_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_connector.c b/drivers/gpu/drm/i915/display/intel_connector.c
index 9bed1ccecea0..4f49d782eca2 100644
--- a/drivers/gpu/drm/i915/display/intel_connector.c
+++ b/drivers/gpu/drm/i915/display/intel_connector.c
@@ -29,13 +29,13 @@
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_edid.h>
 
-#include "display/intel_panel.h"
-
 #include "i915_drv.h"
+#include "intel_backlight.h"
 #include "intel_connector.h"
 #include "intel_display_debugfs.h"
 #include "intel_display_types.h"
 #include "intel_hdcp.h"
+#include "intel_panel.h"
 
 int intel_connector_init(struct intel_connector *connector)
 {
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index f61901e26409..68489c729830 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -29,6 +29,7 @@
 
 #include "i915_drv.h"
 #include "intel_audio.h"
+#include "intel_backlight.h"
 #include "intel_combo_phy.h"
 #include "intel_connector.h"
 #include "intel_crtc.h"
@@ -49,7 +50,6 @@
 #include "intel_hdmi.h"
 #include "intel_hotplug.h"
 #include "intel_lspcon.h"
-#include "intel_panel.h"
 #include "intel_pps.h"
 #include "intel_psr.h"
 #include "intel_snps_phy.h"
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 631cf7d4323c..f87e4d510ea5 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -45,6 +45,7 @@
 #include "i915_drv.h"
 #include "intel_atomic.h"
 #include "intel_audio.h"
+#include "intel_backlight.h"
 #include "intel_connector.h"
 #include "intel_ddi.h"
 #include "intel_de.h"
diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c
index e7b90863aa43..0a77f0e48aa1 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c
@@ -34,10 +34,10 @@
  * for some reason.
  */
 
+#include "intel_backlight.h"
 #include "intel_display_types.h"
 #include "intel_dp.h"
 #include "intel_dp_aux_backlight.h"
-#include "intel_panel.h"
 
 /* TODO:
  * Implement HDR, right now we just implement the bare minimum to bring us back into SDR mode so we
diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
index 508a514c5e37..d77d91c0a03a 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
@@ -475,6 +475,28 @@ intel_dp_prepare_link_train(struct intel_dp *intel_dp,
 	intel_dp_compute_rate(intel_dp, crtc_state->port_clock,
 			      &link_bw, &rate_select);
 
+	/*
+	 * WaEdpLinkRateDataReload
+	 *
+	 * Parade PS8461E MUX (used on varius TGL+ laptops) needs
+	 * to snoop the link rates reported by the sink when we
+	 * use LINK_RATE_SET in order to operate in jitter cleaning
+	 * mode (as opposed to redriver mode). Unfortunately it
+	 * loses track of the snooped link rates when powered down,
+	 * so we need to make it re-snoop often. Without this high
+	 * link rates are not stable.
+	 */
+	if (!link_bw) {
+		struct intel_connector *connector = intel_dp->attached_connector;
+		__le16 sink_rates[DP_MAX_SUPPORTED_RATES];
+
+		drm_dbg_kms(&i915->drm, "[CONNECTOR:%d:%s] Reloading eDP link rates\n",
+			    connector->base.base.id, connector->base.name);
+
+		drm_dp_dpcd_read(&intel_dp->aux, DP_SUPPORTED_LINK_RATES,
+				 sink_rates, sizeof(sink_rates));
+	}
+
 	if (link_bw)
 		drm_dbg_kms(&i915->drm,
 			    "Using LINK_BW_SET value %02x\n", link_bw);
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index 8d13d7b26a25..2a20487effcc 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -817,6 +817,7 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo
 	ret = drm_connector_init(dev, connector, &intel_dp_mst_connector_funcs,
 				 DRM_MODE_CONNECTOR_DisplayPort);
 	if (ret) {
+		drm_dp_mst_put_port_malloc(port);
 		intel_connector_free(intel_connector);
 		return NULL;
 	}
diff --git a/drivers/gpu/drm/i915/display/intel_lvds.c b/drivers/gpu/drm/i915/display/intel_lvds.c
index e0381b0fce91..8f5741ebd58d 100644
--- a/drivers/gpu/drm/i915/display/intel_lvds.c
+++ b/drivers/gpu/drm/i915/display/intel_lvds.c
@@ -40,6 +40,7 @@
 
 #include "i915_drv.h"
 #include "intel_atomic.h"
+#include "intel_backlight.h"
 #include "intel_connector.h"
 #include "intel_de.h"
 #include "intel_display_types.h"
diff --git a/drivers/gpu/drm/i915/display/intel_opregion.c b/drivers/gpu/drm/i915/display/intel_opregion.c
index f7f49b69830f..aad5c1cd3898 100644
--- a/drivers/gpu/drm/i915/display/intel_opregion.c
+++ b/drivers/gpu/drm/i915/display/intel_opregion.c
@@ -30,10 +30,9 @@
 #include <linux/firmware.h>
 #include <acpi/video.h>
 
-#include "display/intel_panel.h"
-
 #include "i915_drv.h"
 #include "intel_acpi.h"
+#include "intel_backlight.h"
 #include "intel_display_types.h"
 #include "intel_opregion.h"
 
diff --git a/drivers/gpu/drm/i915/display/intel_panel.c b/drivers/gpu/drm/i915/display/intel_panel.c
index 7d7a60b4d2de..ad54767440c1 100644
--- a/drivers/gpu/drm/i915/display/intel_panel.c
+++ b/drivers/gpu/drm/i915/display/intel_panel.c
@@ -28,17 +28,13 @@
  *      Chris Wilson <chris@chris-wilson.co.uk>
  */
 
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
 #include <linux/kernel.h>
-#include <linux/moduleparam.h>
 #include <linux/pwm.h>
 
+#include "intel_backlight.h"
 #include "intel_connector.h"
 #include "intel_de.h"
 #include "intel_display_types.h"
-#include "intel_dp_aux_backlight.h"
-#include "intel_dsi_dcs_backlight.h"
 #include "intel_panel.h"
 
 void
@@ -456,1767 +452,6 @@ out:
 	return 0;
 }
 
-/**
- * scale - scale values from one range to another
- * @source_val: value in range [@source_min..@source_max]
- * @source_min: minimum legal value for @source_val
- * @source_max: maximum legal value for @source_val
- * @target_min: corresponding target value for @source_min
- * @target_max: corresponding target value for @source_max
- *
- * Return @source_val in range [@source_min..@source_max] scaled to range
- * [@target_min..@target_max].
- */
-static u32 scale(u32 source_val,
-		 u32 source_min, u32 source_max,
-		 u32 target_min, u32 target_max)
-{
-	u64 target_val;
-
-	WARN_ON(source_min > source_max);
-	WARN_ON(target_min > target_max);
-
-	/* defensive */
-	source_val = clamp(source_val, source_min, source_max);
-
-	/* avoid overflows */
-	target_val = mul_u32_u32(source_val - source_min,
-				 target_max - target_min);
-	target_val = DIV_ROUND_CLOSEST_ULL(target_val, source_max - source_min);
-	target_val += target_min;
-
-	return target_val;
-}
-
-/* Scale user_level in range [0..user_max] to [0..hw_max], clamping the result
- * to [hw_min..hw_max]. */
-static u32 clamp_user_to_hw(struct intel_connector *connector,
-			    u32 user_level, u32 user_max)
-{
-	struct intel_panel *panel = &connector->panel;
-	u32 hw_level;
-
-	hw_level = scale(user_level, 0, user_max, 0, panel->backlight.max);
-	hw_level = clamp(hw_level, panel->backlight.min, panel->backlight.max);
-
-	return hw_level;
-}
-
-/* Scale hw_level in range [hw_min..hw_max] to [0..user_max]. */
-static u32 scale_hw_to_user(struct intel_connector *connector,
-			    u32 hw_level, u32 user_max)
-{
-	struct intel_panel *panel = &connector->panel;
-
-	return scale(hw_level, panel->backlight.min, panel->backlight.max,
-		     0, user_max);
-}
-
-u32 intel_panel_invert_pwm_level(struct intel_connector *connector, u32 val)
-{
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-
-	drm_WARN_ON(&dev_priv->drm, panel->backlight.pwm_level_max == 0);
-
-	if (dev_priv->params.invert_brightness < 0)
-		return val;
-
-	if (dev_priv->params.invert_brightness > 0 ||
-	    dev_priv->quirks & QUIRK_INVERT_BRIGHTNESS) {
-		return panel->backlight.pwm_level_max - val + panel->backlight.pwm_level_min;
-	}
-
-	return val;
-}
-
-void intel_panel_set_pwm_level(const struct drm_connector_state *conn_state, u32 val)
-{
-	struct intel_connector *connector = to_intel_connector(conn_state->connector);
-	struct drm_i915_private *i915 = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-
-	drm_dbg_kms(&i915->drm, "set backlight PWM = %d\n", val);
-	panel->backlight.pwm_funcs->set(conn_state, val);
-}
-
-u32 intel_panel_backlight_level_to_pwm(struct intel_connector *connector, u32 val)
-{
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-
-	drm_WARN_ON_ONCE(&dev_priv->drm,
-			 panel->backlight.max == 0 || panel->backlight.pwm_level_max == 0);
-
-	val = scale(val, panel->backlight.min, panel->backlight.max,
-		    panel->backlight.pwm_level_min, panel->backlight.pwm_level_max);
-
-	return intel_panel_invert_pwm_level(connector, val);
-}
-
-u32 intel_panel_backlight_level_from_pwm(struct intel_connector *connector, u32 val)
-{
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-
-	drm_WARN_ON_ONCE(&dev_priv->drm,
-			 panel->backlight.max == 0 || panel->backlight.pwm_level_max == 0);
-
-	if (dev_priv->params.invert_brightness > 0 ||
-	    (dev_priv->params.invert_brightness == 0 && dev_priv->quirks & QUIRK_INVERT_BRIGHTNESS))
-		val = panel->backlight.pwm_level_max - (val - panel->backlight.pwm_level_min);
-
-	return scale(val, panel->backlight.pwm_level_min, panel->backlight.pwm_level_max,
-		     panel->backlight.min, panel->backlight.max);
-}
-
-static u32 lpt_get_backlight(struct intel_connector *connector, enum pipe unused)
-{
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-
-	return intel_de_read(dev_priv, BLC_PWM_PCH_CTL2) & BACKLIGHT_DUTY_CYCLE_MASK;
-}
-
-static u32 pch_get_backlight(struct intel_connector *connector, enum pipe unused)
-{
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-
-	return intel_de_read(dev_priv, BLC_PWM_CPU_CTL) & BACKLIGHT_DUTY_CYCLE_MASK;
-}
-
-static u32 i9xx_get_backlight(struct intel_connector *connector, enum pipe unused)
-{
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-	u32 val;
-
-	val = intel_de_read(dev_priv, BLC_PWM_CTL) & BACKLIGHT_DUTY_CYCLE_MASK;
-	if (DISPLAY_VER(dev_priv) < 4)
-		val >>= 1;
-
-	if (panel->backlight.combination_mode) {
-		u8 lbpc;
-
-		pci_read_config_byte(to_pci_dev(dev_priv->drm.dev), LBPC, &lbpc);
-		val *= lbpc;
-	}
-
-	return val;
-}
-
-static u32 vlv_get_backlight(struct intel_connector *connector, enum pipe pipe)
-{
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-
-	if (drm_WARN_ON(&dev_priv->drm, pipe != PIPE_A && pipe != PIPE_B))
-		return 0;
-
-	return intel_de_read(dev_priv, VLV_BLC_PWM_CTL(pipe)) & BACKLIGHT_DUTY_CYCLE_MASK;
-}
-
-static u32 bxt_get_backlight(struct intel_connector *connector, enum pipe unused)
-{
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-
-	return intel_de_read(dev_priv,
-			     BXT_BLC_PWM_DUTY(panel->backlight.controller));
-}
-
-static u32 ext_pwm_get_backlight(struct intel_connector *connector, enum pipe unused)
-{
-	struct intel_panel *panel = &connector->panel;
-	struct pwm_state state;
-
-	pwm_get_state(panel->backlight.pwm, &state);
-	return pwm_get_relative_duty_cycle(&state, 100);
-}
-
-static void lpt_set_backlight(const struct drm_connector_state *conn_state, u32 level)
-{
-	struct intel_connector *connector = to_intel_connector(conn_state->connector);
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-
-	u32 val = intel_de_read(dev_priv, BLC_PWM_PCH_CTL2) & ~BACKLIGHT_DUTY_CYCLE_MASK;
-	intel_de_write(dev_priv, BLC_PWM_PCH_CTL2, val | level);
-}
-
-static void pch_set_backlight(const struct drm_connector_state *conn_state, u32 level)
-{
-	struct intel_connector *connector = to_intel_connector(conn_state->connector);
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	u32 tmp;
-
-	tmp = intel_de_read(dev_priv, BLC_PWM_CPU_CTL) & ~BACKLIGHT_DUTY_CYCLE_MASK;
-	intel_de_write(dev_priv, BLC_PWM_CPU_CTL, tmp | level);
-}
-
-static void i9xx_set_backlight(const struct drm_connector_state *conn_state, u32 level)
-{
-	struct intel_connector *connector = to_intel_connector(conn_state->connector);
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-	u32 tmp, mask;
-
-	drm_WARN_ON(&dev_priv->drm, panel->backlight.pwm_level_max == 0);
-
-	if (panel->backlight.combination_mode) {
-		u8 lbpc;
-
-		lbpc = level * 0xfe / panel->backlight.pwm_level_max + 1;
-		level /= lbpc;
-		pci_write_config_byte(to_pci_dev(dev_priv->drm.dev), LBPC, lbpc);
-	}
-
-	if (DISPLAY_VER(dev_priv) == 4) {
-		mask = BACKLIGHT_DUTY_CYCLE_MASK;
-	} else {
-		level <<= 1;
-		mask = BACKLIGHT_DUTY_CYCLE_MASK_PNV;
-	}
-
-	tmp = intel_de_read(dev_priv, BLC_PWM_CTL) & ~mask;
-	intel_de_write(dev_priv, BLC_PWM_CTL, tmp | level);
-}
-
-static void vlv_set_backlight(const struct drm_connector_state *conn_state, u32 level)
-{
-	struct intel_connector *connector = to_intel_connector(conn_state->connector);
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	enum pipe pipe = to_intel_crtc(conn_state->crtc)->pipe;
-	u32 tmp;
-
-	tmp = intel_de_read(dev_priv, VLV_BLC_PWM_CTL(pipe)) & ~BACKLIGHT_DUTY_CYCLE_MASK;
-	intel_de_write(dev_priv, VLV_BLC_PWM_CTL(pipe), tmp | level);
-}
-
-static void bxt_set_backlight(const struct drm_connector_state *conn_state, u32 level)
-{
-	struct intel_connector *connector = to_intel_connector(conn_state->connector);
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-
-	intel_de_write(dev_priv,
-		       BXT_BLC_PWM_DUTY(panel->backlight.controller), level);
-}
-
-static void ext_pwm_set_backlight(const struct drm_connector_state *conn_state, u32 level)
-{
-	struct intel_panel *panel = &to_intel_connector(conn_state->connector)->panel;
-
-	pwm_set_relative_duty_cycle(&panel->backlight.pwm_state, level, 100);
-	pwm_apply_state(panel->backlight.pwm, &panel->backlight.pwm_state);
-}
-
-static void
-intel_panel_actually_set_backlight(const struct drm_connector_state *conn_state, u32 level)
-{
-	struct intel_connector *connector = to_intel_connector(conn_state->connector);
-	struct drm_i915_private *i915 = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-
-	drm_dbg_kms(&i915->drm, "set backlight level = %d\n", level);
-
-	panel->backlight.funcs->set(conn_state, level);
-}
-
-/* set backlight brightness to level in range [0..max], assuming hw min is
- * respected.
- */
-void intel_panel_set_backlight_acpi(const struct drm_connector_state *conn_state,
-				    u32 user_level, u32 user_max)
-{
-	struct intel_connector *connector = to_intel_connector(conn_state->connector);
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-	u32 hw_level;
-
-	/*
-	 * Lack of crtc may occur during driver init because
-	 * connection_mutex isn't held across the entire backlight
-	 * setup + modeset readout, and the BIOS can issue the
-	 * requests at any time.
-	 */
-	if (!panel->backlight.present || !conn_state->crtc)
-		return;
-
-	mutex_lock(&dev_priv->backlight_lock);
-
-	drm_WARN_ON(&dev_priv->drm, panel->backlight.max == 0);
-
-	hw_level = clamp_user_to_hw(connector, user_level, user_max);
-	panel->backlight.level = hw_level;
-
-	if (panel->backlight.device)
-		panel->backlight.device->props.brightness =
-			scale_hw_to_user(connector,
-					 panel->backlight.level,
-					 panel->backlight.device->props.max_brightness);
-
-	if (panel->backlight.enabled)
-		intel_panel_actually_set_backlight(conn_state, hw_level);
-
-	mutex_unlock(&dev_priv->backlight_lock);
-}
-
-static void lpt_disable_backlight(const struct drm_connector_state *old_conn_state, u32 level)
-{
-	struct intel_connector *connector = to_intel_connector(old_conn_state->connector);
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	u32 tmp;
-
-	intel_panel_set_pwm_level(old_conn_state, level);
-
-	/*
-	 * Although we don't support or enable CPU PWM with LPT/SPT based
-	 * systems, it may have been enabled prior to loading the
-	 * driver. Disable to avoid warnings on LCPLL disable.
-	 *
-	 * This needs rework if we need to add support for CPU PWM on PCH split
-	 * platforms.
-	 */
-	tmp = intel_de_read(dev_priv, BLC_PWM_CPU_CTL2);
-	if (tmp & BLM_PWM_ENABLE) {
-		drm_dbg_kms(&dev_priv->drm,
-			    "cpu backlight was enabled, disabling\n");
-		intel_de_write(dev_priv, BLC_PWM_CPU_CTL2,
-			       tmp & ~BLM_PWM_ENABLE);
-	}
-
-	tmp = intel_de_read(dev_priv, BLC_PWM_PCH_CTL1);
-	intel_de_write(dev_priv, BLC_PWM_PCH_CTL1, tmp & ~BLM_PCH_PWM_ENABLE);
-}
-
-static void pch_disable_backlight(const struct drm_connector_state *old_conn_state, u32 val)
-{
-	struct intel_connector *connector = to_intel_connector(old_conn_state->connector);
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	u32 tmp;
-
-	intel_panel_set_pwm_level(old_conn_state, val);
-
-	tmp = intel_de_read(dev_priv, BLC_PWM_CPU_CTL2);
-	intel_de_write(dev_priv, BLC_PWM_CPU_CTL2, tmp & ~BLM_PWM_ENABLE);
-
-	tmp = intel_de_read(dev_priv, BLC_PWM_PCH_CTL1);
-	intel_de_write(dev_priv, BLC_PWM_PCH_CTL1, tmp & ~BLM_PCH_PWM_ENABLE);
-}
-
-static void i9xx_disable_backlight(const struct drm_connector_state *old_conn_state, u32 val)
-{
-	intel_panel_set_pwm_level(old_conn_state, val);
-}
-
-static void i965_disable_backlight(const struct drm_connector_state *old_conn_state, u32 val)
-{
-	struct drm_i915_private *dev_priv = to_i915(old_conn_state->connector->dev);
-	u32 tmp;
-
-	intel_panel_set_pwm_level(old_conn_state, val);
-
-	tmp = intel_de_read(dev_priv, BLC_PWM_CTL2);
-	intel_de_write(dev_priv, BLC_PWM_CTL2, tmp & ~BLM_PWM_ENABLE);
-}
-
-static void vlv_disable_backlight(const struct drm_connector_state *old_conn_state, u32 val)
-{
-	struct intel_connector *connector = to_intel_connector(old_conn_state->connector);
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	enum pipe pipe = to_intel_crtc(old_conn_state->crtc)->pipe;
-	u32 tmp;
-
-	intel_panel_set_pwm_level(old_conn_state, val);
-
-	tmp = intel_de_read(dev_priv, VLV_BLC_PWM_CTL2(pipe));
-	intel_de_write(dev_priv, VLV_BLC_PWM_CTL2(pipe),
-		       tmp & ~BLM_PWM_ENABLE);
-}
-
-static void bxt_disable_backlight(const struct drm_connector_state *old_conn_state, u32 val)
-{
-	struct intel_connector *connector = to_intel_connector(old_conn_state->connector);
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-	u32 tmp;
-
-	intel_panel_set_pwm_level(old_conn_state, val);
-
-	tmp = intel_de_read(dev_priv,
-			    BXT_BLC_PWM_CTL(panel->backlight.controller));
-	intel_de_write(dev_priv, BXT_BLC_PWM_CTL(panel->backlight.controller),
-		       tmp & ~BXT_BLC_PWM_ENABLE);
-
-	if (panel->backlight.controller == 1) {
-		val = intel_de_read(dev_priv, UTIL_PIN_CTL);
-		val &= ~UTIL_PIN_ENABLE;
-		intel_de_write(dev_priv, UTIL_PIN_CTL, val);
-	}
-}
-
-static void cnp_disable_backlight(const struct drm_connector_state *old_conn_state, u32 val)
-{
-	struct intel_connector *connector = to_intel_connector(old_conn_state->connector);
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-	u32 tmp;
-
-	intel_panel_set_pwm_level(old_conn_state, val);
-
-	tmp = intel_de_read(dev_priv,
-			    BXT_BLC_PWM_CTL(panel->backlight.controller));
-	intel_de_write(dev_priv, BXT_BLC_PWM_CTL(panel->backlight.controller),
-		       tmp & ~BXT_BLC_PWM_ENABLE);
-}
-
-static void ext_pwm_disable_backlight(const struct drm_connector_state *old_conn_state, u32 level)
-{
-	struct intel_connector *connector = to_intel_connector(old_conn_state->connector);
-	struct intel_panel *panel = &connector->panel;
-
-	panel->backlight.pwm_state.enabled = false;
-	pwm_apply_state(panel->backlight.pwm, &panel->backlight.pwm_state);
-}
-
-void intel_panel_disable_backlight(const struct drm_connector_state *old_conn_state)
-{
-	struct intel_connector *connector = to_intel_connector(old_conn_state->connector);
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-
-	if (!panel->backlight.present)
-		return;
-
-	/*
-	 * Do not disable backlight on the vga_switcheroo path. When switching
-	 * away from i915, the other client may depend on i915 to handle the
-	 * backlight. This will leave the backlight on unnecessarily when
-	 * another client is not activated.
-	 */
-	if (dev_priv->drm.switch_power_state == DRM_SWITCH_POWER_CHANGING) {
-		drm_dbg_kms(&dev_priv->drm,
-			    "Skipping backlight disable on vga switch\n");
-		return;
-	}
-
-	mutex_lock(&dev_priv->backlight_lock);
-
-	if (panel->backlight.device)
-		panel->backlight.device->props.power = FB_BLANK_POWERDOWN;
-	panel->backlight.enabled = false;
-	panel->backlight.funcs->disable(old_conn_state, 0);
-
-	mutex_unlock(&dev_priv->backlight_lock);
-}
-
-static void lpt_enable_backlight(const struct intel_crtc_state *crtc_state,
-				 const struct drm_connector_state *conn_state, u32 level)
-{
-	struct intel_connector *connector = to_intel_connector(conn_state->connector);
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-	u32 pch_ctl1, pch_ctl2, schicken;
-
-	pch_ctl1 = intel_de_read(dev_priv, BLC_PWM_PCH_CTL1);
-	if (pch_ctl1 & BLM_PCH_PWM_ENABLE) {
-		drm_dbg_kms(&dev_priv->drm, "pch backlight already enabled\n");
-		pch_ctl1 &= ~BLM_PCH_PWM_ENABLE;
-		intel_de_write(dev_priv, BLC_PWM_PCH_CTL1, pch_ctl1);
-	}
-
-	if (HAS_PCH_LPT(dev_priv)) {
-		schicken = intel_de_read(dev_priv, SOUTH_CHICKEN2);
-		if (panel->backlight.alternate_pwm_increment)
-			schicken |= LPT_PWM_GRANULARITY;
-		else
-			schicken &= ~LPT_PWM_GRANULARITY;
-		intel_de_write(dev_priv, SOUTH_CHICKEN2, schicken);
-	} else {
-		schicken = intel_de_read(dev_priv, SOUTH_CHICKEN1);
-		if (panel->backlight.alternate_pwm_increment)
-			schicken |= SPT_PWM_GRANULARITY;
-		else
-			schicken &= ~SPT_PWM_GRANULARITY;
-		intel_de_write(dev_priv, SOUTH_CHICKEN1, schicken);
-	}
-
-	pch_ctl2 = panel->backlight.pwm_level_max << 16;
-	intel_de_write(dev_priv, BLC_PWM_PCH_CTL2, pch_ctl2);
-
-	pch_ctl1 = 0;
-	if (panel->backlight.active_low_pwm)
-		pch_ctl1 |= BLM_PCH_POLARITY;
-
-	/* After LPT, override is the default. */
-	if (HAS_PCH_LPT(dev_priv))
-		pch_ctl1 |= BLM_PCH_OVERRIDE_ENABLE;
-
-	intel_de_write(dev_priv, BLC_PWM_PCH_CTL1, pch_ctl1);
-	intel_de_posting_read(dev_priv, BLC_PWM_PCH_CTL1);
-	intel_de_write(dev_priv, BLC_PWM_PCH_CTL1,
-		       pch_ctl1 | BLM_PCH_PWM_ENABLE);
-
-	/* This won't stick until the above enable. */
-	intel_panel_set_pwm_level(conn_state, level);
-}
-
-static void pch_enable_backlight(const struct intel_crtc_state *crtc_state,
-				 const struct drm_connector_state *conn_state, u32 level)
-{
-	struct intel_connector *connector = to_intel_connector(conn_state->connector);
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
-	u32 cpu_ctl2, pch_ctl1, pch_ctl2;
-
-	cpu_ctl2 = intel_de_read(dev_priv, BLC_PWM_CPU_CTL2);
-	if (cpu_ctl2 & BLM_PWM_ENABLE) {
-		drm_dbg_kms(&dev_priv->drm, "cpu backlight already enabled\n");
-		cpu_ctl2 &= ~BLM_PWM_ENABLE;
-		intel_de_write(dev_priv, BLC_PWM_CPU_CTL2, cpu_ctl2);
-	}
-
-	pch_ctl1 = intel_de_read(dev_priv, BLC_PWM_PCH_CTL1);
-	if (pch_ctl1 & BLM_PCH_PWM_ENABLE) {
-		drm_dbg_kms(&dev_priv->drm, "pch backlight already enabled\n");
-		pch_ctl1 &= ~BLM_PCH_PWM_ENABLE;
-		intel_de_write(dev_priv, BLC_PWM_PCH_CTL1, pch_ctl1);
-	}
-
-	if (cpu_transcoder == TRANSCODER_EDP)
-		cpu_ctl2 = BLM_TRANSCODER_EDP;
-	else
-		cpu_ctl2 = BLM_PIPE(cpu_transcoder);
-	intel_de_write(dev_priv, BLC_PWM_CPU_CTL2, cpu_ctl2);
-	intel_de_posting_read(dev_priv, BLC_PWM_CPU_CTL2);
-	intel_de_write(dev_priv, BLC_PWM_CPU_CTL2, cpu_ctl2 | BLM_PWM_ENABLE);
-
-	/* This won't stick until the above enable. */
-	intel_panel_set_pwm_level(conn_state, level);
-
-	pch_ctl2 = panel->backlight.pwm_level_max << 16;
-	intel_de_write(dev_priv, BLC_PWM_PCH_CTL2, pch_ctl2);
-
-	pch_ctl1 = 0;
-	if (panel->backlight.active_low_pwm)
-		pch_ctl1 |= BLM_PCH_POLARITY;
-
-	intel_de_write(dev_priv, BLC_PWM_PCH_CTL1, pch_ctl1);
-	intel_de_posting_read(dev_priv, BLC_PWM_PCH_CTL1);
-	intel_de_write(dev_priv, BLC_PWM_PCH_CTL1,
-		       pch_ctl1 | BLM_PCH_PWM_ENABLE);
-}
-
-static void i9xx_enable_backlight(const struct intel_crtc_state *crtc_state,
-				  const struct drm_connector_state *conn_state, u32 level)
-{
-	struct intel_connector *connector = to_intel_connector(conn_state->connector);
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-	u32 ctl, freq;
-
-	ctl = intel_de_read(dev_priv, BLC_PWM_CTL);
-	if (ctl & BACKLIGHT_DUTY_CYCLE_MASK_PNV) {
-		drm_dbg_kms(&dev_priv->drm, "backlight already enabled\n");
-		intel_de_write(dev_priv, BLC_PWM_CTL, 0);
-	}
-
-	freq = panel->backlight.pwm_level_max;
-	if (panel->backlight.combination_mode)
-		freq /= 0xff;
-
-	ctl = freq << 17;
-	if (panel->backlight.combination_mode)
-		ctl |= BLM_LEGACY_MODE;
-	if (IS_PINEVIEW(dev_priv) && panel->backlight.active_low_pwm)
-		ctl |= BLM_POLARITY_PNV;
-
-	intel_de_write(dev_priv, BLC_PWM_CTL, ctl);
-	intel_de_posting_read(dev_priv, BLC_PWM_CTL);
-
-	/* XXX: combine this into above write? */
-	intel_panel_set_pwm_level(conn_state, level);
-
-	/*
-	 * Needed to enable backlight on some 855gm models. BLC_HIST_CTL is
-	 * 855gm only, but checking for gen2 is safe, as 855gm is the only gen2
-	 * that has backlight.
-	 */
-	if (DISPLAY_VER(dev_priv) == 2)
-		intel_de_write(dev_priv, BLC_HIST_CTL, BLM_HISTOGRAM_ENABLE);
-}
-
-static void i965_enable_backlight(const struct intel_crtc_state *crtc_state,
-				  const struct drm_connector_state *conn_state, u32 level)
-{
-	struct intel_connector *connector = to_intel_connector(conn_state->connector);
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-	enum pipe pipe = to_intel_crtc(conn_state->crtc)->pipe;
-	u32 ctl, ctl2, freq;
-
-	ctl2 = intel_de_read(dev_priv, BLC_PWM_CTL2);
-	if (ctl2 & BLM_PWM_ENABLE) {
-		drm_dbg_kms(&dev_priv->drm, "backlight already enabled\n");
-		ctl2 &= ~BLM_PWM_ENABLE;
-		intel_de_write(dev_priv, BLC_PWM_CTL2, ctl2);
-	}
-
-	freq = panel->backlight.pwm_level_max;
-	if (panel->backlight.combination_mode)
-		freq /= 0xff;
-
-	ctl = freq << 16;
-	intel_de_write(dev_priv, BLC_PWM_CTL, ctl);
-
-	ctl2 = BLM_PIPE(pipe);
-	if (panel->backlight.combination_mode)
-		ctl2 |= BLM_COMBINATION_MODE;
-	if (panel->backlight.active_low_pwm)
-		ctl2 |= BLM_POLARITY_I965;
-	intel_de_write(dev_priv, BLC_PWM_CTL2, ctl2);
-	intel_de_posting_read(dev_priv, BLC_PWM_CTL2);
-	intel_de_write(dev_priv, BLC_PWM_CTL2, ctl2 | BLM_PWM_ENABLE);
-
-	intel_panel_set_pwm_level(conn_state, level);
-}
-
-static void vlv_enable_backlight(const struct intel_crtc_state *crtc_state,
-				 const struct drm_connector_state *conn_state, u32 level)
-{
-	struct intel_connector *connector = to_intel_connector(conn_state->connector);
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-	enum pipe pipe = to_intel_crtc(crtc_state->uapi.crtc)->pipe;
-	u32 ctl, ctl2;
-
-	ctl2 = intel_de_read(dev_priv, VLV_BLC_PWM_CTL2(pipe));
-	if (ctl2 & BLM_PWM_ENABLE) {
-		drm_dbg_kms(&dev_priv->drm, "backlight already enabled\n");
-		ctl2 &= ~BLM_PWM_ENABLE;
-		intel_de_write(dev_priv, VLV_BLC_PWM_CTL2(pipe), ctl2);
-	}
-
-	ctl = panel->backlight.pwm_level_max << 16;
-	intel_de_write(dev_priv, VLV_BLC_PWM_CTL(pipe), ctl);
-
-	/* XXX: combine this into above write? */
-	intel_panel_set_pwm_level(conn_state, level);
-
-	ctl2 = 0;
-	if (panel->backlight.active_low_pwm)
-		ctl2 |= BLM_POLARITY_I965;
-	intel_de_write(dev_priv, VLV_BLC_PWM_CTL2(pipe), ctl2);
-	intel_de_posting_read(dev_priv, VLV_BLC_PWM_CTL2(pipe));
-	intel_de_write(dev_priv, VLV_BLC_PWM_CTL2(pipe),
-		       ctl2 | BLM_PWM_ENABLE);
-}
-
-static void bxt_enable_backlight(const struct intel_crtc_state *crtc_state,
-				 const struct drm_connector_state *conn_state, u32 level)
-{
-	struct intel_connector *connector = to_intel_connector(conn_state->connector);
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-	enum pipe pipe = to_intel_crtc(crtc_state->uapi.crtc)->pipe;
-	u32 pwm_ctl, val;
-
-	/* Controller 1 uses the utility pin. */
-	if (panel->backlight.controller == 1) {
-		val = intel_de_read(dev_priv, UTIL_PIN_CTL);
-		if (val & UTIL_PIN_ENABLE) {
-			drm_dbg_kms(&dev_priv->drm,
-				    "util pin already enabled\n");
-			val &= ~UTIL_PIN_ENABLE;
-			intel_de_write(dev_priv, UTIL_PIN_CTL, val);
-		}
-
-		val = 0;
-		if (panel->backlight.util_pin_active_low)
-			val |= UTIL_PIN_POLARITY;
-		intel_de_write(dev_priv, UTIL_PIN_CTL,
-			       val | UTIL_PIN_PIPE(pipe) | UTIL_PIN_MODE_PWM | UTIL_PIN_ENABLE);
-	}
-
-	pwm_ctl = intel_de_read(dev_priv,
-				BXT_BLC_PWM_CTL(panel->backlight.controller));
-	if (pwm_ctl & BXT_BLC_PWM_ENABLE) {
-		drm_dbg_kms(&dev_priv->drm, "backlight already enabled\n");
-		pwm_ctl &= ~BXT_BLC_PWM_ENABLE;
-		intel_de_write(dev_priv,
-			       BXT_BLC_PWM_CTL(panel->backlight.controller),
-			       pwm_ctl);
-	}
-
-	intel_de_write(dev_priv,
-		       BXT_BLC_PWM_FREQ(panel->backlight.controller),
-		       panel->backlight.pwm_level_max);
-
-	intel_panel_set_pwm_level(conn_state, level);
-
-	pwm_ctl = 0;
-	if (panel->backlight.active_low_pwm)
-		pwm_ctl |= BXT_BLC_PWM_POLARITY;
-
-	intel_de_write(dev_priv, BXT_BLC_PWM_CTL(panel->backlight.controller),
-		       pwm_ctl);
-	intel_de_posting_read(dev_priv,
-			      BXT_BLC_PWM_CTL(panel->backlight.controller));
-	intel_de_write(dev_priv, BXT_BLC_PWM_CTL(panel->backlight.controller),
-		       pwm_ctl | BXT_BLC_PWM_ENABLE);
-}
-
-static void cnp_enable_backlight(const struct intel_crtc_state *crtc_state,
-				 const struct drm_connector_state *conn_state, u32 level)
-{
-	struct intel_connector *connector = to_intel_connector(conn_state->connector);
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-	u32 pwm_ctl;
-
-	pwm_ctl = intel_de_read(dev_priv,
-				BXT_BLC_PWM_CTL(panel->backlight.controller));
-	if (pwm_ctl & BXT_BLC_PWM_ENABLE) {
-		drm_dbg_kms(&dev_priv->drm, "backlight already enabled\n");
-		pwm_ctl &= ~BXT_BLC_PWM_ENABLE;
-		intel_de_write(dev_priv,
-			       BXT_BLC_PWM_CTL(panel->backlight.controller),
-			       pwm_ctl);
-	}
-
-	intel_de_write(dev_priv,
-		       BXT_BLC_PWM_FREQ(panel->backlight.controller),
-		       panel->backlight.pwm_level_max);
-
-	intel_panel_set_pwm_level(conn_state, level);
-
-	pwm_ctl = 0;
-	if (panel->backlight.active_low_pwm)
-		pwm_ctl |= BXT_BLC_PWM_POLARITY;
-
-	intel_de_write(dev_priv, BXT_BLC_PWM_CTL(panel->backlight.controller),
-		       pwm_ctl);
-	intel_de_posting_read(dev_priv,
-			      BXT_BLC_PWM_CTL(panel->backlight.controller));
-	intel_de_write(dev_priv, BXT_BLC_PWM_CTL(panel->backlight.controller),
-		       pwm_ctl | BXT_BLC_PWM_ENABLE);
-}
-
-static void ext_pwm_enable_backlight(const struct intel_crtc_state *crtc_state,
-				     const struct drm_connector_state *conn_state, u32 level)
-{
-	struct intel_connector *connector = to_intel_connector(conn_state->connector);
-	struct intel_panel *panel = &connector->panel;
-
-	pwm_set_relative_duty_cycle(&panel->backlight.pwm_state, level, 100);
-	panel->backlight.pwm_state.enabled = true;
-	pwm_apply_state(panel->backlight.pwm, &panel->backlight.pwm_state);
-}
-
-static void __intel_panel_enable_backlight(const struct intel_crtc_state *crtc_state,
-					   const struct drm_connector_state *conn_state)
-{
-	struct intel_connector *connector = to_intel_connector(conn_state->connector);
-	struct intel_panel *panel = &connector->panel;
-
-	WARN_ON(panel->backlight.max == 0);
-
-	if (panel->backlight.level <= panel->backlight.min) {
-		panel->backlight.level = panel->backlight.max;
-		if (panel->backlight.device)
-			panel->backlight.device->props.brightness =
-				scale_hw_to_user(connector,
-						 panel->backlight.level,
-						 panel->backlight.device->props.max_brightness);
-	}
-
-	panel->backlight.funcs->enable(crtc_state, conn_state, panel->backlight.level);
-	panel->backlight.enabled = true;
-	if (panel->backlight.device)
-		panel->backlight.device->props.power = FB_BLANK_UNBLANK;
-}
-
-void intel_panel_enable_backlight(const struct intel_crtc_state *crtc_state,
-				  const struct drm_connector_state *conn_state)
-{
-	struct intel_connector *connector = to_intel_connector(conn_state->connector);
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-	enum pipe pipe = to_intel_crtc(crtc_state->uapi.crtc)->pipe;
-
-	if (!panel->backlight.present)
-		return;
-
-	drm_dbg_kms(&dev_priv->drm, "pipe %c\n", pipe_name(pipe));
-
-	mutex_lock(&dev_priv->backlight_lock);
-
-	__intel_panel_enable_backlight(crtc_state, conn_state);
-
-	mutex_unlock(&dev_priv->backlight_lock);
-}
-
-#if IS_ENABLED(CONFIG_BACKLIGHT_CLASS_DEVICE)
-static u32 intel_panel_get_backlight(struct intel_connector *connector)
-{
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-	u32 val = 0;
-
-	mutex_lock(&dev_priv->backlight_lock);
-
-	if (panel->backlight.enabled)
-		val = panel->backlight.funcs->get(connector, intel_connector_get_pipe(connector));
-
-	mutex_unlock(&dev_priv->backlight_lock);
-
-	drm_dbg_kms(&dev_priv->drm, "get backlight PWM = %d\n", val);
-	return val;
-}
-
-/* Scale user_level in range [0..user_max] to [hw_min..hw_max]. */
-static u32 scale_user_to_hw(struct intel_connector *connector,
-			    u32 user_level, u32 user_max)
-{
-	struct intel_panel *panel = &connector->panel;
-
-	return scale(user_level, 0, user_max,
-		     panel->backlight.min, panel->backlight.max);
-}
-
-/* set backlight brightness to level in range [0..max], scaling wrt hw min */
-static void intel_panel_set_backlight(const struct drm_connector_state *conn_state,
-				      u32 user_level, u32 user_max)
-{
-	struct intel_connector *connector = to_intel_connector(conn_state->connector);
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-	u32 hw_level;
-
-	if (!panel->backlight.present)
-		return;
-
-	mutex_lock(&dev_priv->backlight_lock);
-
-	drm_WARN_ON(&dev_priv->drm, panel->backlight.max == 0);
-
-	hw_level = scale_user_to_hw(connector, user_level, user_max);
-	panel->backlight.level = hw_level;
-
-	if (panel->backlight.enabled)
-		intel_panel_actually_set_backlight(conn_state, hw_level);
-
-	mutex_unlock(&dev_priv->backlight_lock);
-}
-
-static int intel_backlight_device_update_status(struct backlight_device *bd)
-{
-	struct intel_connector *connector = bl_get_data(bd);
-	struct intel_panel *panel = &connector->panel;
-	struct drm_device *dev = connector->base.dev;
-
-	drm_modeset_lock(&dev->mode_config.connection_mutex, NULL);
-	DRM_DEBUG_KMS("updating intel_backlight, brightness=%d/%d\n",
-		      bd->props.brightness, bd->props.max_brightness);
-	intel_panel_set_backlight(connector->base.state, bd->props.brightness,
-				  bd->props.max_brightness);
-
-	/*
-	 * Allow flipping bl_power as a sub-state of enabled. Sadly the
-	 * backlight class device does not make it easy to to differentiate
-	 * between callbacks for brightness and bl_power, so our backlight_power
-	 * callback needs to take this into account.
-	 */
-	if (panel->backlight.enabled) {
-		if (panel->backlight.power) {
-			bool enable = bd->props.power == FB_BLANK_UNBLANK &&
-				bd->props.brightness != 0;
-			panel->backlight.power(connector, enable);
-		}
-	} else {
-		bd->props.power = FB_BLANK_POWERDOWN;
-	}
-
-	drm_modeset_unlock(&dev->mode_config.connection_mutex);
-	return 0;
-}
-
-static int intel_backlight_device_get_brightness(struct backlight_device *bd)
-{
-	struct intel_connector *connector = bl_get_data(bd);
-	struct drm_device *dev = connector->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	intel_wakeref_t wakeref;
-	int ret = 0;
-
-	with_intel_runtime_pm(&dev_priv->runtime_pm, wakeref) {
-		u32 hw_level;
-
-		drm_modeset_lock(&dev->mode_config.connection_mutex, NULL);
-
-		hw_level = intel_panel_get_backlight(connector);
-		ret = scale_hw_to_user(connector,
-				       hw_level, bd->props.max_brightness);
-
-		drm_modeset_unlock(&dev->mode_config.connection_mutex);
-	}
-
-	return ret;
-}
-
-static const struct backlight_ops intel_backlight_device_ops = {
-	.update_status = intel_backlight_device_update_status,
-	.get_brightness = intel_backlight_device_get_brightness,
-};
-
-int intel_backlight_device_register(struct intel_connector *connector)
-{
-	struct drm_i915_private *i915 = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-	struct backlight_properties props;
-	struct backlight_device *bd;
-	const char *name;
-	int ret = 0;
-
-	if (WARN_ON(panel->backlight.device))
-		return -ENODEV;
-
-	if (!panel->backlight.present)
-		return 0;
-
-	WARN_ON(panel->backlight.max == 0);
-
-	memset(&props, 0, sizeof(props));
-	props.type = BACKLIGHT_RAW;
-
-	/*
-	 * Note: Everything should work even if the backlight device max
-	 * presented to the userspace is arbitrarily chosen.
-	 */
-	props.max_brightness = panel->backlight.max;
-	props.brightness = scale_hw_to_user(connector,
-					    panel->backlight.level,
-					    props.max_brightness);
-
-	if (panel->backlight.enabled)
-		props.power = FB_BLANK_UNBLANK;
-	else
-		props.power = FB_BLANK_POWERDOWN;
-
-	name = kstrdup("intel_backlight", GFP_KERNEL);
-	if (!name)
-		return -ENOMEM;
-
-	bd = backlight_device_register(name, connector->base.kdev, connector,
-				       &intel_backlight_device_ops, &props);
-
-	/*
-	 * Using the same name independent of the drm device or connector
-	 * prevents registration of multiple backlight devices in the
-	 * driver. However, we need to use the default name for backward
-	 * compatibility. Use unique names for subsequent backlight devices as a
-	 * fallback when the default name already exists.
-	 */
-	if (IS_ERR(bd) && PTR_ERR(bd) == -EEXIST) {
-		kfree(name);
-		name = kasprintf(GFP_KERNEL, "card%d-%s-backlight",
-				 i915->drm.primary->index, connector->base.name);
-		if (!name)
-			return -ENOMEM;
-
-		bd = backlight_device_register(name, connector->base.kdev, connector,
-					       &intel_backlight_device_ops, &props);
-	}
-
-	if (IS_ERR(bd)) {
-		drm_err(&i915->drm,
-			"[CONNECTOR:%d:%s] backlight device %s register failed: %ld\n",
-			connector->base.base.id, connector->base.name, name, PTR_ERR(bd));
-		ret = PTR_ERR(bd);
-		goto out;
-	}
-
-	panel->backlight.device = bd;
-
-	drm_dbg_kms(&i915->drm,
-		    "[CONNECTOR:%d:%s] backlight device %s registered\n",
-		    connector->base.base.id, connector->base.name, name);
-
-out:
-	kfree(name);
-
-	return ret;
-}
-
-void intel_backlight_device_unregister(struct intel_connector *connector)
-{
-	struct intel_panel *panel = &connector->panel;
-
-	if (panel->backlight.device) {
-		backlight_device_unregister(panel->backlight.device);
-		panel->backlight.device = NULL;
-	}
-}
-#endif /* CONFIG_BACKLIGHT_CLASS_DEVICE */
-
-/*
- * CNP: PWM clock frequency is 19.2 MHz or 24 MHz.
- *      PWM increment = 1
- */
-static u32 cnp_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz)
-{
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-
-	return DIV_ROUND_CLOSEST(KHz(RUNTIME_INFO(dev_priv)->rawclk_freq),
-				 pwm_freq_hz);
-}
-
-/*
- * BXT: PWM clock frequency = 19.2 MHz.
- */
-static u32 bxt_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz)
-{
-	return DIV_ROUND_CLOSEST(KHz(19200), pwm_freq_hz);
-}
-
-/*
- * SPT: This value represents the period of the PWM stream in clock periods
- * multiplied by 16 (default increment) or 128 (alternate increment selected in
- * SCHICKEN_1 bit 0). PWM clock is 24 MHz.
- */
-static u32 spt_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz)
-{
-	struct intel_panel *panel = &connector->panel;
-	u32 mul;
-
-	if (panel->backlight.alternate_pwm_increment)
-		mul = 128;
-	else
-		mul = 16;
-
-	return DIV_ROUND_CLOSEST(MHz(24), pwm_freq_hz * mul);
-}
-
-/*
- * LPT: This value represents the period of the PWM stream in clock periods
- * multiplied by 128 (default increment) or 16 (alternate increment, selected in
- * LPT SOUTH_CHICKEN2 register bit 5).
- */
-static u32 lpt_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz)
-{
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-	u32 mul, clock;
-
-	if (panel->backlight.alternate_pwm_increment)
-		mul = 16;
-	else
-		mul = 128;
-
-	if (HAS_PCH_LPT_H(dev_priv))
-		clock = MHz(135); /* LPT:H */
-	else
-		clock = MHz(24); /* LPT:LP */
-
-	return DIV_ROUND_CLOSEST(clock, pwm_freq_hz * mul);
-}
-
-/*
- * ILK/SNB/IVB: This value represents the period of the PWM stream in PCH
- * display raw clocks multiplied by 128.
- */
-static u32 pch_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz)
-{
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-
-	return DIV_ROUND_CLOSEST(KHz(RUNTIME_INFO(dev_priv)->rawclk_freq),
-				 pwm_freq_hz * 128);
-}
-
-/*
- * Gen2: This field determines the number of time base events (display core
- * clock frequency/32) in total for a complete cycle of modulated backlight
- * control.
- *
- * Gen3: A time base event equals the display core clock ([DevPNV] HRAW clock)
- * divided by 32.
- */
-static u32 i9xx_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz)
-{
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	int clock;
-
-	if (IS_PINEVIEW(dev_priv))
-		clock = KHz(RUNTIME_INFO(dev_priv)->rawclk_freq);
-	else
-		clock = KHz(dev_priv->cdclk.hw.cdclk);
-
-	return DIV_ROUND_CLOSEST(clock, pwm_freq_hz * 32);
-}
-
-/*
- * Gen4: This value represents the period of the PWM stream in display core
- * clocks ([DevCTG] HRAW clocks) multiplied by 128.
- *
- */
-static u32 i965_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz)
-{
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	int clock;
-
-	if (IS_G4X(dev_priv))
-		clock = KHz(RUNTIME_INFO(dev_priv)->rawclk_freq);
-	else
-		clock = KHz(dev_priv->cdclk.hw.cdclk);
-
-	return DIV_ROUND_CLOSEST(clock, pwm_freq_hz * 128);
-}
-
-/*
- * VLV: This value represents the period of the PWM stream in display core
- * clocks ([DevCTG] 200MHz HRAW clocks) multiplied by 128 or 25MHz S0IX clocks
- * multiplied by 16. CHV uses a 19.2MHz S0IX clock.
- */
-static u32 vlv_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz)
-{
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	int mul, clock;
-
-	if ((intel_de_read(dev_priv, CBR1_VLV) & CBR_PWM_CLOCK_MUX_SELECT) == 0) {
-		if (IS_CHERRYVIEW(dev_priv))
-			clock = KHz(19200);
-		else
-			clock = MHz(25);
-		mul = 16;
-	} else {
-		clock = KHz(RUNTIME_INFO(dev_priv)->rawclk_freq);
-		mul = 128;
-	}
-
-	return DIV_ROUND_CLOSEST(clock, pwm_freq_hz * mul);
-}
-
-static u16 get_vbt_pwm_freq(struct drm_i915_private *dev_priv)
-{
-	u16 pwm_freq_hz = dev_priv->vbt.backlight.pwm_freq_hz;
-
-	if (pwm_freq_hz) {
-		drm_dbg_kms(&dev_priv->drm,
-			    "VBT defined backlight frequency %u Hz\n",
-			    pwm_freq_hz);
-	} else {
-		pwm_freq_hz = 200;
-		drm_dbg_kms(&dev_priv->drm,
-			    "default backlight frequency %u Hz\n",
-			    pwm_freq_hz);
-	}
-
-	return pwm_freq_hz;
-}
-
-static u32 get_backlight_max_vbt(struct intel_connector *connector)
-{
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-	u16 pwm_freq_hz = get_vbt_pwm_freq(dev_priv);
-	u32 pwm;
-
-	if (!panel->backlight.pwm_funcs->hz_to_pwm) {
-		drm_dbg_kms(&dev_priv->drm,
-			    "backlight frequency conversion not supported\n");
-		return 0;
-	}
-
-	pwm = panel->backlight.pwm_funcs->hz_to_pwm(connector, pwm_freq_hz);
-	if (!pwm) {
-		drm_dbg_kms(&dev_priv->drm,
-			    "backlight frequency conversion failed\n");
-		return 0;
-	}
-
-	return pwm;
-}
-
-/*
- * Note: The setup hooks can't assume pipe is set!
- */
-static u32 get_backlight_min_vbt(struct intel_connector *connector)
-{
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-	int min;
-
-	drm_WARN_ON(&dev_priv->drm, panel->backlight.pwm_level_max == 0);
-
-	/*
-	 * XXX: If the vbt value is 255, it makes min equal to max, which leads
-	 * to problems. There are such machines out there. Either our
-	 * interpretation is wrong or the vbt has bogus data. Or both. Safeguard
-	 * against this by letting the minimum be at most (arbitrarily chosen)
-	 * 25% of the max.
-	 */
-	min = clamp_t(int, dev_priv->vbt.backlight.min_brightness, 0, 64);
-	if (min != dev_priv->vbt.backlight.min_brightness) {
-		drm_dbg_kms(&dev_priv->drm,
-			    "clamping VBT min backlight %d/255 to %d/255\n",
-			    dev_priv->vbt.backlight.min_brightness, min);
-	}
-
-	/* vbt value is a coefficient in range [0..255] */
-	return scale(min, 0, 255, 0, panel->backlight.pwm_level_max);
-}
-
-static int lpt_setup_backlight(struct intel_connector *connector, enum pipe unused)
-{
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-	u32 cpu_ctl2, pch_ctl1, pch_ctl2, val;
-	bool alt, cpu_mode;
-
-	if (HAS_PCH_LPT(dev_priv))
-		alt = intel_de_read(dev_priv, SOUTH_CHICKEN2) & LPT_PWM_GRANULARITY;
-	else
-		alt = intel_de_read(dev_priv, SOUTH_CHICKEN1) & SPT_PWM_GRANULARITY;
-	panel->backlight.alternate_pwm_increment = alt;
-
-	pch_ctl1 = intel_de_read(dev_priv, BLC_PWM_PCH_CTL1);
-	panel->backlight.active_low_pwm = pch_ctl1 & BLM_PCH_POLARITY;
-
-	pch_ctl2 = intel_de_read(dev_priv, BLC_PWM_PCH_CTL2);
-	panel->backlight.pwm_level_max = pch_ctl2 >> 16;
-
-	cpu_ctl2 = intel_de_read(dev_priv, BLC_PWM_CPU_CTL2);
-
-	if (!panel->backlight.pwm_level_max)
-		panel->backlight.pwm_level_max = get_backlight_max_vbt(connector);
-
-	if (!panel->backlight.pwm_level_max)
-		return -ENODEV;
-
-	panel->backlight.pwm_level_min = get_backlight_min_vbt(connector);
-
-	panel->backlight.pwm_enabled = pch_ctl1 & BLM_PCH_PWM_ENABLE;
-
-	cpu_mode = panel->backlight.pwm_enabled && HAS_PCH_LPT(dev_priv) &&
-		   !(pch_ctl1 & BLM_PCH_OVERRIDE_ENABLE) &&
-		   (cpu_ctl2 & BLM_PWM_ENABLE);
-
-	if (cpu_mode) {
-		val = pch_get_backlight(connector, unused);
-
-		drm_dbg_kms(&dev_priv->drm,
-			    "CPU backlight register was enabled, switching to PCH override\n");
-
-		/* Write converted CPU PWM value to PCH override register */
-		lpt_set_backlight(connector->base.state, val);
-		intel_de_write(dev_priv, BLC_PWM_PCH_CTL1,
-			       pch_ctl1 | BLM_PCH_OVERRIDE_ENABLE);
-
-		intel_de_write(dev_priv, BLC_PWM_CPU_CTL2,
-			       cpu_ctl2 & ~BLM_PWM_ENABLE);
-	}
-
-	return 0;
-}
-
-static int pch_setup_backlight(struct intel_connector *connector, enum pipe unused)
-{
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-	u32 cpu_ctl2, pch_ctl1, pch_ctl2;
-
-	pch_ctl1 = intel_de_read(dev_priv, BLC_PWM_PCH_CTL1);
-	panel->backlight.active_low_pwm = pch_ctl1 & BLM_PCH_POLARITY;
-
-	pch_ctl2 = intel_de_read(dev_priv, BLC_PWM_PCH_CTL2);
-	panel->backlight.pwm_level_max = pch_ctl2 >> 16;
-
-	if (!panel->backlight.pwm_level_max)
-		panel->backlight.pwm_level_max = get_backlight_max_vbt(connector);
-
-	if (!panel->backlight.pwm_level_max)
-		return -ENODEV;
-
-	panel->backlight.pwm_level_min = get_backlight_min_vbt(connector);
-
-	cpu_ctl2 = intel_de_read(dev_priv, BLC_PWM_CPU_CTL2);
-	panel->backlight.pwm_enabled = (cpu_ctl2 & BLM_PWM_ENABLE) &&
-		(pch_ctl1 & BLM_PCH_PWM_ENABLE);
-
-	return 0;
-}
-
-static int i9xx_setup_backlight(struct intel_connector *connector, enum pipe unused)
-{
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-	u32 ctl, val;
-
-	ctl = intel_de_read(dev_priv, BLC_PWM_CTL);
-
-	if (DISPLAY_VER(dev_priv) == 2 || IS_I915GM(dev_priv) || IS_I945GM(dev_priv))
-		panel->backlight.combination_mode = ctl & BLM_LEGACY_MODE;
-
-	if (IS_PINEVIEW(dev_priv))
-		panel->backlight.active_low_pwm = ctl & BLM_POLARITY_PNV;
-
-	panel->backlight.pwm_level_max = ctl >> 17;
-
-	if (!panel->backlight.pwm_level_max) {
-		panel->backlight.pwm_level_max = get_backlight_max_vbt(connector);
-		panel->backlight.pwm_level_max >>= 1;
-	}
-
-	if (!panel->backlight.pwm_level_max)
-		return -ENODEV;
-
-	if (panel->backlight.combination_mode)
-		panel->backlight.pwm_level_max *= 0xff;
-
-	panel->backlight.pwm_level_min = get_backlight_min_vbt(connector);
-
-	val = i9xx_get_backlight(connector, unused);
-	val = intel_panel_invert_pwm_level(connector, val);
-	val = clamp(val, panel->backlight.pwm_level_min, panel->backlight.pwm_level_max);
-
-	panel->backlight.pwm_enabled = val != 0;
-
-	return 0;
-}
-
-static int i965_setup_backlight(struct intel_connector *connector, enum pipe unused)
-{
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-	u32 ctl, ctl2;
-
-	ctl2 = intel_de_read(dev_priv, BLC_PWM_CTL2);
-	panel->backlight.combination_mode = ctl2 & BLM_COMBINATION_MODE;
-	panel->backlight.active_low_pwm = ctl2 & BLM_POLARITY_I965;
-
-	ctl = intel_de_read(dev_priv, BLC_PWM_CTL);
-	panel->backlight.pwm_level_max = ctl >> 16;
-
-	if (!panel->backlight.pwm_level_max)
-		panel->backlight.pwm_level_max = get_backlight_max_vbt(connector);
-
-	if (!panel->backlight.pwm_level_max)
-		return -ENODEV;
-
-	if (panel->backlight.combination_mode)
-		panel->backlight.pwm_level_max *= 0xff;
-
-	panel->backlight.pwm_level_min = get_backlight_min_vbt(connector);
-
-	panel->backlight.pwm_enabled = ctl2 & BLM_PWM_ENABLE;
-
-	return 0;
-}
-
-static int vlv_setup_backlight(struct intel_connector *connector, enum pipe pipe)
-{
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-	u32 ctl, ctl2;
-
-	if (drm_WARN_ON(&dev_priv->drm, pipe != PIPE_A && pipe != PIPE_B))
-		return -ENODEV;
-
-	ctl2 = intel_de_read(dev_priv, VLV_BLC_PWM_CTL2(pipe));
-	panel->backlight.active_low_pwm = ctl2 & BLM_POLARITY_I965;
-
-	ctl = intel_de_read(dev_priv, VLV_BLC_PWM_CTL(pipe));
-	panel->backlight.pwm_level_max = ctl >> 16;
-
-	if (!panel->backlight.pwm_level_max)
-		panel->backlight.pwm_level_max = get_backlight_max_vbt(connector);
-
-	if (!panel->backlight.pwm_level_max)
-		return -ENODEV;
-
-	panel->backlight.pwm_level_min = get_backlight_min_vbt(connector);
-
-	panel->backlight.pwm_enabled = ctl2 & BLM_PWM_ENABLE;
-
-	return 0;
-}
-
-static int
-bxt_setup_backlight(struct intel_connector *connector, enum pipe unused)
-{
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-	u32 pwm_ctl, val;
-
-	panel->backlight.controller = dev_priv->vbt.backlight.controller;
-
-	pwm_ctl = intel_de_read(dev_priv,
-				BXT_BLC_PWM_CTL(panel->backlight.controller));
-
-	/* Controller 1 uses the utility pin. */
-	if (panel->backlight.controller == 1) {
-		val = intel_de_read(dev_priv, UTIL_PIN_CTL);
-		panel->backlight.util_pin_active_low =
-					val & UTIL_PIN_POLARITY;
-	}
-
-	panel->backlight.active_low_pwm = pwm_ctl & BXT_BLC_PWM_POLARITY;
-	panel->backlight.pwm_level_max =
-		intel_de_read(dev_priv, BXT_BLC_PWM_FREQ(panel->backlight.controller));
-
-	if (!panel->backlight.pwm_level_max)
-		panel->backlight.pwm_level_max = get_backlight_max_vbt(connector);
-
-	if (!panel->backlight.pwm_level_max)
-		return -ENODEV;
-
-	panel->backlight.pwm_level_min = get_backlight_min_vbt(connector);
-
-	panel->backlight.pwm_enabled = pwm_ctl & BXT_BLC_PWM_ENABLE;
-
-	return 0;
-}
-
-static int
-cnp_setup_backlight(struct intel_connector *connector, enum pipe unused)
-{
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-	u32 pwm_ctl;
-
-	/*
-	 * CNP has the BXT implementation of backlight, but with only one
-	 * controller. TODO: ICP has multiple controllers but we only use
-	 * controller 0 for now.
-	 */
-	panel->backlight.controller = 0;
-
-	pwm_ctl = intel_de_read(dev_priv,
-				BXT_BLC_PWM_CTL(panel->backlight.controller));
-
-	panel->backlight.active_low_pwm = pwm_ctl & BXT_BLC_PWM_POLARITY;
-	panel->backlight.pwm_level_max =
-		intel_de_read(dev_priv, BXT_BLC_PWM_FREQ(panel->backlight.controller));
-
-	if (!panel->backlight.pwm_level_max)
-		panel->backlight.pwm_level_max = get_backlight_max_vbt(connector);
-
-	if (!panel->backlight.pwm_level_max)
-		return -ENODEV;
-
-	panel->backlight.pwm_level_min = get_backlight_min_vbt(connector);
-
-	panel->backlight.pwm_enabled = pwm_ctl & BXT_BLC_PWM_ENABLE;
-
-	return 0;
-}
-
-static int ext_pwm_setup_backlight(struct intel_connector *connector,
-				   enum pipe pipe)
-{
-	struct drm_device *dev = connector->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_panel *panel = &connector->panel;
-	const char *desc;
-	u32 level;
-
-	/* Get the right PWM chip for DSI backlight according to VBT */
-	if (dev_priv->vbt.dsi.config->pwm_blc == PPS_BLC_PMIC) {
-		panel->backlight.pwm = pwm_get(dev->dev, "pwm_pmic_backlight");
-		desc = "PMIC";
-	} else {
-		panel->backlight.pwm = pwm_get(dev->dev, "pwm_soc_backlight");
-		desc = "SoC";
-	}
-
-	if (IS_ERR(panel->backlight.pwm)) {
-		drm_err(&dev_priv->drm, "Failed to get the %s PWM chip\n",
-			desc);
-		panel->backlight.pwm = NULL;
-		return -ENODEV;
-	}
-
-	panel->backlight.pwm_level_max = 100; /* 100% */
-	panel->backlight.pwm_level_min = get_backlight_min_vbt(connector);
-
-	if (pwm_is_enabled(panel->backlight.pwm)) {
-		/* PWM is already enabled, use existing settings */
-		pwm_get_state(panel->backlight.pwm, &panel->backlight.pwm_state);
-
-		level = pwm_get_relative_duty_cycle(&panel->backlight.pwm_state,
-						    100);
-		level = intel_panel_invert_pwm_level(connector, level);
-		panel->backlight.pwm_enabled = true;
-
-		drm_dbg_kms(&dev_priv->drm, "PWM already enabled at freq %ld, VBT freq %d, level %d\n",
-			    NSEC_PER_SEC / (unsigned long)panel->backlight.pwm_state.period,
-			    get_vbt_pwm_freq(dev_priv), level);
-	} else {
-		/* Set period from VBT frequency, leave other settings at 0. */
-		panel->backlight.pwm_state.period =
-			NSEC_PER_SEC / get_vbt_pwm_freq(dev_priv);
-	}
-
-	drm_info(&dev_priv->drm, "Using %s PWM for LCD backlight control\n",
-		 desc);
-	return 0;
-}
-
-static void intel_pwm_set_backlight(const struct drm_connector_state *conn_state, u32 level)
-{
-	struct intel_connector *connector = to_intel_connector(conn_state->connector);
-	struct intel_panel *panel = &connector->panel;
-
-	panel->backlight.pwm_funcs->set(conn_state,
-				       intel_panel_invert_pwm_level(connector, level));
-}
-
-static u32 intel_pwm_get_backlight(struct intel_connector *connector, enum pipe pipe)
-{
-	struct intel_panel *panel = &connector->panel;
-
-	return intel_panel_invert_pwm_level(connector,
-					    panel->backlight.pwm_funcs->get(connector, pipe));
-}
-
-static void intel_pwm_enable_backlight(const struct intel_crtc_state *crtc_state,
-				       const struct drm_connector_state *conn_state, u32 level)
-{
-	struct intel_connector *connector = to_intel_connector(conn_state->connector);
-	struct intel_panel *panel = &connector->panel;
-
-	panel->backlight.pwm_funcs->enable(crtc_state, conn_state,
-					   intel_panel_invert_pwm_level(connector, level));
-}
-
-static void intel_pwm_disable_backlight(const struct drm_connector_state *conn_state, u32 level)
-{
-	struct intel_connector *connector = to_intel_connector(conn_state->connector);
-	struct intel_panel *panel = &connector->panel;
-
-	panel->backlight.pwm_funcs->disable(conn_state,
-					    intel_panel_invert_pwm_level(connector, level));
-}
-
-static int intel_pwm_setup_backlight(struct intel_connector *connector, enum pipe pipe)
-{
-	struct intel_panel *panel = &connector->panel;
-	int ret = panel->backlight.pwm_funcs->setup(connector, pipe);
-
-	if (ret < 0)
-		return ret;
-
-	panel->backlight.min = panel->backlight.pwm_level_min;
-	panel->backlight.max = panel->backlight.pwm_level_max;
-	panel->backlight.level = intel_pwm_get_backlight(connector, pipe);
-	panel->backlight.enabled = panel->backlight.pwm_enabled;
-
-	return 0;
-}
-
-void intel_panel_update_backlight(struct intel_atomic_state *state,
-				  struct intel_encoder *encoder,
-				  const struct intel_crtc_state *crtc_state,
-				  const struct drm_connector_state *conn_state)
-{
-	struct intel_connector *connector = to_intel_connector(conn_state->connector);
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_panel *panel = &connector->panel;
-
-	if (!panel->backlight.present)
-		return;
-
-	mutex_lock(&dev_priv->backlight_lock);
-	if (!panel->backlight.enabled)
-		__intel_panel_enable_backlight(crtc_state, conn_state);
-
-	mutex_unlock(&dev_priv->backlight_lock);
-}
-
-int intel_panel_setup_backlight(struct drm_connector *connector, enum pipe pipe)
-{
-	struct drm_i915_private *dev_priv = to_i915(connector->dev);
-	struct intel_connector *intel_connector = to_intel_connector(connector);
-	struct intel_panel *panel = &intel_connector->panel;
-	int ret;
-
-	if (!dev_priv->vbt.backlight.present) {
-		if (dev_priv->quirks & QUIRK_BACKLIGHT_PRESENT) {
-			drm_dbg_kms(&dev_priv->drm,
-				    "no backlight present per VBT, but present per quirk\n");
-		} else {
-			drm_dbg_kms(&dev_priv->drm,
-				    "no backlight present per VBT\n");
-			return 0;
-		}
-	}
-
-	/* ensure intel_panel has been initialized first */
-	if (drm_WARN_ON(&dev_priv->drm, !panel->backlight.funcs))
-		return -ENODEV;
-
-	/* set level and max in panel struct */
-	mutex_lock(&dev_priv->backlight_lock);
-	ret = panel->backlight.funcs->setup(intel_connector, pipe);
-	mutex_unlock(&dev_priv->backlight_lock);
-
-	if (ret) {
-		drm_dbg_kms(&dev_priv->drm,
-			    "failed to setup backlight for connector %s\n",
-			    connector->name);
-		return ret;
-	}
-
-	panel->backlight.present = true;
-
-	drm_dbg_kms(&dev_priv->drm,
-		    "Connector %s backlight initialized, %s, brightness %u/%u\n",
-		    connector->name,
-		    enableddisabled(panel->backlight.enabled),
-		    panel->backlight.level, panel->backlight.max);
-
-	return 0;
-}
-
-static void intel_panel_destroy_backlight(struct intel_panel *panel)
-{
-	/* dispose of the pwm */
-	if (panel->backlight.pwm)
-		pwm_put(panel->backlight.pwm);
-
-	panel->backlight.present = false;
-}
-
-static const struct intel_panel_bl_funcs bxt_pwm_funcs = {
-	.setup = bxt_setup_backlight,
-	.enable = bxt_enable_backlight,
-	.disable = bxt_disable_backlight,
-	.set = bxt_set_backlight,
-	.get = bxt_get_backlight,
-	.hz_to_pwm = bxt_hz_to_pwm,
-};
-
-static const struct intel_panel_bl_funcs cnp_pwm_funcs = {
-	.setup = cnp_setup_backlight,
-	.enable = cnp_enable_backlight,
-	.disable = cnp_disable_backlight,
-	.set = bxt_set_backlight,
-	.get = bxt_get_backlight,
-	.hz_to_pwm = cnp_hz_to_pwm,
-};
-
-static const struct intel_panel_bl_funcs lpt_pwm_funcs = {
-	.setup = lpt_setup_backlight,
-	.enable = lpt_enable_backlight,
-	.disable = lpt_disable_backlight,
-	.set = lpt_set_backlight,
-	.get = lpt_get_backlight,
-	.hz_to_pwm = lpt_hz_to_pwm,
-};
-
-static const struct intel_panel_bl_funcs spt_pwm_funcs = {
-	.setup = lpt_setup_backlight,
-	.enable = lpt_enable_backlight,
-	.disable = lpt_disable_backlight,
-	.set = lpt_set_backlight,
-	.get = lpt_get_backlight,
-	.hz_to_pwm = spt_hz_to_pwm,
-};
-
-static const struct intel_panel_bl_funcs pch_pwm_funcs = {
-	.setup = pch_setup_backlight,
-	.enable = pch_enable_backlight,
-	.disable = pch_disable_backlight,
-	.set = pch_set_backlight,
-	.get = pch_get_backlight,
-	.hz_to_pwm = pch_hz_to_pwm,
-};
-
-static const struct intel_panel_bl_funcs ext_pwm_funcs = {
-	.setup = ext_pwm_setup_backlight,
-	.enable = ext_pwm_enable_backlight,
-	.disable = ext_pwm_disable_backlight,
-	.set = ext_pwm_set_backlight,
-	.get = ext_pwm_get_backlight,
-};
-
-static const struct intel_panel_bl_funcs vlv_pwm_funcs = {
-	.setup = vlv_setup_backlight,
-	.enable = vlv_enable_backlight,
-	.disable = vlv_disable_backlight,
-	.set = vlv_set_backlight,
-	.get = vlv_get_backlight,
-	.hz_to_pwm = vlv_hz_to_pwm,
-};
-
-static const struct intel_panel_bl_funcs i965_pwm_funcs = {
-	.setup = i965_setup_backlight,
-	.enable = i965_enable_backlight,
-	.disable = i965_disable_backlight,
-	.set = i9xx_set_backlight,
-	.get = i9xx_get_backlight,
-	.hz_to_pwm = i965_hz_to_pwm,
-};
-
-static const struct intel_panel_bl_funcs i9xx_pwm_funcs = {
-	.setup = i9xx_setup_backlight,
-	.enable = i9xx_enable_backlight,
-	.disable = i9xx_disable_backlight,
-	.set = i9xx_set_backlight,
-	.get = i9xx_get_backlight,
-	.hz_to_pwm = i9xx_hz_to_pwm,
-};
-
-static const struct intel_panel_bl_funcs pwm_bl_funcs = {
-	.setup = intel_pwm_setup_backlight,
-	.enable = intel_pwm_enable_backlight,
-	.disable = intel_pwm_disable_backlight,
-	.set = intel_pwm_set_backlight,
-	.get = intel_pwm_get_backlight,
-};
-
-/* Set up chip specific backlight functions */
-static void
-intel_panel_init_backlight_funcs(struct intel_panel *panel)
-{
-	struct intel_connector *connector =
-		container_of(panel, struct intel_connector, panel);
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-
-	if (connector->base.connector_type == DRM_MODE_CONNECTOR_DSI &&
-	    intel_dsi_dcs_init_backlight_funcs(connector) == 0)
-		return;
-
-	if (IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv)) {
-		panel->backlight.pwm_funcs = &bxt_pwm_funcs;
-	} else if (INTEL_PCH_TYPE(dev_priv) >= PCH_CNP) {
-		panel->backlight.pwm_funcs = &cnp_pwm_funcs;
-	} else if (INTEL_PCH_TYPE(dev_priv) >= PCH_LPT) {
-		if (HAS_PCH_LPT(dev_priv))
-			panel->backlight.pwm_funcs = &lpt_pwm_funcs;
-		else
-			panel->backlight.pwm_funcs = &spt_pwm_funcs;
-	} else if (HAS_PCH_SPLIT(dev_priv)) {
-		panel->backlight.pwm_funcs = &pch_pwm_funcs;
-	} else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
-		if (connector->base.connector_type == DRM_MODE_CONNECTOR_DSI) {
-			panel->backlight.pwm_funcs = &ext_pwm_funcs;
-		} else {
-			panel->backlight.pwm_funcs = &vlv_pwm_funcs;
-		}
-	} else if (DISPLAY_VER(dev_priv) == 4) {
-		panel->backlight.pwm_funcs = &i965_pwm_funcs;
-	} else {
-		panel->backlight.pwm_funcs = &i9xx_pwm_funcs;
-	}
-
-	if (connector->base.connector_type == DRM_MODE_CONNECTOR_eDP &&
-	    intel_dp_aux_init_backlight_funcs(connector) == 0)
-		return;
-
-	/* We're using a standard PWM backlight interface */
-	panel->backlight.funcs = &pwm_bl_funcs;
-}
-
 enum drm_connector_status
 intel_panel_detect(struct drm_connector *connector, bool force)
 {
diff --git a/drivers/gpu/drm/i915/display/intel_panel.h b/drivers/gpu/drm/i915/display/intel_panel.h
index 1d340f77bffc..67dbb15026bf 100644
--- a/drivers/gpu/drm/i915/display/intel_panel.h
+++ b/drivers/gpu/drm/i915/display/intel_panel.h
@@ -8,15 +8,13 @@
 
 #include <linux/types.h>
 
-#include "intel_display.h"
-
+enum drm_connector_status;
 struct drm_connector;
 struct drm_connector_state;
 struct drm_display_mode;
+struct drm_i915_private;
 struct intel_connector;
-struct intel_crtc;
 struct intel_crtc_state;
-struct intel_encoder;
 struct intel_panel;
 
 int intel_panel_init(struct intel_panel *panel,
@@ -31,17 +29,6 @@ int intel_pch_panel_fitting(struct intel_crtc_state *crtc_state,
 			    const struct drm_connector_state *conn_state);
 int intel_gmch_panel_fitting(struct intel_crtc_state *crtc_state,
 			     const struct drm_connector_state *conn_state);
-void intel_panel_set_backlight_acpi(const struct drm_connector_state *conn_state,
-				    u32 level, u32 max);
-int intel_panel_setup_backlight(struct drm_connector *connector,
-				enum pipe pipe);
-void intel_panel_enable_backlight(const struct intel_crtc_state *crtc_state,
-				  const struct drm_connector_state *conn_state);
-void intel_panel_update_backlight(struct intel_atomic_state *state,
-				  struct intel_encoder *encoder,
-				  const struct intel_crtc_state *crtc_state,
-				  const struct drm_connector_state *conn_state);
-void intel_panel_disable_backlight(const struct drm_connector_state *old_conn_state);
 struct drm_display_mode *
 intel_panel_edid_downclock_mode(struct intel_connector *connector,
 				const struct drm_display_mode *fixed_mode);
@@ -49,22 +36,5 @@ struct drm_display_mode *
 intel_panel_edid_fixed_mode(struct intel_connector *connector);
 struct drm_display_mode *
 intel_panel_vbt_fixed_mode(struct intel_connector *connector);
-void intel_panel_set_pwm_level(const struct drm_connector_state *conn_state, u32 level);
-u32 intel_panel_invert_pwm_level(struct intel_connector *connector, u32 level);
-u32 intel_panel_backlight_level_to_pwm(struct intel_connector *connector, u32 level);
-u32 intel_panel_backlight_level_from_pwm(struct intel_connector *connector, u32 val);
-
-#if IS_ENABLED(CONFIG_BACKLIGHT_CLASS_DEVICE)
-int intel_backlight_device_register(struct intel_connector *connector);
-void intel_backlight_device_unregister(struct intel_connector *connector);
-#else /* CONFIG_BACKLIGHT_CLASS_DEVICE */
-static inline int intel_backlight_device_register(struct intel_connector *connector)
-{
-	return 0;
-}
-static inline void intel_backlight_device_unregister(struct intel_connector *connector)
-{
-}
-#endif /* CONFIG_BACKLIGHT_CLASS_DEVICE */
 
 #endif /* __INTEL_PANEL_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_quirks.c b/drivers/gpu/drm/i915/display/intel_quirks.c
index 8a52b7a16774..407b096f5392 100644
--- a/drivers/gpu/drm/i915/display/intel_quirks.c
+++ b/drivers/gpu/drm/i915/display/intel_quirks.c
@@ -190,6 +190,9 @@ static struct intel_quirk intel_quirks[] = {
 	/* ASRock ITX*/
 	{ 0x3185, 0x1849, 0x2212, quirk_increase_ddi_disabled_time },
 	{ 0x3184, 0x1849, 0x2212, quirk_increase_ddi_disabled_time },
+	/* ECS Liva Q2 */
+	{ 0x3185, 0x1019, 0xa94d, quirk_increase_ddi_disabled_time },
+	{ 0x3184, 0x1019, 0xa94d, quirk_increase_ddi_disabled_time },
 };
 
 void intel_init_quirks(struct drm_i915_private *i915)
diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c
index 0ee4ff341e25..b27738df447d 100644
--- a/drivers/gpu/drm/i915/display/vlv_dsi.c
+++ b/drivers/gpu/drm/i915/display/vlv_dsi.c
@@ -32,6 +32,7 @@
 
 #include "i915_drv.h"
 #include "intel_atomic.h"
+#include "intel_backlight.h"
 #include "intel_connector.h"
 #include "intel_crtc.h"
 #include "intel_de.h"
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 166bb46408a9..ba2e037a82e4 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -442,6 +442,13 @@ set_proto_ctx_engines_bond(struct i915_user_extension __user *base, void *data)
 	u16 idx, num_bonds;
 	int err, n;
 
+	if (GRAPHICS_VER(i915) >= 12 && !IS_TIGERLAKE(i915) &&
+	    !IS_ROCKETLAKE(i915) && !IS_ALDERLAKE_S(i915)) {
+		drm_dbg(&i915->drm,
+			"Bonding on gen12+ aside from TGL, RKL, and ADL_S not supported\n");
+		return -ENODEV;
+	}
+
 	if (get_user(idx, &ext->virtual_index))
 		return -EFAULT;
 
@@ -720,8 +727,9 @@ static int set_proto_ctx_param(struct drm_i915_file_private *fpriv,
 	case I915_CONTEXT_PARAM_PERSISTENCE:
 		if (args->size)
 			ret = -EINVAL;
-		ret = proto_context_set_persistence(fpriv->dev_priv, pc,
-						    args->value);
+		else
+			ret = proto_context_set_persistence(fpriv->dev_priv, pc,
+							    args->value);
 		break;
 
 	case I915_CONTEXT_PARAM_NO_ZEROMAP:
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 1aa249908b64..0d480867fc0c 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -1060,6 +1060,47 @@ static inline struct i915_ggtt *cache_to_ggtt(struct reloc_cache *cache)
 	return &i915->ggtt;
 }
 
+static void reloc_cache_unmap(struct reloc_cache *cache)
+{
+	void *vaddr;
+
+	if (!cache->vaddr)
+		return;
+
+	vaddr = unmask_page(cache->vaddr);
+	if (cache->vaddr & KMAP)
+		kunmap_atomic(vaddr);
+	else
+		io_mapping_unmap_atomic((void __iomem *)vaddr);
+}
+
+static void reloc_cache_remap(struct reloc_cache *cache,
+			      struct drm_i915_gem_object *obj)
+{
+	void *vaddr;
+
+	if (!cache->vaddr)
+		return;
+
+	if (cache->vaddr & KMAP) {
+		struct page *page = i915_gem_object_get_page(obj, cache->page);
+
+		vaddr = kmap_atomic(page);
+		cache->vaddr = unmask_flags(cache->vaddr) |
+			(unsigned long)vaddr;
+	} else {
+		struct i915_ggtt *ggtt = cache_to_ggtt(cache);
+		unsigned long offset;
+
+		offset = cache->node.start;
+		if (!drm_mm_node_allocated(&cache->node))
+			offset += cache->page << PAGE_SHIFT;
+
+		cache->vaddr = (unsigned long)
+			io_mapping_map_atomic_wc(&ggtt->iomap, offset);
+	}
+}
+
 static void reloc_cache_reset(struct reloc_cache *cache, struct i915_execbuffer *eb)
 {
 	void *vaddr;
@@ -1324,10 +1365,17 @@ eb_relocate_entry(struct i915_execbuffer *eb,
 		 * batchbuffers.
 		 */
 		if (reloc->write_domain == I915_GEM_DOMAIN_INSTRUCTION &&
-		    GRAPHICS_VER(eb->i915) == 6) {
+		    GRAPHICS_VER(eb->i915) == 6 &&
+		    !i915_vma_is_bound(target->vma, I915_VMA_GLOBAL_BIND)) {
+			struct i915_vma *vma = target->vma;
+
+			reloc_cache_unmap(&eb->reloc_cache);
+			mutex_lock(&vma->vm->mutex);
 			err = i915_vma_bind(target->vma,
 					    target->vma->obj->cache_level,
 					    PIN_GLOBAL, NULL);
+			mutex_unlock(&vma->vm->mutex);
+			reloc_cache_remap(&eb->reloc_cache, ev->vma->obj);
 			if (err)
 				return err;
 		}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c
index 6fb9afb65034..5f48d5ea5c15 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c
@@ -224,6 +224,12 @@ void __i915_gem_free_object(struct drm_i915_gem_object *obj)
 			GEM_BUG_ON(vma->obj != obj);
 			spin_unlock(&obj->vma.lock);
 
+			/* Verify that the vma is unbound under the vm mutex. */
+			mutex_lock(&vma->vm->mutex);
+			atomic_and(~I915_VMA_PIN_MASK, &vma->flags);
+			__i915_vma_unbind(vma);
+			mutex_unlock(&vma->vm->mutex);
+
 			__i915_vma_put(vma);
 
 			spin_lock(&obj->vma.lock);
diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h
index e54351a170e2..a63631ea0ec4 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
@@ -152,6 +152,14 @@ struct intel_context {
 	/** sseu: Control eu/slice partitioning */
 	struct intel_sseu sseu;
 
+	/**
+	 * pinned_contexts_link: List link for the engine's pinned contexts.
+	 * This is only used if this is a perma-pinned kernel context and
+	 * the list is assumed to only be manipulated during driver load
+	 * or unload time so no mutex protection currently.
+	 */
+	struct list_head pinned_contexts_link;
+
 	u8 wa_bb_page; /* if set, page num reserved for context workarounds */
 
 	struct {
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 0d9105a31d84..eb99441e0ada 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -320,6 +320,7 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id)
 
 	BUILD_BUG_ON(BITS_PER_TYPE(engine->mask) < I915_NUM_ENGINES);
 
+	INIT_LIST_HEAD(&engine->pinned_contexts_list);
 	engine->id = id;
 	engine->legacy_idx = INVALID_ENGINE;
 	engine->mask = BIT(id);
@@ -875,6 +876,8 @@ intel_engine_create_pinned_context(struct intel_engine_cs *engine,
 		return ERR_PTR(err);
 	}
 
+	list_add_tail(&ce->pinned_contexts_link, &engine->pinned_contexts_list);
+
 	/*
 	 * Give our perma-pinned kernel timelines a separate lockdep class,
 	 * so that we can use them from within the normal user timelines
@@ -897,6 +900,7 @@ void intel_engine_destroy_pinned_context(struct intel_context *ce)
 	list_del(&ce->timeline->engine_link);
 	mutex_unlock(&hwsp->vm->mutex);
 
+	list_del(&ce->pinned_contexts_link);
 	intel_context_unpin(ce);
 	intel_context_put(ce);
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
index 1f07ac4e0672..dacd62773735 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
@@ -298,6 +298,29 @@ void intel_engine_init__pm(struct intel_engine_cs *engine)
 	intel_engine_init_heartbeat(engine);
 }
 
+/**
+ * intel_engine_reset_pinned_contexts - Reset the pinned contexts of
+ * an engine.
+ * @engine: The engine whose pinned contexts we want to reset.
+ *
+ * Typically the pinned context LMEM images lose or get their content
+ * corrupted on suspend. This function resets their images.
+ */
+void intel_engine_reset_pinned_contexts(struct intel_engine_cs *engine)
+{
+	struct intel_context *ce;
+
+	list_for_each_entry(ce, &engine->pinned_contexts_list,
+			    pinned_contexts_link) {
+		/* kernel context gets reset at __engine_unpark() */
+		if (ce == engine->kernel_context)
+			continue;
+
+		dbg_poison_ce(ce);
+		ce->ops->reset(ce);
+	}
+}
+
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftest_engine_pm.c"
 #endif
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.h b/drivers/gpu/drm/i915/gt/intel_engine_pm.h
index 70ea46d6cfb0..8520c595f5e1 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.h
@@ -69,4 +69,6 @@ intel_engine_create_kernel_request(struct intel_engine_cs *engine)
 
 void intel_engine_init__pm(struct intel_engine_cs *engine);
 
+void intel_engine_reset_pinned_contexts(struct intel_engine_cs *engine);
+
 #endif /* INTEL_ENGINE_PM_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index ed91bcff20eb..adc44c9fac6d 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -304,6 +304,13 @@ struct intel_engine_cs {
 
 	struct intel_context *kernel_context; /* pinned */
 
+	/**
+	 * pinned_contexts_list: List of pinned contexts. This list is only
+	 * assumed to be manipulated during driver load- or unload time and
+	 * does therefore not have any additional protection.
+	 */
+	struct list_head pinned_contexts_list;
+
 	intel_engine_mask_t saturated; /* submitting semaphores too late? */
 
 	struct {
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index cafb0608ffb4..416f5e0657f0 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -2787,6 +2787,8 @@ static void execlists_sanitize(struct intel_engine_cs *engine)
 
 	/* And scrub the dirty cachelines for the HWSP */
 	clflush_cache_range(engine->status_page.addr, PAGE_SIZE);
+
+	intel_engine_reset_pinned_contexts(engine);
 }
 
 static void enable_error_interrupt(struct intel_engine_cs *engine)
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index e1e1d17d49fd..ed8ad3b26395 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -949,6 +949,9 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt)
 	if (I915_SELFTEST_ONLY(gt->awake == -ENODEV))
 		return;
 
+	if (intel_gt_is_wedged(gt))
+		return;
+
 	if (GRAPHICS_VER(i915) == 12) {
 		regs = gen12_regs;
 		num = ARRAY_SIZE(gen12_regs);
@@ -970,6 +973,20 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt)
 	mutex_lock(&gt->tlb_invalidate_lock);
 	intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
 
+	spin_lock_irq(&uncore->lock); /* serialise invalidate with GT reset */
+
+	for_each_engine(engine, gt, id) {
+		struct reg_and_bit rb;
+
+		rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
+		if (!i915_mmio_reg_offset(rb.reg))
+			continue;
+
+		intel_uncore_write_fw(uncore, rb.reg, rb.bit);
+	}
+
+	spin_unlock_irq(&uncore->lock);
+
 	for_each_engine(engine, gt, id) {
 		/*
 		 * HW architecture suggest typical invalidation time at 40us,
@@ -984,7 +1001,6 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt)
 		if (!i915_mmio_reg_offset(rb.reg))
 			continue;
 
-		intel_uncore_write_fw(uncore, rb.reg, rb.bit);
 		if (__intel_wait_for_register_fw(uncore,
 						 rb.reg, rb.bit, 0,
 						 timeout_us, timeout_ms,
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index 91200c43951f..18b0e57c58c1 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -293,9 +293,9 @@ static int gen6_hw_domain_reset(struct intel_gt *gt, u32 hw_domain_mask)
 	return err;
 }
 
-static int gen6_reset_engines(struct intel_gt *gt,
-			      intel_engine_mask_t engine_mask,
-			      unsigned int retry)
+static int __gen6_reset_engines(struct intel_gt *gt,
+				intel_engine_mask_t engine_mask,
+				unsigned int retry)
 {
 	static const u32 hw_engine_mask[] = {
 		[RCS0]  = GEN6_GRDOM_RENDER,
@@ -322,6 +322,20 @@ static int gen6_reset_engines(struct intel_gt *gt,
 	return gen6_hw_domain_reset(gt, hw_mask);
 }
 
+static int gen6_reset_engines(struct intel_gt *gt,
+			      intel_engine_mask_t engine_mask,
+			      unsigned int retry)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&gt->uncore->lock, flags);
+	ret = __gen6_reset_engines(gt, engine_mask, retry);
+	spin_unlock_irqrestore(&gt->uncore->lock, flags);
+
+	return ret;
+}
+
 static struct intel_engine_cs *find_sfc_paired_vecs_engine(struct intel_engine_cs *engine)
 {
 	int vecs_id;
@@ -488,9 +502,9 @@ static void gen11_unlock_sfc(struct intel_engine_cs *engine)
 	rmw_clear_fw(uncore, sfc_lock.lock_reg, sfc_lock.lock_bit);
 }
 
-static int gen11_reset_engines(struct intel_gt *gt,
-			       intel_engine_mask_t engine_mask,
-			       unsigned int retry)
+static int __gen11_reset_engines(struct intel_gt *gt,
+				 intel_engine_mask_t engine_mask,
+				 unsigned int retry)
 {
 	static const u32 hw_engine_mask[] = {
 		[RCS0]  = GEN11_GRDOM_RENDER,
@@ -601,8 +615,11 @@ static int gen8_reset_engines(struct intel_gt *gt,
 	struct intel_engine_cs *engine;
 	const bool reset_non_ready = retry >= 1;
 	intel_engine_mask_t tmp;
+	unsigned long flags;
 	int ret;
 
+	spin_lock_irqsave(&gt->uncore->lock, flags);
+
 	for_each_engine_masked(engine, gt, engine_mask, tmp) {
 		ret = gen8_engine_reset_prepare(engine);
 		if (ret && !reset_non_ready)
@@ -623,15 +640,26 @@ static int gen8_reset_engines(struct intel_gt *gt,
 		 */
 	}
 
+	/*
+	 * Wa_22011100796:dg2, whenever Full soft reset is required,
+	 * reset all individual engines firstly, and then do a full soft reset.
+	 *
+	 * This is best effort, so ignore any error from the initial reset.
+	 */
+	if (IS_DG2(gt->i915) && engine_mask == ALL_ENGINES)
+		__gen11_reset_engines(gt, gt->info.engine_mask, 0);
+
 	if (GRAPHICS_VER(gt->i915) >= 11)
-		ret = gen11_reset_engines(gt, engine_mask, retry);
+		ret = __gen11_reset_engines(gt, engine_mask, retry);
 	else
-		ret = gen6_reset_engines(gt, engine_mask, retry);
+		ret = __gen6_reset_engines(gt, engine_mask, retry);
 
 skip_reset:
 	for_each_engine_masked(engine, gt, engine_mask, tmp)
 		gen8_engine_reset_cancel(engine);
 
+	spin_unlock_irqrestore(&gt->uncore->lock, flags);
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
index 2958e2fae380..02e18e70c78e 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
@@ -17,6 +17,7 @@
 #include "intel_ring.h"
 #include "shmem_utils.h"
 #include "intel_engine_heartbeat.h"
+#include "intel_engine_pm.h"
 
 /* Rough estimate of the typical request size, performing a flush,
  * set-context and then emitting the batch.
@@ -291,7 +292,9 @@ static void xcs_sanitize(struct intel_engine_cs *engine)
 	sanitize_hwsp(engine);
 
 	/* And scrub the dirty cachelines for the HWSP */
-	clflush_cache_range(engine->status_page.addr, PAGE_SIZE);
+	drm_clflush_virt_range(engine->status_page.addr, PAGE_SIZE);
+
+	intel_engine_reset_pinned_contexts(engine);
 }
 
 static void reset_prepare(struct intel_engine_cs *engine)
diff --git a/drivers/gpu/drm/i915/gt/mock_engine.c b/drivers/gpu/drm/i915/gt/mock_engine.c
index 2c1af030310c..8b89215afe46 100644
--- a/drivers/gpu/drm/i915/gt/mock_engine.c
+++ b/drivers/gpu/drm/i915/gt/mock_engine.c
@@ -376,6 +376,8 @@ int mock_engine_init(struct intel_engine_cs *engine)
 {
 	struct intel_context *ce;
 
+	INIT_LIST_HEAD(&engine->pinned_contexts_list);
+
 	engine->sched_engine = i915_sched_engine_create(ENGINE_MOCK);
 	if (!engine->sched_engine)
 		return -ENOMEM;
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index b0977a3b699b..bc2950fbbaf9 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -153,8 +153,8 @@ static int live_lrc_layout(void *arg)
 			continue;
 
 		hw = shmem_pin_map(engine->default_state);
-		if (IS_ERR(hw)) {
-			err = PTR_ERR(hw);
+		if (!hw) {
+			err = -ENOMEM;
 			break;
 		}
 		hw += LRC_STATE_OFFSET / sizeof(*hw);
@@ -329,8 +329,8 @@ static int live_lrc_fixed(void *arg)
 			continue;
 
 		hw = shmem_pin_map(engine->default_state);
-		if (IS_ERR(hw)) {
-			err = PTR_ERR(hw);
+		if (!hw) {
+			err = -ENOMEM;
 			break;
 		}
 		hw += LRC_STATE_OFFSET / sizeof(*hw);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c
index 76fe766ad1bc..bb951b8d5203 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c
@@ -159,6 +159,6 @@ int intel_guc_fw_upload(struct intel_guc *guc)
 	return 0;
 
 out:
-	intel_uc_fw_change_status(&guc->fw, INTEL_UC_FIRMWARE_FAIL);
+	intel_uc_fw_change_status(&guc->fw, INTEL_UC_FIRMWARE_LOAD_FAIL);
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 93c9de8f43e8..6e09a1cca37b 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -2347,6 +2347,8 @@ static void guc_sanitize(struct intel_engine_cs *engine)
 
 	/* And scrub the dirty cachelines for the HWSP */
 	clflush_cache_range(engine->status_page.addr, PAGE_SIZE);
+
+	intel_engine_reset_pinned_contexts(engine);
 }
 
 static void setup_hwsp(struct intel_engine_cs *engine)
@@ -2422,9 +2424,13 @@ static inline void guc_init_lrc_mapping(struct intel_guc *guc)
 	 * and even it did this code would be run again.
 	 */
 
-	for_each_engine(engine, gt, id)
-		if (engine->kernel_context)
-			guc_kernel_context_pin(guc, engine->kernel_context);
+	for_each_engine(engine, gt, id) {
+		struct intel_context *ce;
+
+		list_for_each_entry(ce, &engine->pinned_contexts_list,
+				    pinned_contexts_link)
+			guc_kernel_context_pin(guc, ce);
+	}
 }
 
 static void guc_release(struct intel_engine_cs *engine)
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
index fc5387b410a2..9ee22ac92540 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
@@ -191,7 +191,7 @@ int intel_huc_auth(struct intel_huc *huc)
 
 fail:
 	i915_probe_error(gt->i915, "HuC: Authentication failed %d\n", ret);
-	intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_FAIL);
+	intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_LOAD_FAIL);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
index 3a16d08608a5..6be7fbf9d18a 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
@@ -526,7 +526,7 @@ fail:
 	i915_probe_error(gt->i915, "Failed to load %s firmware %s (%d)\n",
 			 intel_uc_fw_type_repr(uc_fw->type), uc_fw->path,
 			 err);
-	intel_uc_fw_change_status(uc_fw, INTEL_UC_FIRMWARE_FAIL);
+	intel_uc_fw_change_status(uc_fw, INTEL_UC_FIRMWARE_LOAD_FAIL);
 	return err;
 }
 
@@ -544,7 +544,7 @@ int intel_uc_fw_init(struct intel_uc_fw *uc_fw)
 	if (err) {
 		DRM_DEBUG_DRIVER("%s fw pin-pages err=%d\n",
 				 intel_uc_fw_type_repr(uc_fw->type), err);
-		intel_uc_fw_change_status(uc_fw, INTEL_UC_FIRMWARE_FAIL);
+		intel_uc_fw_change_status(uc_fw, INTEL_UC_FIRMWARE_INIT_FAIL);
 	}
 
 	return err;
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h
index 99bb1fe1af66..c1a7246fb7d6 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h
@@ -31,11 +31,12 @@ struct intel_gt;
  * |            |    MISSING <--/    |    \--> ERROR                |
  * |   fetch    |                    V                              |
  * |            |                 AVAILABLE                         |
- * +------------+-                   |                             -+
+ * +------------+-                   |   \                         -+
+ * |            |                    |    \--> INIT FAIL            |
  * |   init     |                    V                              |
  * |            |        /------> LOADABLE <----<-----------\       |
  * +------------+-       \         /    \        \           \     -+
- * |            |         FAIL <--<      \--> TRANSFERRED     \     |
+ * |            |    LOAD FAIL <--<      \--> TRANSFERRED     \     |
  * |   upload   |                  \           /   \          /     |
  * |            |                   \---------/     \--> RUNNING    |
  * +------------+---------------------------------------------------+
@@ -49,8 +50,9 @@ enum intel_uc_fw_status {
 	INTEL_UC_FIRMWARE_MISSING, /* blob not found on the system */
 	INTEL_UC_FIRMWARE_ERROR, /* invalid format or version */
 	INTEL_UC_FIRMWARE_AVAILABLE, /* blob found and copied in mem */
+	INTEL_UC_FIRMWARE_INIT_FAIL, /* failed to prepare fw objects for load */
 	INTEL_UC_FIRMWARE_LOADABLE, /* all fw-required objects are ready */
-	INTEL_UC_FIRMWARE_FAIL, /* failed to xfer or init/auth the fw */
+	INTEL_UC_FIRMWARE_LOAD_FAIL, /* failed to xfer or init/auth the fw */
 	INTEL_UC_FIRMWARE_TRANSFERRED, /* dma xfer done */
 	INTEL_UC_FIRMWARE_RUNNING /* init/auth done */
 };
@@ -121,10 +123,12 @@ const char *intel_uc_fw_status_repr(enum intel_uc_fw_status status)
 		return "ERROR";
 	case INTEL_UC_FIRMWARE_AVAILABLE:
 		return "AVAILABLE";
+	case INTEL_UC_FIRMWARE_INIT_FAIL:
+		return "INIT FAIL";
 	case INTEL_UC_FIRMWARE_LOADABLE:
 		return "LOADABLE";
-	case INTEL_UC_FIRMWARE_FAIL:
-		return "FAIL";
+	case INTEL_UC_FIRMWARE_LOAD_FAIL:
+		return "LOAD FAIL";
 	case INTEL_UC_FIRMWARE_TRANSFERRED:
 		return "TRANSFERRED";
 	case INTEL_UC_FIRMWARE_RUNNING:
@@ -146,7 +150,8 @@ static inline int intel_uc_fw_status_to_error(enum intel_uc_fw_status status)
 		return -ENOENT;
 	case INTEL_UC_FIRMWARE_ERROR:
 		return -ENOEXEC;
-	case INTEL_UC_FIRMWARE_FAIL:
+	case INTEL_UC_FIRMWARE_INIT_FAIL:
+	case INTEL_UC_FIRMWARE_LOAD_FAIL:
 		return -EIO;
 	case INTEL_UC_FIRMWARE_SELECTED:
 		return -ESTALE;
diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index c4118b808268..11971ee929f8 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -3115,9 +3115,9 @@ void intel_gvt_update_reg_whitelist(struct intel_vgpu *vgpu)
 			continue;
 
 		vaddr = shmem_pin_map(engine->default_state);
-		if (IS_ERR(vaddr)) {
-			gvt_err("failed to map %s->default state, err:%zd\n",
-				engine->name, PTR_ERR(vaddr));
+		if (!vaddr) {
+			gvt_err("failed to map %s->default state\n",
+				engine->name);
 			return;
 		}
 
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index cde0a477fb49..7ed7dba42c83 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -909,7 +909,7 @@ static int update_fdi_rx_iir_status(struct intel_vgpu *vgpu,
 	else if (FDI_RX_IMR_TO_PIPE(offset) != INVALID_INDEX)
 		index = FDI_RX_IMR_TO_PIPE(offset);
 	else {
-		gvt_vgpu_err("Unsupport registers %x\n", offset);
+		gvt_vgpu_err("Unsupported registers %x\n", offset);
 		return -EINVAL;
 	}
 
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index dfd20060812b..3df304edabc7 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -376,6 +376,7 @@ int i915_vma_bind(struct i915_vma *vma,
 	u32 bind_flags;
 	u32 vma_flags;
 
+	lockdep_assert_held(&vma->vm->mutex);
 	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
 	GEM_BUG_ON(vma->size > vma->node.size);
 
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 1a27e4833adf..9123baf723d8 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -6638,7 +6638,10 @@ void skl_wm_get_hw_state(struct drm_i915_private *dev_priv)
 		enum plane_id plane_id;
 		u8 slices;
 
-		skl_pipe_wm_get_hw_state(crtc, &crtc_state->wm.skl.optimal);
+		memset(&crtc_state->wm.skl.optimal, 0,
+		       sizeof(crtc_state->wm.skl.optimal));
+		if (crtc_state->hw.active)
+			skl_pipe_wm_get_hw_state(crtc, &crtc_state->wm.skl.optimal);
 		crtc_state->wm.skl.raw = crtc_state->wm.skl.optimal;
 
 		memset(&dbuf_state->ddb[pipe], 0, sizeof(dbuf_state->ddb[pipe]));
@@ -6649,6 +6652,9 @@ void skl_wm_get_hw_state(struct drm_i915_private *dev_priv)
 			struct skl_ddb_entry *ddb_uv =
 				&crtc_state->wm.skl.plane_ddb_uv[plane_id];
 
+			if (!crtc_state->hw.active)
+				continue;
+
 			skl_ddb_get_hw_plane_state(dev_priv, crtc->pipe,
 						   plane_id, ddb_y, ddb_uv);
 
diff --git a/drivers/gpu/drm/imx/dcss/dcss-dev.c b/drivers/gpu/drm/imx/dcss/dcss-dev.c
index e24671382435..a964cb6c9c58 100644
--- a/drivers/gpu/drm/imx/dcss/dcss-dev.c
+++ b/drivers/gpu/drm/imx/dcss/dcss-dev.c
@@ -261,6 +261,7 @@ struct dcss_dev *dcss_dev_create(struct device *dev, bool hdmi_output)
 
 	ret = dcss_submodules_init(dcss);
 	if (ret) {
+		of_node_put(dcss->of_port);
 		dev_err(dev, "submodules initialization failed\n");
 		goto clks_err;
 	}
@@ -291,6 +292,8 @@ void dcss_dev_destroy(struct dcss_dev *dcss)
 		dcss_clocks_disable(dcss);
 	}
 
+	of_node_put(dcss->of_port);
+
 	pm_runtime_disable(dcss->dev);
 
 	dcss_submodules_stop(dcss);
diff --git a/drivers/gpu/drm/lima/lima_gem.c b/drivers/gpu/drm/lima/lima_gem.c
index de62966243cd..09ea621a4806 100644
--- a/drivers/gpu/drm/lima/lima_gem.c
+++ b/drivers/gpu/drm/lima/lima_gem.c
@@ -127,7 +127,7 @@ int lima_gem_create_handle(struct drm_device *dev, struct drm_file *file,
 		if (err)
 			goto out;
 	} else {
-		struct sg_table *sgt = drm_gem_shmem_get_pages_sgt(obj);
+		struct sg_table *sgt = drm_gem_shmem_get_pages_sgt(shmem);
 
 		if (IS_ERR(sgt)) {
 			err = PTR_ERR(sgt);
@@ -151,7 +151,7 @@ static void lima_gem_free_object(struct drm_gem_object *obj)
 	if (!list_empty(&bo->va))
 		dev_err(obj->dev->dev, "lima gem free bo still has va\n");
 
-	drm_gem_shmem_free_object(obj);
+	drm_gem_shmem_free(&bo->base);
 }
 
 static int lima_gem_object_open(struct drm_gem_object *obj, struct drm_file *file)
@@ -179,7 +179,7 @@ static int lima_gem_pin(struct drm_gem_object *obj)
 	if (bo->heap_size)
 		return -EINVAL;
 
-	return drm_gem_shmem_pin(obj);
+	return drm_gem_shmem_pin(&bo->base);
 }
 
 static int lima_gem_vmap(struct drm_gem_object *obj, struct dma_buf_map *map)
@@ -189,7 +189,7 @@ static int lima_gem_vmap(struct drm_gem_object *obj, struct dma_buf_map *map)
 	if (bo->heap_size)
 		return -EINVAL;
 
-	return drm_gem_shmem_vmap(obj, map);
+	return drm_gem_shmem_vmap(&bo->base, map);
 }
 
 static int lima_gem_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
@@ -199,19 +199,19 @@ static int lima_gem_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
 	if (bo->heap_size)
 		return -EINVAL;
 
-	return drm_gem_shmem_mmap(obj, vma);
+	return drm_gem_shmem_mmap(&bo->base, vma);
 }
 
 static const struct drm_gem_object_funcs lima_gem_funcs = {
 	.free = lima_gem_free_object,
 	.open = lima_gem_object_open,
 	.close = lima_gem_object_close,
-	.print_info = drm_gem_shmem_print_info,
+	.print_info = drm_gem_shmem_object_print_info,
 	.pin = lima_gem_pin,
-	.unpin = drm_gem_shmem_unpin,
-	.get_sg_table = drm_gem_shmem_get_sg_table,
+	.unpin = drm_gem_shmem_object_unpin,
+	.get_sg_table = drm_gem_shmem_object_get_sg_table,
 	.vmap = lima_gem_vmap,
-	.vunmap = drm_gem_shmem_vunmap,
+	.vunmap = drm_gem_shmem_object_vunmap,
 	.mmap = lima_gem_mmap,
 };
 
diff --git a/drivers/gpu/drm/lima/lima_sched.c b/drivers/gpu/drm/lima/lima_sched.c
index dba8329937a3..2e817dbdcad7 100644
--- a/drivers/gpu/drm/lima/lima_sched.c
+++ b/drivers/gpu/drm/lima/lima_sched.c
@@ -390,7 +390,7 @@ static void lima_sched_build_error_task_list(struct lima_sched_task *task)
 		} else {
 			buffer_chunk->size = lima_bo_size(bo);
 
-			ret = drm_gem_shmem_vmap(&bo->base.base, &map);
+			ret = drm_gem_shmem_vmap(&bo->base, &map);
 			if (ret) {
 				kvfree(et);
 				goto out;
@@ -398,7 +398,7 @@ static void lima_sched_build_error_task_list(struct lima_sched_task *task)
 
 			memcpy(buffer_chunk + 1, map.vaddr, buffer_chunk->size);
 
-			drm_gem_shmem_vunmap(&bo->base.base, &map);
+			drm_gem_shmem_vunmap(&bo->base, &map);
 		}
 
 		buffer_chunk = (void *)(buffer_chunk + 1) + buffer_chunk->size;
diff --git a/drivers/gpu/drm/mcde/mcde_dsi.c b/drivers/gpu/drm/mcde/mcde_dsi.c
index 180ebbccbeda..0b58d7f4ba78 100644
--- a/drivers/gpu/drm/mcde/mcde_dsi.c
+++ b/drivers/gpu/drm/mcde/mcde_dsi.c
@@ -1111,6 +1111,7 @@ static int mcde_dsi_bind(struct device *dev, struct device *master,
 			bridge = of_drm_find_bridge(child);
 			if (!bridge) {
 				dev_err(dev, "failed to find bridge\n");
+				of_node_put(child);
 				return -EINVAL;
 			}
 		}
diff --git a/drivers/gpu/drm/mediatek/mtk_disp_drv.h b/drivers/gpu/drm/mediatek/mtk_disp_drv.h
index 86c3068894b1..974462831133 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_drv.h
+++ b/drivers/gpu/drm/mediatek/mtk_disp_drv.h
@@ -76,9 +76,11 @@ void mtk_ovl_layer_off(struct device *dev, unsigned int idx,
 void mtk_ovl_start(struct device *dev);
 void mtk_ovl_stop(struct device *dev);
 unsigned int mtk_ovl_supported_rotations(struct device *dev);
-void mtk_ovl_enable_vblank(struct device *dev,
-			   void (*vblank_cb)(void *),
-			   void *vblank_cb_data);
+void mtk_ovl_register_vblank_cb(struct device *dev,
+				void (*vblank_cb)(void *),
+				void *vblank_cb_data);
+void mtk_ovl_unregister_vblank_cb(struct device *dev);
+void mtk_ovl_enable_vblank(struct device *dev);
 void mtk_ovl_disable_vblank(struct device *dev);
 
 void mtk_rdma_bypass_shadow(struct device *dev);
@@ -93,9 +95,11 @@ void mtk_rdma_layer_config(struct device *dev, unsigned int idx,
 			   struct cmdq_pkt *cmdq_pkt);
 void mtk_rdma_start(struct device *dev);
 void mtk_rdma_stop(struct device *dev);
-void mtk_rdma_enable_vblank(struct device *dev,
-			    void (*vblank_cb)(void *),
-			    void *vblank_cb_data);
+void mtk_rdma_register_vblank_cb(struct device *dev,
+				 void (*vblank_cb)(void *),
+				 void *vblank_cb_data);
+void mtk_rdma_unregister_vblank_cb(struct device *dev);
+void mtk_rdma_enable_vblank(struct device *dev);
 void mtk_rdma_disable_vblank(struct device *dev);
 
 #endif
diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
index 5326989d5206..411cf0f21661 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
+++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
@@ -96,14 +96,28 @@ static irqreturn_t mtk_disp_ovl_irq_handler(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-void mtk_ovl_enable_vblank(struct device *dev,
-			   void (*vblank_cb)(void *),
-			   void *vblank_cb_data)
+void mtk_ovl_register_vblank_cb(struct device *dev,
+				void (*vblank_cb)(void *),
+				void *vblank_cb_data)
 {
 	struct mtk_disp_ovl *ovl = dev_get_drvdata(dev);
 
 	ovl->vblank_cb = vblank_cb;
 	ovl->vblank_cb_data = vblank_cb_data;
+}
+
+void mtk_ovl_unregister_vblank_cb(struct device *dev)
+{
+	struct mtk_disp_ovl *ovl = dev_get_drvdata(dev);
+
+	ovl->vblank_cb = NULL;
+	ovl->vblank_cb_data = NULL;
+}
+
+void mtk_ovl_enable_vblank(struct device *dev)
+{
+	struct mtk_disp_ovl *ovl = dev_get_drvdata(dev);
+
 	writel(0x0, ovl->regs + DISP_REG_OVL_INTSTA);
 	writel_relaxed(OVL_FME_CPL_INT, ovl->regs + DISP_REG_OVL_INTEN);
 }
@@ -112,8 +126,6 @@ void mtk_ovl_disable_vblank(struct device *dev)
 {
 	struct mtk_disp_ovl *ovl = dev_get_drvdata(dev);
 
-	ovl->vblank_cb = NULL;
-	ovl->vblank_cb_data = NULL;
 	writel_relaxed(0x0, ovl->regs + DISP_REG_OVL_INTEN);
 }
 
diff --git a/drivers/gpu/drm/mediatek/mtk_disp_rdma.c b/drivers/gpu/drm/mediatek/mtk_disp_rdma.c
index 75d7f45579e2..a6a6cb5f75af 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_rdma.c
+++ b/drivers/gpu/drm/mediatek/mtk_disp_rdma.c
@@ -94,24 +94,32 @@ static void rdma_update_bits(struct device *dev, unsigned int reg,
 	writel(tmp, rdma->regs + reg);
 }
 
-void mtk_rdma_enable_vblank(struct device *dev,
-			    void (*vblank_cb)(void *),
-			    void *vblank_cb_data)
+void mtk_rdma_register_vblank_cb(struct device *dev,
+				 void (*vblank_cb)(void *),
+				 void *vblank_cb_data)
 {
 	struct mtk_disp_rdma *rdma = dev_get_drvdata(dev);
 
 	rdma->vblank_cb = vblank_cb;
 	rdma->vblank_cb_data = vblank_cb_data;
-	rdma_update_bits(dev, DISP_REG_RDMA_INT_ENABLE, RDMA_FRAME_END_INT,
-			 RDMA_FRAME_END_INT);
 }
 
-void mtk_rdma_disable_vblank(struct device *dev)
+void mtk_rdma_unregister_vblank_cb(struct device *dev)
 {
 	struct mtk_disp_rdma *rdma = dev_get_drvdata(dev);
 
 	rdma->vblank_cb = NULL;
 	rdma->vblank_cb_data = NULL;
+}
+
+void mtk_rdma_enable_vblank(struct device *dev)
+{
+	rdma_update_bits(dev, DISP_REG_RDMA_INT_ENABLE, RDMA_FRAME_END_INT,
+			 RDMA_FRAME_END_INT);
+}
+
+void mtk_rdma_disable_vblank(struct device *dev)
+{
 	rdma_update_bits(dev, DISP_REG_RDMA_INT_ENABLE, RDMA_FRAME_END_INT, 0);
 }
 
diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c
index e61cd67b978f..41c783349321 100644
--- a/drivers/gpu/drm/mediatek/mtk_dpi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dpi.c
@@ -54,13 +54,7 @@ enum mtk_dpi_out_channel_swap {
 };
 
 enum mtk_dpi_out_color_format {
-	MTK_DPI_COLOR_FORMAT_RGB,
-	MTK_DPI_COLOR_FORMAT_RGB_FULL,
-	MTK_DPI_COLOR_FORMAT_YCBCR_444,
-	MTK_DPI_COLOR_FORMAT_YCBCR_422,
-	MTK_DPI_COLOR_FORMAT_XV_YCC,
-	MTK_DPI_COLOR_FORMAT_YCBCR_444_FULL,
-	MTK_DPI_COLOR_FORMAT_YCBCR_422_FULL
+	MTK_DPI_COLOR_FORMAT_RGB
 };
 
 struct mtk_dpi {
@@ -364,24 +358,11 @@ static void mtk_dpi_config_disable_edge(struct mtk_dpi *dpi)
 static void mtk_dpi_config_color_format(struct mtk_dpi *dpi,
 					enum mtk_dpi_out_color_format format)
 {
-	if ((format == MTK_DPI_COLOR_FORMAT_YCBCR_444) ||
-	    (format == MTK_DPI_COLOR_FORMAT_YCBCR_444_FULL)) {
-		mtk_dpi_config_yuv422_enable(dpi, false);
-		mtk_dpi_config_csc_enable(dpi, true);
-		mtk_dpi_config_swap_input(dpi, false);
-		mtk_dpi_config_channel_swap(dpi, MTK_DPI_OUT_CHANNEL_SWAP_BGR);
-	} else if ((format == MTK_DPI_COLOR_FORMAT_YCBCR_422) ||
-		   (format == MTK_DPI_COLOR_FORMAT_YCBCR_422_FULL)) {
-		mtk_dpi_config_yuv422_enable(dpi, true);
-		mtk_dpi_config_csc_enable(dpi, true);
-		mtk_dpi_config_swap_input(dpi, true);
-		mtk_dpi_config_channel_swap(dpi, MTK_DPI_OUT_CHANNEL_SWAP_RGB);
-	} else {
-		mtk_dpi_config_yuv422_enable(dpi, false);
-		mtk_dpi_config_csc_enable(dpi, false);
-		mtk_dpi_config_swap_input(dpi, false);
-		mtk_dpi_config_channel_swap(dpi, MTK_DPI_OUT_CHANNEL_SWAP_RGB);
-	}
+	/* only support RGB888 */
+	mtk_dpi_config_yuv422_enable(dpi, false);
+	mtk_dpi_config_csc_enable(dpi, false);
+	mtk_dpi_config_swap_input(dpi, false);
+	mtk_dpi_config_channel_swap(dpi, MTK_DPI_OUT_CHANNEL_SWAP_RGB);
 }
 
 static void mtk_dpi_dual_edge(struct mtk_dpi *dpi)
@@ -436,7 +417,6 @@ static int mtk_dpi_power_on(struct mtk_dpi *dpi)
 	if (dpi->pinctrl && dpi->pins_dpi)
 		pinctrl_select_state(dpi->pinctrl, dpi->pins_dpi);
 
-	mtk_dpi_enable(dpi);
 	return 0;
 
 err_pixel:
@@ -658,6 +638,7 @@ static void mtk_dpi_bridge_enable(struct drm_bridge *bridge)
 
 	mtk_dpi_power_on(dpi);
 	mtk_dpi_set_display_mode(dpi, &dpi->mode);
+	mtk_dpi_enable(dpi);
 }
 
 static enum drm_mode_status
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
index a4e80e499674..34bb6c713a90 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
@@ -4,6 +4,8 @@
  */
 
 #include <linux/clk.h>
+#include <linux/dma-mapping.h>
+#include <linux/mailbox_controller.h>
 #include <linux/pm_runtime.h>
 #include <linux/soc/mediatek/mtk-cmdq.h>
 #include <linux/soc/mediatek/mtk-mmsys.h>
@@ -50,8 +52,10 @@ struct mtk_drm_crtc {
 	bool				pending_async_planes;
 
 #if IS_REACHABLE(CONFIG_MTK_CMDQ)
-	struct cmdq_client		*cmdq_client;
+	struct cmdq_client		cmdq_client;
+	struct cmdq_pkt			cmdq_handle;
 	u32				cmdq_event;
+	u32				cmdq_vblank_cnt;
 #endif
 
 	struct device			*mmsys_dev;
@@ -104,11 +108,63 @@ static void mtk_drm_finish_page_flip(struct mtk_drm_crtc *mtk_crtc)
 	}
 }
 
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+static int mtk_drm_cmdq_pkt_create(struct cmdq_client *client, struct cmdq_pkt *pkt,
+				   size_t size)
+{
+	struct device *dev;
+	dma_addr_t dma_addr;
+
+	pkt->va_base = kzalloc(size, GFP_KERNEL);
+	if (!pkt->va_base) {
+		kfree(pkt);
+		return -ENOMEM;
+	}
+	pkt->buf_size = size;
+	pkt->cl = (void *)client;
+
+	dev = client->chan->mbox->dev;
+	dma_addr = dma_map_single(dev, pkt->va_base, pkt->buf_size,
+				  DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, dma_addr)) {
+		dev_err(dev, "dma map failed, size=%u\n", (u32)(u64)size);
+		kfree(pkt->va_base);
+		kfree(pkt);
+		return -ENOMEM;
+	}
+
+	pkt->pa_base = dma_addr;
+
+	return 0;
+}
+
+static void mtk_drm_cmdq_pkt_destroy(struct cmdq_pkt *pkt)
+{
+	struct cmdq_client *client = (struct cmdq_client *)pkt->cl;
+
+	dma_unmap_single(client->chan->mbox->dev, pkt->pa_base, pkt->buf_size,
+			 DMA_TO_DEVICE);
+	kfree(pkt->va_base);
+	kfree(pkt);
+}
+#endif
+
 static void mtk_drm_crtc_destroy(struct drm_crtc *crtc)
 {
 	struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc);
+	int i;
 
 	mtk_mutex_put(mtk_crtc->mutex);
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	mtk_drm_cmdq_pkt_destroy(&mtk_crtc->cmdq_handle);
+#endif
+
+	for (i = 0; i < mtk_crtc->ddp_comp_nr; i++) {
+		struct mtk_ddp_comp *comp;
+
+		comp = mtk_crtc->ddp_comp[i];
+		mtk_ddp_comp_unregister_vblank_cb(comp);
+	}
 
 	drm_crtc_cleanup(crtc);
 }
@@ -222,9 +278,12 @@ struct mtk_ddp_comp *mtk_drm_ddp_comp_for_plane(struct drm_crtc *crtc,
 }
 
 #if IS_REACHABLE(CONFIG_MTK_CMDQ)
-static void ddp_cmdq_cb(struct cmdq_cb_data data)
+static void ddp_cmdq_cb(struct mbox_client *cl, void *mssg)
 {
-	cmdq_pkt_destroy(data.data);
+	struct cmdq_client *cmdq_cl = container_of(cl, struct cmdq_client, client);
+	struct mtk_drm_crtc *mtk_crtc = container_of(cmdq_cl, struct mtk_drm_crtc, cmdq_client);
+
+	mtk_crtc->cmdq_vblank_cnt = 0;
 }
 #endif
 
@@ -430,7 +489,7 @@ static void mtk_drm_crtc_update_config(struct mtk_drm_crtc *mtk_crtc,
 				       bool needs_vblank)
 {
 #if IS_REACHABLE(CONFIG_MTK_CMDQ)
-	struct cmdq_pkt *cmdq_handle;
+	struct cmdq_pkt *cmdq_handle = &mtk_crtc->cmdq_handle;
 #endif
 	struct drm_crtc *crtc = &mtk_crtc->base;
 	struct mtk_drm_private *priv = crtc->dev->dev_private;
@@ -468,14 +527,28 @@ static void mtk_drm_crtc_update_config(struct mtk_drm_crtc *mtk_crtc,
 		mtk_mutex_release(mtk_crtc->mutex);
 	}
 #if IS_REACHABLE(CONFIG_MTK_CMDQ)
-	if (mtk_crtc->cmdq_client) {
-		mbox_flush(mtk_crtc->cmdq_client->chan, 2000);
-		cmdq_handle = cmdq_pkt_create(mtk_crtc->cmdq_client, PAGE_SIZE);
+	if (mtk_crtc->cmdq_client.chan) {
+		mbox_flush(mtk_crtc->cmdq_client.chan, 2000);
+		cmdq_handle->cmd_buf_size = 0;
 		cmdq_pkt_clear_event(cmdq_handle, mtk_crtc->cmdq_event);
 		cmdq_pkt_wfe(cmdq_handle, mtk_crtc->cmdq_event, false);
 		mtk_crtc_ddp_config(crtc, cmdq_handle);
 		cmdq_pkt_finalize(cmdq_handle);
-		cmdq_pkt_flush_async(cmdq_handle, ddp_cmdq_cb, cmdq_handle);
+		dma_sync_single_for_device(mtk_crtc->cmdq_client.chan->mbox->dev,
+					   cmdq_handle->pa_base,
+					   cmdq_handle->cmd_buf_size,
+					   DMA_TO_DEVICE);
+		/*
+		 * CMDQ command should execute in next 3 vblank.
+		 * One vblank interrupt before send message (occasionally)
+		 * and one vblank interrupt after cmdq done,
+		 * so it's timeout after 3 vblank interrupt.
+		 * If it fail to execute in next 3 vblank, timeout happen.
+		 */
+		mtk_crtc->cmdq_vblank_cnt = 3;
+
+		mbox_send_message(mtk_crtc->cmdq_client.chan, cmdq_handle);
+		mbox_client_txdone(mtk_crtc->cmdq_client.chan, 0);
 	}
 #endif
 	mtk_crtc->config_updating = false;
@@ -489,12 +562,15 @@ static void mtk_crtc_ddp_irq(void *data)
 	struct mtk_drm_private *priv = crtc->dev->dev_private;
 
 #if IS_REACHABLE(CONFIG_MTK_CMDQ)
-	if (!priv->data->shadow_register && !mtk_crtc->cmdq_client)
+	if (!priv->data->shadow_register && !mtk_crtc->cmdq_client.chan)
+		mtk_crtc_ddp_config(crtc, NULL);
+	else if (mtk_crtc->cmdq_vblank_cnt > 0 && --mtk_crtc->cmdq_vblank_cnt == 0)
+		DRM_ERROR("mtk_crtc %d CMDQ execute command timeout!\n",
+			  drm_crtc_index(&mtk_crtc->base));
 #else
 	if (!priv->data->shadow_register)
-#endif
 		mtk_crtc_ddp_config(crtc, NULL);
-
+#endif
 	mtk_drm_finish_page_flip(mtk_crtc);
 }
 
@@ -503,7 +579,7 @@ static int mtk_drm_crtc_enable_vblank(struct drm_crtc *crtc)
 	struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc);
 	struct mtk_ddp_comp *comp = mtk_crtc->ddp_comp[0];
 
-	mtk_ddp_comp_enable_vblank(comp, mtk_crtc_ddp_irq, &mtk_crtc->base);
+	mtk_ddp_comp_enable_vblank(comp);
 
 	return 0;
 }
@@ -803,6 +879,9 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 			if (comp->funcs->ctm_set)
 				has_ctm = true;
 		}
+
+		mtk_ddp_comp_register_vblank_cb(comp, mtk_crtc_ddp_irq,
+						&mtk_crtc->base);
 	}
 
 	for (i = 0; i < mtk_crtc->ddp_comp_nr; i++)
@@ -829,16 +908,20 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 	mutex_init(&mtk_crtc->hw_lock);
 
 #if IS_REACHABLE(CONFIG_MTK_CMDQ)
-	mtk_crtc->cmdq_client =
-			cmdq_mbox_create(mtk_crtc->mmsys_dev,
-					 drm_crtc_index(&mtk_crtc->base));
-	if (IS_ERR(mtk_crtc->cmdq_client)) {
+	mtk_crtc->cmdq_client.client.dev = mtk_crtc->mmsys_dev;
+	mtk_crtc->cmdq_client.client.tx_block = false;
+	mtk_crtc->cmdq_client.client.knows_txdone = true;
+	mtk_crtc->cmdq_client.client.rx_callback = ddp_cmdq_cb;
+	mtk_crtc->cmdq_client.chan =
+			mbox_request_channel(&mtk_crtc->cmdq_client.client,
+					     drm_crtc_index(&mtk_crtc->base));
+	if (IS_ERR(mtk_crtc->cmdq_client.chan)) {
 		dev_dbg(dev, "mtk_crtc %d failed to create mailbox client, writing register by CPU now\n",
 			drm_crtc_index(&mtk_crtc->base));
-		mtk_crtc->cmdq_client = NULL;
+		mtk_crtc->cmdq_client.chan = NULL;
 	}
 
-	if (mtk_crtc->cmdq_client) {
+	if (mtk_crtc->cmdq_client.chan) {
 		ret = of_property_read_u32_index(priv->mutex_node,
 						 "mediatek,gce-events",
 						 drm_crtc_index(&mtk_crtc->base),
@@ -846,8 +929,18 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 		if (ret) {
 			dev_dbg(dev, "mtk_crtc %d failed to get mediatek,gce-events property\n",
 				drm_crtc_index(&mtk_crtc->base));
-			cmdq_mbox_destroy(mtk_crtc->cmdq_client);
-			mtk_crtc->cmdq_client = NULL;
+			mbox_free_channel(mtk_crtc->cmdq_client.chan);
+			mtk_crtc->cmdq_client.chan = NULL;
+		} else {
+			ret = mtk_drm_cmdq_pkt_create(&mtk_crtc->cmdq_client,
+						      &mtk_crtc->cmdq_handle,
+						      PAGE_SIZE);
+			if (ret) {
+				dev_dbg(dev, "mtk_crtc %d failed to create cmdq packet\n",
+					drm_crtc_index(&mtk_crtc->base));
+				mbox_free_channel(mtk_crtc->cmdq_client.chan);
+				mtk_crtc->cmdq_client.chan = NULL;
+			}
 		}
 	}
 #endif
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
index 99cbf44463e4..22d23668b484 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
@@ -276,6 +276,8 @@ static const struct mtk_ddp_comp_funcs ddp_ovl = {
 	.config = mtk_ovl_config,
 	.start = mtk_ovl_start,
 	.stop = mtk_ovl_stop,
+	.register_vblank_cb = mtk_ovl_register_vblank_cb,
+	.unregister_vblank_cb = mtk_ovl_unregister_vblank_cb,
 	.enable_vblank = mtk_ovl_enable_vblank,
 	.disable_vblank = mtk_ovl_disable_vblank,
 	.supported_rotations = mtk_ovl_supported_rotations,
@@ -292,6 +294,8 @@ static const struct mtk_ddp_comp_funcs ddp_rdma = {
 	.config = mtk_rdma_config,
 	.start = mtk_rdma_start,
 	.stop = mtk_rdma_stop,
+	.register_vblank_cb = mtk_rdma_register_vblank_cb,
+	.unregister_vblank_cb = mtk_rdma_unregister_vblank_cb,
 	.enable_vblank = mtk_rdma_enable_vblank,
 	.disable_vblank = mtk_rdma_disable_vblank,
 	.layer_nr = mtk_rdma_layer_nr,
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
index bb914d976cf5..25cb50f2391f 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
@@ -47,9 +47,11 @@ struct mtk_ddp_comp_funcs {
 		       unsigned int bpc, struct cmdq_pkt *cmdq_pkt);
 	void (*start)(struct device *dev);
 	void (*stop)(struct device *dev);
-	void (*enable_vblank)(struct device *dev,
-			      void (*vblank_cb)(void *),
-			      void *vblank_cb_data);
+	void (*register_vblank_cb)(struct device *dev,
+				   void (*vblank_cb)(void *),
+				   void *vblank_cb_data);
+	void (*unregister_vblank_cb)(struct device *dev);
+	void (*enable_vblank)(struct device *dev);
 	void (*disable_vblank)(struct device *dev);
 	unsigned int (*supported_rotations)(struct device *dev);
 	unsigned int (*layer_nr)(struct device *dev);
@@ -110,12 +112,25 @@ static inline void mtk_ddp_comp_stop(struct mtk_ddp_comp *comp)
 		comp->funcs->stop(comp->dev);
 }
 
-static inline void mtk_ddp_comp_enable_vblank(struct mtk_ddp_comp *comp,
-					      void (*vblank_cb)(void *),
-					      void *vblank_cb_data)
+static inline void mtk_ddp_comp_register_vblank_cb(struct mtk_ddp_comp *comp,
+						   void (*vblank_cb)(void *),
+						   void *vblank_cb_data)
+{
+	if (comp->funcs && comp->funcs->register_vblank_cb)
+		comp->funcs->register_vblank_cb(comp->dev, vblank_cb,
+						vblank_cb_data);
+}
+
+static inline void mtk_ddp_comp_unregister_vblank_cb(struct mtk_ddp_comp *comp)
+{
+	if (comp->funcs && comp->funcs->unregister_vblank_cb)
+		comp->funcs->unregister_vblank_cb(comp->dev);
+}
+
+static inline void mtk_ddp_comp_enable_vblank(struct mtk_ddp_comp *comp)
 {
 	if (comp->funcs && comp->funcs->enable_vblank)
-		comp->funcs->enable_vblank(comp->dev, vblank_cb, vblank_cb_data);
+		comp->funcs->enable_vblank(comp->dev);
 }
 
 static inline void mtk_ddp_comp_disable_vblank(struct mtk_ddp_comp *comp)
diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index 5d90d2eb0019..ac14e598a14f 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -203,6 +203,7 @@ struct mtk_dsi {
 	struct mtk_phy_timing phy_timing;
 	int refcount;
 	bool enabled;
+	bool lanes_ready;
 	u32 irq_data;
 	wait_queue_head_t irq_wait_queue;
 	const struct mtk_dsi_driver_data *driver_data;
@@ -649,18 +650,11 @@ static int mtk_dsi_poweron(struct mtk_dsi *dsi)
 	mtk_dsi_reset_engine(dsi);
 	mtk_dsi_phy_timconfig(dsi);
 
-	mtk_dsi_rxtx_control(dsi);
-	usleep_range(30, 100);
-	mtk_dsi_reset_dphy(dsi);
 	mtk_dsi_ps_control_vact(dsi);
 	mtk_dsi_set_vm_cmd(dsi);
 	mtk_dsi_config_vdo_timing(dsi);
 	mtk_dsi_set_interrupt_enable(dsi);
 
-	mtk_dsi_clk_ulp_mode_leave(dsi);
-	mtk_dsi_lane0_ulp_mode_leave(dsi);
-	mtk_dsi_clk_hs_mode(dsi, 0);
-
 	return 0;
 err_disable_engine_clk:
 	clk_disable_unprepare(dsi->engine_clk);
@@ -679,19 +673,11 @@ static void mtk_dsi_poweroff(struct mtk_dsi *dsi)
 	if (--dsi->refcount != 0)
 		return;
 
-	/*
-	 * mtk_dsi_stop() and mtk_dsi_start() is asymmetric, since
-	 * mtk_dsi_stop() should be called after mtk_drm_crtc_atomic_disable(),
-	 * which needs irq for vblank, and mtk_dsi_stop() will disable irq.
-	 * mtk_dsi_start() needs to be called in mtk_output_dsi_enable(),
-	 * after dsi is fully set.
-	 */
-	mtk_dsi_stop(dsi);
-
-	mtk_dsi_switch_to_cmd_mode(dsi, VM_DONE_INT_FLAG, 500);
 	mtk_dsi_reset_engine(dsi);
 	mtk_dsi_lane0_ulp_mode_enter(dsi);
 	mtk_dsi_clk_ulp_mode_enter(dsi);
+	/* set the lane number as 0 to pull down mipi */
+	writel(0, dsi->regs + DSI_TXRX_CTRL);
 
 	mtk_dsi_disable(dsi);
 
@@ -699,21 +685,31 @@ static void mtk_dsi_poweroff(struct mtk_dsi *dsi)
 	clk_disable_unprepare(dsi->digital_clk);
 
 	phy_power_off(dsi->phy);
+
+	dsi->lanes_ready = false;
 }
 
-static void mtk_output_dsi_enable(struct mtk_dsi *dsi)
+static void mtk_dsi_lane_ready(struct mtk_dsi *dsi)
 {
-	int ret;
+	if (!dsi->lanes_ready) {
+		dsi->lanes_ready = true;
+		mtk_dsi_rxtx_control(dsi);
+		usleep_range(30, 100);
+		mtk_dsi_reset_dphy(dsi);
+		mtk_dsi_clk_ulp_mode_leave(dsi);
+		mtk_dsi_lane0_ulp_mode_leave(dsi);
+		mtk_dsi_clk_hs_mode(dsi, 0);
+		msleep(20);
+		/* The reaction time after pulling up the mipi signal for dsi_rx */
+	}
+}
 
+static void mtk_output_dsi_enable(struct mtk_dsi *dsi)
+{
 	if (dsi->enabled)
 		return;
 
-	ret = mtk_dsi_poweron(dsi);
-	if (ret < 0) {
-		DRM_ERROR("failed to power on dsi\n");
-		return;
-	}
-
+	mtk_dsi_lane_ready(dsi);
 	mtk_dsi_set_mode(dsi);
 	mtk_dsi_clk_hs_mode(dsi, 1);
 
@@ -727,7 +723,16 @@ static void mtk_output_dsi_disable(struct mtk_dsi *dsi)
 	if (!dsi->enabled)
 		return;
 
-	mtk_dsi_poweroff(dsi);
+	/*
+	 * mtk_dsi_stop() and mtk_dsi_start() is asymmetric, since
+	 * mtk_dsi_stop() should be called after mtk_drm_crtc_atomic_disable(),
+	 * which needs irq for vblank, and mtk_dsi_stop() will disable irq.
+	 * mtk_dsi_start() needs to be called in mtk_output_dsi_enable(),
+	 * after dsi is fully set.
+	 */
+	mtk_dsi_stop(dsi);
+
+	mtk_dsi_switch_to_cmd_mode(dsi, VM_DONE_INT_FLAG, 500);
 
 	dsi->enabled = false;
 }
@@ -751,24 +756,50 @@ static void mtk_dsi_bridge_mode_set(struct drm_bridge *bridge,
 	drm_display_mode_to_videomode(adjusted, &dsi->vm);
 }
 
-static void mtk_dsi_bridge_disable(struct drm_bridge *bridge)
+static void mtk_dsi_bridge_atomic_disable(struct drm_bridge *bridge,
+					  struct drm_bridge_state *old_bridge_state)
 {
 	struct mtk_dsi *dsi = bridge_to_dsi(bridge);
 
 	mtk_output_dsi_disable(dsi);
 }
 
-static void mtk_dsi_bridge_enable(struct drm_bridge *bridge)
+static void mtk_dsi_bridge_atomic_enable(struct drm_bridge *bridge,
+					 struct drm_bridge_state *old_bridge_state)
 {
 	struct mtk_dsi *dsi = bridge_to_dsi(bridge);
 
+	if (dsi->refcount == 0)
+		return;
+
 	mtk_output_dsi_enable(dsi);
 }
 
+static void mtk_dsi_bridge_atomic_pre_enable(struct drm_bridge *bridge,
+					     struct drm_bridge_state *old_bridge_state)
+{
+	struct mtk_dsi *dsi = bridge_to_dsi(bridge);
+	int ret;
+
+	ret = mtk_dsi_poweron(dsi);
+	if (ret < 0)
+		DRM_ERROR("failed to power on dsi\n");
+}
+
+static void mtk_dsi_bridge_atomic_post_disable(struct drm_bridge *bridge,
+					       struct drm_bridge_state *old_bridge_state)
+{
+	struct mtk_dsi *dsi = bridge_to_dsi(bridge);
+
+	mtk_dsi_poweroff(dsi);
+}
+
 static const struct drm_bridge_funcs mtk_dsi_bridge_funcs = {
 	.attach = mtk_dsi_bridge_attach,
-	.disable = mtk_dsi_bridge_disable,
-	.enable = mtk_dsi_bridge_enable,
+	.atomic_disable = mtk_dsi_bridge_atomic_disable,
+	.atomic_enable = mtk_dsi_bridge_atomic_enable,
+	.atomic_pre_enable = mtk_dsi_bridge_atomic_pre_enable,
+	.atomic_post_disable = mtk_dsi_bridge_atomic_post_disable,
 	.mode_set = mtk_dsi_bridge_mode_set,
 };
 
@@ -891,24 +922,35 @@ static ssize_t mtk_dsi_host_transfer(struct mipi_dsi_host *host,
 	u8 read_data[16];
 	void *src_addr;
 	u8 irq_flag = CMD_DONE_INT_FLAG;
+	u32 dsi_mode;
+	int ret;
 
-	if (readl(dsi->regs + DSI_MODE_CTRL) & MODE) {
-		DRM_ERROR("dsi engine is not command mode\n");
-		return -EINVAL;
+	dsi_mode = readl(dsi->regs + DSI_MODE_CTRL);
+	if (dsi_mode & MODE) {
+		mtk_dsi_stop(dsi);
+		ret = mtk_dsi_switch_to_cmd_mode(dsi, VM_DONE_INT_FLAG, 500);
+		if (ret)
+			goto restore_dsi_mode;
 	}
 
 	if (MTK_DSI_HOST_IS_READ(msg->type))
 		irq_flag |= LPRX_RD_RDY_INT_FLAG;
 
-	if (mtk_dsi_host_send_cmd(dsi, msg, irq_flag) < 0)
-		return -ETIME;
+	mtk_dsi_lane_ready(dsi);
 
-	if (!MTK_DSI_HOST_IS_READ(msg->type))
-		return 0;
+	ret = mtk_dsi_host_send_cmd(dsi, msg, irq_flag);
+	if (ret)
+		goto restore_dsi_mode;
+
+	if (!MTK_DSI_HOST_IS_READ(msg->type)) {
+		recv_cnt = 0;
+		goto restore_dsi_mode;
+	}
 
 	if (!msg->rx_buf) {
 		DRM_ERROR("dsi receive buffer size may be NULL\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto restore_dsi_mode;
 	}
 
 	for (i = 0; i < 16; i++)
@@ -933,7 +975,13 @@ static ssize_t mtk_dsi_host_transfer(struct mipi_dsi_host *host,
 	DRM_INFO("dsi get %d byte data from the panel address(0x%x)\n",
 		 recv_cnt, *((u8 *)(msg->tx_buf)));
 
-	return recv_cnt;
+restore_dsi_mode:
+	if (dsi_mode & MODE) {
+		mtk_dsi_set_mode(dsi);
+		mtk_dsi_start(dsi);
+	}
+
+	return ret < 0 ? ret : recv_cnt;
 }
 
 static const struct mipi_dsi_host_ops mtk_dsi_ops = {
diff --git a/drivers/gpu/drm/meson/Kconfig b/drivers/gpu/drm/meson/Kconfig
index 9f9281dd49f8..a4e1ed96e5e8 100644
--- a/drivers/gpu/drm/meson/Kconfig
+++ b/drivers/gpu/drm/meson/Kconfig
@@ -6,9 +6,11 @@ config DRM_MESON
 	select DRM_KMS_HELPER
 	select DRM_KMS_CMA_HELPER
 	select DRM_GEM_CMA_HELPER
+	select DRM_DISPLAY_CONNECTOR
 	select VIDEOMODE_HELPERS
 	select REGMAP_MMIO
 	select MESON_CANVAS
+	select CEC_CORE if CEC_NOTIFIER
 
 config DRM_MESON_DW_HDMI
 	tristate "HDMI Synopsys Controller support for Amlogic Meson Display"
diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c
index c98525d60df5..a56607501d36 100644
--- a/drivers/gpu/drm/meson/meson_drv.c
+++ b/drivers/gpu/drm/meson/meson_drv.c
@@ -114,8 +114,11 @@ static bool meson_vpu_has_available_connectors(struct device *dev)
 	for_each_endpoint_of_node(dev->of_node, ep) {
 		/* If the endpoint node exists, consider it enabled */
 		remote = of_graph_get_remote_port(ep);
-		if (remote)
+		if (remote) {
+			of_node_put(remote);
+			of_node_put(ep);
 			return true;
+		}
 	}
 
 	return false;
diff --git a/drivers/gpu/drm/meson/meson_dw_hdmi.c b/drivers/gpu/drm/meson/meson_dw_hdmi.c
index fb540a503efe..5cd2b2ebbbd3 100644
--- a/drivers/gpu/drm/meson/meson_dw_hdmi.c
+++ b/drivers/gpu/drm/meson/meson_dw_hdmi.c
@@ -803,6 +803,7 @@ static int meson_dw_hdmi_bind(struct device *dev, struct device *master,
 	dw_plat_data->input_bus_encoding = V4L2_YCBCR_ENC_709;
 	dw_plat_data->ycbcr_420_allowed = true;
 	dw_plat_data->disable_cec = true;
+	dw_plat_data->output_port = 1;
 
 	if (dw_hdmi_is_compatible(meson_dw_hdmi, "amlogic,meson-gxl-dw-hdmi") ||
 	    dw_hdmi_is_compatible(meson_dw_hdmi, "amlogic,meson-gxm-dw-hdmi") ||
diff --git a/drivers/gpu/drm/meson/meson_encoder_hdmi.c b/drivers/gpu/drm/meson/meson_encoder_hdmi.c
index db332fa4cd54..a7692584487c 100644
--- a/drivers/gpu/drm/meson/meson_encoder_hdmi.c
+++ b/drivers/gpu/drm/meson/meson_encoder_hdmi.c
@@ -14,8 +14,11 @@
 #include <linux/regulator/consumer.h>
 #include <linux/reset.h>
 
+#include <media/cec-notifier.h>
+
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_bridge.h>
+#include <drm/drm_bridge_connector.h>
 #include <drm/drm_device.h>
 #include <drm/drm_edid.h>
 #include <drm/drm_probe_helper.h>
@@ -34,8 +37,10 @@ struct meson_encoder_hdmi {
 	struct drm_encoder encoder;
 	struct drm_bridge bridge;
 	struct drm_bridge *next_bridge;
+	struct drm_connector *connector;
 	struct meson_drm *priv;
 	unsigned long output_bus_fmt;
+	struct cec_notifier *cec_notifier;
 };
 
 #define bridge_to_meson_encoder_hdmi(x) \
@@ -50,6 +55,14 @@ static int meson_encoder_hdmi_attach(struct drm_bridge *bridge,
 				 &encoder_hdmi->bridge, flags);
 }
 
+static void meson_encoder_hdmi_detach(struct drm_bridge *bridge)
+{
+	struct meson_encoder_hdmi *encoder_hdmi = bridge_to_meson_encoder_hdmi(bridge);
+
+	cec_notifier_conn_unregister(encoder_hdmi->cec_notifier);
+	encoder_hdmi->cec_notifier = NULL;
+}
+
 static void meson_encoder_hdmi_set_vclk(struct meson_encoder_hdmi *encoder_hdmi,
 					const struct drm_display_mode *mode)
 {
@@ -298,9 +311,30 @@ static int meson_encoder_hdmi_atomic_check(struct drm_bridge *bridge,
 	return 0;
 }
 
+static void meson_encoder_hdmi_hpd_notify(struct drm_bridge *bridge,
+					  enum drm_connector_status status)
+{
+	struct meson_encoder_hdmi *encoder_hdmi = bridge_to_meson_encoder_hdmi(bridge);
+	struct edid *edid;
+
+	if (!encoder_hdmi->cec_notifier)
+		return;
+
+	if (status == connector_status_connected) {
+		edid = drm_bridge_get_edid(encoder_hdmi->next_bridge, encoder_hdmi->connector);
+		if (!edid)
+			return;
+
+		cec_notifier_set_phys_addr_from_edid(encoder_hdmi->cec_notifier, edid);
+	} else
+		cec_notifier_phys_addr_invalidate(encoder_hdmi->cec_notifier);
+}
+
 static const struct drm_bridge_funcs meson_encoder_hdmi_bridge_funcs = {
 	.attach = meson_encoder_hdmi_attach,
+	.detach = meson_encoder_hdmi_detach,
 	.mode_valid = meson_encoder_hdmi_mode_valid,
+	.hpd_notify = meson_encoder_hdmi_hpd_notify,
 	.atomic_enable = meson_encoder_hdmi_atomic_enable,
 	.atomic_disable = meson_encoder_hdmi_atomic_disable,
 	.atomic_get_input_bus_fmts = meson_encoder_hdmi_get_inp_bus_fmts,
@@ -313,6 +347,7 @@ static const struct drm_bridge_funcs meson_encoder_hdmi_bridge_funcs = {
 int meson_encoder_hdmi_init(struct meson_drm *priv)
 {
 	struct meson_encoder_hdmi *meson_encoder_hdmi;
+	struct platform_device *pdev;
 	struct device_node *remote;
 	int ret;
 
@@ -330,13 +365,15 @@ int meson_encoder_hdmi_init(struct meson_drm *priv)
 	meson_encoder_hdmi->next_bridge = of_drm_find_bridge(remote);
 	if (!meson_encoder_hdmi->next_bridge) {
 		dev_err(priv->dev, "Failed to find HDMI transceiver bridge\n");
-		return -EPROBE_DEFER;
+		ret = -EPROBE_DEFER;
+		goto err_put_node;
 	}
 
 	/* HDMI Encoder Bridge */
 	meson_encoder_hdmi->bridge.funcs = &meson_encoder_hdmi_bridge_funcs;
 	meson_encoder_hdmi->bridge.of_node = priv->dev->of_node;
 	meson_encoder_hdmi->bridge.type = DRM_MODE_CONNECTOR_HDMIA;
+	meson_encoder_hdmi->bridge.interlace_allowed = true;
 
 	drm_bridge_add(&meson_encoder_hdmi->bridge);
 
@@ -347,24 +384,73 @@ int meson_encoder_hdmi_init(struct meson_drm *priv)
 				      DRM_MODE_ENCODER_TMDS);
 	if (ret) {
 		dev_err(priv->dev, "Failed to init HDMI encoder: %d\n", ret);
-		return ret;
+		goto err_put_node;
 	}
 
 	meson_encoder_hdmi->encoder.possible_crtcs = BIT(0);
 
 	/* Attach HDMI Encoder Bridge to Encoder */
-	ret = drm_bridge_attach(&meson_encoder_hdmi->encoder, &meson_encoder_hdmi->bridge, NULL, 0);
+	ret = drm_bridge_attach(&meson_encoder_hdmi->encoder, &meson_encoder_hdmi->bridge, NULL,
+				DRM_BRIDGE_ATTACH_NO_CONNECTOR);
 	if (ret) {
 		dev_err(priv->dev, "Failed to attach bridge: %d\n", ret);
-		return ret;
+		goto err_put_node;
 	}
 
+	/* Initialize & attach Bridge Connector */
+	meson_encoder_hdmi->connector = drm_bridge_connector_init(priv->drm,
+							&meson_encoder_hdmi->encoder);
+	if (IS_ERR(meson_encoder_hdmi->connector)) {
+		dev_err(priv->dev, "Unable to create HDMI bridge connector\n");
+		ret = PTR_ERR(meson_encoder_hdmi->connector);
+		goto err_put_node;
+	}
+	drm_connector_attach_encoder(meson_encoder_hdmi->connector,
+				     &meson_encoder_hdmi->encoder);
+
 	/*
 	 * We should have now in place:
-	 * encoder->[hdmi encoder bridge]->[dw-hdmi bridge]->[dw-hdmi connector]
+	 * encoder->[hdmi encoder bridge]->[dw-hdmi bridge]->[display connector bridge]->[display connector]
+	 */
+
+	/*
+	 * drm_connector_attach_max_bpc_property() requires the
+	 * connector to have a state.
 	 */
+	drm_atomic_helper_connector_reset(meson_encoder_hdmi->connector);
+
+	if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXL) ||
+	    meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM) ||
+	    meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A))
+		drm_connector_attach_hdr_output_metadata_property(meson_encoder_hdmi->connector);
+
+	drm_connector_attach_max_bpc_property(meson_encoder_hdmi->connector, 8, 8);
+
+	/* Handle this here until handled by drm_bridge_connector_init() */
+	meson_encoder_hdmi->connector->ycbcr_420_allowed = true;
+
+	pdev = of_find_device_by_node(remote);
+	of_node_put(remote);
+	if (pdev) {
+		struct cec_connector_info conn_info;
+		struct cec_notifier *notifier;
+
+		cec_fill_conn_info_from_drm(&conn_info, meson_encoder_hdmi->connector);
+
+		notifier = cec_notifier_conn_register(&pdev->dev, NULL, &conn_info);
+		if (!notifier) {
+			put_device(&pdev->dev);
+			return -ENOMEM;
+		}
+
+		meson_encoder_hdmi->cec_notifier = notifier;
+	}
 
 	dev_dbg(priv->dev, "HDMI encoder initialized\n");
 
 	return 0;
+
+err_put_node:
+	of_node_put(remote);
+	return ret;
 }
diff --git a/drivers/gpu/drm/meson/meson_plane.c b/drivers/gpu/drm/meson/meson_plane.c
index 8640a8a8a469..44aa52629443 100644
--- a/drivers/gpu/drm/meson/meson_plane.c
+++ b/drivers/gpu/drm/meson/meson_plane.c
@@ -168,7 +168,7 @@ static void meson_plane_atomic_update(struct drm_plane *plane,
 
 	/* Enable OSD and BLK0, set max global alpha */
 	priv->viu.osd1_ctrl_stat = OSD_ENABLE |
-				   (0xFF << OSD_GLOBAL_ALPHA_SHIFT) |
+				   (0x100 << OSD_GLOBAL_ALPHA_SHIFT) |
 				   OSD_BLK0_ENABLE;
 
 	priv->viu.osd1_ctrl_stat2 = readl(priv->io_base +
diff --git a/drivers/gpu/drm/meson/meson_viu.c b/drivers/gpu/drm/meson/meson_viu.c
index 259f3e6bec90..d4b907889a21 100644
--- a/drivers/gpu/drm/meson/meson_viu.c
+++ b/drivers/gpu/drm/meson/meson_viu.c
@@ -94,7 +94,7 @@ static void meson_viu_set_g12a_osd1_matrix(struct meson_drm *priv,
 		priv->io_base + _REG(VPP_WRAP_OSD1_MATRIX_COEF11_12));
 	writel(((m[9] & 0x1fff) << 16) | (m[10] & 0x1fff),
 		priv->io_base + _REG(VPP_WRAP_OSD1_MATRIX_COEF20_21));
-	writel((m[11] & 0x1fff) << 16,
+	writel((m[11] & 0x1fff),
 		priv->io_base +	_REG(VPP_WRAP_OSD1_MATRIX_COEF22));
 
 	writel(((m[18] & 0xfff) << 16) | (m[19] & 0xfff),
@@ -469,17 +469,17 @@ void meson_viu_init(struct meson_drm *priv)
 			priv->io_base + _REG(VD2_IF0_LUMA_FIFO_SIZE));
 
 	if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A)) {
-		writel_relaxed(VIU_OSD_BLEND_REORDER(0, 1) |
-			       VIU_OSD_BLEND_REORDER(1, 0) |
-			       VIU_OSD_BLEND_REORDER(2, 0) |
-			       VIU_OSD_BLEND_REORDER(3, 0) |
-			       VIU_OSD_BLEND_DIN_EN(1) |
-			       VIU_OSD_BLEND1_DIN3_BYPASS_TO_DOUT1 |
-			       VIU_OSD_BLEND1_DOUT_BYPASS_TO_BLEND2 |
-			       VIU_OSD_BLEND_DIN0_BYPASS_TO_DOUT0 |
-			       VIU_OSD_BLEND_BLEN2_PREMULT_EN(1) |
-			       VIU_OSD_BLEND_HOLD_LINES(4),
-			       priv->io_base + _REG(VIU_OSD_BLEND_CTRL));
+		u32 val = (u32)VIU_OSD_BLEND_REORDER(0, 1) |
+			  (u32)VIU_OSD_BLEND_REORDER(1, 0) |
+			  (u32)VIU_OSD_BLEND_REORDER(2, 0) |
+			  (u32)VIU_OSD_BLEND_REORDER(3, 0) |
+			  (u32)VIU_OSD_BLEND_DIN_EN(1) |
+			  (u32)VIU_OSD_BLEND1_DIN3_BYPASS_TO_DOUT1 |
+			  (u32)VIU_OSD_BLEND1_DOUT_BYPASS_TO_BLEND2 |
+			  (u32)VIU_OSD_BLEND_DIN0_BYPASS_TO_DOUT0 |
+			  (u32)VIU_OSD_BLEND_BLEN2_PREMULT_EN(1) |
+			  (u32)VIU_OSD_BLEND_HOLD_LINES(4);
+		writel_relaxed(val, priv->io_base + _REG(VIU_OSD_BLEND_CTRL));
 
 		writel_relaxed(OSD_BLEND_PATH_SEL_ENABLE,
 			       priv->io_base + _REG(OSD1_BLEND_SRC_CTRL));
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
index 768012243b44..2186fc947e5b 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
@@ -230,6 +230,9 @@ static void _dpu_crtc_blend_setup_mixer(struct drm_crtc *crtc,
 		if (!state)
 			continue;
 
+		if (!state->visible)
+			continue;
+
 		pstate = to_dpu_plane_state(state);
 		fb = state->fb;
 
@@ -898,6 +901,20 @@ struct plane_state {
 	u32 pipe_id;
 };
 
+static bool dpu_crtc_needs_dirtyfb(struct drm_crtc_state *cstate)
+{
+	struct drm_crtc *crtc = cstate->crtc;
+	struct drm_encoder *encoder;
+
+	drm_for_each_encoder_mask (encoder, crtc->dev, cstate->encoder_mask) {
+		if (dpu_encoder_get_intf_mode(encoder) == INTF_MODE_CMD) {
+			return true;
+		}
+	}
+
+	return false;
+}
+
 static int dpu_crtc_atomic_check(struct drm_crtc *crtc,
 		struct drm_atomic_state *state)
 {
@@ -918,6 +935,7 @@ static int dpu_crtc_atomic_check(struct drm_crtc *crtc,
 	const struct drm_plane_state *pipe_staged[SSPP_MAX];
 	int left_zpos_cnt = 0, right_zpos_cnt = 0;
 	struct drm_rect crtc_rect = { 0 };
+	bool needs_dirtyfb = dpu_crtc_needs_dirtyfb(crtc_state);
 
 	pstates = kzalloc(sizeof(*pstates) * DPU_STAGE_MAX * 4, GFP_KERNEL);
 
@@ -949,6 +967,7 @@ static int dpu_crtc_atomic_check(struct drm_crtc *crtc,
 
 	 /* get plane state for all drm planes associated with crtc state */
 	drm_atomic_crtc_state_for_each_plane_state(plane, pstate, crtc_state) {
+		struct dpu_plane_state *dpu_pstate = to_dpu_plane_state(pstate);
 		struct drm_rect dst, clip = crtc_rect;
 
 		if (IS_ERR_OR_NULL(pstate)) {
@@ -960,11 +979,16 @@ static int dpu_crtc_atomic_check(struct drm_crtc *crtc,
 		if (cnt >= DPU_STAGE_MAX * 4)
 			continue;
 
-		pstates[cnt].dpu_pstate = to_dpu_plane_state(pstate);
+		if (!pstate->visible)
+			continue;
+
+		pstates[cnt].dpu_pstate = dpu_pstate;
 		pstates[cnt].drm_pstate = pstate;
 		pstates[cnt].stage = pstate->normalized_zpos;
 		pstates[cnt].pipe_id = dpu_plane_pipe(plane);
 
+		dpu_pstate->needs_dirtyfb = needs_dirtyfb;
+
 		if (pipe_staged[pstates[cnt].pipe_id]) {
 			multirect_plane[multirect_count].r0 =
 				pipe_staged[pstates[cnt].pipe_id];
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
index c989621209aa..e32fe89c203c 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
@@ -894,7 +894,7 @@ static int dpu_plane_prepare_fb(struct drm_plane *plane,
 
 	if (pstate->aspace) {
 		ret = msm_framebuffer_prepare(new_state->fb,
-				pstate->aspace);
+				pstate->aspace, pstate->needs_dirtyfb);
 		if (ret) {
 			DPU_ERROR("failed to prepare framebuffer\n");
 			return ret;
@@ -925,7 +925,8 @@ static void dpu_plane_cleanup_fb(struct drm_plane *plane,
 
 	DPU_DEBUG_PLANE(pdpu, "FB[%u]\n", old_state->fb->base.id);
 
-	msm_framebuffer_cleanup(old_state->fb, old_pstate->aspace);
+	msm_framebuffer_cleanup(old_state->fb, old_pstate->aspace,
+				old_pstate->needs_dirtyfb);
 }
 
 static bool dpu_plane_validate_src(struct drm_rect *src,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h
index 34e03ac05f4a..17ff48564c8a 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h
@@ -28,6 +28,7 @@
  * @cdp_cfg:	CDP configuration
  * @plane_fetch_bw: calculated BW per plane
  * @plane_clk: calculated clk per plane
+ * @needs_dirtyfb: whether attached CRTC needs pixel data explicitly flushed
  */
 struct dpu_plane_state {
 	struct drm_plane_state base;
@@ -45,6 +46,8 @@ struct dpu_plane_state {
 	struct dpu_hw_pipe_cdp_cfg cdp_cfg;
 	u64 plane_fetch_bw;
 	u64 plane_clk;
+
+	bool needs_dirtyfb;
 };
 
 /**
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c
index 49bdabea8ed5..3e20f72d75ef 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c
@@ -7,6 +7,7 @@
 #include <drm/drm_atomic.h>
 #include <drm/drm_damage_helper.h>
 #include <drm/drm_fourcc.h>
+#include <drm/drm_gem_atomic_helper.h>
 
 #include "mdp4_kms.h"
 
@@ -90,6 +91,20 @@ static const struct drm_plane_funcs mdp4_plane_funcs = {
 		.atomic_destroy_state = drm_atomic_helper_plane_destroy_state,
 };
 
+static int mdp4_plane_prepare_fb(struct drm_plane *plane,
+				 struct drm_plane_state *new_state)
+{
+	struct msm_drm_private *priv = plane->dev->dev_private;
+	struct msm_kms *kms = priv->kms;
+
+	if (!new_state->fb)
+		return 0;
+
+	drm_gem_plane_helper_prepare_fb(plane, new_state);
+
+	return msm_framebuffer_prepare(new_state->fb, kms->aspace, false);
+}
+
 static void mdp4_plane_cleanup_fb(struct drm_plane *plane,
 				  struct drm_plane_state *old_state)
 {
@@ -102,7 +117,7 @@ static void mdp4_plane_cleanup_fb(struct drm_plane *plane,
 		return;
 
 	DBG("%s: cleanup: FB[%u]", mdp4_plane->name, fb->base.id);
-	msm_framebuffer_cleanup(fb, kms->aspace);
+	msm_framebuffer_cleanup(fb, kms->aspace, false);
 }
 
 
@@ -130,7 +145,7 @@ static void mdp4_plane_atomic_update(struct drm_plane *plane,
 }
 
 static const struct drm_plane_helper_funcs mdp4_plane_helper_funcs = {
-		.prepare_fb = msm_atomic_prepare_fb,
+		.prepare_fb = mdp4_plane_prepare_fb,
 		.cleanup_fb = mdp4_plane_cleanup_fb,
 		.atomic_check = mdp4_plane_atomic_check,
 		.atomic_update = mdp4_plane_atomic_update,
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
index 0e02e252ff89..31447da0af25 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
@@ -696,6 +696,8 @@ static int mdp5_crtc_atomic_check(struct drm_crtc *crtc,
 {
 	struct drm_crtc_state *crtc_state = drm_atomic_get_new_crtc_state(state,
 									  crtc);
+	struct mdp5_crtc_state *mdp5_cstate = to_mdp5_crtc_state(crtc_state);
+	struct mdp5_interface *intf = mdp5_cstate->pipeline.intf;
 	struct mdp5_kms *mdp5_kms = get_kms(crtc);
 	struct drm_plane *plane;
 	struct drm_device *dev = crtc->dev;
@@ -712,12 +714,18 @@ static int mdp5_crtc_atomic_check(struct drm_crtc *crtc,
 	DBG("%s: check", crtc->name);
 
 	drm_atomic_crtc_state_for_each_plane_state(plane, pstate, crtc_state) {
+		struct mdp5_plane_state *mdp5_pstate =
+				to_mdp5_plane_state(pstate);
+
 		if (!pstate->visible)
 			continue;
 
 		pstates[cnt].plane = plane;
 		pstates[cnt].state = to_mdp5_plane_state(pstate);
 
+		mdp5_pstate->needs_dirtyfb =
+			intf->mode == MDP5_INTF_DSI_MODE_COMMAND;
+
 		/*
 		 * if any plane on this crtc uses 2 hwpipes, then we need
 		 * the crtc to have a right hwmixer.
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.h b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.h
index ac269a6802df..29bf11f08601 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.h
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.h
@@ -100,6 +100,11 @@ struct mdp5_plane_state {
 
 	/* assigned by crtc blender */
 	enum mdp_mixer_stage_id stage;
+
+	/* whether attached CRTC needs pixel data explicitly flushed to
+	 * display (ex. DSI command mode display)
+	 */
+	bool needs_dirtyfb;
 };
 #define to_mdp5_plane_state(x) \
 		container_of(x, struct mdp5_plane_state, base)
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_pipe.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_pipe.c
index a4f5cb90f3e8..e4b8a789835a 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_pipe.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_pipe.c
@@ -123,12 +123,13 @@ int mdp5_pipe_release(struct drm_atomic_state *s, struct mdp5_hw_pipe *hwpipe)
 {
 	struct msm_drm_private *priv = s->dev->dev_private;
 	struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(priv->kms));
-	struct mdp5_global_state *state = mdp5_get_global_state(s);
+	struct mdp5_global_state *state;
 	struct mdp5_hw_pipe_state *new_state;
 
 	if (!hwpipe)
 		return 0;
 
+	state = mdp5_get_global_state(s);
 	if (IS_ERR(state))
 		return PTR_ERR(state);
 
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c
index c0d947bce9e9..9c42776cb9a8 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c
@@ -8,6 +8,7 @@
 #include <drm/drm_atomic.h>
 #include <drm/drm_damage_helper.h>
 #include <drm/drm_fourcc.h>
+#include <drm/drm_gem_atomic_helper.h>
 #include <drm/drm_print.h>
 
 #include "mdp5_kms.h"
@@ -143,18 +144,34 @@ static const struct drm_plane_funcs mdp5_plane_funcs = {
 		.atomic_print_state = mdp5_plane_atomic_print_state,
 };
 
+static int mdp5_plane_prepare_fb(struct drm_plane *plane,
+				 struct drm_plane_state *new_state)
+{
+	struct msm_drm_private *priv = plane->dev->dev_private;
+	struct msm_kms *kms = priv->kms;
+	bool needs_dirtyfb = to_mdp5_plane_state(new_state)->needs_dirtyfb;
+
+	if (!new_state->fb)
+		return 0;
+
+	drm_gem_plane_helper_prepare_fb(plane, new_state);
+
+	return msm_framebuffer_prepare(new_state->fb, kms->aspace, needs_dirtyfb);
+}
+
 static void mdp5_plane_cleanup_fb(struct drm_plane *plane,
 				  struct drm_plane_state *old_state)
 {
 	struct mdp5_kms *mdp5_kms = get_kms(plane);
 	struct msm_kms *kms = &mdp5_kms->base.base;
 	struct drm_framebuffer *fb = old_state->fb;
+	bool needed_dirtyfb = to_mdp5_plane_state(old_state)->needs_dirtyfb;
 
 	if (!fb)
 		return;
 
 	DBG("%s: cleanup: FB[%u]", plane->name, fb->base.id);
-	msm_framebuffer_cleanup(fb, kms->aspace);
+	msm_framebuffer_cleanup(fb, kms->aspace, needed_dirtyfb);
 }
 
 static int mdp5_plane_atomic_check_with_state(struct drm_crtc_state *crtc_state,
@@ -452,7 +469,7 @@ static void mdp5_plane_atomic_async_update(struct drm_plane *plane,
 }
 
 static const struct drm_plane_helper_funcs mdp5_plane_helper_funcs = {
-		.prepare_fb = msm_atomic_prepare_fb,
+		.prepare_fb = mdp5_plane_prepare_fb,
 		.cleanup_fb = mdp5_plane_cleanup_fb,
 		.atomic_check = mdp5_plane_atomic_check,
 		.atomic_update = mdp5_plane_atomic_update,
diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c
index b6f4ce2a48af..6d9eec98e0d3 100644
--- a/drivers/gpu/drm/msm/dp/dp_ctrl.c
+++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c
@@ -1198,7 +1198,7 @@ static int dp_ctrl_link_train_2(struct dp_ctrl_private *ctrl,
 	if (ret)
 		return ret;
 
-	dp_ctrl_train_pattern_set(ctrl, pattern | DP_RECOVERED_CLOCK_OUT_EN);
+	dp_ctrl_train_pattern_set(ctrl, pattern);
 
 	for (tries = 0; tries <= maximum_retries; tries++) {
 		drm_dp_link_train_channel_eq_delay(ctrl->aux, ctrl->panel->dpcd);
diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.c b/drivers/gpu/drm/msm/dsi/dsi_cfg.c
index 96bbc8b6d009..ce3901439c69 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_cfg.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.c
@@ -109,7 +109,7 @@ static const char * const dsi_8996_bus_clk_names[] = {
 static const struct msm_dsi_config msm8996_dsi_cfg = {
 	.io_offset = DSI_6G_REG_SHIFT,
 	.reg_cfg = {
-		.num = 2,
+		.num = 3,
 		.regs = {
 			{"vdda", 18160, 1 },	/* 1.25 V */
 			{"vcca", 17000, 32 },	/* 0.925 V */
@@ -148,7 +148,7 @@ static const char * const dsi_sdm660_bus_clk_names[] = {
 static const struct msm_dsi_config sdm660_dsi_cfg = {
 	.io_offset = DSI_6G_REG_SHIFT,
 	.reg_cfg = {
-		.num = 2,
+		.num = 1,
 		.regs = {
 			{"vdda", 12560, 4 },	/* 1.2 V */
 		},
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
index a878b8b079c6..6a917fe69a83 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
@@ -347,7 +347,7 @@ int msm_dsi_dphy_timing_calc_v3(struct msm_dsi_dphy_timing *timing,
 	} else {
 		timing->shared_timings.clk_pre =
 			linear_inter(tmax, tmin, pcnt2, 0, false);
-			timing->shared_timings.clk_pre_inc_by_2 = 0;
+		timing->shared_timings.clk_pre_inc_by_2 = 0;
 	}
 
 	timing->ta_go = 3;
diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c
index fab09e7c6efc..458f4e4316dd 100644
--- a/drivers/gpu/drm/msm/msm_atomic.c
+++ b/drivers/gpu/drm/msm/msm_atomic.c
@@ -5,7 +5,6 @@
  */
 
 #include <drm/drm_atomic_uapi.h>
-#include <drm/drm_gem_atomic_helper.h>
 #include <drm/drm_vblank.h>
 
 #include "msm_atomic_trace.h"
@@ -13,20 +12,6 @@
 #include "msm_gem.h"
 #include "msm_kms.h"
 
-int msm_atomic_prepare_fb(struct drm_plane *plane,
-			  struct drm_plane_state *new_state)
-{
-	struct msm_drm_private *priv = plane->dev->dev_private;
-	struct msm_kms *kms = priv->kms;
-
-	if (!new_state->fb)
-		return 0;
-
-	drm_gem_plane_helper_prepare_fb(plane, new_state);
-
-	return msm_framebuffer_prepare(new_state->fb, kms->aspace);
-}
-
 /*
  * Helpers to control vblanks while we flush.. basically just to ensure
  * that vblank accounting is switched on, so we get valid seqn/timestamp
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index bd5132bb9bde..8488e49817e1 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -247,8 +247,6 @@ struct msm_format {
 
 struct msm_pending_timer;
 
-int msm_atomic_prepare_fb(struct drm_plane *plane,
-			  struct drm_plane_state *new_state);
 int msm_atomic_init_pending_timer(struct msm_pending_timer *timer,
 		struct msm_kms *kms, int crtc_idx);
 void msm_atomic_destroy_pending_timer(struct msm_pending_timer *timer);
@@ -308,9 +306,9 @@ int msm_gem_prime_pin(struct drm_gem_object *obj);
 void msm_gem_prime_unpin(struct drm_gem_object *obj);
 
 int msm_framebuffer_prepare(struct drm_framebuffer *fb,
-		struct msm_gem_address_space *aspace);
+		struct msm_gem_address_space *aspace, bool needs_dirtyfb);
 void msm_framebuffer_cleanup(struct drm_framebuffer *fb,
-		struct msm_gem_address_space *aspace);
+		struct msm_gem_address_space *aspace, bool needed_dirtyfb);
 uint32_t msm_framebuffer_iova(struct drm_framebuffer *fb,
 		struct msm_gem_address_space *aspace, int plane);
 struct drm_gem_object *msm_framebuffer_bo(struct drm_framebuffer *fb, int plane);
diff --git a/drivers/gpu/drm/msm/msm_fb.c b/drivers/gpu/drm/msm/msm_fb.c
index 4d34df5354e0..7137492fe78e 100644
--- a/drivers/gpu/drm/msm/msm_fb.c
+++ b/drivers/gpu/drm/msm/msm_fb.c
@@ -18,16 +18,36 @@
 struct msm_framebuffer {
 	struct drm_framebuffer base;
 	const struct msm_format *format;
+
+	/* Count of # of attached planes which need dirtyfb: */
+	refcount_t dirtyfb;
 };
 #define to_msm_framebuffer(x) container_of(x, struct msm_framebuffer, base)
 
 static struct drm_framebuffer *msm_framebuffer_init(struct drm_device *dev,
 		const struct drm_mode_fb_cmd2 *mode_cmd, struct drm_gem_object **bos);
 
+static int msm_framebuffer_dirtyfb(struct drm_framebuffer *fb,
+				   struct drm_file *file_priv, unsigned int flags,
+				   unsigned int color, struct drm_clip_rect *clips,
+				   unsigned int num_clips)
+{
+	struct msm_framebuffer *msm_fb = to_msm_framebuffer(fb);
+
+	/* If this fb is not used on any display requiring pixel data to be
+	 * flushed, then skip dirtyfb
+	 */
+	if (refcount_read(&msm_fb->dirtyfb) == 1)
+		return 0;
+
+	return drm_atomic_helper_dirtyfb(fb, file_priv, flags, color,
+					 clips, num_clips);
+}
+
 static const struct drm_framebuffer_funcs msm_framebuffer_funcs = {
 	.create_handle = drm_gem_fb_create_handle,
 	.destroy = drm_gem_fb_destroy,
-	.dirty = drm_atomic_helper_dirtyfb,
+	.dirty = msm_framebuffer_dirtyfb,
 };
 
 #ifdef CONFIG_DEBUG_FS
@@ -48,17 +68,19 @@ void msm_framebuffer_describe(struct drm_framebuffer *fb, struct seq_file *m)
 }
 #endif
 
-/* prepare/pin all the fb's bo's for scanout.  Note that it is not valid
- * to prepare an fb more multiple different initiator 'id's.  But that
- * should be fine, since only the scanout (mdpN) side of things needs
- * this, the gpu doesn't care about fb's.
+/* prepare/pin all the fb's bo's for scanout.
  */
 int msm_framebuffer_prepare(struct drm_framebuffer *fb,
-		struct msm_gem_address_space *aspace)
+		struct msm_gem_address_space *aspace,
+		bool needs_dirtyfb)
 {
+	struct msm_framebuffer *msm_fb = to_msm_framebuffer(fb);
 	int ret, i, n = fb->format->num_planes;
 	uint64_t iova;
 
+	if (needs_dirtyfb)
+		refcount_inc(&msm_fb->dirtyfb);
+
 	for (i = 0; i < n; i++) {
 		ret = msm_gem_get_and_pin_iova(fb->obj[i], aspace, &iova);
 		drm_dbg_state(fb->dev, "FB[%u]: iova[%d]: %08llx (%d)", fb->base.id, i, iova, ret);
@@ -70,10 +92,15 @@ int msm_framebuffer_prepare(struct drm_framebuffer *fb,
 }
 
 void msm_framebuffer_cleanup(struct drm_framebuffer *fb,
-		struct msm_gem_address_space *aspace)
+		struct msm_gem_address_space *aspace,
+		bool needed_dirtyfb)
 {
+	struct msm_framebuffer *msm_fb = to_msm_framebuffer(fb);
 	int i, n = fb->format->num_planes;
 
+	if (needed_dirtyfb)
+		refcount_dec(&msm_fb->dirtyfb);
+
 	for (i = 0; i < n; i++)
 		msm_gem_unpin_iova(fb->obj[i], aspace);
 }
@@ -194,6 +221,8 @@ static struct drm_framebuffer *msm_framebuffer_init(struct drm_device *dev,
 		goto fail;
 	}
 
+	refcount_set(&msm_fb->dirtyfb, 1);
+
 	drm_dbg_state(dev, "create: FB ID: %d (%p)", fb->base.id, fb);
 
 	return fb;
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 7fb7ff043bcd..1f74bab9e231 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -889,7 +889,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	submit->fence_id = idr_alloc_cyclic(&queue->fence_idr,
 			submit->user_fence, 1, INT_MAX, GFP_KERNEL);
 	if (submit->fence_id < 0) {
-		ret = submit->fence_id = 0;
+		ret = submit->fence_id;
 		submit->fence_id = 0;
 		goto out;
 	}
diff --git a/drivers/gpu/drm/msm/msm_rd.c b/drivers/gpu/drm/msm/msm_rd.c
index b55398a34fa4..e3f0dd4a3679 100644
--- a/drivers/gpu/drm/msm/msm_rd.c
+++ b/drivers/gpu/drm/msm/msm_rd.c
@@ -191,6 +191,9 @@ static int rd_open(struct inode *inode, struct file *file)
 	file->private_data = rd;
 	rd->open = true;
 
+	/* Reset fifo to clear any previously unread data: */
+	rd->fifo.head = rd->fifo.tail = 0;
+
 	/* the parsing tools need to know gpu-id to know which
 	 * register database to load.
 	 */
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index c58bcdba2c7a..511fb8dfb4c4 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -820,6 +820,15 @@ nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict,
 		if (ret == 0) {
 			ret = nouveau_fence_new(chan, false, &fence);
 			if (ret == 0) {
+				/* TODO: figure out a better solution here
+				 *
+				 * wait on the fence here explicitly as going through
+				 * ttm_bo_move_accel_cleanup somehow doesn't seem to do it.
+				 *
+				 * Without this the operation can timeout and we'll fallback to a
+				 * software copy, which might take several minutes to finish.
+				 */
+				nouveau_fence_wait(fence, false, false);
 				ret = ttm_bo_move_accel_cleanup(bo,
 								&fence->base,
 								evict, false,
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index 22b83a6577eb..df83c4654e26 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -1361,13 +1361,11 @@ nouveau_connector_create(struct drm_device *dev,
 		snprintf(aux_name, sizeof(aux_name), "sor-%04x-%04x",
 			 dcbe->hasht, dcbe->hashm);
 		nv_connector->aux.name = kstrdup(aux_name, GFP_KERNEL);
-		drm_dp_aux_init(&nv_connector->aux);
-		if (ret) {
-			NV_ERROR(drm, "Failed to init AUX adapter for sor-%04x-%04x: %d\n",
-				 dcbe->hasht, dcbe->hashm, ret);
+		if (!nv_connector->aux.name) {
 			kfree(nv_connector);
-			return ERR_PTR(ret);
+			return ERR_PTR(-ENOMEM);
 		}
+		drm_dp_aux_init(&nv_connector->aux);
 		fallthrough;
 	default:
 		funcs = &nouveau_connector_funcs;
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index 929de41c281f..b8667bdc04ba 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -518,7 +518,7 @@ nouveau_display_hpd_work(struct work_struct *work)
 
 	pm_runtime_mark_last_busy(drm->dev->dev);
 noop:
-	pm_runtime_put_sync(drm->dev->dev);
+	pm_runtime_put_autosuspend(dev->dev);
 }
 
 #ifdef CONFIG_ACPI
@@ -540,7 +540,7 @@ nouveau_display_acpi_ntfy(struct notifier_block *nb, unsigned long val,
 				 * it's own hotplug events.
 				 */
 				pm_runtime_put_autosuspend(drm->dev->dev);
-			} else if (ret == 0) {
+			} else if (ret == 0 || ret == -EINPROGRESS) {
 				/* We've started resuming the GPU already, so
 				 * it will handle scheduling a full reprobe
 				 * itself
diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c
index 92987daa5e17..5e72e6cb2f84 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dmem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c
@@ -679,7 +679,11 @@ nouveau_dmem_migrate_vma(struct nouveau_drm *drm,
 		goto out_free_dma;
 
 	for (i = 0; i < npages; i += max) {
-		args.end = start + (max << PAGE_SHIFT);
+		if (args.start + (max << PAGE_SHIFT) > end)
+			args.end = end;
+		else
+			args.end = args.start + (max << PAGE_SHIFT);
+
 		ret = migrate_vma_setup(&args);
 		if (ret)
 			goto out_free_pfns;
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
index 4f9b3aa5deda..20ac1ce2c0f1 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
@@ -466,7 +466,7 @@ nouveau_fbcon_set_suspend_work(struct work_struct *work)
 	if (state == FBINFO_STATE_RUNNING) {
 		nouveau_fbcon_hotplug_resume(drm->fbcon);
 		pm_runtime_mark_last_busy(drm->dev->dev);
-		pm_runtime_put_sync(drm->dev->dev);
+		pm_runtime_put_autosuspend(drm->dev->dev);
 	}
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
index 88d262ba648c..76156833a832 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
@@ -2606,6 +2606,27 @@ nv172_chipset = {
 };
 
 static const struct nvkm_device_chip
+nv173_chipset = {
+	.name = "GA103",
+	.bar      = { 0x00000001, tu102_bar_new },
+	.bios     = { 0x00000001, nvkm_bios_new },
+	.devinit  = { 0x00000001, ga100_devinit_new },
+	.fb       = { 0x00000001, ga102_fb_new },
+	.gpio     = { 0x00000001, ga102_gpio_new },
+	.i2c      = { 0x00000001, gm200_i2c_new },
+	.imem     = { 0x00000001, nv50_instmem_new },
+	.mc       = { 0x00000001, ga100_mc_new },
+	.mmu      = { 0x00000001, tu102_mmu_new },
+	.pci      = { 0x00000001, gp100_pci_new },
+	.privring = { 0x00000001, gm200_privring_new },
+	.timer    = { 0x00000001, gk20a_timer_new },
+	.top      = { 0x00000001, ga100_top_new },
+	.disp     = { 0x00000001, ga102_disp_new },
+	.dma      = { 0x00000001, gv100_dma_new },
+	.fifo     = { 0x00000001, ga102_fifo_new },
+};
+
+static const struct nvkm_device_chip
 nv174_chipset = {
 	.name = "GA104",
 	.bar      = { 0x00000001, tu102_bar_new },
@@ -3092,6 +3113,7 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
 		case 0x167: device->chip = &nv167_chipset; break;
 		case 0x168: device->chip = &nv168_chipset; break;
 		case 0x172: device->chip = &nv172_chipset; break;
+		case 0x173: device->chip = &nv173_chipset; break;
 		case 0x174: device->chip = &nv174_chipset; break;
 		case 0x176: device->chip = &nv176_chipset; break;
 		case 0x177: device->chip = &nv177_chipset; break;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/base.c
index 64e423dddd9e..6c318e41bde0 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/base.c
@@ -33,7 +33,7 @@ nvbios_addr(struct nvkm_bios *bios, u32 *addr, u8 size)
 {
 	u32 p = *addr;
 
-	if (*addr > bios->image0_size && bios->imaged_addr) {
+	if (*addr >= bios->image0_size && bios->imaged_addr) {
 		*addr -= bios->image0_size;
 		*addr += bios->imaged_addr;
 	}
diff --git a/drivers/gpu/drm/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig
index 5663037fff13..5d0dfb23fdb4 100644
--- a/drivers/gpu/drm/panel/Kconfig
+++ b/drivers/gpu/drm/panel/Kconfig
@@ -384,6 +384,8 @@ config DRM_PANEL_SAMSUNG_ATNA33XC20
 	depends on OF
 	depends on BACKLIGHT_CLASS_DEVICE
 	depends on PM
+	select DRM_DISPLAY_DP_HELPER
+	select DRM_DISPLAY_HELPER
 	select DRM_DP_AUX_BUS
 	help
 	  DRM panel driver for the Samsung ATNA33XC20 panel. This panel can't
diff --git a/drivers/gpu/drm/panfrost/panfrost_devfreq.c b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
index 194af7f607a6..be36dd060a2b 100644
--- a/drivers/gpu/drm/panfrost/panfrost_devfreq.c
+++ b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
@@ -132,6 +132,17 @@ int panfrost_devfreq_init(struct panfrost_device *pfdev)
 		return PTR_ERR(opp);
 
 	panfrost_devfreq_profile.initial_freq = cur_freq;
+
+	/*
+	 * Set the recommend OPP this will enable and configure the regulator
+	 * if any and will avoid a switch off by regulator_late_cleanup()
+	 */
+	ret = dev_pm_opp_set_opp(dev, opp);
+	if (ret) {
+		DRM_DEV_ERROR(dev, "Couldn't set recommended OPP\n");
+		return ret;
+	}
+
 	dev_pm_opp_put(opp);
 
 	/*
diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c
index 1ffaef5ec5ff..e48e357ea4f1 100644
--- a/drivers/gpu/drm/panfrost/panfrost_drv.c
+++ b/drivers/gpu/drm/panfrost/panfrost_drv.c
@@ -418,12 +418,12 @@ static int panfrost_ioctl_madvise(struct drm_device *dev, void *data,
 		}
 	}
 
-	args->retained = drm_gem_shmem_madvise(gem_obj, args->madv);
+	args->retained = drm_gem_shmem_madvise(&bo->base, args->madv);
 
 	if (args->retained) {
 		if (args->madv == PANFROST_MADV_DONTNEED)
-			list_add_tail(&bo->base.madv_list,
-				      &pfdev->shrinker_list);
+			list_move_tail(&bo->base.madv_list,
+				       &pfdev->shrinker_list);
 		else if (args->madv == PANFROST_MADV_WILLNEED)
 			list_del_init(&bo->base.madv_list);
 	}
diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.c b/drivers/gpu/drm/panfrost/panfrost_gem.c
index 23377481f4e3..6d9bdb9180cb 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gem.c
@@ -49,7 +49,7 @@ static void panfrost_gem_free_object(struct drm_gem_object *obj)
 		kvfree(bo->sgts);
 	}
 
-	drm_gem_shmem_free_object(obj);
+	drm_gem_shmem_free(&bo->base);
 }
 
 struct panfrost_gem_mapping *
@@ -187,23 +187,25 @@ void panfrost_gem_close(struct drm_gem_object *obj, struct drm_file *file_priv)
 
 static int panfrost_gem_pin(struct drm_gem_object *obj)
 {
-	if (to_panfrost_bo(obj)->is_heap)
+	struct panfrost_gem_object *bo = to_panfrost_bo(obj);
+
+	if (bo->is_heap)
 		return -EINVAL;
 
-	return drm_gem_shmem_pin(obj);
+	return drm_gem_shmem_pin(&bo->base);
 }
 
 static const struct drm_gem_object_funcs panfrost_gem_funcs = {
 	.free = panfrost_gem_free_object,
 	.open = panfrost_gem_open,
 	.close = panfrost_gem_close,
-	.print_info = drm_gem_shmem_print_info,
+	.print_info = drm_gem_shmem_object_print_info,
 	.pin = panfrost_gem_pin,
-	.unpin = drm_gem_shmem_unpin,
-	.get_sg_table = drm_gem_shmem_get_sg_table,
-	.vmap = drm_gem_shmem_vmap,
-	.vunmap = drm_gem_shmem_vunmap,
-	.mmap = drm_gem_shmem_mmap,
+	.unpin = drm_gem_shmem_object_unpin,
+	.get_sg_table = drm_gem_shmem_object_get_sg_table,
+	.vmap = drm_gem_shmem_object_vmap,
+	.vunmap = drm_gem_shmem_object_vunmap,
+	.mmap = drm_gem_shmem_object_mmap,
 };
 
 /**
diff --git a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c
index 1b9f68d8e9aa..b0142341e223 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c
@@ -52,7 +52,7 @@ static bool panfrost_gem_purge(struct drm_gem_object *obj)
 		goto unlock_mappings;
 
 	panfrost_gem_teardown_mappings_locked(bo);
-	drm_gem_shmem_purge_locked(obj);
+	drm_gem_shmem_purge_locked(&bo->base);
 	ret = true;
 
 	mutex_unlock(&shmem->pages_lock);
diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index dfe5f1d29763..c3292a6bd1ae 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -288,7 +288,8 @@ static int mmu_map_sg(struct panfrost_device *pfdev, struct panfrost_mmu *mmu,
 int panfrost_mmu_map(struct panfrost_gem_mapping *mapping)
 {
 	struct panfrost_gem_object *bo = mapping->obj;
-	struct drm_gem_object *obj = &bo->base.base;
+	struct drm_gem_shmem_object *shmem = &bo->base;
+	struct drm_gem_object *obj = &shmem->base;
 	struct panfrost_device *pfdev = to_panfrost_device(obj->dev);
 	struct sg_table *sgt;
 	int prot = IOMMU_READ | IOMMU_WRITE;
@@ -299,7 +300,7 @@ int panfrost_mmu_map(struct panfrost_gem_mapping *mapping)
 	if (bo->noexec)
 		prot |= IOMMU_NOEXEC;
 
-	sgt = drm_gem_shmem_get_pages_sgt(obj);
+	sgt = drm_gem_shmem_get_pages_sgt(shmem);
 	if (WARN_ON(IS_ERR(sgt)))
 		return PTR_ERR(sgt);
 
@@ -501,7 +502,7 @@ err_map:
 err_pages:
 	drm_gem_shmem_put_pages(&bo->base);
 err_bo:
-	drm_gem_object_put(&bo->base.base);
+	panfrost_gem_mapping_put(bomapping);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c
index 5ab03d605f57..9d9c067c1d70 100644
--- a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c
+++ b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c
@@ -105,7 +105,7 @@ static int panfrost_perfcnt_enable_locked(struct panfrost_device *pfdev,
 		goto err_close_bo;
 	}
 
-	ret = drm_gem_shmem_vmap(&bo->base, &map);
+	ret = drm_gem_shmem_vmap(bo, &map);
 	if (ret)
 		goto err_put_mapping;
 	perfcnt->buf = map.vaddr;
@@ -164,7 +164,7 @@ static int panfrost_perfcnt_enable_locked(struct panfrost_device *pfdev,
 	return 0;
 
 err_vunmap:
-	drm_gem_shmem_vunmap(&bo->base, &map);
+	drm_gem_shmem_vunmap(bo, &map);
 err_put_mapping:
 	panfrost_gem_mapping_put(perfcnt->mapping);
 err_close_bo:
@@ -194,7 +194,7 @@ static int panfrost_perfcnt_disable_locked(struct panfrost_device *pfdev,
 		  GPU_PERFCNT_CFG_MODE(GPU_PERFCNT_CFG_MODE_OFF));
 
 	perfcnt->user = NULL;
-	drm_gem_shmem_vunmap(&perfcnt->mapping->obj->base.base, &map);
+	drm_gem_shmem_vunmap(&perfcnt->mapping->obj->base, &map);
 	perfcnt->buf = NULL;
 	panfrost_gem_close(&perfcnt->mapping->obj->base.base, file_priv);
 	panfrost_mmu_as_put(pfdev, perfcnt->mapping->mmu);
diff --git a/drivers/gpu/drm/radeon/.gitignore b/drivers/gpu/drm/radeon/.gitignore
index 9c1a94153983..d8777383a64a 100644
--- a/drivers/gpu/drm/radeon/.gitignore
+++ b/drivers/gpu/drm/radeon/.gitignore
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0-only
+# SPDX-License-Identifier: MIT
 mkregtable
 *_reg_safe.h
 
diff --git a/drivers/gpu/drm/radeon/Kconfig b/drivers/gpu/drm/radeon/Kconfig
index 6f60f4840cc5..52819e7f1fca 100644
--- a/drivers/gpu/drm/radeon/Kconfig
+++ b/drivers/gpu/drm/radeon/Kconfig
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0-only
+# SPDX-License-Identifier: MIT
 config DRM_RADEON_USERPTR
 	bool "Always enable userptr support"
 	depends on DRM_RADEON
diff --git a/drivers/gpu/drm/radeon/Makefile b/drivers/gpu/drm/radeon/Makefile
index 11c97edde54d..3d502f1bbfcb 100644
--- a/drivers/gpu/drm/radeon/Makefile
+++ b/drivers/gpu/drm/radeon/Makefile
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 #
 # Makefile for the drm device driver.  This driver provides support for the
 # Direct Rendering Infrastructure (DRI) in XFree86 4.1.0 and higher.
diff --git a/drivers/gpu/drm/radeon/ni_dpm.c b/drivers/gpu/drm/radeon/ni_dpm.c
index 769f666335ac..672d2239293e 100644
--- a/drivers/gpu/drm/radeon/ni_dpm.c
+++ b/drivers/gpu/drm/radeon/ni_dpm.c
@@ -2741,10 +2741,10 @@ static int ni_set_mc_special_registers(struct radeon_device *rdev,
 					table->mc_reg_table_entry[k].mc_data[j] |= 0x100;
 			}
 			j++;
-			if (j > SMC_NISLANDS_MC_REGISTER_ARRAY_SIZE)
-				return -EINVAL;
 			break;
 		case MC_SEQ_RESERVE_M >> 2:
+			if (j >= SMC_NISLANDS_MC_REGISTER_ARRAY_SIZE)
+				return -EINVAL;
 			temp_reg = RREG32(MC_PMG_CMD_MRS1);
 			table->mc_reg_address[j].s1 = MC_PMG_CMD_MRS1 >> 2;
 			table->mc_reg_address[j].s0 = MC_SEQ_PMG_CMD_MRS1_LP >> 2;
@@ -2753,8 +2753,6 @@ static int ni_set_mc_special_registers(struct radeon_device *rdev,
 					(temp_reg & 0xffff0000) |
 					(table->mc_reg_table_entry[k].mc_data[i] & 0x0000ffff);
 			j++;
-			if (j > SMC_NISLANDS_MC_REGISTER_ARRAY_SIZE)
-				return -EINVAL;
 			break;
 		default:
 			break;
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 4f0fbf667431..92905ebb7b45 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1617,6 +1617,9 @@ int radeon_suspend_kms(struct drm_device *dev, bool suspend,
 		if (r) {
 			/* delay GPU reset to resume */
 			radeon_fence_driver_force_completion(rdev, i);
+		} else {
+			/* finish executing delayed work */
+			flush_delayed_work(&rdev->fence_drv[i].lockup_work);
 		}
 	}
 
diff --git a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c
index ade2327a10e2..512581698a1e 100644
--- a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c
+++ b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c
@@ -398,7 +398,15 @@ static int rockchip_dp_probe(struct platform_device *pdev)
 	if (IS_ERR(dp->adp))
 		return PTR_ERR(dp->adp);
 
-	return component_add(dev, &rockchip_dp_component_ops);
+	ret = component_add(dev, &rockchip_dp_component_ops);
+	if (ret)
+		goto err_dp_remove;
+
+	return 0;
+
+err_dp_remove:
+	analogix_dp_remove(dp->adp);
+	return ret;
 }
 
 static int rockchip_dp_remove(struct platform_device *pdev)
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index 8b4287d40379..d5b74ea06a45 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -1550,6 +1550,9 @@ static struct drm_crtc_state *vop_crtc_duplicate_state(struct drm_crtc *crtc)
 {
 	struct rockchip_crtc_state *rockchip_state;
 
+	if (WARN_ON(!crtc->state))
+		return NULL;
+
 	rockchip_state = kzalloc(sizeof(*rockchip_state), GFP_KERNEL);
 	if (!rockchip_state)
 		return NULL;
diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
index 4f5efcace68e..51edb4244af7 100644
--- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
+++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
@@ -531,7 +531,7 @@ static void sun6i_dsi_setup_timings(struct sun6i_dsi *dsi,
 				    struct drm_display_mode *mode)
 {
 	struct mipi_dsi_device *device = dsi->device;
-	unsigned int Bpp = mipi_dsi_pixel_format_to_bpp(device->format) / 8;
+	int Bpp = mipi_dsi_pixel_format_to_bpp(device->format) / 8;
 	u16 hbp = 0, hfp = 0, hsa = 0, hblk = 0, vblk = 0;
 	u32 basic_ctl = 0;
 	size_t bytes;
@@ -555,7 +555,7 @@ static void sun6i_dsi_setup_timings(struct sun6i_dsi *dsi,
 		 * (4 bytes). Its minimal size is therefore 10 bytes
 		 */
 #define HSA_PACKET_OVERHEAD	10
-		hsa = max((unsigned int)HSA_PACKET_OVERHEAD,
+		hsa = max(HSA_PACKET_OVERHEAD,
 			  (mode->hsync_end - mode->hsync_start) * Bpp - HSA_PACKET_OVERHEAD);
 
 		/*
@@ -564,7 +564,7 @@ static void sun6i_dsi_setup_timings(struct sun6i_dsi *dsi,
 		 * therefore 6 bytes
 		 */
 #define HBP_PACKET_OVERHEAD	6
-		hbp = max((unsigned int)HBP_PACKET_OVERHEAD,
+		hbp = max(HBP_PACKET_OVERHEAD,
 			  (mode->htotal - mode->hsync_end) * Bpp - HBP_PACKET_OVERHEAD);
 
 		/*
@@ -574,7 +574,7 @@ static void sun6i_dsi_setup_timings(struct sun6i_dsi *dsi,
 		 * 16 bytes
 		 */
 #define HFP_PACKET_OVERHEAD	16
-		hfp = max((unsigned int)HFP_PACKET_OVERHEAD,
+		hfp = max(HFP_PACKET_OVERHEAD,
 			  (mode->hsync_start - mode->hdisplay) * Bpp - HFP_PACKET_OVERHEAD);
 
 		/*
@@ -583,7 +583,7 @@ static void sun6i_dsi_setup_timings(struct sun6i_dsi *dsi,
 		 * bytes). Its minimal size is therefore 10 bytes.
 		 */
 #define HBLK_PACKET_OVERHEAD	10
-		hblk = max((unsigned int)HBLK_PACKET_OVERHEAD,
+		hblk = max(HBLK_PACKET_OVERHEAD,
 			   (mode->htotal - (mode->hsync_end - mode->hsync_start)) * Bpp -
 			   HBLK_PACKET_OVERHEAD);
 
diff --git a/drivers/gpu/drm/tegra/vic.c b/drivers/gpu/drm/tegra/vic.c
index da4af5371991..d3e2fab91086 100644
--- a/drivers/gpu/drm/tegra/vic.c
+++ b/drivers/gpu/drm/tegra/vic.c
@@ -275,7 +275,7 @@ cleanup:
 }
 
 
-static int vic_runtime_resume(struct device *dev)
+static int __maybe_unused vic_runtime_resume(struct device *dev)
 {
 	struct vic *vic = dev_get_drvdata(dev);
 	int err;
@@ -309,7 +309,7 @@ disable:
 	return err;
 }
 
-static int vic_runtime_suspend(struct device *dev)
+static int __maybe_unused vic_runtime_suspend(struct device *dev)
 {
 	struct vic *vic = dev_get_drvdata(dev);
 	int err;
diff --git a/drivers/gpu/drm/tiny/simpledrm.c b/drivers/gpu/drm/tiny/simpledrm.c
index 3e3f9ba1e885..f3c2c173ca4b 100644
--- a/drivers/gpu/drm/tiny/simpledrm.c
+++ b/drivers/gpu/drm/tiny/simpledrm.c
@@ -614,7 +614,7 @@ static const struct drm_connector_funcs simpledrm_connector_funcs = {
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
 };
 
-static int
+static enum drm_mode_status
 simpledrm_simple_display_pipe_mode_valid(struct drm_simple_display_pipe *pipe,
 				    const struct drm_display_mode *mode)
 {
diff --git a/drivers/gpu/drm/tiny/st7735r.c b/drivers/gpu/drm/tiny/st7735r.c
index fc40dd10efa8..713e4b286210 100644
--- a/drivers/gpu/drm/tiny/st7735r.c
+++ b/drivers/gpu/drm/tiny/st7735r.c
@@ -174,6 +174,7 @@ MODULE_DEVICE_TABLE(of, st7735r_of_match);
 
 static const struct spi_device_id st7735r_id[] = {
 	{ "jd-t18003-t01", (uintptr_t)&jd_t18003_t01_cfg },
+	{ "rh128128t", (uintptr_t)&rh128128t_cfg },
 	{ },
 };
 MODULE_DEVICE_TABLE(spi, st7735r_id);
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 900edaf5d68e..33e78f56123e 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -987,7 +987,7 @@ int ttm_bo_validate(struct ttm_buffer_object *bo,
 	/*
 	 * We might need to add a TTM.
 	 */
-	if (bo->resource->mem_type == TTM_PL_SYSTEM) {
+	if (!bo->resource || bo->resource->mem_type == TTM_PL_SYSTEM) {
 		ret = ttm_tt_create(bo, true);
 		if (ret)
 			return ret;
diff --git a/drivers/gpu/drm/v3d/v3d_bo.c b/drivers/gpu/drm/v3d/v3d_bo.c
index 6a8731ab9d7d..0d9af62f69ad 100644
--- a/drivers/gpu/drm/v3d/v3d_bo.c
+++ b/drivers/gpu/drm/v3d/v3d_bo.c
@@ -47,18 +47,18 @@ void v3d_free_object(struct drm_gem_object *obj)
 	/* GPU execution may have dirtied any pages in the BO. */
 	bo->base.pages_mark_dirty_on_put = true;
 
-	drm_gem_shmem_free_object(obj);
+	drm_gem_shmem_free(&bo->base);
 }
 
 static const struct drm_gem_object_funcs v3d_gem_funcs = {
 	.free = v3d_free_object,
-	.print_info = drm_gem_shmem_print_info,
-	.pin = drm_gem_shmem_pin,
-	.unpin = drm_gem_shmem_unpin,
-	.get_sg_table = drm_gem_shmem_get_sg_table,
-	.vmap = drm_gem_shmem_vmap,
-	.vunmap = drm_gem_shmem_vunmap,
-	.mmap = drm_gem_shmem_mmap,
+	.print_info = drm_gem_shmem_object_print_info,
+	.pin = drm_gem_shmem_object_pin,
+	.unpin = drm_gem_shmem_object_unpin,
+	.get_sg_table = drm_gem_shmem_object_get_sg_table,
+	.vmap = drm_gem_shmem_object_vmap,
+	.vunmap = drm_gem_shmem_object_vunmap,
+	.mmap = drm_gem_shmem_object_mmap,
 };
 
 /* gem_create_object function for allocating a BO struct and doing
@@ -95,7 +95,7 @@ v3d_bo_create_finish(struct drm_gem_object *obj)
 	/* So far we pin the BO in the MMU for its lifetime, so use
 	 * shmem's helper for getting a lifetime sgt.
 	 */
-	sgt = drm_gem_shmem_get_pages_sgt(&bo->base.base);
+	sgt = drm_gem_shmem_get_pages_sgt(&bo->base);
 	if (IS_ERR(sgt))
 		return PTR_ERR(sgt);
 
@@ -141,7 +141,7 @@ struct v3d_bo *v3d_bo_create(struct drm_device *dev, struct drm_file *file_priv,
 	return bo;
 
 free_obj:
-	drm_gem_shmem_free_object(&shmem_obj->base);
+	drm_gem_shmem_free(shmem_obj);
 	return ERR_PTR(ret);
 }
 
@@ -159,7 +159,7 @@ v3d_prime_import_sg_table(struct drm_device *dev,
 
 	ret = v3d_bo_create_finish(obj);
 	if (ret) {
-		drm_gem_shmem_free_object(obj);
+		drm_gem_shmem_free(&to_v3d_bo(obj)->base);
 		return ERR_PTR(ret);
 	}
 
diff --git a/drivers/gpu/drm/vc4/Kconfig b/drivers/gpu/drm/vc4/Kconfig
index 345a5570a3da..e2c147d4015e 100644
--- a/drivers/gpu/drm/vc4/Kconfig
+++ b/drivers/gpu/drm/vc4/Kconfig
@@ -5,6 +5,7 @@ config DRM_VC4
 	depends on DRM
 	depends on SND && SND_SOC
 	depends on COMMON_CLK
+	depends on PM
 	select DRM_KMS_HELPER
 	select DRM_KMS_CMA_HELPER
 	select DRM_GEM_CMA_HELPER
diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index 88dbb282d15c..3b8576f19321 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -330,7 +330,8 @@ static void vc4_crtc_config_pv(struct drm_crtc *crtc, struct drm_atomic_state *s
 	u32 pixel_rep = (mode->flags & DRM_MODE_FLAG_DBLCLK) ? 2 : 1;
 	bool is_dsi = (vc4_encoder->type == VC4_ENCODER_TYPE_DSI0 ||
 		       vc4_encoder->type == VC4_ENCODER_TYPE_DSI1);
-	u32 format = is_dsi ? PV_CONTROL_FORMAT_DSIV_24 : PV_CONTROL_FORMAT_24;
+	bool is_dsi1 = vc4_encoder->type == VC4_ENCODER_TYPE_DSI1;
+	u32 format = is_dsi1 ? PV_CONTROL_FORMAT_DSIV_24 : PV_CONTROL_FORMAT_24;
 	u8 ppc = pv_data->pixels_per_clock;
 	bool debug_dump_regs = false;
 
@@ -356,7 +357,8 @@ static void vc4_crtc_config_pv(struct drm_crtc *crtc, struct drm_atomic_state *s
 				 PV_HORZB_HACTIVE));
 
 	CRTC_WRITE(PV_VERTA,
-		   VC4_SET_FIELD(mode->crtc_vtotal - mode->crtc_vsync_end,
+		   VC4_SET_FIELD(mode->crtc_vtotal - mode->crtc_vsync_end +
+				 interlace,
 				 PV_VERTA_VBP) |
 		   VC4_SET_FIELD(mode->crtc_vsync_end - mode->crtc_vsync_start,
 				 PV_VERTA_VSYNC));
@@ -368,7 +370,7 @@ static void vc4_crtc_config_pv(struct drm_crtc *crtc, struct drm_atomic_state *s
 	if (interlace) {
 		CRTC_WRITE(PV_VERTA_EVEN,
 			   VC4_SET_FIELD(mode->crtc_vtotal -
-					 mode->crtc_vsync_end - 1,
+					 mode->crtc_vsync_end,
 					 PV_VERTA_VBP) |
 			   VC4_SET_FIELD(mode->crtc_vsync_end -
 					 mode->crtc_vsync_start,
@@ -388,7 +390,7 @@ static void vc4_crtc_config_pv(struct drm_crtc *crtc, struct drm_atomic_state *s
 			   PV_VCONTROL_CONTINUOUS |
 			   (is_dsi ? PV_VCONTROL_DSI : 0) |
 			   PV_VCONTROL_INTERLACE |
-			   VC4_SET_FIELD(mode->htotal * pixel_rep / 2,
+			   VC4_SET_FIELD(mode->htotal * pixel_rep / (2 * ppc),
 					 PV_VCONTROL_ODD_DELAY));
 		CRTC_WRITE(PV_VSYNCD_EVEN, 0);
 	} else {
diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c
index f6c16c5aee68..ef8fa2850ed6 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -214,6 +214,15 @@ static void vc4_match_add_drivers(struct device *dev,
 	}
 }
 
+static const struct of_device_id vc4_dma_range_matches[] = {
+	{ .compatible = "brcm,bcm2711-hvs" },
+	{ .compatible = "brcm,bcm2835-hvs" },
+	{ .compatible = "brcm,bcm2835-v3d" },
+	{ .compatible = "brcm,cygnus-v3d" },
+	{ .compatible = "brcm,vc4-v3d" },
+	{}
+};
+
 static int vc4_drm_bind(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
@@ -231,6 +240,16 @@ static int vc4_drm_bind(struct device *dev)
 		vc4_drm_driver.driver_features &= ~DRIVER_RENDER;
 	of_node_put(node);
 
+	node = of_find_matching_node_and_match(NULL, vc4_dma_range_matches,
+					       NULL);
+	if (node) {
+		ret = of_dma_configure(dev, node, true);
+		of_node_put(node);
+
+		if (ret)
+			return ret;
+	}
+
 	vc4 = devm_drm_dev_alloc(dev, &vc4_drm_driver, struct vc4_dev, base);
 	if (IS_ERR(vc4))
 		return PTR_ERR(vc4);
diff --git a/drivers/gpu/drm/vc4/vc4_dsi.c b/drivers/gpu/drm/vc4/vc4_dsi.c
index ca8506316660..b7b2c76770dc 100644
--- a/drivers/gpu/drm/vc4/vc4_dsi.c
+++ b/drivers/gpu/drm/vc4/vc4_dsi.c
@@ -181,8 +181,50 @@
 
 #define DSI0_TXPKT_PIX_FIFO		0x20 /* AKA PIX_FIFO */
 
-#define DSI0_INT_STAT		0x24
-#define DSI0_INT_EN		0x28
+#define DSI0_INT_STAT			0x24
+#define DSI0_INT_EN			0x28
+# define DSI0_INT_FIFO_ERR		BIT(25)
+# define DSI0_INT_CMDC_DONE_MASK	VC4_MASK(24, 23)
+# define DSI0_INT_CMDC_DONE_SHIFT	23
+#  define DSI0_INT_CMDC_DONE_NO_REPEAT		1
+#  define DSI0_INT_CMDC_DONE_REPEAT		3
+# define DSI0_INT_PHY_DIR_RTF		BIT(22)
+# define DSI0_INT_PHY_D1_ULPS		BIT(21)
+# define DSI0_INT_PHY_D1_STOP		BIT(20)
+# define DSI0_INT_PHY_RXLPDT		BIT(19)
+# define DSI0_INT_PHY_RXTRIG		BIT(18)
+# define DSI0_INT_PHY_D0_ULPS		BIT(17)
+# define DSI0_INT_PHY_D0_LPDT		BIT(16)
+# define DSI0_INT_PHY_D0_FTR		BIT(15)
+# define DSI0_INT_PHY_D0_STOP		BIT(14)
+/* Signaled when the clock lane enters the given state. */
+# define DSI0_INT_PHY_CLK_ULPS		BIT(13)
+# define DSI0_INT_PHY_CLK_HS		BIT(12)
+# define DSI0_INT_PHY_CLK_FTR		BIT(11)
+/* Signaled on timeouts */
+# define DSI0_INT_PR_TO			BIT(10)
+# define DSI0_INT_TA_TO			BIT(9)
+# define DSI0_INT_LPRX_TO		BIT(8)
+# define DSI0_INT_HSTX_TO		BIT(7)
+/* Contention on a line when trying to drive the line low */
+# define DSI0_INT_ERR_CONT_LP1		BIT(6)
+# define DSI0_INT_ERR_CONT_LP0		BIT(5)
+/* Control error: incorrect line state sequence on data lane 0. */
+# define DSI0_INT_ERR_CONTROL		BIT(4)
+# define DSI0_INT_ERR_SYNC_ESC		BIT(3)
+# define DSI0_INT_RX2_PKT		BIT(2)
+# define DSI0_INT_RX1_PKT		BIT(1)
+# define DSI0_INT_CMD_PKT		BIT(0)
+
+#define DSI0_INTERRUPTS_ALWAYS_ENABLED	(DSI0_INT_ERR_SYNC_ESC | \
+					 DSI0_INT_ERR_CONTROL |	 \
+					 DSI0_INT_ERR_CONT_LP0 | \
+					 DSI0_INT_ERR_CONT_LP1 | \
+					 DSI0_INT_HSTX_TO |	 \
+					 DSI0_INT_LPRX_TO |	 \
+					 DSI0_INT_TA_TO |	 \
+					 DSI0_INT_PR_TO)
+
 # define DSI1_INT_PHY_D3_ULPS		BIT(30)
 # define DSI1_INT_PHY_D3_STOP		BIT(29)
 # define DSI1_INT_PHY_D2_ULPS		BIT(28)
@@ -761,6 +803,9 @@ static void vc4_dsi_encoder_disable(struct drm_encoder *encoder)
 	list_for_each_entry_reverse(iter, &dsi->bridge_chain, chain_node) {
 		if (iter->funcs->disable)
 			iter->funcs->disable(iter);
+
+		if (iter == dsi->bridge)
+			break;
 	}
 
 	vc4_dsi_ulps(dsi, true);
@@ -805,11 +850,9 @@ static bool vc4_dsi_encoder_mode_fixup(struct drm_encoder *encoder,
 	/* Find what divider gets us a faster clock than the requested
 	 * pixel clock.
 	 */
-	for (divider = 1; divider < 8; divider++) {
-		if (parent_rate / divider < pll_clock) {
-			divider--;
+	for (divider = 1; divider < 255; divider++) {
+		if (parent_rate / (divider + 1) < pll_clock)
 			break;
-		}
 	}
 
 	/* Now that we've picked a PLL divider, calculate back to its
@@ -894,6 +937,9 @@ static void vc4_dsi_encoder_enable(struct drm_encoder *encoder)
 
 		DSI_PORT_WRITE(PHY_AFEC0, afec0);
 
+		/* AFEC reset hold time */
+		mdelay(1);
+
 		DSI_PORT_WRITE(PHY_AFEC1,
 			       VC4_SET_FIELD(6,  DSI0_PHY_AFEC1_IDR_DLANE1) |
 			       VC4_SET_FIELD(6,  DSI0_PHY_AFEC1_IDR_DLANE0) |
@@ -1060,12 +1106,9 @@ static void vc4_dsi_encoder_enable(struct drm_encoder *encoder)
 		DSI_PORT_WRITE(CTRL, DSI_PORT_READ(CTRL) | DSI1_CTRL_EN);
 
 	/* Bring AFE out of reset. */
-	if (dsi->variant->port == 0) {
-	} else {
-		DSI_PORT_WRITE(PHY_AFEC0,
-			       DSI_PORT_READ(PHY_AFEC0) &
-			       ~DSI1_PHY_AFEC0_RESET);
-	}
+	DSI_PORT_WRITE(PHY_AFEC0,
+		       DSI_PORT_READ(PHY_AFEC0) &
+		       ~DSI_PORT_BIT(PHY_AFEC0_RESET));
 
 	vc4_dsi_ulps(dsi, false);
 
@@ -1184,13 +1227,28 @@ static ssize_t vc4_dsi_host_transfer(struct mipi_dsi_host *host,
 	/* Enable the appropriate interrupt for the transfer completion. */
 	dsi->xfer_result = 0;
 	reinit_completion(&dsi->xfer_completion);
-	DSI_PORT_WRITE(INT_STAT, DSI1_INT_TXPKT1_DONE | DSI1_INT_PHY_DIR_RTF);
-	if (msg->rx_len) {
-		DSI_PORT_WRITE(INT_EN, (DSI1_INTERRUPTS_ALWAYS_ENABLED |
-					DSI1_INT_PHY_DIR_RTF));
+	if (dsi->variant->port == 0) {
+		DSI_PORT_WRITE(INT_STAT,
+			       DSI0_INT_CMDC_DONE_MASK | DSI1_INT_PHY_DIR_RTF);
+		if (msg->rx_len) {
+			DSI_PORT_WRITE(INT_EN, (DSI0_INTERRUPTS_ALWAYS_ENABLED |
+						DSI0_INT_PHY_DIR_RTF));
+		} else {
+			DSI_PORT_WRITE(INT_EN,
+				       (DSI0_INTERRUPTS_ALWAYS_ENABLED |
+					VC4_SET_FIELD(DSI0_INT_CMDC_DONE_NO_REPEAT,
+						      DSI0_INT_CMDC_DONE)));
+		}
 	} else {
-		DSI_PORT_WRITE(INT_EN, (DSI1_INTERRUPTS_ALWAYS_ENABLED |
-					DSI1_INT_TXPKT1_DONE));
+		DSI_PORT_WRITE(INT_STAT,
+			       DSI1_INT_TXPKT1_DONE | DSI1_INT_PHY_DIR_RTF);
+		if (msg->rx_len) {
+			DSI_PORT_WRITE(INT_EN, (DSI1_INTERRUPTS_ALWAYS_ENABLED |
+						DSI1_INT_PHY_DIR_RTF));
+		} else {
+			DSI_PORT_WRITE(INT_EN, (DSI1_INTERRUPTS_ALWAYS_ENABLED |
+						DSI1_INT_TXPKT1_DONE));
+		}
 	}
 
 	/* Send the packet. */
@@ -1207,7 +1265,7 @@ static ssize_t vc4_dsi_host_transfer(struct mipi_dsi_host *host,
 		ret = dsi->xfer_result;
 	}
 
-	DSI_PORT_WRITE(INT_EN, DSI1_INTERRUPTS_ALWAYS_ENABLED);
+	DSI_PORT_WRITE(INT_EN, DSI_PORT_BIT(INTERRUPTS_ALWAYS_ENABLED));
 
 	if (ret)
 		goto reset_fifo_and_return;
@@ -1253,7 +1311,7 @@ reset_fifo_and_return:
 		       DSI_PORT_BIT(CTRL_RESET_FIFOS));
 
 	DSI_PORT_WRITE(TXPKT1C, 0);
-	DSI_PORT_WRITE(INT_EN, DSI1_INTERRUPTS_ALWAYS_ENABLED);
+	DSI_PORT_WRITE(INT_EN, DSI_PORT_BIT(INTERRUPTS_ALWAYS_ENABLED));
 	return ret;
 }
 
@@ -1390,26 +1448,28 @@ static irqreturn_t vc4_dsi_irq_handler(int irq, void *data)
 	DSI_PORT_WRITE(INT_STAT, stat);
 
 	dsi_handle_error(dsi, &ret, stat,
-			 DSI1_INT_ERR_SYNC_ESC, "LPDT sync");
+			 DSI_PORT_BIT(INT_ERR_SYNC_ESC), "LPDT sync");
 	dsi_handle_error(dsi, &ret, stat,
-			 DSI1_INT_ERR_CONTROL, "data lane 0 sequence");
+			 DSI_PORT_BIT(INT_ERR_CONTROL), "data lane 0 sequence");
 	dsi_handle_error(dsi, &ret, stat,
-			 DSI1_INT_ERR_CONT_LP0, "LP0 contention");
+			 DSI_PORT_BIT(INT_ERR_CONT_LP0), "LP0 contention");
 	dsi_handle_error(dsi, &ret, stat,
-			 DSI1_INT_ERR_CONT_LP1, "LP1 contention");
+			 DSI_PORT_BIT(INT_ERR_CONT_LP1), "LP1 contention");
 	dsi_handle_error(dsi, &ret, stat,
-			 DSI1_INT_HSTX_TO, "HSTX timeout");
+			 DSI_PORT_BIT(INT_HSTX_TO), "HSTX timeout");
 	dsi_handle_error(dsi, &ret, stat,
-			 DSI1_INT_LPRX_TO, "LPRX timeout");
+			 DSI_PORT_BIT(INT_LPRX_TO), "LPRX timeout");
 	dsi_handle_error(dsi, &ret, stat,
-			 DSI1_INT_TA_TO, "turnaround timeout");
+			 DSI_PORT_BIT(INT_TA_TO), "turnaround timeout");
 	dsi_handle_error(dsi, &ret, stat,
-			 DSI1_INT_PR_TO, "peripheral reset timeout");
+			 DSI_PORT_BIT(INT_PR_TO), "peripheral reset timeout");
 
-	if (stat & (DSI1_INT_TXPKT1_DONE | DSI1_INT_PHY_DIR_RTF)) {
+	if (stat & ((dsi->variant->port ? DSI1_INT_TXPKT1_DONE :
+					  DSI0_INT_CMDC_DONE_MASK) |
+		    DSI_PORT_BIT(INT_PHY_DIR_RTF))) {
 		complete(&dsi->xfer_completion);
 		ret = IRQ_HANDLED;
-	} else if (stat & DSI1_INT_HSTX_TO) {
+	} else if (stat & DSI_PORT_BIT(INT_HSTX_TO)) {
 		complete(&dsi->xfer_completion);
 		dsi->xfer_result = -ETIMEDOUT;
 		ret = IRQ_HANDLED;
@@ -1487,22 +1547,32 @@ vc4_dsi_init_phy_clocks(struct vc4_dsi *dsi)
 				      dsi->clk_onecell);
 }
 
+static void vc4_dsi_dma_mem_release(void *ptr)
+{
+	struct vc4_dsi *dsi = ptr;
+	struct device *dev = &dsi->pdev->dev;
+
+	dma_free_coherent(dev, 4, dsi->reg_dma_mem, dsi->reg_dma_paddr);
+	dsi->reg_dma_mem = NULL;
+}
+
+static void vc4_dsi_dma_chan_release(void *ptr)
+{
+	struct vc4_dsi *dsi = ptr;
+
+	dma_release_channel(dsi->reg_dma_chan);
+	dsi->reg_dma_chan = NULL;
+}
+
 static int vc4_dsi_bind(struct device *dev, struct device *master, void *data)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct drm_device *drm = dev_get_drvdata(master);
 	struct vc4_dsi *dsi = dev_get_drvdata(dev);
 	struct vc4_dsi_encoder *vc4_dsi_encoder;
-	struct drm_panel *panel;
-	const struct of_device_id *match;
-	dma_cap_mask_t dma_mask;
 	int ret;
 
-	match = of_match_device(vc4_dsi_dt_match, dev);
-	if (!match)
-		return -ENODEV;
-
-	dsi->variant = match->data;
+	dsi->variant = of_device_get_match_data(dev);
 
 	vc4_dsi_encoder = devm_kzalloc(dev, sizeof(*vc4_dsi_encoder),
 				       GFP_KERNEL);
@@ -1510,7 +1580,8 @@ static int vc4_dsi_bind(struct device *dev, struct device *master, void *data)
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&dsi->bridge_chain);
-	vc4_dsi_encoder->base.type = VC4_ENCODER_TYPE_DSI1;
+	vc4_dsi_encoder->base.type = dsi->variant->port ?
+			VC4_ENCODER_TYPE_DSI1 : VC4_ENCODER_TYPE_DSI0;
 	vc4_dsi_encoder->dsi = dsi;
 	dsi->encoder = &vc4_dsi_encoder->base.base;
 
@@ -1533,6 +1604,8 @@ static int vc4_dsi_bind(struct device *dev, struct device *master, void *data)
 	 * so set up a channel for talking to it.
 	 */
 	if (dsi->variant->broken_axi_workaround) {
+		dma_cap_mask_t dma_mask;
+
 		dsi->reg_dma_mem = dma_alloc_coherent(dev, 4,
 						      &dsi->reg_dma_paddr,
 						      GFP_KERNEL);
@@ -1541,8 +1614,13 @@ static int vc4_dsi_bind(struct device *dev, struct device *master, void *data)
 			return -ENOMEM;
 		}
 
+		ret = devm_add_action_or_reset(dev, vc4_dsi_dma_mem_release, dsi);
+		if (ret)
+			return ret;
+
 		dma_cap_zero(dma_mask);
 		dma_cap_set(DMA_MEMCPY, dma_mask);
+
 		dsi->reg_dma_chan = dma_request_chan_by_mask(&dma_mask);
 		if (IS_ERR(dsi->reg_dma_chan)) {
 			ret = PTR_ERR(dsi->reg_dma_chan);
@@ -1552,6 +1630,10 @@ static int vc4_dsi_bind(struct device *dev, struct device *master, void *data)
 			return ret;
 		}
 
+		ret = devm_add_action_or_reset(dev, vc4_dsi_dma_chan_release, dsi);
+		if (ret)
+			return ret;
+
 		/* Get the physical address of the device's registers.  The
 		 * struct resource for the regs gives us the bus address
 		 * instead.
@@ -1605,27 +1687,9 @@ static int vc4_dsi_bind(struct device *dev, struct device *master, void *data)
 		return ret;
 	}
 
-	ret = drm_of_find_panel_or_bridge(dev->of_node, 0, 0,
-					  &panel, &dsi->bridge);
-	if (ret) {
-		/* If the bridge or panel pointed by dev->of_node is not
-		 * enabled, just return 0 here so that we don't prevent the DRM
-		 * dev from being registered. Of course that means the DSI
-		 * encoder won't be exposed, but that's not a problem since
-		 * nothing is connected to it.
-		 */
-		if (ret == -ENODEV)
-			return 0;
-
-		return ret;
-	}
-
-	if (panel) {
-		dsi->bridge = devm_drm_panel_bridge_add_typed(dev, panel,
-							      DRM_MODE_CONNECTOR_DSI);
-		if (IS_ERR(dsi->bridge))
-			return PTR_ERR(dsi->bridge);
-	}
+	dsi->bridge = devm_drm_of_get_bridge(dev, dev->of_node, 0, 0);
+	if (IS_ERR(dsi->bridge))
+		return PTR_ERR(dsi->bridge);
 
 	/* The esc clock rate is supposed to always be 100Mhz. */
 	ret = clk_set_rate(dsi->escape_clock, 100 * 1000000);
@@ -1663,8 +1727,7 @@ static void vc4_dsi_unbind(struct device *dev, struct device *master,
 {
 	struct vc4_dsi *dsi = dev_get_drvdata(dev);
 
-	if (dsi->bridge)
-		pm_runtime_disable(dev);
+	pm_runtime_disable(dev);
 
 	/*
 	 * Restore the bridge_chain so the bridge detach procedure can happen
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
index ef7bea7c43a0..9b3e642a08e1 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
@@ -79,6 +79,9 @@
 #define VC5_HDMI_VERTB_VSPO_SHIFT		16
 #define VC5_HDMI_VERTB_VSPO_MASK		VC4_MASK(29, 16)
 
+#define VC5_HDMI_MISC_CONTROL_PIXEL_REP_SHIFT	0
+#define VC5_HDMI_MISC_CONTROL_PIXEL_REP_MASK	VC4_MASK(3, 0)
+
 #define VC5_HDMI_SCRAMBLER_CTL_ENABLE		BIT(0)
 
 #define VC5_HDMI_DEEP_COLOR_CONFIG_1_INIT_PACK_PHASE_SHIFT	8
@@ -173,9 +176,9 @@ vc4_hdmi_connector_detect(struct drm_connector *connector, bool force)
 
 	WARN_ON(pm_runtime_resume_and_get(&vc4_hdmi->pdev->dev));
 
-	if (vc4_hdmi->hpd_gpio &&
-	    gpiod_get_value_cansleep(vc4_hdmi->hpd_gpio)) {
-		connected = true;
+	if (vc4_hdmi->hpd_gpio) {
+		if (gpiod_get_value_cansleep(vc4_hdmi->hpd_gpio))
+			connected = true;
 	} else if (drm_probe_ddc(vc4_hdmi->ddc)) {
 		connected = true;
 	} else if (HDMI_READ(HDMI_HOTPLUG) & VC4_HDMI_HOTPLUG_CONNECTED) {
@@ -735,12 +738,12 @@ static void vc4_hdmi_set_timings(struct vc4_hdmi *vc4_hdmi,
 				   VC4_HDMI_VERTA_VFP) |
 		     VC4_SET_FIELD(mode->crtc_vdisplay, VC4_HDMI_VERTA_VAL));
 	u32 vertb = (VC4_SET_FIELD(0, VC4_HDMI_VERTB_VSPO) |
-		     VC4_SET_FIELD(mode->crtc_vtotal - mode->crtc_vsync_end,
+		     VC4_SET_FIELD(mode->crtc_vtotal - mode->crtc_vsync_end +
+				   interlaced,
 				   VC4_HDMI_VERTB_VBP));
 	u32 vertb_even = (VC4_SET_FIELD(0, VC4_HDMI_VERTB_VSPO) |
 			  VC4_SET_FIELD(mode->crtc_vtotal -
-					mode->crtc_vsync_end -
-					interlaced,
+					mode->crtc_vsync_end,
 					VC4_HDMI_VERTB_VBP));
 
 	HDMI_WRITE(HDMI_HORZA,
@@ -780,13 +783,13 @@ static void vc5_hdmi_set_timings(struct vc4_hdmi *vc4_hdmi,
 		     VC4_SET_FIELD(mode->crtc_vsync_start - mode->crtc_vdisplay,
 				   VC5_HDMI_VERTA_VFP) |
 		     VC4_SET_FIELD(mode->crtc_vdisplay, VC5_HDMI_VERTA_VAL));
-	u32 vertb = (VC4_SET_FIELD(0, VC5_HDMI_VERTB_VSPO) |
+	u32 vertb = (VC4_SET_FIELD(mode->htotal >> (2 - pixel_rep),
+				   VC5_HDMI_VERTB_VSPO) |
 		     VC4_SET_FIELD(mode->crtc_vtotal - mode->crtc_vsync_end,
 				   VC4_HDMI_VERTB_VBP));
 	u32 vertb_even = (VC4_SET_FIELD(0, VC5_HDMI_VERTB_VSPO) |
 			  VC4_SET_FIELD(mode->crtc_vtotal -
-					mode->crtc_vsync_end -
-					interlaced,
+					mode->crtc_vsync_end - interlaced,
 					VC4_HDMI_VERTB_VBP));
 	unsigned char gcp;
 	bool gcp_en;
@@ -849,6 +852,11 @@ static void vc5_hdmi_set_timings(struct vc4_hdmi *vc4_hdmi,
 	reg |= gcp_en ? VC5_HDMI_GCP_CONFIG_GCP_ENABLE : 0;
 	HDMI_WRITE(HDMI_GCP_CONFIG, reg);
 
+	reg = HDMI_READ(HDMI_MISC_CONTROL);
+	reg &= ~VC5_HDMI_MISC_CONTROL_PIXEL_REP_MASK;
+	reg |= VC4_SET_FIELD(0, VC5_HDMI_MISC_CONTROL_PIXEL_REP);
+	HDMI_WRITE(HDMI_MISC_CONTROL, reg);
+
 	HDMI_WRITE(HDMI_CLOCK_STOP, 0);
 }
 
@@ -1383,10 +1391,10 @@ static int vc4_hdmi_audio_prepare(struct device *dev, void *data,
 
 	/* Set the MAI threshold */
 	HDMI_WRITE(HDMI_MAI_THR,
-		   VC4_SET_FIELD(0x10, VC4_HD_MAI_THR_PANICHIGH) |
-		   VC4_SET_FIELD(0x10, VC4_HD_MAI_THR_PANICLOW) |
-		   VC4_SET_FIELD(0x10, VC4_HD_MAI_THR_DREQHIGH) |
-		   VC4_SET_FIELD(0x10, VC4_HD_MAI_THR_DREQLOW));
+		   VC4_SET_FIELD(0x08, VC4_HD_MAI_THR_PANICHIGH) |
+		   VC4_SET_FIELD(0x08, VC4_HD_MAI_THR_PANICLOW) |
+		   VC4_SET_FIELD(0x06, VC4_HD_MAI_THR_DREQHIGH) |
+		   VC4_SET_FIELD(0x08, VC4_HD_MAI_THR_DREQLOW));
 
 	HDMI_WRITE(HDMI_MAI_CONFIG,
 		   VC4_HDMI_MAI_CONFIG_BIT_REVERSE |
@@ -1470,12 +1478,12 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *vc4_hdmi)
 	struct device *dev = &vc4_hdmi->pdev->dev;
 	struct platform_device *codec_pdev;
 	const __be32 *addr;
-	int index;
+	int index, len;
 	int ret;
 
-	if (!of_find_property(dev->of_node, "dmas", NULL)) {
+	if (!of_find_property(dev->of_node, "dmas", &len) || !len) {
 		dev_warn(dev,
-			 "'dmas' DT property is missing, no HDMI audio\n");
+			 "'dmas' DT property is missing or empty, no HDMI audio\n");
 		return 0;
 	}
 
@@ -2114,7 +2122,7 @@ static int vc5_hdmi_init_resources(struct vc4_hdmi *vc4_hdmi)
 	return 0;
 }
 
-static int __maybe_unused vc4_hdmi_runtime_suspend(struct device *dev)
+static int vc4_hdmi_runtime_suspend(struct device *dev)
 {
 	struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev);
 
@@ -2211,17 +2219,15 @@ static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data)
 	if (ret)
 		goto err_put_ddc;
 
+	pm_runtime_enable(dev);
+
 	/*
-	 * We need to have the device powered up at this point to call
-	 * our reset hook and for the CEC init.
+	 *  We need to have the device powered up at this point to call
+	 *  our reset hook and for the CEC init.
 	 */
-	ret = vc4_hdmi_runtime_resume(dev);
+	ret = pm_runtime_resume_and_get(dev);
 	if (ret)
-		goto err_put_ddc;
-
-	pm_runtime_get_noresume(dev);
-	pm_runtime_set_active(dev);
-	pm_runtime_enable(dev);
+		goto err_disable_runtime_pm;
 
 	if (vc4_hdmi->variant->reset)
 		vc4_hdmi->variant->reset(vc4_hdmi);
@@ -2270,6 +2276,7 @@ err_destroy_conn:
 err_destroy_encoder:
 	drm_encoder_cleanup(encoder);
 	pm_runtime_put_sync(dev);
+err_disable_runtime_pm:
 	pm_runtime_disable(dev);
 err_put_ddc:
 	put_device(&vc4_hdmi->ddc->dev);
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi_regs.h b/drivers/gpu/drm/vc4/vc4_hdmi_regs.h
index 19d2fdc446bc..f126fa425a1d 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi_regs.h
+++ b/drivers/gpu/drm/vc4/vc4_hdmi_regs.h
@@ -123,6 +123,7 @@ enum vc4_hdmi_field {
 	HDMI_VERTB0,
 	HDMI_VERTB1,
 	HDMI_VID_CTL,
+	HDMI_MISC_CONTROL,
 };
 
 struct vc4_hdmi_register {
@@ -233,6 +234,7 @@ static const struct vc4_hdmi_register __maybe_unused vc5_hdmi_hdmi0_fields[] = {
 	VC4_HDMI_REG(HDMI_VERTB0, 0x0f0),
 	VC4_HDMI_REG(HDMI_VERTA1, 0x0f4),
 	VC4_HDMI_REG(HDMI_VERTB1, 0x0f8),
+	VC4_HDMI_REG(HDMI_MISC_CONTROL, 0x100),
 	VC4_HDMI_REG(HDMI_MAI_CHANNEL_MAP, 0x09c),
 	VC4_HDMI_REG(HDMI_MAI_CONFIG, 0x0a0),
 	VC4_HDMI_REG(HDMI_DEEP_COLOR_CONFIG_1, 0x170),
@@ -313,6 +315,7 @@ static const struct vc4_hdmi_register __maybe_unused vc5_hdmi_hdmi1_fields[] = {
 	VC4_HDMI_REG(HDMI_VERTB0, 0x0f0),
 	VC4_HDMI_REG(HDMI_VERTA1, 0x0f4),
 	VC4_HDMI_REG(HDMI_VERTB1, 0x0f8),
+	VC4_HDMI_REG(HDMI_MISC_CONTROL, 0x100),
 	VC4_HDMI_REG(HDMI_MAI_CHANNEL_MAP, 0x09c),
 	VC4_HDMI_REG(HDMI_MAI_CONFIG, 0x0a0),
 	VC4_HDMI_REG(HDMI_DEEP_COLOR_CONFIG_1, 0x170),
diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index 19161b6ab27f..8574acefd40e 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -303,16 +303,16 @@ static int vc4_plane_margins_adj(struct drm_plane_state *pstate)
 					       adjhdisplay,
 					       crtc_state->mode.hdisplay);
 	vc4_pstate->crtc_x += left;
-	if (vc4_pstate->crtc_x > crtc_state->mode.hdisplay - left)
-		vc4_pstate->crtc_x = crtc_state->mode.hdisplay - left;
+	if (vc4_pstate->crtc_x > crtc_state->mode.hdisplay - right)
+		vc4_pstate->crtc_x = crtc_state->mode.hdisplay - right;
 
 	adjvdisplay = crtc_state->mode.vdisplay - (top + bottom);
 	vc4_pstate->crtc_y = DIV_ROUND_CLOSEST(vc4_pstate->crtc_y *
 					       adjvdisplay,
 					       crtc_state->mode.vdisplay);
 	vc4_pstate->crtc_y += top;
-	if (vc4_pstate->crtc_y > crtc_state->mode.vdisplay - top)
-		vc4_pstate->crtc_y = crtc_state->mode.vdisplay - top;
+	if (vc4_pstate->crtc_y > crtc_state->mode.vdisplay - bottom)
+		vc4_pstate->crtc_y = crtc_state->mode.vdisplay - bottom;
 
 	vc4_pstate->crtc_w = DIV_ROUND_CLOSEST(vc4_pstate->crtc_w *
 					       adjhdisplay,
@@ -332,7 +332,6 @@ static int vc4_plane_setup_clipping_and_scaling(struct drm_plane_state *state)
 	struct vc4_plane_state *vc4_state = to_vc4_plane_state(state);
 	struct drm_framebuffer *fb = state->fb;
 	struct drm_gem_cma_object *bo = drm_fb_cma_get_gem_obj(fb, 0);
-	u32 subpixel_src_mask = (1 << 16) - 1;
 	int num_planes = fb->format->num_planes;
 	struct drm_crtc_state *crtc_state;
 	u32 h_subsample = fb->format->hsub;
@@ -354,18 +353,15 @@ static int vc4_plane_setup_clipping_and_scaling(struct drm_plane_state *state)
 	for (i = 0; i < num_planes; i++)
 		vc4_state->offsets[i] = bo->paddr + fb->offsets[i];
 
-	/* We don't support subpixel source positioning for scaling. */
-	if ((state->src.x1 & subpixel_src_mask) ||
-	    (state->src.x2 & subpixel_src_mask) ||
-	    (state->src.y1 & subpixel_src_mask) ||
-	    (state->src.y2 & subpixel_src_mask)) {
-		return -EINVAL;
-	}
-
-	vc4_state->src_x = state->src.x1 >> 16;
-	vc4_state->src_y = state->src.y1 >> 16;
-	vc4_state->src_w[0] = (state->src.x2 - state->src.x1) >> 16;
-	vc4_state->src_h[0] = (state->src.y2 - state->src.y1) >> 16;
+	/*
+	 * We don't support subpixel source positioning for scaling,
+	 * but fractional coordinates can be generated by clipping
+	 * so just round for now
+	 */
+	vc4_state->src_x = DIV_ROUND_CLOSEST(state->src.x1, 1 << 16);
+	vc4_state->src_y = DIV_ROUND_CLOSEST(state->src.y1, 1 << 16);
+	vc4_state->src_w[0] = DIV_ROUND_CLOSEST(state->src.x2, 1 << 16) - vc4_state->src_x;
+	vc4_state->src_h[0] = DIV_ROUND_CLOSEST(state->src.y2, 1 << 16) - vc4_state->src_y;
 
 	vc4_state->crtc_x = state->dst.x1;
 	vc4_state->crtc_y = state->dst.y1;
diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
index 5c1ad1596889..15c3e63db396 100644
--- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c
+++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
@@ -512,8 +512,10 @@ static int virtio_gpu_get_caps_ioctl(struct drm_device *dev,
 	spin_unlock(&vgdev->display_info_lock);
 
 	/* not in cache - need to talk to hw */
-	virtio_gpu_cmd_get_capset(vgdev, found_valid, args->cap_set_ver,
-				  &cache_ent);
+	ret = virtio_gpu_cmd_get_capset(vgdev, found_valid, args->cap_set_ver,
+					&cache_ent);
+	if (ret)
+		return ret;
 	virtio_gpu_notify(vgdev);
 
 copy_exit:
diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c
index f648b0e24447..9af9f355e0a7 100644
--- a/drivers/gpu/drm/virtio/virtgpu_object.c
+++ b/drivers/gpu/drm/virtio/virtgpu_object.c
@@ -79,10 +79,10 @@ void virtio_gpu_cleanup_object(struct virtio_gpu_object *bo)
 			sg_free_table(shmem->pages);
 			kfree(shmem->pages);
 			shmem->pages = NULL;
-			drm_gem_shmem_unpin(&bo->base.base);
+			drm_gem_shmem_unpin(&bo->base);
 		}
 
-		drm_gem_shmem_free_object(&bo->base.base);
+		drm_gem_shmem_free(&bo->base);
 	} else if (virtio_gpu_is_vram(bo)) {
 		struct virtio_gpu_object_vram *vram = to_virtio_gpu_vram(bo);
 
@@ -116,15 +116,14 @@ static const struct drm_gem_object_funcs virtio_gpu_shmem_funcs = {
 	.free = virtio_gpu_free_object,
 	.open = virtio_gpu_gem_object_open,
 	.close = virtio_gpu_gem_object_close,
-
-	.print_info = drm_gem_shmem_print_info,
+	.print_info = drm_gem_shmem_object_print_info,
 	.export = virtgpu_gem_prime_export,
-	.pin = drm_gem_shmem_pin,
-	.unpin = drm_gem_shmem_unpin,
-	.get_sg_table = drm_gem_shmem_get_sg_table,
-	.vmap = drm_gem_shmem_vmap,
-	.vunmap = drm_gem_shmem_vunmap,
-	.mmap = drm_gem_shmem_mmap,
+	.pin = drm_gem_shmem_object_pin,
+	.unpin = drm_gem_shmem_object_unpin,
+	.get_sg_table = drm_gem_shmem_object_get_sg_table,
+	.vmap = drm_gem_shmem_object_vmap,
+	.vunmap = drm_gem_shmem_object_vunmap,
+	.mmap = drm_gem_shmem_object_mmap,
 };
 
 bool virtio_gpu_is_shmem(struct virtio_gpu_object *bo)
@@ -157,7 +156,7 @@ static int virtio_gpu_object_shmem_init(struct virtio_gpu_device *vgdev,
 	struct scatterlist *sg;
 	int si, ret;
 
-	ret = drm_gem_shmem_pin(&bo->base.base);
+	ret = drm_gem_shmem_pin(&bo->base);
 	if (ret < 0)
 		return -EINVAL;
 
@@ -167,10 +166,10 @@ static int virtio_gpu_object_shmem_init(struct virtio_gpu_device *vgdev,
 	 * dma-ops. This is discouraged for other drivers, but should be fine
 	 * since virtio_gpu doesn't support dma-buf import from other devices.
 	 */
-	shmem->pages = drm_gem_shmem_get_sg_table(&bo->base.base);
-	if (!shmem->pages) {
-		drm_gem_shmem_unpin(&bo->base.base);
-		return -EINVAL;
+	shmem->pages = drm_gem_shmem_get_sg_table(&bo->base);
+	if (IS_ERR(shmem->pages)) {
+		drm_gem_shmem_unpin(&bo->base);
+		return PTR_ERR(shmem->pages);
 	}
 
 	if (use_dma_api) {
@@ -277,6 +276,6 @@ err_put_objs:
 err_put_id:
 	virtio_gpu_resource_id_put(vgdev, bo->hw_res_handle);
 err_free_gem:
-	drm_gem_shmem_free_object(&shmem_obj->base);
+	drm_gem_shmem_free(shmem_obj);
 	return ret;
 }
diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_client.c b/drivers/hid/amd-sfh-hid/amd_sfh_client.c
index 6284db50ec9b..ab149b80f86c 100644
--- a/drivers/hid/amd-sfh-hid/amd_sfh_client.c
+++ b/drivers/hid/amd-sfh-hid/amd_sfh_client.c
@@ -154,6 +154,8 @@ int amd_sfh_hid_client_init(struct amd_mp2_dev *privdata)
 	dev = &privdata->pdev->dev;
 
 	cl_data->num_hid_devices = amd_mp2_get_sensor_num(privdata, &cl_data->sensor_idx[0]);
+	if (cl_data->num_hid_devices == 0)
+		return -ENODEV;
 
 	INIT_DELAYED_WORK(&cl_data->work, amd_sfh_work);
 	INIT_DELAYED_WORK(&cl_data->work_buffer, amd_sfh_work_buffer);
diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_hid.c b/drivers/hid/amd-sfh-hid/amd_sfh_hid.c
index a4bda2ac713e..3b0615c6aecf 100644
--- a/drivers/hid/amd-sfh-hid/amd_sfh_hid.c
+++ b/drivers/hid/amd-sfh-hid/amd_sfh_hid.c
@@ -98,11 +98,15 @@ static int amdtp_wait_for_response(struct hid_device *hid)
 
 void amdtp_hid_wakeup(struct hid_device *hid)
 {
-	struct amdtp_hid_data *hid_data = hid->driver_data;
-	struct amdtp_cl_data *cli_data = hid_data->cli_data;
+	struct amdtp_hid_data *hid_data;
+	struct amdtp_cl_data *cli_data;
 
-	cli_data->request_done[cli_data->cur_hid_dev] = true;
-	wake_up_interruptible(&hid_data->hid_wait);
+	if (hid) {
+		hid_data = hid->driver_data;
+		cli_data = hid_data->cli_data;
+		cli_data->request_done[cli_data->cur_hid_dev] = true;
+		wake_up_interruptible(&hid_data->hid_wait);
+	}
 }
 
 static struct hid_ll_driver amdtp_hid_ll_driver = {
diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
index ae8f1f2536e9..f17f061aeb79 100644
--- a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
+++ b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
@@ -281,11 +281,29 @@ static int amd_sfh_irq_init(struct amd_mp2_dev *privdata)
 	return 0;
 }
 
+static const struct dmi_system_id dmi_nodevs[] = {
+	{
+		/*
+		 * Google Chromebooks use Chrome OS Embedded Controller Sensor
+		 * Hub instead of Sensor Hub Fusion and leaves MP2
+		 * uninitialized, which disables all functionalities, even
+		 * including the registers necessary for feature detections.
+		 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Google"),
+		},
+	},
+	{ }
+};
+
 static int amd_mp2_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct amd_mp2_dev *privdata;
 	int rc;
 
+	if (dmi_first_match(dmi_nodevs))
+		return -ENODEV;
+
 	privdata = devm_kzalloc(&pdev->dev, sizeof(*privdata), GFP_KERNEL);
 	if (!privdata)
 		return -ENOMEM;
@@ -323,7 +341,8 @@ static int amd_mp2_pci_probe(struct pci_dev *pdev, const struct pci_device_id *i
 	rc = amd_sfh_hid_client_init(privdata);
 	if (rc) {
 		amd_sfh_clear_intr(privdata);
-		dev_err(&pdev->dev, "amd_sfh_hid_client_init failed\n");
+		if (rc != -EOPNOTSUPP)
+			dev_err(&pdev->dev, "amd_sfh_hid_client_init failed\n");
 		return rc;
 	}
 
diff --git a/drivers/hid/hid-alps.c b/drivers/hid/hid-alps.c
index 2b986d0dbde4..db146d0f7937 100644
--- a/drivers/hid/hid-alps.c
+++ b/drivers/hid/hid-alps.c
@@ -831,6 +831,8 @@ static const struct hid_device_id alps_id[] = {
 	{ HID_DEVICE(HID_BUS_ANY, HID_GROUP_ANY,
 		USB_VENDOR_ID_ALPS_JP, HID_DEVICE_ID_ALPS_U1) },
 	{ HID_DEVICE(HID_BUS_ANY, HID_GROUP_ANY,
+		USB_VENDOR_ID_ALPS_JP, HID_DEVICE_ID_ALPS_U1_UNICORN_LEGACY) },
+	{ HID_DEVICE(HID_BUS_ANY, HID_GROUP_ANY,
 		USB_VENDOR_ID_ALPS_JP, HID_DEVICE_ID_ALPS_T4_BTNLESS) },
 	{ }
 };
diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c
index 08c9a9a60ae4..b59c3dafa6a4 100644
--- a/drivers/hid/hid-asus.c
+++ b/drivers/hid/hid-asus.c
@@ -1212,6 +1212,13 @@ static __u8 *asus_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		rdesc = new_rdesc;
 	}
 
+	if (drvdata->quirks & QUIRK_ROG_NKEY_KEYBOARD &&
+			*rsize == 331 && rdesc[190] == 0x85 && rdesc[191] == 0x5a &&
+			rdesc[204] == 0x95 && rdesc[205] == 0x05) {
+		hid_info(hdev, "Fixing up Asus N-KEY keyb report descriptor\n");
+		rdesc[205] = 0x01;
+	}
+
 	return rdesc;
 }
 
diff --git a/drivers/hid/hid-cp2112.c b/drivers/hid/hid-cp2112.c
index 477baa30889c..172f20e88c6c 100644
--- a/drivers/hid/hid-cp2112.c
+++ b/drivers/hid/hid-cp2112.c
@@ -788,6 +788,11 @@ static int cp2112_xfer(struct i2c_adapter *adap, u16 addr,
 		data->word = le16_to_cpup((__le16 *)buf);
 		break;
 	case I2C_SMBUS_I2C_BLOCK_DATA:
+		if (read_length > I2C_SMBUS_BLOCK_MAX) {
+			ret = -EINVAL;
+			goto power_normal;
+		}
+
 		memcpy(data->block + 1, buf, read_length);
 		break;
 	case I2C_SMBUS_BLOCK_DATA:
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 42b5b050b72d..cb2b48d6915e 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -398,6 +398,8 @@
 #define USB_DEVICE_ID_ASUS_UX550VE_TOUCHSCREEN	0x2544
 #define USB_DEVICE_ID_ASUS_UX550_TOUCHSCREEN	0x2706
 #define I2C_DEVICE_ID_SURFACE_GO_TOUCHSCREEN	0x261A
+#define I2C_DEVICE_ID_SURFACE_GO2_TOUCHSCREEN	0x2A1C
+#define I2C_DEVICE_ID_LENOVO_YOGA_C630_TOUCHSCREEN	0x279F
 
 #define USB_VENDOR_ID_ELECOM		0x056e
 #define USB_DEVICE_ID_ELECOM_BM084	0x0061
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index 3172987a9ebd..f197aed6444a 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -333,6 +333,10 @@ static const struct hid_device_id hid_battery_quirks[] = {
 	  HID_BATTERY_QUIRK_IGNORE },
 	{ HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_SURFACE_GO_TOUCHSCREEN),
 	  HID_BATTERY_QUIRK_IGNORE },
+	{ HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_SURFACE_GO2_TOUCHSCREEN),
+	  HID_BATTERY_QUIRK_IGNORE },
+	{ HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_LENOVO_YOGA_C630_TOUCHSCREEN),
+	  HID_BATTERY_QUIRK_IGNORE },
 	{}
 };
 
diff --git a/drivers/hid/hid-mcp2221.c b/drivers/hid/hid-mcp2221.c
index 4211b9839209..de52e9f7bb8c 100644
--- a/drivers/hid/hid-mcp2221.c
+++ b/drivers/hid/hid-mcp2221.c
@@ -385,6 +385,9 @@ static int mcp_smbus_write(struct mcp2221 *mcp, u16 addr,
 		data_len = 7;
 		break;
 	default:
+		if (len > I2C_SMBUS_BLOCK_MAX)
+			return -EINVAL;
+
 		memcpy(&mcp->txbuf[5], buf, len);
 		data_len = len + 5;
 	}
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index f382444dc2db..a14c48de4446 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -194,6 +194,7 @@ static void mt_post_parse(struct mt_device *td, struct mt_application *app);
 #define MT_CLS_WIN_8_FORCE_MULTI_INPUT		0x0015
 #define MT_CLS_WIN_8_DISABLE_WAKEUP		0x0016
 #define MT_CLS_WIN_8_NO_STICKY_FINGERS		0x0017
+#define MT_CLS_WIN_8_FORCE_MULTI_INPUT_NSMU	0x0018
 
 /* vendor specific classes */
 #define MT_CLS_3M				0x0101
@@ -286,6 +287,15 @@ static const struct mt_class mt_classes[] = {
 			MT_QUIRK_WIN8_PTP_BUTTONS |
 			MT_QUIRK_FORCE_MULTI_INPUT,
 		.export_all_inputs = true },
+	{ .name = MT_CLS_WIN_8_FORCE_MULTI_INPUT_NSMU,
+		.quirks = MT_QUIRK_IGNORE_DUPLICATES |
+			MT_QUIRK_HOVERING |
+			MT_QUIRK_CONTACT_CNT_ACCURATE |
+			MT_QUIRK_STICKY_FINGERS |
+			MT_QUIRK_WIN8_PTP_BUTTONS |
+			MT_QUIRK_FORCE_MULTI_INPUT |
+			MT_QUIRK_NOT_SEEN_MEANS_UP,
+		.export_all_inputs = true },
 	{ .name = MT_CLS_WIN_8_DISABLE_WAKEUP,
 		.quirks = MT_QUIRK_ALWAYS_VALID |
 			MT_QUIRK_IGNORE_DUPLICATES |
@@ -783,6 +793,7 @@ static int mt_touch_input_mapping(struct hid_device *hdev, struct hid_input *hi,
 		case HID_DG_CONFIDENCE:
 			if ((cls->name == MT_CLS_WIN_8 ||
 			     cls->name == MT_CLS_WIN_8_FORCE_MULTI_INPUT ||
+			     cls->name == MT_CLS_WIN_8_FORCE_MULTI_INPUT_NSMU ||
 			     cls->name == MT_CLS_WIN_8_DISABLE_WAKEUP) &&
 				(field->application == HID_DG_TOUCHPAD ||
 				 field->application == HID_DG_TOUCHSCREEN))
@@ -2033,7 +2044,7 @@ static const struct hid_device_id mt_devices[] = {
 			   USB_DEVICE_ID_LENOVO_X1_TAB3) },
 
 	/* Lenovo X12 TAB Gen 1 */
-	{ .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT,
+	{ .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT_NSMU,
 		HID_DEVICE(BUS_USB, HID_GROUP_MULTITOUCH_WIN_8,
 			   USB_VENDOR_ID_LENOVO,
 			   USB_DEVICE_ID_LENOVO_X12_TAB) },
diff --git a/drivers/hid/hid-steam.c b/drivers/hid/hid-steam.c
index a3b151b29bd7..fc616db4231b 100644
--- a/drivers/hid/hid-steam.c
+++ b/drivers/hid/hid-steam.c
@@ -134,6 +134,11 @@ static int steam_recv_report(struct steam_device *steam,
 	int ret;
 
 	r = steam->hdev->report_enum[HID_FEATURE_REPORT].report_id_hash[0];
+	if (!r) {
+		hid_err(steam->hdev, "No HID_FEATURE_REPORT submitted -  nothing to read\n");
+		return -EINVAL;
+	}
+
 	if (hid_report_len(r) < 64)
 		return -EINVAL;
 
@@ -165,6 +170,11 @@ static int steam_send_report(struct steam_device *steam,
 	int ret;
 
 	r = steam->hdev->report_enum[HID_FEATURE_REPORT].report_id_hash[0];
+	if (!r) {
+		hid_err(steam->hdev, "No HID_FEATURE_REPORT submitted -  nothing to read\n");
+		return -EINVAL;
+	}
+
 	if (hid_report_len(r) < 64)
 		return -EINVAL;
 
diff --git a/drivers/hid/hid-thrustmaster.c b/drivers/hid/hid-thrustmaster.c
index a28c3e575650..2221bc26e611 100644
--- a/drivers/hid/hid-thrustmaster.c
+++ b/drivers/hid/hid-thrustmaster.c
@@ -67,12 +67,13 @@ static const struct tm_wheel_info tm_wheels_infos[] = {
 	{0x0200, 0x0005, "Thrustmaster T300RS (Missing Attachment)"},
 	{0x0206, 0x0005, "Thrustmaster T300RS"},
 	{0x0209, 0x0005, "Thrustmaster T300RS (Open Wheel Attachment)"},
+	{0x020a, 0x0005, "Thrustmaster T300RS (Sparco R383 Mod)"},
 	{0x0204, 0x0005, "Thrustmaster T300 Ferrari Alcantara Edition"},
 	{0x0002, 0x0002, "Thrustmaster T500RS"}
 	//{0x0407, 0x0001, "Thrustmaster TMX"}
 };
 
-static const uint8_t tm_wheels_infos_length = 4;
+static const uint8_t tm_wheels_infos_length = 7;
 
 /*
  * This structs contains (in little endian) the response data
diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c
index 79faac87a06f..11b0ed4f3f8c 100644
--- a/drivers/hid/hidraw.c
+++ b/drivers/hid/hidraw.c
@@ -346,10 +346,13 @@ static int hidraw_release(struct inode * inode, struct file * file)
 	unsigned int minor = iminor(inode);
 	struct hidraw_list *list = file->private_data;
 	unsigned long flags;
+	int i;
 
 	mutex_lock(&minors_lock);
 
 	spin_lock_irqsave(&hidraw_table[minor]->list_lock, flags);
+	for (i = list->tail; i < list->head; i++)
+		kfree(list->buffer[i].value);
 	list_del(&list->node);
 	spin_unlock_irqrestore(&hidraw_table[minor]->list_lock, flags);
 	kfree(list);
diff --git a/drivers/hid/intel-ish-hid/ishtp-hid.h b/drivers/hid/intel-ish-hid/ishtp-hid.h
index 6a5cc11aefd8..35dddc5015b3 100644
--- a/drivers/hid/intel-ish-hid/ishtp-hid.h
+++ b/drivers/hid/intel-ish-hid/ishtp-hid.h
@@ -105,7 +105,7 @@ struct report_list {
  * @multi_packet_cnt:	Count of fragmented packet count
  *
  * This structure is used to store completion flags and per client data like
- * like report description, number of HID devices etc.
+ * report description, number of HID devices etc.
  */
 struct ishtp_cl_data {
 	/* completion flags */
diff --git a/drivers/hid/intel-ish-hid/ishtp/client.c b/drivers/hid/intel-ish-hid/ishtp/client.c
index 405e0d5212cc..df0a825694f5 100644
--- a/drivers/hid/intel-ish-hid/ishtp/client.c
+++ b/drivers/hid/intel-ish-hid/ishtp/client.c
@@ -626,13 +626,14 @@ static void ishtp_cl_read_complete(struct ishtp_cl_rb *rb)
 }
 
 /**
- * ipc_tx_callback() - IPC tx callback function
+ * ipc_tx_send() - IPC tx send function
  * @prm: Pointer to client device instance
  *
- * Send message over IPC either first time or on callback on previous message
- * completion
+ * Send message over IPC. Message will be split into fragments
+ * if message size is bigger than IPC FIFO size, and all
+ * fragments will be sent one by one.
  */
-static void ipc_tx_callback(void *prm)
+static void ipc_tx_send(void *prm)
 {
 	struct ishtp_cl	*cl = prm;
 	struct ishtp_cl_tx_ring	*cl_msg;
@@ -677,32 +678,41 @@ static void ipc_tx_callback(void *prm)
 			    list);
 	rem = cl_msg->send_buf.size - cl->tx_offs;
 
-	ishtp_hdr.host_addr = cl->host_client_id;
-	ishtp_hdr.fw_addr = cl->fw_client_id;
-	ishtp_hdr.reserved = 0;
-	pmsg = cl_msg->send_buf.data + cl->tx_offs;
+	while (rem > 0) {
+		ishtp_hdr.host_addr = cl->host_client_id;
+		ishtp_hdr.fw_addr = cl->fw_client_id;
+		ishtp_hdr.reserved = 0;
+		pmsg = cl_msg->send_buf.data + cl->tx_offs;
+
+		if (rem <= dev->mtu) {
+			/* Last fragment or only one packet */
+			ishtp_hdr.length = rem;
+			ishtp_hdr.msg_complete = 1;
+			/* Submit to IPC queue with no callback */
+			ishtp_write_message(dev, &ishtp_hdr, pmsg);
+			cl->tx_offs = 0;
+			cl->sending = 0;
 
-	if (rem <= dev->mtu) {
-		ishtp_hdr.length = rem;
-		ishtp_hdr.msg_complete = 1;
-		cl->sending = 0;
-		list_del_init(&cl_msg->list);	/* Must be before write */
-		spin_unlock_irqrestore(&cl->tx_list_spinlock, tx_flags);
-		/* Submit to IPC queue with no callback */
-		ishtp_write_message(dev, &ishtp_hdr, pmsg);
-		spin_lock_irqsave(&cl->tx_free_list_spinlock, tx_free_flags);
-		list_add_tail(&cl_msg->list, &cl->tx_free_list.list);
-		++cl->tx_ring_free_size;
-		spin_unlock_irqrestore(&cl->tx_free_list_spinlock,
-			tx_free_flags);
-	} else {
-		/* Send IPC fragment */
-		spin_unlock_irqrestore(&cl->tx_list_spinlock, tx_flags);
-		cl->tx_offs += dev->mtu;
-		ishtp_hdr.length = dev->mtu;
-		ishtp_hdr.msg_complete = 0;
-		ishtp_send_msg(dev, &ishtp_hdr, pmsg, ipc_tx_callback, cl);
+			break;
+		} else {
+			/* Send ipc fragment */
+			ishtp_hdr.length = dev->mtu;
+			ishtp_hdr.msg_complete = 0;
+			/* All fregments submitted to IPC queue with no callback */
+			ishtp_write_message(dev, &ishtp_hdr, pmsg);
+			cl->tx_offs += dev->mtu;
+			rem = cl_msg->send_buf.size - cl->tx_offs;
+		}
 	}
+
+	list_del_init(&cl_msg->list);
+	spin_unlock_irqrestore(&cl->tx_list_spinlock, tx_flags);
+
+	spin_lock_irqsave(&cl->tx_free_list_spinlock, tx_free_flags);
+	list_add_tail(&cl_msg->list, &cl->tx_free_list.list);
+	++cl->tx_ring_free_size;
+	spin_unlock_irqrestore(&cl->tx_free_list_spinlock,
+		tx_free_flags);
 }
 
 /**
@@ -720,7 +730,7 @@ static void ishtp_cl_send_msg_ipc(struct ishtp_device *dev,
 		return;
 
 	cl->tx_offs = 0;
-	ipc_tx_callback(cl);
+	ipc_tx_send(cl);
 	++cl->send_msg_cnt_ipc;
 }
 
diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
index b1bbf297f66b..7e67c41d97a4 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -2124,7 +2124,7 @@ static int wacom_register_inputs(struct wacom *wacom)
 
 	error = wacom_setup_pad_input_capabilities(pad_input_dev, wacom_wac);
 	if (error) {
-		/* no pad in use on this interface */
+		/* no pad events using this interface */
 		input_free_device(pad_input_dev);
 		wacom_wac->pad_input = NULL;
 		pad_input_dev = NULL;
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index a7176fc0635d..c454231afec8 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -638,9 +638,26 @@ static int wacom_intuos_id_mangle(int tool_id)
 	return (tool_id & ~0xFFF) << 4 | (tool_id & 0xFFF);
 }
 
+static bool wacom_is_art_pen(int tool_id)
+{
+	bool is_art_pen = false;
+
+	switch (tool_id) {
+	case 0x885:	/* Intuos3 Marker Pen */
+	case 0x804:	/* Intuos4/5 13HD/24HD Marker Pen */
+	case 0x10804:	/* Intuos4/5 13HD/24HD Art Pen */
+		is_art_pen = true;
+		break;
+	}
+	return is_art_pen;
+}
+
 static int wacom_intuos_get_tool_type(int tool_id)
 {
-	int tool_type;
+	int tool_type = BTN_TOOL_PEN;
+
+	if (wacom_is_art_pen(tool_id))
+		return tool_type;
 
 	switch (tool_id) {
 	case 0x812: /* Inking pen */
@@ -655,12 +672,9 @@ static int wacom_intuos_get_tool_type(int tool_id)
 	case 0x852:
 	case 0x823: /* Intuos3 Grip Pen */
 	case 0x813: /* Intuos3 Classic Pen */
-	case 0x885: /* Intuos3 Marker Pen */
 	case 0x802: /* Intuos4/5 13HD/24HD General Pen */
-	case 0x804: /* Intuos4/5 13HD/24HD Marker Pen */
 	case 0x8e2: /* IntuosHT2 pen */
 	case 0x022:
-	case 0x10804: /* Intuos4/5 13HD/24HD Art Pen */
 	case 0x10842: /* MobileStudio Pro Pro Pen slim */
 	case 0x14802: /* Intuos4/5 13HD/24HD Classic Pen */
 	case 0x16802: /* Cintiq 13HD Pro Pen */
@@ -718,10 +732,6 @@ static int wacom_intuos_get_tool_type(int tool_id)
 	case 0x10902: /* Intuos4/5 13HD/24HD Airbrush */
 		tool_type = BTN_TOOL_AIRBRUSH;
 		break;
-
-	default: /* Unknown tool */
-		tool_type = BTN_TOOL_PEN;
-		break;
 	}
 	return tool_type;
 }
@@ -2007,7 +2017,6 @@ static void wacom_wac_pad_usage_mapping(struct hid_device *hdev,
 		wacom_wac->has_mute_touch_switch = true;
 		usage->type = EV_SW;
 		usage->code = SW_MUTE_DEVICE;
-		features->device_type |= WACOM_DEVICETYPE_PAD;
 		break;
 	case WACOM_HID_WD_TOUCHSTRIP:
 		wacom_map_usage(input, usage, field, EV_ABS, ABS_RX, 0);
@@ -2087,6 +2096,30 @@ static void wacom_wac_pad_event(struct hid_device *hdev, struct hid_field *field
 			wacom_wac->hid_data.inrange_state |= value;
 	}
 
+	/* Process touch switch state first since it is reported through touch interface,
+	 * which is indepentent of pad interface. In the case when there are no other pad
+	 * events, the pad interface will not even be created.
+	 */
+	if ((equivalent_usage == WACOM_HID_WD_MUTE_DEVICE) ||
+	   (equivalent_usage == WACOM_HID_WD_TOUCHONOFF)) {
+		if (wacom_wac->shared->touch_input) {
+			bool *is_touch_on = &wacom_wac->shared->is_touch_on;
+
+			if (equivalent_usage == WACOM_HID_WD_MUTE_DEVICE && value)
+				*is_touch_on = !(*is_touch_on);
+			else if (equivalent_usage == WACOM_HID_WD_TOUCHONOFF)
+				*is_touch_on = value;
+
+			input_report_switch(wacom_wac->shared->touch_input,
+					    SW_MUTE_DEVICE, !(*is_touch_on));
+			input_sync(wacom_wac->shared->touch_input);
+		}
+		return;
+	}
+
+	if (!input)
+		return;
+
 	switch (equivalent_usage) {
 	case WACOM_HID_WD_TOUCHRING:
 		/*
@@ -2122,22 +2155,6 @@ static void wacom_wac_pad_event(struct hid_device *hdev, struct hid_field *field
 			input_event(input, usage->type, usage->code, 0);
 		break;
 
-	case WACOM_HID_WD_MUTE_DEVICE:
-	case WACOM_HID_WD_TOUCHONOFF:
-		if (wacom_wac->shared->touch_input) {
-			bool *is_touch_on = &wacom_wac->shared->is_touch_on;
-
-			if (equivalent_usage == WACOM_HID_WD_MUTE_DEVICE && value)
-				*is_touch_on = !(*is_touch_on);
-			else if (equivalent_usage == WACOM_HID_WD_TOUCHONOFF)
-				*is_touch_on = value;
-
-			input_report_switch(wacom_wac->shared->touch_input,
-					    SW_MUTE_DEVICE, !(*is_touch_on));
-			input_sync(wacom_wac->shared->touch_input);
-		}
-		break;
-
 	case WACOM_HID_WD_MODE_CHANGE:
 		if (wacom_wac->is_direct_mode != value) {
 			wacom_wac->is_direct_mode = value;
@@ -2323,6 +2340,9 @@ static void wacom_wac_pen_event(struct hid_device *hdev, struct hid_field *field
 		}
 		return;
 	case HID_DG_TWIST:
+		/* don't modify the value if the pen doesn't support the feature */
+		if (!wacom_is_art_pen(wacom_wac->id[0])) return;
+
 		/*
 		 * Userspace expects pen twist to have its zero point when
 		 * the buttons/finger is on the tablet's left. HID values
@@ -2795,7 +2815,7 @@ void wacom_wac_event(struct hid_device *hdev, struct hid_field *field,
 	/* usage tests must precede field tests */
 	if (WACOM_BATTERY_USAGE(usage))
 		wacom_wac_battery_event(hdev, field, usage, value);
-	else if (WACOM_PAD_FIELD(field) && wacom->wacom_wac.pad_input)
+	else if (WACOM_PAD_FIELD(field))
 		wacom_wac_pad_event(hdev, field, usage, value);
 	else if (WACOM_PEN_FIELD(field) && wacom->wacom_wac.pen_input)
 		wacom_wac_pen_event(hdev, field, usage, value);
diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c
index 3cf334c46c31..3248b48f37f6 100644
--- a/drivers/hv/hv_balloon.c
+++ b/drivers/hv/hv_balloon.c
@@ -17,6 +17,7 @@
 #include <linux/slab.h>
 #include <linux/kthread.h>
 #include <linux/completion.h>
+#include <linux/count_zeros.h>
 #include <linux/memory_hotplug.h>
 #include <linux/memory.h>
 #include <linux/notifier.h>
@@ -1130,6 +1131,7 @@ static void post_status(struct hv_dynmem_device *dm)
 	struct dm_status status;
 	unsigned long now = jiffies;
 	unsigned long last_post = last_post_time;
+	unsigned long num_pages_avail, num_pages_committed;
 
 	if (pressure_report_delay > 0) {
 		--pressure_report_delay;
@@ -1154,16 +1156,21 @@ static void post_status(struct hv_dynmem_device *dm)
 	 * num_pages_onlined) as committed to the host, otherwise it can try
 	 * asking us to balloon them out.
 	 */
-	status.num_avail = si_mem_available();
-	status.num_committed = vm_memory_committed() +
+	num_pages_avail = si_mem_available();
+	num_pages_committed = vm_memory_committed() +
 		dm->num_pages_ballooned +
 		(dm->num_pages_added > dm->num_pages_onlined ?
 		 dm->num_pages_added - dm->num_pages_onlined : 0) +
 		compute_balloon_floor();
 
-	trace_balloon_status(status.num_avail, status.num_committed,
+	trace_balloon_status(num_pages_avail, num_pages_committed,
 			     vm_memory_committed(), dm->num_pages_ballooned,
 			     dm->num_pages_added, dm->num_pages_onlined);
+
+	/* Convert numbers of pages into numbers of HV_HYP_PAGEs. */
+	status.num_avail = num_pages_avail * NR_HV_HYP_PAGES_IN_PAGE;
+	status.num_committed = num_pages_committed * NR_HV_HYP_PAGES_IN_PAGE;
+
 	/*
 	 * If our transaction ID is no longer current, just don't
 	 * send the status. This can happen if we were interrupted
diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c
index 9cb1c3588038..597cbb4391bd 100644
--- a/drivers/hwmon/dell-smm-hwmon.c
+++ b/drivers/hwmon/dell-smm-hwmon.c
@@ -1198,6 +1198,14 @@ static const struct dmi_system_id i8k_whitelist_fan_control[] __initconst = {
 		},
 		.driver_data = (void *)&i8k_fan_control_data[I8K_FAN_34A3_35A3],
 	},
+	{
+		.ident = "Dell XPS 13 7390",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "XPS 13 7390"),
+		},
+		.driver_data = (void *)&i8k_fan_control_data[I8K_FAN_34A3_35A3],
+	},
 	{ }
 };
 
diff --git a/drivers/hwmon/drivetemp.c b/drivers/hwmon/drivetemp.c
index 1eb37106a220..5bac2b0fc7bb 100644
--- a/drivers/hwmon/drivetemp.c
+++ b/drivers/hwmon/drivetemp.c
@@ -621,3 +621,4 @@ module_exit(drivetemp_exit);
 MODULE_AUTHOR("Guenter Roeck <linus@roeck-us.net>");
 MODULE_DESCRIPTION("Hard drive temperature monitor");
 MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:drivetemp");
diff --git a/drivers/hwmon/gpio-fan.c b/drivers/hwmon/gpio-fan.c
index befe989ca7b9..fbf3f5a4ecb6 100644
--- a/drivers/hwmon/gpio-fan.c
+++ b/drivers/hwmon/gpio-fan.c
@@ -391,6 +391,9 @@ static int gpio_fan_set_cur_state(struct thermal_cooling_device *cdev,
 	if (!fan_data)
 		return -EINVAL;
 
+	if (state >= fan_data->num_speed)
+		return -EINVAL;
+
 	set_fan_speed(fan_data, state);
 	return 0;
 }
diff --git a/drivers/hwmon/ibmaem.c b/drivers/hwmon/ibmaem.c
index a4ec85207782..2e6d6a5cffa1 100644
--- a/drivers/hwmon/ibmaem.c
+++ b/drivers/hwmon/ibmaem.c
@@ -550,7 +550,7 @@ static int aem_init_aem1_inst(struct aem_ipmi_data *probe, u8 module_handle)
 
 	res = platform_device_add(data->pdev);
 	if (res)
-		goto ipmi_err;
+		goto dev_add_err;
 
 	platform_set_drvdata(data->pdev, data);
 
@@ -598,7 +598,9 @@ hwmon_reg_err:
 	ipmi_destroy_user(data->ipmi.user);
 ipmi_err:
 	platform_set_drvdata(data->pdev, NULL);
-	platform_device_unregister(data->pdev);
+	platform_device_del(data->pdev);
+dev_add_err:
+	platform_device_put(data->pdev);
 dev_err:
 	ida_simple_remove(&aem_ida, data->id);
 id_err:
@@ -690,7 +692,7 @@ static int aem_init_aem2_inst(struct aem_ipmi_data *probe,
 
 	res = platform_device_add(data->pdev);
 	if (res)
-		goto ipmi_err;
+		goto dev_add_err;
 
 	platform_set_drvdata(data->pdev, data);
 
@@ -738,7 +740,9 @@ hwmon_reg_err:
 	ipmi_destroy_user(data->ipmi.user);
 ipmi_err:
 	platform_set_drvdata(data->pdev, NULL);
-	platform_device_unregister(data->pdev);
+	platform_device_del(data->pdev);
+dev_add_err:
+	platform_device_put(data->pdev);
 dev_err:
 	ida_simple_remove(&aem_ida, data->id);
 id_err:
diff --git a/drivers/hwmon/mr75203.c b/drivers/hwmon/mr75203.c
index 1ba1e3145969..05da83841536 100644
--- a/drivers/hwmon/mr75203.c
+++ b/drivers/hwmon/mr75203.c
@@ -68,8 +68,9 @@
 
 /* VM Individual Macro Register */
 #define VM_COM_REG_SIZE	0x200
-#define VM_SDIF_DONE(n)	(VM_COM_REG_SIZE + 0x34 + 0x200 * (n))
-#define VM_SDIF_DATA(n)	(VM_COM_REG_SIZE + 0x40 + 0x200 * (n))
+#define VM_SDIF_DONE(vm)	(VM_COM_REG_SIZE + 0x34 + 0x200 * (vm))
+#define VM_SDIF_DATA(vm, ch)	\
+	(VM_COM_REG_SIZE + 0x40 + 0x200 * (vm) + 0x4 * (ch))
 
 /* SDA Slave Register */
 #define IP_CTRL			0x00
@@ -115,6 +116,7 @@ struct pvt_device {
 	u32			t_num;
 	u32			p_num;
 	u32			v_num;
+	u32			c_num;
 	u32			ip_freq;
 	u8			*vm_idx;
 };
@@ -178,14 +180,15 @@ static int pvt_read_in(struct device *dev, u32 attr, int channel, long *val)
 {
 	struct pvt_device *pvt = dev_get_drvdata(dev);
 	struct regmap *v_map = pvt->v_map;
+	u8 vm_idx, ch_idx;
 	u32 n, stat;
-	u8 vm_idx;
 	int ret;
 
-	if (channel >= pvt->v_num)
+	if (channel >= pvt->v_num * pvt->c_num)
 		return -EINVAL;
 
-	vm_idx = pvt->vm_idx[channel];
+	vm_idx = pvt->vm_idx[channel / pvt->c_num];
+	ch_idx = channel % pvt->c_num;
 
 	switch (attr) {
 	case hwmon_in_input:
@@ -196,13 +199,23 @@ static int pvt_read_in(struct device *dev, u32 attr, int channel, long *val)
 		if (ret)
 			return ret;
 
-		ret = regmap_read(v_map, VM_SDIF_DATA(vm_idx), &n);
+		ret = regmap_read(v_map, VM_SDIF_DATA(vm_idx, ch_idx), &n);
 		if(ret < 0)
 			return ret;
 
 		n &= SAMPLE_DATA_MSK;
-		/* Convert the N bitstream count into voltage */
-		*val = (PVT_N_CONST * n - PVT_R_CONST) >> PVT_CONV_BITS;
+		/*
+		 * Convert the N bitstream count into voltage.
+		 * To support negative voltage calculation for 64bit machines
+		 * n must be cast to long, since n and *val differ both in
+		 * signedness and in size.
+		 * Division is used instead of right shift, because for signed
+		 * numbers, the sign bit is used to fill the vacated bit
+		 * positions, and if the number is negative, 1 is used.
+		 * BIT(x) may not be used instead of (1 << x) because it's
+		 * unsigned.
+		 */
+		*val = (PVT_N_CONST * (long)n - PVT_R_CONST) / (1 << PVT_CONV_BITS);
 
 		return 0;
 	default:
@@ -385,6 +398,19 @@ static int pvt_init(struct pvt_device *pvt)
 		if (ret)
 			return ret;
 
+		val = (BIT(pvt->c_num) - 1) | VM_CH_INIT |
+		      IP_POLL << SDIF_ADDR_SFT | SDIF_WRN_W | SDIF_PROG;
+		ret = regmap_write(v_map, SDIF_W, val);
+		if (ret < 0)
+			return ret;
+
+		ret = regmap_read_poll_timeout(v_map, SDIF_STAT,
+					       val, !(val & SDIF_BUSY),
+					       PVT_POLL_DELAY_US,
+					       PVT_POLL_TIMEOUT_US);
+		if (ret)
+			return ret;
+
 		val = CFG1_VOL_MEAS_MODE | CFG1_PARALLEL_OUT |
 		      CFG1_14_BIT | IP_CFG << SDIF_ADDR_SFT |
 		      SDIF_WRN_W | SDIF_PROG;
@@ -499,8 +525,8 @@ static int pvt_reset_control_deassert(struct device *dev, struct pvt_device *pvt
 
 static int mr75203_probe(struct platform_device *pdev)
 {
+	u32 ts_num, vm_num, pd_num, ch_num, val, index, i;
 	const struct hwmon_channel_info **pvt_info;
-	u32 ts_num, vm_num, pd_num, val, index, i;
 	struct device *dev = &pdev->dev;
 	u32 *temp_config, *in_config;
 	struct device *hwmon_dev;
@@ -541,9 +567,11 @@ static int mr75203_probe(struct platform_device *pdev)
 	ts_num = (val & TS_NUM_MSK) >> TS_NUM_SFT;
 	pd_num = (val & PD_NUM_MSK) >> PD_NUM_SFT;
 	vm_num = (val & VM_NUM_MSK) >> VM_NUM_SFT;
+	ch_num = (val & CH_NUM_MSK) >> CH_NUM_SFT;
 	pvt->t_num = ts_num;
 	pvt->p_num = pd_num;
 	pvt->v_num = vm_num;
+	pvt->c_num = ch_num;
 	val = 0;
 	if (ts_num)
 		val++;
@@ -580,7 +608,7 @@ static int mr75203_probe(struct platform_device *pdev)
 	}
 
 	if (vm_num) {
-		u32 num = vm_num;
+		u32 total_ch;
 
 		ret = pvt_get_regmap(pdev, "vm", pvt);
 		if (ret)
@@ -594,30 +622,30 @@ static int mr75203_probe(struct platform_device *pdev)
 		ret = device_property_read_u8_array(dev, "intel,vm-map",
 						    pvt->vm_idx, vm_num);
 		if (ret) {
-			num = 0;
+			/*
+			 * Incase intel,vm-map property is not defined, we
+			 * assume incremental channel numbers.
+			 */
+			for (i = 0; i < vm_num; i++)
+				pvt->vm_idx[i] = i;
 		} else {
 			for (i = 0; i < vm_num; i++)
 				if (pvt->vm_idx[i] >= vm_num ||
 				    pvt->vm_idx[i] == 0xff) {
-					num = i;
+					pvt->v_num = i;
+					vm_num = i;
 					break;
 				}
 		}
 
-		/*
-		 * Incase intel,vm-map property is not defined, we assume
-		 * incremental channel numbers.
-		 */
-		for (i = num; i < vm_num; i++)
-			pvt->vm_idx[i] = i;
-
-		in_config = devm_kcalloc(dev, num + 1,
+		total_ch = ch_num * vm_num;
+		in_config = devm_kcalloc(dev, total_ch + 1,
 					 sizeof(*in_config), GFP_KERNEL);
 		if (!in_config)
 			return -ENOMEM;
 
-		memset32(in_config, HWMON_I_INPUT, num);
-		in_config[num] = 0;
+		memset32(in_config, HWMON_I_INPUT, total_ch);
+		in_config[total_ch] = 0;
 		pvt_in.config = in_config;
 
 		pvt_info[index++] = &pvt_in;
diff --git a/drivers/hwmon/occ/common.c b/drivers/hwmon/occ/common.c
index ae664613289c..bbe5e4ef4113 100644
--- a/drivers/hwmon/occ/common.c
+++ b/drivers/hwmon/occ/common.c
@@ -132,22 +132,20 @@ struct extended_sensor {
 static int occ_poll(struct occ *occ)
 {
 	int rc;
-	u16 checksum = occ->poll_cmd_data + occ->seq_no + 1;
-	u8 cmd[8];
+	u8 cmd[7];
 	struct occ_poll_response_header *header;
 
 	/* big endian */
-	cmd[0] = occ->seq_no++;		/* sequence number */
+	cmd[0] = 0;			/* sequence number */
 	cmd[1] = 0;			/* cmd type */
 	cmd[2] = 0;			/* data length msb */
 	cmd[3] = 1;			/* data length lsb */
 	cmd[4] = occ->poll_cmd_data;	/* data */
-	cmd[5] = checksum >> 8;		/* checksum msb */
-	cmd[6] = checksum & 0xFF;	/* checksum lsb */
-	cmd[7] = 0;
+	cmd[5] = 0;			/* checksum msb */
+	cmd[6] = 0;			/* checksum lsb */
 
 	/* mutex should already be locked if necessary */
-	rc = occ->send_cmd(occ, cmd);
+	rc = occ->send_cmd(occ, cmd, sizeof(cmd), &occ->resp, sizeof(occ->resp));
 	if (rc) {
 		occ->last_error = rc;
 		if (occ->error_count++ > OCC_ERROR_COUNT_THRESHOLD)
@@ -184,25 +182,24 @@ static int occ_set_user_power_cap(struct occ *occ, u16 user_power_cap)
 {
 	int rc;
 	u8 cmd[8];
-	u16 checksum = 0x24;
+	u8 resp[8];
 	__be16 user_power_cap_be = cpu_to_be16(user_power_cap);
 
-	cmd[0] = 0;
-	cmd[1] = 0x22;
-	cmd[2] = 0;
-	cmd[3] = 2;
+	cmd[0] = 0;	/* sequence number */
+	cmd[1] = 0x22;	/* cmd type */
+	cmd[2] = 0;	/* data length msb */
+	cmd[3] = 2;	/* data length lsb */
 
 	memcpy(&cmd[4], &user_power_cap_be, 2);
 
-	checksum += cmd[4] + cmd[5];
-	cmd[6] = checksum >> 8;
-	cmd[7] = checksum & 0xFF;
+	cmd[6] = 0;	/* checksum msb */
+	cmd[7] = 0;	/* checksum lsb */
 
 	rc = mutex_lock_interruptible(&occ->lock);
 	if (rc)
 		return rc;
 
-	rc = occ->send_cmd(occ, cmd);
+	rc = occ->send_cmd(occ, cmd, sizeof(cmd), resp, sizeof(resp));
 
 	mutex_unlock(&occ->lock);
 
@@ -1144,8 +1141,6 @@ int occ_setup(struct occ *occ, const char *name)
 {
 	int rc;
 
-	/* start with 1 to avoid false match with zero-initialized SRAM buffer */
-	occ->seq_no = 1;
 	mutex_init(&occ->lock);
 	occ->groups[0] = &occ->group;
 
diff --git a/drivers/hwmon/occ/common.h b/drivers/hwmon/occ/common.h
index e6df719770e8..7abf19102062 100644
--- a/drivers/hwmon/occ/common.h
+++ b/drivers/hwmon/occ/common.h
@@ -95,9 +95,9 @@ struct occ {
 	struct occ_sensors sensors;
 
 	int powr_sample_time_us;	/* average power sample time */
-	u8 seq_no;
 	u8 poll_cmd_data;		/* to perform OCC poll command */
-	int (*send_cmd)(struct occ *occ, u8 *cmd);
+	int (*send_cmd)(struct occ *occ, u8 *cmd, size_t len, void *resp,
+			size_t resp_len);
 
 	unsigned long next_update;
 	struct mutex lock;		/* lock OCC access */
diff --git a/drivers/hwmon/occ/p8_i2c.c b/drivers/hwmon/occ/p8_i2c.c
index 0cf8588be35a..c35c07964d85 100644
--- a/drivers/hwmon/occ/p8_i2c.c
+++ b/drivers/hwmon/occ/p8_i2c.c
@@ -97,18 +97,22 @@ static int p8_i2c_occ_putscom_u32(struct i2c_client *client, u32 address,
 }
 
 static int p8_i2c_occ_putscom_be(struct i2c_client *client, u32 address,
-				 u8 *data)
+				 u8 *data, size_t len)
 {
-	__be32 data0, data1;
+	__be32 data0 = 0, data1 = 0;
 
-	memcpy(&data0, data, 4);
-	memcpy(&data1, data + 4, 4);
+	memcpy(&data0, data, min_t(size_t, len, 4));
+	if (len > 4) {
+		len -= 4;
+		memcpy(&data1, data + 4, min_t(size_t, len, 4));
+	}
 
 	return p8_i2c_occ_putscom_u32(client, address, be32_to_cpu(data0),
 				      be32_to_cpu(data1));
 }
 
-static int p8_i2c_occ_send_cmd(struct occ *occ, u8 *cmd)
+static int p8_i2c_occ_send_cmd(struct occ *occ, u8 *cmd, size_t len,
+			       void *resp, size_t resp_len)
 {
 	int i, rc;
 	unsigned long start;
@@ -117,7 +121,7 @@ static int p8_i2c_occ_send_cmd(struct occ *occ, u8 *cmd)
 	const long wait_time = msecs_to_jiffies(OCC_CMD_IN_PRG_WAIT_MS);
 	struct p8_i2c_occ *ctx = to_p8_i2c_occ(occ);
 	struct i2c_client *client = ctx->client;
-	struct occ_response *resp = &occ->resp;
+	struct occ_response *or = (struct occ_response *)resp;
 
 	start = jiffies;
 
@@ -127,7 +131,7 @@ static int p8_i2c_occ_send_cmd(struct occ *occ, u8 *cmd)
 		return rc;
 
 	/* write command (expected to already be BE), we need bus-endian... */
-	rc = p8_i2c_occ_putscom_be(client, OCB_DATA3, cmd);
+	rc = p8_i2c_occ_putscom_be(client, OCB_DATA3, cmd, len);
 	if (rc)
 		return rc;
 
@@ -148,7 +152,7 @@ static int p8_i2c_occ_send_cmd(struct occ *occ, u8 *cmd)
 			return rc;
 
 		/* wait for OCC */
-		if (resp->return_status == OCC_RESP_CMD_IN_PRG) {
+		if (or->return_status == OCC_RESP_CMD_IN_PRG) {
 			rc = -EALREADY;
 
 			if (time_after(jiffies, start + timeout))
@@ -160,7 +164,7 @@ static int p8_i2c_occ_send_cmd(struct occ *occ, u8 *cmd)
 	} while (rc);
 
 	/* check the OCC response */
-	switch (resp->return_status) {
+	switch (or->return_status) {
 	case OCC_RESP_CMD_IN_PRG:
 		rc = -ETIMEDOUT;
 		break;
@@ -189,8 +193,8 @@ static int p8_i2c_occ_send_cmd(struct occ *occ, u8 *cmd)
 	if (rc < 0)
 		return rc;
 
-	data_length = get_unaligned_be16(&resp->data_length);
-	if (data_length > OCC_RESP_DATA_BYTES)
+	data_length = get_unaligned_be16(&or->data_length);
+	if ((data_length + 7) > resp_len)
 		return -EMSGSIZE;
 
 	/* fetch the rest of the response data */
diff --git a/drivers/hwmon/occ/p9_sbe.c b/drivers/hwmon/occ/p9_sbe.c
index f6387cc0b754..14923e78e1f3 100644
--- a/drivers/hwmon/occ/p9_sbe.c
+++ b/drivers/hwmon/occ/p9_sbe.c
@@ -16,18 +16,17 @@ struct p9_sbe_occ {
 
 #define to_p9_sbe_occ(x)	container_of((x), struct p9_sbe_occ, occ)
 
-static int p9_sbe_occ_send_cmd(struct occ *occ, u8 *cmd)
+static int p9_sbe_occ_send_cmd(struct occ *occ, u8 *cmd, size_t len,
+			       void *resp, size_t resp_len)
 {
-	struct occ_response *resp = &occ->resp;
 	struct p9_sbe_occ *ctx = to_p9_sbe_occ(occ);
-	size_t resp_len = sizeof(*resp);
 	int rc;
 
-	rc = fsi_occ_submit(ctx->sbe, cmd, 8, resp, &resp_len);
+	rc = fsi_occ_submit(ctx->sbe, cmd, len, resp, &resp_len);
 	if (rc < 0)
 		return rc;
 
-	switch (resp->return_status) {
+	switch (((struct occ_response *)resp)->return_status) {
 	case OCC_RESP_CMD_IN_PRG:
 		rc = -ETIMEDOUT;
 		break;
diff --git a/drivers/hwmon/sht15.c b/drivers/hwmon/sht15.c
index 7f4a63959730..ae4d14257a11 100644
--- a/drivers/hwmon/sht15.c
+++ b/drivers/hwmon/sht15.c
@@ -1020,25 +1020,20 @@ err_release_reg:
 static int sht15_remove(struct platform_device *pdev)
 {
 	struct sht15_data *data = platform_get_drvdata(pdev);
+	int ret;
 
-	/*
-	 * Make sure any reads from the device are done and
-	 * prevent new ones beginning
-	 */
-	mutex_lock(&data->read_lock);
-	if (sht15_soft_reset(data)) {
-		mutex_unlock(&data->read_lock);
-		return -EFAULT;
-	}
 	hwmon_device_unregister(data->hwmon_dev);
 	sysfs_remove_group(&pdev->dev.kobj, &sht15_attr_group);
+
+	ret = sht15_soft_reset(data);
+	if (ret)
+		dev_err(&pdev->dev, "Failed to reset device (%pe)\n", ERR_PTR(ret));
+
 	if (!IS_ERR(data->reg)) {
 		regulator_unregister_notifier(data->reg, &data->nb);
 		regulator_disable(data->reg);
 	}
 
-	mutex_unlock(&data->read_lock);
-
 	return 0;
 }
 
diff --git a/drivers/hwmon/tps23861.c b/drivers/hwmon/tps23861.c
index 8bd6435c13e8..2148fd543bb4 100644
--- a/drivers/hwmon/tps23861.c
+++ b/drivers/hwmon/tps23861.c
@@ -489,18 +489,20 @@ static char *tps23861_port_poe_plus_status(struct tps23861_data *data, int port)
 
 static int tps23861_port_resistance(struct tps23861_data *data, int port)
 {
-	u16 regval;
+	unsigned int raw_val;
+	__le16 regval;
 
 	regmap_bulk_read(data->regmap,
 			 PORT_1_RESISTANCE_LSB + PORT_N_RESISTANCE_LSB_OFFSET * (port - 1),
 			 &regval,
 			 2);
 
-	switch (FIELD_GET(PORT_RESISTANCE_RSN_MASK, regval)) {
+	raw_val = le16_to_cpu(regval);
+	switch (FIELD_GET(PORT_RESISTANCE_RSN_MASK, raw_val)) {
 	case PORT_RESISTANCE_RSN_OTHER:
-		return (FIELD_GET(PORT_RESISTANCE_MASK, regval) * RESISTANCE_LSB) / 10000;
+		return (FIELD_GET(PORT_RESISTANCE_MASK, raw_val) * RESISTANCE_LSB) / 10000;
 	case PORT_RESISTANCE_RSN_LOW:
-		return (FIELD_GET(PORT_RESISTANCE_MASK, regval) * RESISTANCE_LSB_LOW) / 10000;
+		return (FIELD_GET(PORT_RESISTANCE_MASK, raw_val) * RESISTANCE_LSB_LOW) / 10000;
 	case PORT_RESISTANCE_RSN_SHORT:
 	case PORT_RESISTANCE_RSN_OPEN:
 	default:
diff --git a/drivers/hwtracing/coresight/coresight-core.c b/drivers/hwtracing/coresight/coresight-core.c
index a6bdf4cf80ca..6471f4232a2e 100644
--- a/drivers/hwtracing/coresight/coresight-core.c
+++ b/drivers/hwtracing/coresight/coresight-core.c
@@ -1427,6 +1427,7 @@ static int coresight_remove_match(struct device *dev, void *data)
 			 * platform data.
 			 */
 			fwnode_handle_put(conn->child_fwnode);
+			conn->child_fwnode = NULL;
 			/* No need to continue */
 			break;
 		}
diff --git a/drivers/hwtracing/coresight/coresight-etm4x.h b/drivers/hwtracing/coresight/coresight-etm4x.h
index e5b79bdb9851..794b29639035 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x.h
+++ b/drivers/hwtracing/coresight/coresight-etm4x.h
@@ -7,6 +7,7 @@
 #define _CORESIGHT_CORESIGHT_ETM_H
 
 #include <asm/local.h>
+#include <linux/const.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>
 #include "coresight-priv.h"
@@ -417,7 +418,7 @@
 	({									\
 		u64 __val;							\
 										\
-		if (__builtin_constant_p((offset)))				\
+		if (__is_constexpr((offset)))					\
 			__val = read_etm4x_sysreg_const_offset((offset));	\
 		else								\
 			__val = etm4x_sysreg_read((offset), true, (_64bit));	\
diff --git a/drivers/hwtracing/intel_th/msu-sink.c b/drivers/hwtracing/intel_th/msu-sink.c
index 2c7f5116be12..891b28ea25fe 100644
--- a/drivers/hwtracing/intel_th/msu-sink.c
+++ b/drivers/hwtracing/intel_th/msu-sink.c
@@ -71,6 +71,9 @@ static int msu_sink_alloc_window(void *data, struct sg_table **sgt, size_t size)
 		block = dma_alloc_coherent(priv->dev->parent->parent,
 					   PAGE_SIZE, &sg_dma_address(sg_ptr),
 					   GFP_KERNEL);
+		if (!block)
+			return -ENOMEM;
+
 		sg_set_buf(sg_ptr, block, PAGE_SIZE);
 	}
 
diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c
index 432ade0842f6..d95d916b4682 100644
--- a/drivers/hwtracing/intel_th/msu.c
+++ b/drivers/hwtracing/intel_th/msu.c
@@ -1069,6 +1069,16 @@ msc_buffer_set_uc(struct msc *msc) {}
 static inline void msc_buffer_set_wb(struct msc *msc) {}
 #endif /* CONFIG_X86 */
 
+static struct page *msc_sg_page(struct scatterlist *sg)
+{
+	void *addr = sg_virt(sg);
+
+	if (is_vmalloc_addr(addr))
+		return vmalloc_to_page(addr);
+
+	return sg_page(sg);
+}
+
 /**
  * msc_buffer_win_alloc() - alloc a window for a multiblock mode
  * @msc:	MSC device
@@ -1139,7 +1149,7 @@ static void __msc_buffer_win_free(struct msc *msc, struct msc_window *win)
 	int i;
 
 	for_each_sg(win->sgt->sgl, sg, win->nr_segs, i) {
-		struct page *page = sg_page(sg);
+		struct page *page = msc_sg_page(sg);
 
 		page->mapping = NULL;
 		dma_free_coherent(msc_dev(win->msc)->parent->parent, PAGE_SIZE,
@@ -1403,7 +1413,7 @@ found:
 	pgoff -= win->pgoff;
 
 	for_each_sg(win->sgt->sgl, sg, win->nr_segs, blk) {
-		struct page *page = sg_page(sg);
+		struct page *page = msc_sg_page(sg);
 		size_t pgsz = PFN_DOWN(sg->length);
 
 		if (pgoff < pgsz)
diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c
index 7da4f298ed01..147d338c191e 100644
--- a/drivers/hwtracing/intel_th/pci.c
+++ b/drivers/hwtracing/intel_th/pci.c
@@ -100,8 +100,10 @@ static int intel_th_pci_probe(struct pci_dev *pdev,
 		}
 
 	th = intel_th_alloc(&pdev->dev, drvdata, resource, r);
-	if (IS_ERR(th))
-		return PTR_ERR(th);
+	if (IS_ERR(th)) {
+		err = PTR_ERR(th);
+		goto err_free_irq;
+	}
 
 	th->activate   = intel_th_pci_activate;
 	th->deactivate = intel_th_pci_deactivate;
@@ -109,6 +111,10 @@ static int intel_th_pci_probe(struct pci_dev *pdev,
 	pci_set_master(pdev);
 
 	return 0;
+
+err_free_irq:
+	pci_free_irq_vectors(pdev);
+	return err;
 }
 
 static void intel_th_pci_remove(struct pci_dev *pdev)
@@ -279,6 +285,21 @@ static const struct pci_device_id intel_th_pci_id_table[] = {
 		.driver_data = (kernel_ulong_t)&intel_th_2x,
 	},
 	{
+		/* Meteor Lake-P */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7e24),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
+	{
+		/* Raptor Lake-S */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7a26),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
+	{
+		/* Raptor Lake-S CPU */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa76f),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
+	{
 		/* Alder Lake CPU */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x466f),
 		.driver_data = (kernel_ulong_t)&intel_th_2x,
diff --git a/drivers/i2c/busses/i2c-cadence.c b/drivers/i2c/busses/i2c-cadence.c
index b4c1ad19cdae..33f5588a50c0 100644
--- a/drivers/i2c/busses/i2c-cadence.c
+++ b/drivers/i2c/busses/i2c-cadence.c
@@ -388,9 +388,9 @@ static irqreturn_t cdns_i2c_slave_isr(void *ptr)
  */
 static irqreturn_t cdns_i2c_master_isr(void *ptr)
 {
-	unsigned int isr_status, avail_bytes, updatetx;
+	unsigned int isr_status, avail_bytes;
 	unsigned int bytes_to_send;
-	bool hold_quirk;
+	bool updatetx;
 	struct cdns_i2c *id = ptr;
 	/* Signal completion only after everything is updated */
 	int done_flag = 0;
@@ -410,11 +410,7 @@ static irqreturn_t cdns_i2c_master_isr(void *ptr)
 	 * Check if transfer size register needs to be updated again for a
 	 * large data receive operation.
 	 */
-	updatetx = 0;
-	if (id->recv_count > id->curr_recv_count)
-		updatetx = 1;
-
-	hold_quirk = (id->quirks & CDNS_I2C_BROKEN_HOLD_BIT) && updatetx;
+	updatetx = id->recv_count > id->curr_recv_count;
 
 	/* When receiving, handle data interrupt and completion interrupt */
 	if (id->p_recv_buf &&
@@ -445,7 +441,7 @@ static irqreturn_t cdns_i2c_master_isr(void *ptr)
 				break;
 			}
 
-			if (cdns_is_holdquirk(id, hold_quirk))
+			if (cdns_is_holdquirk(id, updatetx))
 				break;
 		}
 
@@ -456,7 +452,7 @@ static irqreturn_t cdns_i2c_master_isr(void *ptr)
 		 * maintain transfer size non-zero while performing a large
 		 * receive operation.
 		 */
-		if (cdns_is_holdquirk(id, hold_quirk)) {
+		if (cdns_is_holdquirk(id, updatetx)) {
 			/* wait while fifo is full */
 			while (cdns_i2c_readreg(CDNS_I2C_XFER_SIZE_OFFSET) !=
 			       (id->curr_recv_count - CDNS_I2C_FIFO_DEPTH))
@@ -478,22 +474,6 @@ static irqreturn_t cdns_i2c_master_isr(void *ptr)
 						  CDNS_I2C_XFER_SIZE_OFFSET);
 				id->curr_recv_count = id->recv_count;
 			}
-		} else if (id->recv_count && !hold_quirk &&
-						!id->curr_recv_count) {
-
-			/* Set the slave address in address register*/
-			cdns_i2c_writereg(id->p_msg->addr & CDNS_I2C_ADDR_MASK,
-						CDNS_I2C_ADDR_OFFSET);
-
-			if (id->recv_count > CDNS_I2C_TRANSFER_SIZE) {
-				cdns_i2c_writereg(CDNS_I2C_TRANSFER_SIZE,
-						CDNS_I2C_XFER_SIZE_OFFSET);
-				id->curr_recv_count = CDNS_I2C_TRANSFER_SIZE;
-			} else {
-				cdns_i2c_writereg(id->recv_count,
-						CDNS_I2C_XFER_SIZE_OFFSET);
-				id->curr_recv_count = id->recv_count;
-			}
 		}
 
 		/* Clear hold (if not repeated start) and signal completion */
@@ -593,8 +573,13 @@ static void cdns_i2c_mrecv(struct cdns_i2c *id)
 	ctrl_reg = cdns_i2c_readreg(CDNS_I2C_CR_OFFSET);
 	ctrl_reg |= CDNS_I2C_CR_RW | CDNS_I2C_CR_CLR_FIFO;
 
+	/*
+	 * Receive up to I2C_SMBUS_BLOCK_MAX data bytes, plus one message length
+	 * byte, plus one checksum byte if PEC is enabled. p_msg->len will be 2 if
+	 * PEC is enabled, otherwise 1.
+	 */
 	if (id->p_msg->flags & I2C_M_RECV_LEN)
-		id->recv_count = I2C_SMBUS_BLOCK_MAX + 1;
+		id->recv_count = I2C_SMBUS_BLOCK_MAX + id->p_msg->len;
 
 	id->curr_recv_count = id->recv_count;
 
@@ -809,6 +794,9 @@ static int cdns_i2c_process_msg(struct cdns_i2c *id, struct i2c_msg *msg,
 	if (id->err_status & CDNS_I2C_IXR_ARB_LOST)
 		return -EAGAIN;
 
+	if (msg->flags & I2C_M_RECV_LEN)
+		msg->len += min_t(unsigned int, msg->buf[0], I2C_SMBUS_BLOCK_MAX);
+
 	return 0;
 }
 
@@ -1338,6 +1326,7 @@ static int cdns_i2c_probe(struct platform_device *pdev)
 	return 0;
 
 err_clk_dis:
+	clk_notifier_unregister(id->clk, &id->clk_rate_change_nb);
 	clk_disable_unprepare(id->clk);
 	pm_runtime_disable(&pdev->dev);
 	pm_runtime_set_suspended(&pdev->dev);
diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c
index fbf4392812b9..c94f25e62bf8 100644
--- a/drivers/i2c/busses/i2c-imx.c
+++ b/drivers/i2c/busses/i2c-imx.c
@@ -1742,9 +1742,7 @@ static int i2c_imx_remove(struct platform_device *pdev)
 	struct imx_i2c_struct *i2c_imx = platform_get_drvdata(pdev);
 	int irq, ret;
 
-	ret = pm_runtime_resume_and_get(&pdev->dev);
-	if (ret < 0)
-		return ret;
+	ret = pm_runtime_get_sync(&pdev->dev);
 
 	/* remove adapter */
 	dev_dbg(&i2c_imx->adapter.dev, "adapter removed\n");
@@ -1753,17 +1751,21 @@ static int i2c_imx_remove(struct platform_device *pdev)
 	if (i2c_imx->dma)
 		i2c_imx_dma_free(i2c_imx);
 
-	/* setup chip registers to defaults */
-	imx_i2c_write_reg(0, i2c_imx, IMX_I2C_IADR);
-	imx_i2c_write_reg(0, i2c_imx, IMX_I2C_IFDR);
-	imx_i2c_write_reg(0, i2c_imx, IMX_I2C_I2CR);
-	imx_i2c_write_reg(0, i2c_imx, IMX_I2C_I2SR);
+	if (ret == 0) {
+		/* setup chip registers to defaults */
+		imx_i2c_write_reg(0, i2c_imx, IMX_I2C_IADR);
+		imx_i2c_write_reg(0, i2c_imx, IMX_I2C_IFDR);
+		imx_i2c_write_reg(0, i2c_imx, IMX_I2C_I2CR);
+		imx_i2c_write_reg(0, i2c_imx, IMX_I2C_I2SR);
+		clk_disable(i2c_imx->clk);
+	}
 
 	clk_notifier_unregister(i2c_imx->clk, &i2c_imx->clk_change_nb);
 	irq = platform_get_irq(pdev, 0);
 	if (irq >= 0)
 		free_irq(irq, i2c_imx);
-	clk_disable_unprepare(i2c_imx->clk);
+
+	clk_unprepare(i2c_imx->clk);
 
 	pm_runtime_put_noidle(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
diff --git a/drivers/i2c/busses/i2c-mlxcpld.c b/drivers/i2c/busses/i2c-mlxcpld.c
index 015e11c4663f..077d716c73ca 100644
--- a/drivers/i2c/busses/i2c-mlxcpld.c
+++ b/drivers/i2c/busses/i2c-mlxcpld.c
@@ -49,7 +49,7 @@
 #define MLXCPLD_LPCI2C_NACK_IND		2
 
 #define MLXCPLD_I2C_FREQ_1000KHZ_SET	0x04
-#define MLXCPLD_I2C_FREQ_400KHZ_SET	0x0c
+#define MLXCPLD_I2C_FREQ_400KHZ_SET	0x0e
 #define MLXCPLD_I2C_FREQ_100KHZ_SET	0x42
 
 enum mlxcpld_i2c_frequency {
diff --git a/drivers/i2c/busses/i2c-mxs.c b/drivers/i2c/busses/i2c-mxs.c
index 864a3f1bd4e1..68f67d084c63 100644
--- a/drivers/i2c/busses/i2c-mxs.c
+++ b/drivers/i2c/busses/i2c-mxs.c
@@ -799,7 +799,7 @@ static int mxs_i2c_probe(struct platform_device *pdev)
 	if (!i2c)
 		return -ENOMEM;
 
-	i2c->dev_type = (enum mxs_i2c_devtype)of_device_get_match_data(&pdev->dev);
+	i2c->dev_type = (uintptr_t)of_device_get_match_data(&pdev->dev);
 
 	i2c->regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(i2c->regs))
diff --git a/drivers/i2c/busses/i2c-npcm7xx.c b/drivers/i2c/busses/i2c-npcm7xx.c
index d9ac62c1ac25..31e3d2c9d6bc 100644
--- a/drivers/i2c/busses/i2c-npcm7xx.c
+++ b/drivers/i2c/busses/i2c-npcm7xx.c
@@ -123,11 +123,11 @@ enum i2c_addr {
  * Since the addr regs are sprinkled all over the address space,
  * use this array to get the address or each register.
  */
-#define I2C_NUM_OWN_ADDR 10
+#define I2C_NUM_OWN_ADDR 2
+#define I2C_NUM_OWN_ADDR_SUPPORTED 2
+
 static const int npcm_i2caddr[I2C_NUM_OWN_ADDR] = {
-	NPCM_I2CADDR1, NPCM_I2CADDR2, NPCM_I2CADDR3, NPCM_I2CADDR4,
-	NPCM_I2CADDR5, NPCM_I2CADDR6, NPCM_I2CADDR7, NPCM_I2CADDR8,
-	NPCM_I2CADDR9, NPCM_I2CADDR10,
+	NPCM_I2CADDR1, NPCM_I2CADDR2,
 };
 #endif
 
@@ -391,14 +391,10 @@ static void npcm_i2c_disable(struct npcm_i2c *bus)
 #if IS_ENABLED(CONFIG_I2C_SLAVE)
 	int i;
 
-	/* select bank 0 for I2C addresses */
-	npcm_i2c_select_bank(bus, I2C_BANK_0);
-
 	/* Slave addresses removal */
-	for (i = I2C_SLAVE_ADDR1; i < I2C_NUM_OWN_ADDR; i++)
+	for (i = I2C_SLAVE_ADDR1; i < I2C_NUM_OWN_ADDR_SUPPORTED; i++)
 		iowrite8(0, bus->reg + npcm_i2caddr[i]);
 
-	npcm_i2c_select_bank(bus, I2C_BANK_1);
 #endif
 	/* Disable module */
 	i2cctl2 = ioread8(bus->reg + NPCM_I2CCTL2);
@@ -603,8 +599,7 @@ static int npcm_i2c_slave_enable(struct npcm_i2c *bus, enum i2c_addr addr_type,
 			i2cctl1 &= ~NPCM_I2CCTL1_GCMEN;
 		iowrite8(i2cctl1, bus->reg + NPCM_I2CCTL1);
 		return 0;
-	}
-	if (addr_type == I2C_ARP_ADDR) {
+	} else if (addr_type == I2C_ARP_ADDR) {
 		i2cctl3 = ioread8(bus->reg + NPCM_I2CCTL3);
 		if (enable)
 			i2cctl3 |= I2CCTL3_ARPMEN;
@@ -613,16 +608,16 @@ static int npcm_i2c_slave_enable(struct npcm_i2c *bus, enum i2c_addr addr_type,
 		iowrite8(i2cctl3, bus->reg + NPCM_I2CCTL3);
 		return 0;
 	}
+	if (addr_type > I2C_SLAVE_ADDR2 && addr_type <= I2C_SLAVE_ADDR10)
+		dev_err(bus->dev, "try to enable more than 2 SA not supported\n");
+
 	if (addr_type >= I2C_ARP_ADDR)
 		return -EFAULT;
-	/* select bank 0 for address 3 to 10 */
-	if (addr_type > I2C_SLAVE_ADDR2)
-		npcm_i2c_select_bank(bus, I2C_BANK_0);
+
 	/* Set and enable the address */
 	iowrite8(sa_reg, bus->reg + npcm_i2caddr[addr_type]);
 	npcm_i2c_slave_int_enable(bus, enable);
-	if (addr_type > I2C_SLAVE_ADDR2)
-		npcm_i2c_select_bank(bus, I2C_BANK_1);
+
 	return 0;
 }
 #endif
@@ -843,15 +838,11 @@ static u8 npcm_i2c_get_slave_addr(struct npcm_i2c *bus, enum i2c_addr addr_type)
 {
 	u8 slave_add;
 
-	/* select bank 0 for address 3 to 10 */
-	if (addr_type > I2C_SLAVE_ADDR2)
-		npcm_i2c_select_bank(bus, I2C_BANK_0);
+	if (addr_type > I2C_SLAVE_ADDR2 && addr_type <= I2C_SLAVE_ADDR10)
+		dev_err(bus->dev, "get slave: try to use more than 2 SA not supported\n");
 
 	slave_add = ioread8(bus->reg + npcm_i2caddr[(int)addr_type]);
 
-	if (addr_type > I2C_SLAVE_ADDR2)
-		npcm_i2c_select_bank(bus, I2C_BANK_1);
-
 	return slave_add;
 }
 
@@ -861,12 +852,12 @@ static int npcm_i2c_remove_slave_addr(struct npcm_i2c *bus, u8 slave_add)
 
 	/* Set the enable bit */
 	slave_add |= 0x80;
-	npcm_i2c_select_bank(bus, I2C_BANK_0);
-	for (i = I2C_SLAVE_ADDR1; i < I2C_NUM_OWN_ADDR; i++) {
+
+	for (i = I2C_SLAVE_ADDR1; i < I2C_NUM_OWN_ADDR_SUPPORTED; i++) {
 		if (ioread8(bus->reg + npcm_i2caddr[i]) == slave_add)
 			iowrite8(0, bus->reg + npcm_i2caddr[i]);
 	}
-	npcm_i2c_select_bank(bus, I2C_BANK_1);
+
 	return 0;
 }
 
@@ -921,11 +912,15 @@ static int npcm_i2c_slave_get_wr_buf(struct npcm_i2c *bus)
 	for (i = 0; i < I2C_HW_FIFO_SIZE; i++) {
 		if (bus->slv_wr_size >= I2C_HW_FIFO_SIZE)
 			break;
-		i2c_slave_event(bus->slave, I2C_SLAVE_READ_REQUESTED, &value);
+		if (bus->state == I2C_SLAVE_MATCH) {
+			i2c_slave_event(bus->slave, I2C_SLAVE_READ_REQUESTED, &value);
+			bus->state = I2C_OPER_STARTED;
+		} else {
+			i2c_slave_event(bus->slave, I2C_SLAVE_READ_PROCESSED, &value);
+		}
 		ind = (bus->slv_wr_ind + bus->slv_wr_size) % I2C_HW_FIFO_SIZE;
 		bus->slv_wr_buf[ind] = value;
 		bus->slv_wr_size++;
-		i2c_slave_event(bus->slave, I2C_SLAVE_READ_PROCESSED, &value);
 	}
 	return I2C_HW_FIFO_SIZE - ret;
 }
@@ -973,7 +968,6 @@ static void npcm_i2c_slave_xmit(struct npcm_i2c *bus, u16 nwrite,
 	if (nwrite == 0)
 		return;
 
-	bus->state = I2C_OPER_STARTED;
 	bus->operation = I2C_WRITE_OPER;
 
 	/* get the next buffer */
diff --git a/drivers/i2c/busses/i2c-piix4.c b/drivers/i2c/busses/i2c-piix4.c
index ac8e7d60672a..39cb1b7bb865 100644
--- a/drivers/i2c/busses/i2c-piix4.c
+++ b/drivers/i2c/busses/i2c-piix4.c
@@ -161,7 +161,6 @@ static const char *piix4_aux_port_name_sb800 = " port 1";
 
 struct sb800_mmio_cfg {
 	void __iomem *addr;
-	struct resource *res;
 	bool use_mmio;
 };
 
@@ -179,13 +178,11 @@ static int piix4_sb800_region_request(struct device *dev,
 				      struct sb800_mmio_cfg *mmio_cfg)
 {
 	if (mmio_cfg->use_mmio) {
-		struct resource *res;
 		void __iomem *addr;
 
-		res = request_mem_region_muxed(SB800_PIIX4_FCH_PM_ADDR,
-					       SB800_PIIX4_FCH_PM_SIZE,
-					       "sb800_piix4_smb");
-		if (!res) {
+		if (!request_mem_region_muxed(SB800_PIIX4_FCH_PM_ADDR,
+					      SB800_PIIX4_FCH_PM_SIZE,
+					      "sb800_piix4_smb")) {
 			dev_err(dev,
 				"SMBus base address memory region 0x%x already in use.\n",
 				SB800_PIIX4_FCH_PM_ADDR);
@@ -195,12 +192,12 @@ static int piix4_sb800_region_request(struct device *dev,
 		addr = ioremap(SB800_PIIX4_FCH_PM_ADDR,
 			       SB800_PIIX4_FCH_PM_SIZE);
 		if (!addr) {
-			release_resource(res);
+			release_mem_region(SB800_PIIX4_FCH_PM_ADDR,
+					   SB800_PIIX4_FCH_PM_SIZE);
 			dev_err(dev, "SMBus base address mapping failed.\n");
 			return -ENOMEM;
 		}
 
-		mmio_cfg->res = res;
 		mmio_cfg->addr = addr;
 
 		return 0;
@@ -222,7 +219,8 @@ static void piix4_sb800_region_release(struct device *dev,
 {
 	if (mmio_cfg->use_mmio) {
 		iounmap(mmio_cfg->addr);
-		release_resource(mmio_cfg->res);
+		release_mem_region(SB800_PIIX4_FCH_PM_ADDR,
+				   SB800_PIIX4_FCH_PM_SIZE);
 		return;
 	}
 
diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index cfbef70e8ba7..8fb065caf30b 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -2464,8 +2464,9 @@ void i2c_put_adapter(struct i2c_adapter *adap)
 	if (!adap)
 		return;
 
-	put_device(&adap->dev);
 	module_put(adap->owner);
+	/* Should be last, otherwise we risk use-after-free with 'adap' */
+	put_device(&adap->dev);
 }
 EXPORT_SYMBOL(i2c_put_adapter);
 
diff --git a/drivers/i2c/muxes/i2c-mux-gpmux.c b/drivers/i2c/muxes/i2c-mux-gpmux.c
index d3acd8d66c32..33024acaac02 100644
--- a/drivers/i2c/muxes/i2c-mux-gpmux.c
+++ b/drivers/i2c/muxes/i2c-mux-gpmux.c
@@ -134,6 +134,7 @@ static int i2c_mux_probe(struct platform_device *pdev)
 	return 0;
 
 err_children:
+	of_node_put(child);
 	i2c_mux_del_adapters(muxc);
 err_parent:
 	i2c_put_adapter(parent);
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index e6c543b5ee1d..376e631e80d6 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -47,11 +47,13 @@
 #include <linux/tick.h>
 #include <trace/events/power.h>
 #include <linux/sched.h>
+#include <linux/sched/smt.h>
 #include <linux/notifier.h>
 #include <linux/cpu.h>
 #include <linux/moduleparam.h>
 #include <asm/cpu_device_id.h>
 #include <asm/intel-family.h>
+#include <asm/nospec-branch.h>
 #include <asm/mwait.h>
 #include <asm/msr.h>
 
@@ -94,6 +96,12 @@ static unsigned int mwait_substates __initdata;
 #define CPUIDLE_FLAG_ALWAYS_ENABLE	BIT(15)
 
 /*
+ * Disable IBRS across idle (when KERNEL_IBRS), is exclusive vs IRQ_ENABLE
+ * above.
+ */
+#define CPUIDLE_FLAG_IBRS		BIT(16)
+
+/*
  * MWAIT takes an 8-bit "hint" in EAX "suggesting"
  * the C-state (top nibble) and sub-state (bottom nibble)
  * 0x00 means "MWAIT(C1)", 0x10 means "MWAIT(C2)" etc.
@@ -132,6 +140,24 @@ static __cpuidle int intel_idle(struct cpuidle_device *dev,
 	return index;
 }
 
+static __cpuidle int intel_idle_ibrs(struct cpuidle_device *dev,
+				     struct cpuidle_driver *drv, int index)
+{
+	bool smt_active = sched_smt_active();
+	u64 spec_ctrl = spec_ctrl_current();
+	int ret;
+
+	if (smt_active)
+		wrmsrl(MSR_IA32_SPEC_CTRL, 0);
+
+	ret = intel_idle(dev, drv, index);
+
+	if (smt_active)
+		wrmsrl(MSR_IA32_SPEC_CTRL, spec_ctrl);
+
+	return ret;
+}
+
 /**
  * intel_idle_s2idle - Ask the processor to enter the given idle state.
  * @dev: cpuidle device of the target CPU.
@@ -653,7 +679,7 @@ static struct cpuidle_state skl_cstates[] __initdata = {
 	{
 		.name = "C6",
 		.desc = "MWAIT 0x20",
-		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED | CPUIDLE_FLAG_IBRS,
 		.exit_latency = 85,
 		.target_residency = 200,
 		.enter = &intel_idle,
@@ -661,7 +687,7 @@ static struct cpuidle_state skl_cstates[] __initdata = {
 	{
 		.name = "C7s",
 		.desc = "MWAIT 0x33",
-		.flags = MWAIT2flg(0x33) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x33) | CPUIDLE_FLAG_TLB_FLUSHED | CPUIDLE_FLAG_IBRS,
 		.exit_latency = 124,
 		.target_residency = 800,
 		.enter = &intel_idle,
@@ -669,7 +695,7 @@ static struct cpuidle_state skl_cstates[] __initdata = {
 	{
 		.name = "C8",
 		.desc = "MWAIT 0x40",
-		.flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TLB_FLUSHED | CPUIDLE_FLAG_IBRS,
 		.exit_latency = 200,
 		.target_residency = 800,
 		.enter = &intel_idle,
@@ -677,7 +703,7 @@ static struct cpuidle_state skl_cstates[] __initdata = {
 	{
 		.name = "C9",
 		.desc = "MWAIT 0x50",
-		.flags = MWAIT2flg(0x50) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x50) | CPUIDLE_FLAG_TLB_FLUSHED | CPUIDLE_FLAG_IBRS,
 		.exit_latency = 480,
 		.target_residency = 5000,
 		.enter = &intel_idle,
@@ -685,7 +711,7 @@ static struct cpuidle_state skl_cstates[] __initdata = {
 	{
 		.name = "C10",
 		.desc = "MWAIT 0x60",
-		.flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED | CPUIDLE_FLAG_IBRS,
 		.exit_latency = 890,
 		.target_residency = 5000,
 		.enter = &intel_idle,
@@ -714,7 +740,7 @@ static struct cpuidle_state skx_cstates[] __initdata = {
 	{
 		.name = "C6",
 		.desc = "MWAIT 0x20",
-		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED | CPUIDLE_FLAG_IBRS,
 		.exit_latency = 133,
 		.target_residency = 600,
 		.enter = &intel_idle,
@@ -1574,6 +1600,11 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv)
 		/* Structure copy. */
 		drv->states[drv->state_count] = cpuidle_state_table[cstate];
 
+		if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) &&
+		    cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_IBRS) {
+			drv->states[drv->state_count].enter = intel_idle_ibrs;
+		}
+
 		if ((disabled_states_mask & BIT(drv->state_count)) ||
 		    ((icpu->use_acpi || force_use_acpi) &&
 		     intel_idle_off_by_default(mwait_hint) &&
diff --git a/drivers/iio/accel/bma400.h b/drivers/iio/accel/bma400.h
index 5ad10db9819f..416090c6b1e8 100644
--- a/drivers/iio/accel/bma400.h
+++ b/drivers/iio/accel/bma400.h
@@ -83,8 +83,27 @@
 #define BMA400_ACC_ODR_MIN_WHOLE_HZ 25
 #define BMA400_ACC_ODR_MIN_HZ       12
 
-#define BMA400_SCALE_MIN            38357
-#define BMA400_SCALE_MAX            306864
+/*
+ * BMA400_SCALE_MIN macro value represents m/s^2 for 1 LSB before
+ * converting to micro values for +-2g range.
+ *
+ * For +-2g - 1 LSB = 0.976562 milli g = 0.009576 m/s^2
+ * For +-4g - 1 LSB = 1.953125 milli g = 0.019153 m/s^2
+ * For +-16g - 1 LSB = 7.8125 milli g = 0.076614 m/s^2
+ *
+ * The raw value which is used to select the different ranges is determined
+ * by the first bit set position from the scale value, so BMA400_SCALE_MIN
+ * should be odd.
+ *
+ * Scale values for +-2g, +-4g, +-8g and +-16g are populated into bma400_scales
+ * array by left shifting BMA400_SCALE_MIN.
+ * e.g.:
+ * To select +-2g = 9577 << 0 = raw value to write is 0.
+ * To select +-8g = 9577 << 2 = raw value to write is 2.
+ * To select +-16g = 9577 << 3 = raw value to write is 3.
+ */
+#define BMA400_SCALE_MIN            9577
+#define BMA400_SCALE_MAX            76617
 
 #define BMA400_NUM_REGULATORS       2
 #define BMA400_VDD_REGULATOR        0
diff --git a/drivers/iio/accel/bma400_core.c b/drivers/iio/accel/bma400_core.c
index 21520e022a21..7e6598534650 100644
--- a/drivers/iio/accel/bma400_core.c
+++ b/drivers/iio/accel/bma400_core.c
@@ -13,14 +13,14 @@
 
 #include <linux/bitops.h>
 #include <linux/device.h>
-#include <linux/iio/iio.h>
-#include <linux/iio/sysfs.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/regmap.h>
 #include <linux/regulator/consumer.h>
 
+#include <linux/iio/iio.h>
+
 #include "bma400.h"
 
 /*
diff --git a/drivers/iio/accel/cros_ec_accel_legacy.c b/drivers/iio/accel/cros_ec_accel_legacy.c
index b6f3471b62dc..3b77fded2dc0 100644
--- a/drivers/iio/accel/cros_ec_accel_legacy.c
+++ b/drivers/iio/accel/cros_ec_accel_legacy.c
@@ -215,7 +215,7 @@ static int cros_ec_accel_legacy_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	ret = cros_ec_sensors_core_init(pdev, indio_dev, true,
-					cros_ec_sensors_capture, NULL);
+					cros_ec_sensors_capture);
 	if (ret)
 		return ret;
 
@@ -235,7 +235,7 @@ static int cros_ec_accel_legacy_probe(struct platform_device *pdev)
 		state->sign[CROS_EC_SENSOR_Z] = -1;
 	}
 
-	return devm_iio_device_register(dev, indio_dev);
+	return cros_ec_sensors_core_register(dev, indio_dev, NULL);
 }
 
 static struct platform_driver cros_ec_accel_platform_driver = {
diff --git a/drivers/iio/adc/ad7292.c b/drivers/iio/adc/ad7292.c
index 3271a31afde1..e3e14a1253e8 100644
--- a/drivers/iio/adc/ad7292.c
+++ b/drivers/iio/adc/ad7292.c
@@ -287,10 +287,8 @@ static int ad7292_probe(struct spi_device *spi)
 
 		ret = devm_add_action_or_reset(&spi->dev,
 					       ad7292_regulator_disable, st);
-		if (ret) {
-			regulator_disable(st->reg);
+		if (ret)
 			return ret;
-		}
 
 		ret = regulator_get_voltage(st->reg);
 		if (ret < 0)
diff --git a/drivers/iio/adc/mcp3911.c b/drivers/iio/adc/mcp3911.c
index e573da5397bb..65278270a75c 100644
--- a/drivers/iio/adc/mcp3911.c
+++ b/drivers/iio/adc/mcp3911.c
@@ -38,8 +38,8 @@
 #define MCP3911_CHANNEL(x)		(MCP3911_REG_CHANNEL0 + x * 3)
 #define MCP3911_OFFCAL(x)		(MCP3911_REG_OFFCAL_CH0 + x * 6)
 
-/* Internal voltage reference in uV */
-#define MCP3911_INT_VREF_UV		1200000
+/* Internal voltage reference in mV */
+#define MCP3911_INT_VREF_MV		1200
 
 #define MCP3911_REG_READ(reg, id)	((((reg) << 1) | ((id) << 5) | (1 << 0)) & 0xff)
 #define MCP3911_REG_WRITE(reg, id)	((((reg) << 1) | ((id) << 5) | (0 << 0)) & 0xff)
@@ -111,6 +111,8 @@ static int mcp3911_read_raw(struct iio_dev *indio_dev,
 		if (ret)
 			goto out;
 
+		*val = sign_extend32(*val, 23);
+
 		ret = IIO_VAL_INT;
 		break;
 
@@ -135,11 +137,18 @@ static int mcp3911_read_raw(struct iio_dev *indio_dev,
 
 			*val = ret / 1000;
 		} else {
-			*val = MCP3911_INT_VREF_UV;
+			*val = MCP3911_INT_VREF_MV;
 		}
 
-		*val2 = 24;
-		ret = IIO_VAL_FRACTIONAL_LOG2;
+		/*
+		 * For 24bit Conversion
+		 * Raw = ((Voltage)/(Vref) * 2^23 * Gain * 1.5
+		 * Voltage = Raw * (Vref)/(2^23 * Gain * 1.5)
+		 */
+
+		/* val2 = (2^23 * 1.5) */
+		*val2 = 12582912;
+		ret = IIO_VAL_FRACTIONAL;
 		break;
 	}
 
diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_lid_angle.c b/drivers/iio/common/cros_ec_sensors/cros_ec_lid_angle.c
index af801e203623..02d3cf36acb0 100644
--- a/drivers/iio/common/cros_ec_sensors/cros_ec_lid_angle.c
+++ b/drivers/iio/common/cros_ec_sensors/cros_ec_lid_angle.c
@@ -97,7 +97,7 @@ static int cros_ec_lid_angle_probe(struct platform_device *pdev)
 	if (!indio_dev)
 		return -ENOMEM;
 
-	ret = cros_ec_sensors_core_init(pdev, indio_dev, false, NULL, NULL);
+	ret = cros_ec_sensors_core_init(pdev, indio_dev, false, NULL);
 	if (ret)
 		return ret;
 
@@ -113,7 +113,7 @@ static int cros_ec_lid_angle_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	return devm_iio_device_register(dev, indio_dev);
+	return cros_ec_sensors_core_register(dev, indio_dev, NULL);
 }
 
 static const struct platform_device_id cros_ec_lid_angle_ids[] = {
diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c
index 376a5b30010a..5cce34fdff02 100644
--- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c
+++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c
@@ -235,8 +235,7 @@ static int cros_ec_sensors_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	ret = cros_ec_sensors_core_init(pdev, indio_dev, true,
-					cros_ec_sensors_capture,
-					cros_ec_sensors_push_data);
+					cros_ec_sensors_capture);
 	if (ret)
 		return ret;
 
@@ -297,7 +296,8 @@ static int cros_ec_sensors_probe(struct platform_device *pdev)
 	else
 		state->core.read_ec_sensors_data = cros_ec_sensors_read_cmd;
 
-	return devm_iio_device_register(dev, indio_dev);
+	return cros_ec_sensors_core_register(dev, indio_dev,
+			cros_ec_sensors_push_data);
 }
 
 static const struct platform_device_id cros_ec_sensors_ids[] = {
diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c
index 28bde13003b7..b0c1dc8cc4c5 100644
--- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c
+++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c
@@ -234,21 +234,18 @@ static void cros_ec_sensors_core_clean(void *arg)
 
 /**
  * cros_ec_sensors_core_init() - basic initialization of the core structure
- * @pdev:		platform device created for the sensors
+ * @pdev:		platform device created for the sensor
  * @indio_dev:		iio device structure of the device
  * @physical_device:	true if the device refers to a physical device
  * @trigger_capture:    function pointer to call buffer is triggered,
  *    for backward compatibility.
- * @push_data:          function to call when cros_ec_sensorhub receives
- *    a sample for that sensor.
  *
  * Return: 0 on success, -errno on failure.
  */
 int cros_ec_sensors_core_init(struct platform_device *pdev,
 			      struct iio_dev *indio_dev,
 			      bool physical_device,
-			      cros_ec_sensors_capture_t trigger_capture,
-			      cros_ec_sensorhub_push_data_cb_t push_data)
+			      cros_ec_sensors_capture_t trigger_capture)
 {
 	struct device *dev = &pdev->dev;
 	struct cros_ec_sensors_core_state *state = iio_priv(indio_dev);
@@ -339,17 +336,6 @@ int cros_ec_sensors_core_init(struct platform_device *pdev,
 			if (ret)
 				return ret;
 
-			ret = cros_ec_sensorhub_register_push_data(
-					sensor_hub, sensor_platform->sensor_num,
-					indio_dev, push_data);
-			if (ret)
-				return ret;
-
-			ret = devm_add_action_or_reset(
-					dev, cros_ec_sensors_core_clean, pdev);
-			if (ret)
-				return ret;
-
 			/* Timestamp coming from FIFO are in ns since boot. */
 			ret = iio_device_set_clock(indio_dev, CLOCK_BOOTTIME);
 			if (ret)
@@ -372,6 +358,46 @@ int cros_ec_sensors_core_init(struct platform_device *pdev,
 EXPORT_SYMBOL_GPL(cros_ec_sensors_core_init);
 
 /**
+ * cros_ec_sensors_core_register() - Register callback to FIFO and IIO when
+ * sensor is ready.
+ * It must be called at the end of the sensor probe routine.
+ * @dev:		device created for the sensor
+ * @indio_dev:		iio device structure of the device
+ * @push_data:          function to call when cros_ec_sensorhub receives
+ *    a sample for that sensor.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+int cros_ec_sensors_core_register(struct device *dev,
+				  struct iio_dev *indio_dev,
+				  cros_ec_sensorhub_push_data_cb_t push_data)
+{
+	struct cros_ec_sensor_platform *sensor_platform = dev_get_platdata(dev);
+	struct cros_ec_sensorhub *sensor_hub = dev_get_drvdata(dev->parent);
+	struct platform_device *pdev = to_platform_device(dev);
+	struct cros_ec_dev *ec = sensor_hub->ec;
+	int ret;
+
+	ret = devm_iio_device_register(dev, indio_dev);
+	if (ret)
+		return ret;
+
+	if (!push_data ||
+	    !cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE_FIFO))
+		return 0;
+
+	ret = cros_ec_sensorhub_register_push_data(
+			sensor_hub, sensor_platform->sensor_num,
+			indio_dev, push_data);
+	if (ret)
+		return ret;
+
+	return devm_add_action_or_reset(
+			dev, cros_ec_sensors_core_clean, pdev);
+}
+EXPORT_SYMBOL_GPL(cros_ec_sensors_core_register);
+
+/**
  * cros_ec_motion_send_host_cmd() - send motion sense host command
  * @state:		pointer to state information for device
  * @opt_length:	optional length to reduce the response size, useful on the data
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_magn.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_magn.c
index f282e9cc34c5..6aee6c989485 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_magn.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_magn.c
@@ -261,6 +261,7 @@ int inv_mpu_magn_set_rate(const struct inv_mpu6050_state *st, int fifo_rate)
  */
 int inv_mpu_magn_set_orient(struct inv_mpu6050_state *st)
 {
+	struct device *dev = regmap_get_device(st->map);
 	const char *orient;
 	char *str;
 	int i;
@@ -279,22 +280,27 @@ int inv_mpu_magn_set_orient(struct inv_mpu6050_state *st)
 		st->magn_orient.rotation[4] = st->orientation.rotation[1];
 		st->magn_orient.rotation[5] = st->orientation.rotation[2];
 		/* z <- -z */
-		for (i = 0; i < 3; ++i) {
-			orient = st->orientation.rotation[6 + i];
-			/* use length + 2 for adding minus sign if needed */
-			str = devm_kzalloc(regmap_get_device(st->map),
-					   strlen(orient) + 2, GFP_KERNEL);
-			if (str == NULL)
+		for (i = 6; i < 9; ++i) {
+			orient = st->orientation.rotation[i];
+
+			/*
+			 * The value is negated according to one of the following
+			 * rules:
+			 *
+			 * 1) Drop leading minus.
+			 * 2) Leave 0 as is.
+			 * 3) Add leading minus.
+			 */
+			if (orient[0] == '-')
+				str = devm_kstrdup(dev, orient + 1, GFP_KERNEL);
+			else if (!strcmp(orient, "0"))
+				str = devm_kstrdup(dev, orient, GFP_KERNEL);
+			else
+				str = devm_kasprintf(dev, GFP_KERNEL, "-%s", orient);
+			if (!str)
 				return -ENOMEM;
-			if (strcmp(orient, "0") == 0) {
-				strcpy(str, orient);
-			} else if (orient[0] == '-') {
-				strcpy(str, &orient[1]);
-			} else {
-				str[0] = '-';
-				strcpy(&str[1], orient);
-			}
-			st->magn_orient.rotation[6 + i] = str;
+
+			st->magn_orient.rotation[i] = str;
 		}
 		break;
 	default:
diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index 3e1e86d987cc..a7f5d432c95d 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -818,7 +818,23 @@ static ssize_t iio_format_avail_list(char *buf, const int *vals,
 
 static ssize_t iio_format_avail_range(char *buf, const int *vals, int type)
 {
-	return iio_format_list(buf, vals, type, 3, "[", "]");
+	int length;
+
+	/*
+	 * length refers to the array size , not the number of elements.
+	 * The purpose is to print the range [min , step ,max] so length should
+	 * be 3 in case of int, and 6 for other types.
+	 */
+	switch (type) {
+	case IIO_VAL_INT:
+		length = 3;
+		break;
+	default:
+		length = 6;
+		break;
+	}
+
+	return iio_format_list(buf, vals, type, length, "[", "]");
 }
 
 static ssize_t iio_read_channel_info_avail(struct device *dev,
diff --git a/drivers/iio/light/cros_ec_light_prox.c b/drivers/iio/light/cros_ec_light_prox.c
index de472f23d1cb..16b893bae388 100644
--- a/drivers/iio/light/cros_ec_light_prox.c
+++ b/drivers/iio/light/cros_ec_light_prox.c
@@ -181,8 +181,7 @@ static int cros_ec_light_prox_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	ret = cros_ec_sensors_core_init(pdev, indio_dev, true,
-					cros_ec_sensors_capture,
-					cros_ec_sensors_push_data);
+					cros_ec_sensors_capture);
 	if (ret)
 		return ret;
 
@@ -240,7 +239,8 @@ static int cros_ec_light_prox_probe(struct platform_device *pdev)
 
 	state->core.read_ec_sensors_data = cros_ec_sensors_read_cmd;
 
-	return devm_iio_device_register(dev, indio_dev);
+	return cros_ec_sensors_core_register(dev, indio_dev,
+					     cros_ec_sensors_push_data);
 }
 
 static const struct platform_device_id cros_ec_light_prox_ids[] = {
diff --git a/drivers/iio/light/isl29028.c b/drivers/iio/light/isl29028.c
index 9de3262aa688..a62787f5d5e7 100644
--- a/drivers/iio/light/isl29028.c
+++ b/drivers/iio/light/isl29028.c
@@ -625,7 +625,7 @@ static int isl29028_probe(struct i2c_client *client,
 					 ISL29028_POWER_OFF_DELAY_MS);
 	pm_runtime_use_autosuspend(&client->dev);
 
-	ret = devm_iio_device_register(indio_dev->dev.parent, indio_dev);
+	ret = iio_device_register(indio_dev);
 	if (ret < 0) {
 		dev_err(&client->dev,
 			"%s(): iio registration failed with error %d\n",
diff --git a/drivers/iio/pressure/cros_ec_baro.c b/drivers/iio/pressure/cros_ec_baro.c
index 2f882e109423..0511edbf868d 100644
--- a/drivers/iio/pressure/cros_ec_baro.c
+++ b/drivers/iio/pressure/cros_ec_baro.c
@@ -138,8 +138,7 @@ static int cros_ec_baro_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	ret = cros_ec_sensors_core_init(pdev, indio_dev, true,
-					cros_ec_sensors_capture,
-					cros_ec_sensors_push_data);
+					cros_ec_sensors_capture);
 	if (ret)
 		return ret;
 
@@ -186,7 +185,8 @@ static int cros_ec_baro_probe(struct platform_device *pdev)
 
 	state->core.read_ec_sensors_data = cros_ec_sensors_read_cmd;
 
-	return devm_iio_device_register(dev, indio_dev);
+	return cros_ec_sensors_core_register(dev, indio_dev,
+					     cros_ec_sensors_push_data);
 }
 
 static const struct platform_device_id cros_ec_baro_ids[] = {
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index 1c107d6d03b9..b985e0d9bc05 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -1252,8 +1252,10 @@ struct ib_cm_id *ib_cm_insert_listen(struct ib_device *device,
 		return ERR_CAST(cm_id_priv);
 
 	err = cm_init_listen(cm_id_priv, service_id, 0);
-	if (err)
+	if (err) {
+		ib_destroy_cm_id(&cm_id_priv->id);
 		return ERR_PTR(err);
+	}
 
 	spin_lock_irq(&cm_id_priv->lock);
 	listen_id_priv = cm_insert_listen(cm_id_priv, cm_handler);
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index a814dabcdff4..0da66dd40d6a 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -1718,8 +1718,8 @@ cma_ib_id_from_event(struct ib_cm_id *cm_id,
 		}
 
 		if (!validate_net_dev(*net_dev,
-				 (struct sockaddr *)&req->listen_addr_storage,
-				 (struct sockaddr *)&req->src_addr_storage)) {
+				 (struct sockaddr *)&req->src_addr_storage,
+				 (struct sockaddr *)&req->listen_addr_storage)) {
 			id_priv = ERR_PTR(-EHOSTUNREACH);
 			goto err;
 		}
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index 7a47343d11f9..b052de1b9ccb 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -463,7 +463,7 @@ retry:
 		mutex_unlock(&umem_odp->umem_mutex);
 
 out_put_mm:
-	mmput(owning_mm);
+	mmput_async(owning_mm);
 out_put_task:
 	if (owning_process)
 		put_task_struct(owning_process);
diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c
index 3ebdd42fec36..686d170a5947 100644
--- a/drivers/infiniband/hw/hfi1/file_ops.c
+++ b/drivers/infiniband/hw/hfi1/file_ops.c
@@ -1179,8 +1179,10 @@ static int setup_base_ctxt(struct hfi1_filedata *fd,
 		goto done;
 
 	ret = init_user_ctxt(fd, uctxt);
-	if (ret)
+	if (ret) {
+		hfi1_free_ctxt_rcv_groups(uctxt);
 		goto done;
+	}
 
 	user_init(uctxt);
 
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index bf01210c56c2..1dbad159f379 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -5854,8 +5854,8 @@ static irqreturn_t hns_roce_v2_msix_interrupt_abn(int irq, void *dev_id)
 
 		dev_err(dev, "AEQ overflow!\n");
 
-		int_st |= 1 << HNS_ROCE_V2_VF_INT_ST_AEQ_OVERFLOW_S;
-		roce_write(hr_dev, ROCEE_VF_ABN_INT_ST_REG, int_st);
+		roce_write(hr_dev, ROCEE_VF_ABN_INT_ST_REG,
+			   1 << HNS_ROCE_V2_VF_INT_ST_AEQ_OVERFLOW_S);
 
 		/* Set reset level for reset_event() */
 		if (ops->set_default_reset_request)
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
index df4501e77fd1..d3d5b5f57052 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
@@ -98,7 +98,7 @@
 
 #define HNS_ROCE_V2_QPC_TIMER_ENTRY_SZ		PAGE_SIZE
 #define HNS_ROCE_V2_CQC_TIMER_ENTRY_SZ		PAGE_SIZE
-#define HNS_ROCE_V2_PAGE_SIZE_SUPPORTED		0xFFFFF000
+#define HNS_ROCE_V2_PAGE_SIZE_SUPPORTED		0xFFFF000
 #define HNS_ROCE_V2_MAX_INNER_MTPT_NUM		2
 #define HNS_ROCE_INVALID_LKEY			0x0
 #define HNS_ROCE_INVALID_SGE_LENGTH		0x80000000
diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c
index 9af4509894e6..5d50d2d1deca 100644
--- a/drivers/infiniband/hw/hns/hns_roce_qp.c
+++ b/drivers/infiniband/hw/hns/hns_roce_qp.c
@@ -495,11 +495,8 @@ static int set_rq_size(struct hns_roce_dev *hr_dev, struct ib_qp_cap *cap,
 	hr_qp->rq.max_gs = roundup_pow_of_two(max(1U, cap->max_recv_sge) +
 					      hr_qp->rq.rsv_sge);
 
-	if (hr_dev->caps.max_rq_sg <= HNS_ROCE_SGE_IN_WQE)
-		hr_qp->rq.wqe_shift = ilog2(hr_dev->caps.max_rq_desc_sz);
-	else
-		hr_qp->rq.wqe_shift = ilog2(hr_dev->caps.max_rq_desc_sz *
-					    hr_qp->rq.max_gs);
+	hr_qp->rq.wqe_shift = ilog2(hr_dev->caps.max_rq_desc_sz *
+				    hr_qp->rq.max_gs);
 
 	hr_qp->rq.wqe_cnt = cnt;
 	if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_RQ_INLINE &&
diff --git a/drivers/infiniband/hw/irdma/cm.c b/drivers/infiniband/hw/irdma/cm.c
index 632f65e53b63..b08c67bb264c 100644
--- a/drivers/infiniband/hw/irdma/cm.c
+++ b/drivers/infiniband/hw/irdma/cm.c
@@ -1477,12 +1477,13 @@ irdma_find_listener(struct irdma_cm_core *cm_core, u32 *dst_addr, u16 dst_port,
 	list_for_each_entry (listen_node, &cm_core->listen_list, list) {
 		memcpy(listen_addr, listen_node->loc_addr, sizeof(listen_addr));
 		listen_port = listen_node->loc_port;
+		if (listen_port != dst_port ||
+		    !(listener_state & listen_node->listener_state))
+			continue;
 		/* compare node pair, return node handle if a match */
-		if ((!memcmp(listen_addr, dst_addr, sizeof(listen_addr)) ||
-		     !memcmp(listen_addr, ip_zero, sizeof(listen_addr))) &&
-		    listen_port == dst_port &&
-		    vlan_id == listen_node->vlan_id &&
-		    (listener_state & listen_node->listener_state)) {
+		if (!memcmp(listen_addr, ip_zero, sizeof(listen_addr)) ||
+		    (!memcmp(listen_addr, dst_addr, sizeof(listen_addr)) &&
+		     vlan_id == listen_node->vlan_id)) {
 			refcount_inc(&listen_node->refcnt);
 			spin_unlock_irqrestore(&cm_core->listen_list_lock,
 					       flags);
@@ -4221,10 +4222,6 @@ void irdma_cm_teardown_connections(struct irdma_device *iwdev, u32 *ipaddr,
 	struct irdma_cm_node *cm_node;
 	struct list_head teardown_list;
 	struct ib_qp_attr attr;
-	struct irdma_sc_vsi *vsi = &iwdev->vsi;
-	struct irdma_sc_qp *sc_qp;
-	struct irdma_qp *qp;
-	int i;
 
 	INIT_LIST_HEAD(&teardown_list);
 
@@ -4241,52 +4238,6 @@ void irdma_cm_teardown_connections(struct irdma_device *iwdev, u32 *ipaddr,
 			irdma_cm_disconn(cm_node->iwqp);
 		irdma_rem_ref_cm_node(cm_node);
 	}
-	if (!iwdev->roce_mode)
-		return;
-
-	INIT_LIST_HEAD(&teardown_list);
-	for (i = 0; i < IRDMA_MAX_USER_PRIORITY; i++) {
-		mutex_lock(&vsi->qos[i].qos_mutex);
-		list_for_each_safe (list_node, list_core_temp,
-				    &vsi->qos[i].qplist) {
-			u32 qp_ip[4];
-
-			sc_qp = container_of(list_node, struct irdma_sc_qp,
-					     list);
-			if (sc_qp->qp_uk.qp_type != IRDMA_QP_TYPE_ROCE_RC)
-				continue;
-
-			qp = sc_qp->qp_uk.back_qp;
-			if (!disconnect_all) {
-				if (nfo->ipv4)
-					qp_ip[0] = qp->udp_info.local_ipaddr[3];
-				else
-					memcpy(qp_ip,
-					       &qp->udp_info.local_ipaddr[0],
-					       sizeof(qp_ip));
-			}
-
-			if (disconnect_all ||
-			    (nfo->vlan_id == (qp->udp_info.vlan_tag & VLAN_VID_MASK) &&
-			     !memcmp(qp_ip, ipaddr, nfo->ipv4 ? 4 : 16))) {
-				spin_lock(&iwdev->rf->qptable_lock);
-				if (iwdev->rf->qp_table[sc_qp->qp_uk.qp_id]) {
-					irdma_qp_add_ref(&qp->ibqp);
-					list_add(&qp->teardown_entry,
-						 &teardown_list);
-				}
-				spin_unlock(&iwdev->rf->qptable_lock);
-			}
-		}
-		mutex_unlock(&vsi->qos[i].qos_mutex);
-	}
-
-	list_for_each_safe (list_node, list_core_temp, &teardown_list) {
-		qp = container_of(list_node, struct irdma_qp, teardown_entry);
-		attr.qp_state = IB_QPS_ERR;
-		irdma_modify_qp_roce(&qp->ibqp, &attr, IB_QP_STATE, NULL);
-		irdma_qp_rem_ref(&qp->ibqp);
-	}
 }
 
 /**
diff --git a/drivers/infiniband/hw/irdma/hw.c b/drivers/infiniband/hw/irdma/hw.c
index 4f763e552eae..3d5d3f8d5ded 100644
--- a/drivers/infiniband/hw/irdma/hw.c
+++ b/drivers/infiniband/hw/irdma/hw.c
@@ -257,10 +257,6 @@ static void irdma_process_aeq(struct irdma_pci_f *rf)
 				iwqp->last_aeq = info->ae_id;
 			spin_unlock_irqrestore(&iwqp->lock, flags);
 			ctx_info = &iwqp->ctx_info;
-			if (rdma_protocol_roce(&iwqp->iwdev->ibdev, 1))
-				ctx_info->roce_info->err_rq_idx_valid = true;
-			else
-				ctx_info->iwarp_info->err_rq_idx_valid = true;
 		} else {
 			if (info->ae_id != IRDMA_AE_CQ_OPERATION_ERROR)
 				continue;
@@ -370,16 +366,12 @@ static void irdma_process_aeq(struct irdma_pci_f *rf)
 		case IRDMA_AE_LCE_FUNCTION_CATASTROPHIC:
 		case IRDMA_AE_LCE_CQ_CATASTROPHIC:
 		case IRDMA_AE_UDA_XMIT_DGRAM_TOO_LONG:
-			if (rdma_protocol_roce(&iwdev->ibdev, 1))
-				ctx_info->roce_info->err_rq_idx_valid = false;
-			else
-				ctx_info->iwarp_info->err_rq_idx_valid = false;
-			fallthrough;
 		default:
 			ibdev_err(&iwdev->ibdev, "abnormal ae_id = 0x%x bool qp=%d qp_id = %d\n",
 				  info->ae_id, info->qp, info->qp_cq_id);
 			if (rdma_protocol_roce(&iwdev->ibdev, 1)) {
-				if (!info->sq && ctx_info->roce_info->err_rq_idx_valid) {
+				ctx_info->roce_info->err_rq_idx_valid = info->rq;
+				if (info->rq) {
 					ctx_info->roce_info->err_rq_idx = info->wqe_idx;
 					irdma_sc_qp_setctx_roce(&iwqp->sc_qp, iwqp->host_ctx.va,
 								ctx_info);
@@ -388,7 +380,8 @@ static void irdma_process_aeq(struct irdma_pci_f *rf)
 				irdma_cm_disconn(iwqp);
 				break;
 			}
-			if (!info->sq && ctx_info->iwarp_info->err_rq_idx_valid) {
+			ctx_info->iwarp_info->err_rq_idx_valid = info->rq;
+			if (info->rq) {
 				ctx_info->iwarp_info->err_rq_idx = info->wqe_idx;
 				ctx_info->tcp_info_valid = false;
 				ctx_info->iwarp_info_valid = true;
diff --git a/drivers/infiniband/hw/irdma/i40iw_hw.c b/drivers/infiniband/hw/irdma/i40iw_hw.c
index 64148ad8a604..040d4e2b9767 100644
--- a/drivers/infiniband/hw/irdma/i40iw_hw.c
+++ b/drivers/infiniband/hw/irdma/i40iw_hw.c
@@ -202,6 +202,7 @@ void i40iw_init_hw(struct irdma_sc_dev *dev)
 	dev->hw_attrs.uk_attrs.max_hw_read_sges = I40IW_MAX_SGE_RD;
 	dev->hw_attrs.max_hw_device_pages = I40IW_MAX_PUSH_PAGE_COUNT;
 	dev->hw_attrs.uk_attrs.max_hw_inline = I40IW_MAX_INLINE_DATA_SIZE;
+	dev->hw_attrs.page_size_cap = SZ_4K | SZ_2M;
 	dev->hw_attrs.max_hw_ird = I40IW_MAX_IRD_SIZE;
 	dev->hw_attrs.max_hw_ord = I40IW_MAX_ORD_SIZE;
 	dev->hw_attrs.max_hw_wqes = I40IW_MAX_WQ_ENTRIES;
diff --git a/drivers/infiniband/hw/irdma/icrdma_hw.c b/drivers/infiniband/hw/irdma/icrdma_hw.c
index cf53b17510cd..5986fd906308 100644
--- a/drivers/infiniband/hw/irdma/icrdma_hw.c
+++ b/drivers/infiniband/hw/irdma/icrdma_hw.c
@@ -139,6 +139,7 @@ void icrdma_init_hw(struct irdma_sc_dev *dev)
 	dev->cqp_db = dev->hw_regs[IRDMA_CQPDB];
 	dev->cq_ack_db = dev->hw_regs[IRDMA_CQACK];
 	dev->irq_ops = &icrdma_irq_ops;
+	dev->hw_attrs.page_size_cap = SZ_4K | SZ_2M | SZ_1G;
 	dev->hw_attrs.max_hw_ird = ICRDMA_MAX_IRD_SIZE;
 	dev->hw_attrs.max_hw_ord = ICRDMA_MAX_ORD_SIZE;
 	dev->hw_attrs.max_stat_inst = ICRDMA_MAX_STATS_COUNT;
diff --git a/drivers/infiniband/hw/irdma/irdma.h b/drivers/infiniband/hw/irdma/irdma.h
index 46c12334c735..4789e85d717b 100644
--- a/drivers/infiniband/hw/irdma/irdma.h
+++ b/drivers/infiniband/hw/irdma/irdma.h
@@ -127,6 +127,7 @@ struct irdma_hw_attrs {
 	u64 max_hw_outbound_msg_size;
 	u64 max_hw_inbound_msg_size;
 	u64 max_mr_size;
+	u64 page_size_cap;
 	u32 min_hw_qp_id;
 	u32 min_hw_aeq_size;
 	u32 max_hw_aeq_size;
diff --git a/drivers/infiniband/hw/irdma/uk.c b/drivers/infiniband/hw/irdma/uk.c
index 9b544a3b1288..aecd64a7dbba 100644
--- a/drivers/infiniband/hw/irdma/uk.c
+++ b/drivers/infiniband/hw/irdma/uk.c
@@ -501,7 +501,8 @@ enum irdma_status_code irdma_uk_send(struct irdma_qp_uk *qp,
 			      FIELD_PREP(IRDMAQPSQ_IMMDATA, info->imm_data));
 		i = 0;
 	} else {
-		qp->wqe_ops.iw_set_fragment(wqe, 0, op_info->sg_list,
+		qp->wqe_ops.iw_set_fragment(wqe, 0,
+					    frag_cnt ? op_info->sg_list : NULL,
 					    qp->swqe_polarity);
 		i = 1;
 	}
@@ -1068,6 +1069,7 @@ irdma_uk_cq_poll_cmpl(struct irdma_cq_uk *cq, struct irdma_cq_poll_info *info)
 	enum irdma_status_code ret_code;
 	bool move_cq_head = true;
 	u8 polarity;
+	u8 op_type;
 	bool ext_valid;
 	__le64 *ext_cqe;
 
@@ -1250,7 +1252,6 @@ irdma_uk_cq_poll_cmpl(struct irdma_cq_uk *cq, struct irdma_cq_poll_info *info)
 			do {
 				__le64 *sw_wqe;
 				u64 wqe_qword;
-				u8 op_type;
 				u32 tail;
 
 				tail = qp->sq_ring.tail;
@@ -1267,6 +1268,8 @@ irdma_uk_cq_poll_cmpl(struct irdma_cq_uk *cq, struct irdma_cq_poll_info *info)
 					break;
 				}
 			} while (1);
+			if (op_type == IRDMA_OP_TYPE_BIND_MW && info->minor_err == FLUSH_PROT_ERR)
+				info->minor_err = FLUSH_MW_BIND_ERR;
 			qp->sq_flush_seen = true;
 			if (!IRDMA_RING_MORE_WORK(qp->sq_ring))
 				qp->sq_flush_complete = true;
diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c
index 8a3ac4257e86..5275616398d8 100644
--- a/drivers/infiniband/hw/irdma/verbs.c
+++ b/drivers/infiniband/hw/irdma/verbs.c
@@ -29,22 +29,25 @@ static int irdma_query_device(struct ib_device *ibdev,
 	props->vendor_part_id = pcidev->device;
 
 	props->hw_ver = rf->pcidev->revision;
-	props->page_size_cap = SZ_4K | SZ_2M | SZ_1G;
+	props->page_size_cap = hw_attrs->page_size_cap;
 	props->max_mr_size = hw_attrs->max_mr_size;
 	props->max_qp = rf->max_qp - rf->used_qps;
 	props->max_qp_wr = hw_attrs->max_qp_wr;
 	props->max_send_sge = hw_attrs->uk_attrs.max_hw_wq_frags;
 	props->max_recv_sge = hw_attrs->uk_attrs.max_hw_wq_frags;
 	props->max_cq = rf->max_cq - rf->used_cqs;
-	props->max_cqe = rf->max_cqe;
+	props->max_cqe = rf->max_cqe - 1;
 	props->max_mr = rf->max_mr - rf->used_mrs;
 	props->max_mw = props->max_mr;
 	props->max_pd = rf->max_pd - rf->used_pds;
 	props->max_sge_rd = hw_attrs->uk_attrs.max_hw_read_sges;
 	props->max_qp_rd_atom = hw_attrs->max_hw_ird;
 	props->max_qp_init_rd_atom = hw_attrs->max_hw_ord;
-	if (rdma_protocol_roce(ibdev, 1))
+	if (rdma_protocol_roce(ibdev, 1)) {
+		props->device_cap_flags |= IB_DEVICE_RC_RNR_NAK_GEN;
 		props->max_pkeys = IRDMA_PKEY_TBL_SZ;
+	}
+
 	props->max_ah = rf->max_ah;
 	props->max_mcast_grp = rf->max_mcg;
 	props->max_mcast_qp_attach = IRDMA_MAX_MGS_PER_CTX;
@@ -1759,11 +1762,11 @@ static int irdma_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
 	spin_unlock_irqrestore(&iwcq->lock, flags);
 
 	irdma_cq_wq_destroy(iwdev->rf, cq);
-	irdma_cq_free_rsrc(iwdev->rf, iwcq);
 
 	spin_lock_irqsave(&iwceq->ce_lock, flags);
 	irdma_sc_cleanup_ceqes(cq, ceq);
 	spin_unlock_irqrestore(&iwceq->ce_lock, flags);
+	irdma_cq_free_rsrc(iwdev->rf, iwcq);
 
 	return 0;
 }
@@ -2776,7 +2779,7 @@ static struct ib_mr *irdma_reg_user_mr(struct ib_pd *pd, u64 start, u64 len,
 
 	if (req.reg_type == IRDMA_MEMREG_TYPE_MEM) {
 		iwmr->page_size = ib_umem_find_best_pgsz(region,
-							 SZ_4K | SZ_2M | SZ_1G,
+							 iwdev->rf->sc_dev.hw_attrs.page_size_cap,
 							 virt);
 		if (unlikely(!iwmr->page_size)) {
 			kfree(iwmr);
diff --git a/drivers/infiniband/hw/mlx5/fs.c b/drivers/infiniband/hw/mlx5/fs.c
index 5fbc0a8454b9..8a7e182af530 100644
--- a/drivers/infiniband/hw/mlx5/fs.c
+++ b/drivers/infiniband/hw/mlx5/fs.c
@@ -2078,12 +2078,10 @@ static int mlx5_ib_matcher_ns(struct uverbs_attr_bundle *attrs,
 		if (err)
 			return err;
 
-		if (flags) {
-			mlx5_ib_ft_type_to_namespace(
+		if (flags)
+			return mlx5_ib_ft_type_to_namespace(
 				MLX5_IB_UAPI_FLOW_TABLE_TYPE_NIC_TX,
 				&obj->ns_type);
-			return 0;
-		}
 	}
 
 	obj->ns_type = MLX5_FLOW_NAMESPACE_BYPASS;
diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c
index ec242a5a17a3..f6f2df855c2e 100644
--- a/drivers/infiniband/hw/mlx5/mad.c
+++ b/drivers/infiniband/hw/mlx5/mad.c
@@ -166,6 +166,12 @@ static int process_pma_cmd(struct mlx5_ib_dev *dev, u32 port_num,
 		mdev = dev->mdev;
 		mdev_port_num = 1;
 	}
+	if (MLX5_CAP_GEN(dev->mdev, num_ports) == 1) {
+		/* set local port to one for Function-Per-Port HCA. */
+		mdev = dev->mdev;
+		mdev_port_num = 1;
+	}
+
 	/* Declaring support of extended counters */
 	if (in_mad->mad_hdr.attr_id == IB_PMA_CLASS_PORT_INFO) {
 		struct ib_class_port_info cpi = {};
diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h
index 8def88cfa300..db9ef3e1eb97 100644
--- a/drivers/infiniband/hw/qedr/qedr.h
+++ b/drivers/infiniband/hw/qedr/qedr.h
@@ -418,6 +418,7 @@ struct qedr_qp {
 	u32 sq_psn;
 	u32 qkey;
 	u32 dest_qp_num;
+	u8 timeout;
 
 	/* Relevant to qps created from kernel space only (ULPs) */
 	u8 prev_wqe_size;
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index f652d083ff20..bb0c2b93a34d 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -2622,6 +2622,8 @@ int qedr_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 					1 << max_t(int, attr->timeout - 8, 0);
 		else
 			qp_params.ack_timeout = 0;
+
+		qp->timeout = attr->timeout;
 	}
 
 	if (attr_mask & IB_QP_RETRY_CNT) {
@@ -2781,7 +2783,7 @@ int qedr_query_qp(struct ib_qp *ibqp,
 	rdma_ah_set_dgid_raw(&qp_attr->ah_attr, &params.dgid.bytes[0]);
 	rdma_ah_set_port_num(&qp_attr->ah_attr, 1);
 	rdma_ah_set_sl(&qp_attr->ah_attr, 0);
-	qp_attr->timeout = params.timeout;
+	qp_attr->timeout = qp->timeout;
 	qp_attr->rnr_retry = params.rnr_retry;
 	qp_attr->retry_cnt = params.retry_cnt;
 	qp_attr->min_rnr_timer = params.min_rnr_nak_timer;
@@ -3091,7 +3093,7 @@ static struct qedr_mr *__qedr_alloc_mr(struct ib_pd *ibpd,
 		else
 			DP_ERR(dev, "roce alloc tid returned error %d\n", rc);
 
-		goto err0;
+		goto err1;
 	}
 
 	/* Index only, 18 bit long, lkey = itid << 8 | key */
@@ -3115,7 +3117,7 @@ static struct qedr_mr *__qedr_alloc_mr(struct ib_pd *ibpd,
 	rc = dev->ops->rdma_register_tid(dev->rdma_ctx, &mr->hw_mr);
 	if (rc) {
 		DP_ERR(dev, "roce register tid returned an error %d\n", rc);
-		goto err1;
+		goto err2;
 	}
 
 	mr->ibmr.lkey = mr->hw_mr.itid << 8 | mr->hw_mr.key;
@@ -3124,8 +3126,10 @@ static struct qedr_mr *__qedr_alloc_mr(struct ib_pd *ibpd,
 	DP_DEBUG(dev, QEDR_MSG_MR, "alloc frmr: %x\n", mr->ibmr.lkey);
 	return mr;
 
-err1:
+err2:
 	dev->ops->rdma_free_tid(dev->rdma_ctx, mr->hw_mr.itid);
+err1:
+	qedr_free_pbl(dev, &mr->info.pbl_info, mr->info.pbl_table);
 err0:
 	kfree(mr);
 	return ERR_PTR(rc);
diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c
index d2d802c776fd..48a3864ada29 100644
--- a/drivers/infiniband/sw/rxe/rxe_comp.c
+++ b/drivers/infiniband/sw/rxe/rxe_comp.c
@@ -142,10 +142,7 @@ static inline enum comp_state get_wqe(struct rxe_qp *qp,
 	/* we come here whether or not we found a response packet to see if
 	 * there are any posted WQEs
 	 */
-	if (qp->is_user)
-		wqe = queue_head(qp->sq.queue, QUEUE_TYPE_FROM_USER);
-	else
-		wqe = queue_head(qp->sq.queue, QUEUE_TYPE_KERNEL);
+	wqe = queue_head(qp->sq.queue, QUEUE_TYPE_FROM_CLIENT);
 	*wqe_p = wqe;
 
 	/* no WQE or requester has not started it yet */
@@ -432,10 +429,7 @@ static void do_complete(struct rxe_qp *qp, struct rxe_send_wqe *wqe)
 	if (post)
 		make_send_cqe(qp, wqe, &cqe);
 
-	if (qp->is_user)
-		advance_consumer(qp->sq.queue, QUEUE_TYPE_FROM_USER);
-	else
-		advance_consumer(qp->sq.queue, QUEUE_TYPE_KERNEL);
+	queue_advance_consumer(qp->sq.queue, QUEUE_TYPE_FROM_CLIENT);
 
 	if (post)
 		rxe_cq_post(qp->scq, &cqe, 0);
@@ -539,7 +533,7 @@ static void rxe_drain_resp_pkts(struct rxe_qp *qp, bool notify)
 			wqe->status = IB_WC_WR_FLUSH_ERR;
 			do_complete(qp, wqe);
 		} else {
-			advance_consumer(q, q->type);
+			queue_advance_consumer(q, q->type);
 		}
 	}
 }
diff --git a/drivers/infiniband/sw/rxe/rxe_cq.c b/drivers/infiniband/sw/rxe/rxe_cq.c
index aef288f164fd..4eedaa0244b3 100644
--- a/drivers/infiniband/sw/rxe/rxe_cq.c
+++ b/drivers/infiniband/sw/rxe/rxe_cq.c
@@ -25,11 +25,7 @@ int rxe_cq_chk_attr(struct rxe_dev *rxe, struct rxe_cq *cq,
 	}
 
 	if (cq) {
-		if (cq->is_user)
-			count = queue_count(cq->queue, QUEUE_TYPE_TO_USER);
-		else
-			count = queue_count(cq->queue, QUEUE_TYPE_KERNEL);
-
+		count = queue_count(cq->queue, QUEUE_TYPE_TO_CLIENT);
 		if (cqe < count) {
 			pr_warn("cqe(%d) < current # elements in queue (%d)",
 				cqe, count);
@@ -65,7 +61,7 @@ int rxe_cq_from_init(struct rxe_dev *rxe, struct rxe_cq *cq, int cqe,
 	int err;
 	enum queue_type type;
 
-	type = uresp ? QUEUE_TYPE_TO_USER : QUEUE_TYPE_KERNEL;
+	type = QUEUE_TYPE_TO_CLIENT;
 	cq->queue = rxe_queue_init(rxe, &cqe,
 			sizeof(struct rxe_cqe), type);
 	if (!cq->queue) {
@@ -117,11 +113,7 @@ int rxe_cq_post(struct rxe_cq *cq, struct rxe_cqe *cqe, int solicited)
 
 	spin_lock_irqsave(&cq->cq_lock, flags);
 
-	if (cq->is_user)
-		full = queue_full(cq->queue, QUEUE_TYPE_TO_USER);
-	else
-		full = queue_full(cq->queue, QUEUE_TYPE_KERNEL);
-
+	full = queue_full(cq->queue, QUEUE_TYPE_TO_CLIENT);
 	if (unlikely(full)) {
 		spin_unlock_irqrestore(&cq->cq_lock, flags);
 		if (cq->ibcq.event_handler) {
@@ -134,17 +126,10 @@ int rxe_cq_post(struct rxe_cq *cq, struct rxe_cqe *cqe, int solicited)
 		return -EBUSY;
 	}
 
-	if (cq->is_user)
-		addr = producer_addr(cq->queue, QUEUE_TYPE_TO_USER);
-	else
-		addr = producer_addr(cq->queue, QUEUE_TYPE_KERNEL);
-
+	addr = queue_producer_addr(cq->queue, QUEUE_TYPE_TO_CLIENT);
 	memcpy(addr, cqe, sizeof(*cqe));
 
-	if (cq->is_user)
-		advance_producer(cq->queue, QUEUE_TYPE_TO_USER);
-	else
-		advance_producer(cq->queue, QUEUE_TYPE_KERNEL);
+	queue_advance_producer(cq->queue, QUEUE_TYPE_TO_CLIENT);
 
 	spin_unlock_irqrestore(&cq->cq_lock, flags);
 
diff --git a/drivers/infiniband/sw/rxe/rxe_loc.h b/drivers/infiniband/sw/rxe/rxe_loc.h
index 4fd73b51fabf..21bd969718bd 100644
--- a/drivers/infiniband/sw/rxe/rxe_loc.h
+++ b/drivers/infiniband/sw/rxe/rxe_loc.h
@@ -85,7 +85,7 @@ struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 key,
 			 enum rxe_mr_lookup_type type);
 int mr_check_range(struct rxe_mr *mr, u64 iova, size_t length);
 int advance_dma_data(struct rxe_dma_info *dma, unsigned int length);
-int rxe_invalidate_mr(struct rxe_qp *qp, u32 rkey);
+int rxe_invalidate_mr(struct rxe_qp *qp, u32 key);
 int rxe_reg_fast_mr(struct rxe_qp *qp, struct rxe_send_wqe *wqe);
 int rxe_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata);
 void rxe_mr_cleanup(struct rxe_pool_entry *arg);
diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c
index bedcf15aaea7..7c2e7b291b65 100644
--- a/drivers/infiniband/sw/rxe/rxe_mr.c
+++ b/drivers/infiniband/sw/rxe/rxe_mr.c
@@ -522,22 +522,22 @@ struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 key,
 	return mr;
 }
 
-int rxe_invalidate_mr(struct rxe_qp *qp, u32 rkey)
+int rxe_invalidate_mr(struct rxe_qp *qp, u32 key)
 {
 	struct rxe_dev *rxe = to_rdev(qp->ibqp.device);
 	struct rxe_mr *mr;
 	int ret;
 
-	mr = rxe_pool_get_index(&rxe->mr_pool, rkey >> 8);
+	mr = rxe_pool_get_index(&rxe->mr_pool, key >> 8);
 	if (!mr) {
-		pr_err("%s: No MR for rkey %#x\n", __func__, rkey);
+		pr_err("%s: No MR for key %#x\n", __func__, key);
 		ret = -EINVAL;
 		goto err;
 	}
 
-	if (rkey != mr->rkey) {
-		pr_err("%s: rkey (%#x) doesn't match mr->rkey (%#x)\n",
-			__func__, rkey, mr->rkey);
+	if (mr->rkey ? (key != mr->rkey) : (key != mr->lkey)) {
+		pr_err("%s: wr key (%#x) doesn't match mr key (%#x)\n",
+			__func__, key, (mr->rkey ? mr->rkey : mr->lkey));
 		ret = -EINVAL;
 		goto err_drop_ref;
 	}
diff --git a/drivers/infiniband/sw/rxe/rxe_mw.c b/drivers/infiniband/sw/rxe/rxe_mw.c
index a5e2ea7d80f0..933a0b29275b 100644
--- a/drivers/infiniband/sw/rxe/rxe_mw.c
+++ b/drivers/infiniband/sw/rxe/rxe_mw.c
@@ -71,8 +71,6 @@ int rxe_dealloc_mw(struct ib_mw *ibmw)
 static int rxe_check_bind_mw(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
 			 struct rxe_mw *mw, struct rxe_mr *mr)
 {
-	u32 key = wqe->wr.wr.mw.rkey & 0xff;
-
 	if (mw->ibmw.type == IB_MW_TYPE_1) {
 		if (unlikely(mw->state != RXE_MW_STATE_VALID)) {
 			pr_err_once(
@@ -110,11 +108,6 @@ static int rxe_check_bind_mw(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
 		}
 	}
 
-	if (unlikely(key == (mw->rkey & 0xff))) {
-		pr_err_once("attempt to bind MW with same key\n");
-		return -EINVAL;
-	}
-
 	/* remaining checks only apply to a nonzero MR */
 	if (!mr)
 		return 0;
diff --git a/drivers/infiniband/sw/rxe/rxe_param.h b/drivers/infiniband/sw/rxe/rxe_param.h
index b5a70cbe94aa..872389870106 100644
--- a/drivers/infiniband/sw/rxe/rxe_param.h
+++ b/drivers/infiniband/sw/rxe/rxe_param.h
@@ -103,6 +103,12 @@ enum rxe_device_param {
 	RXE_INFLIGHT_SKBS_PER_QP_HIGH	= 64,
 	RXE_INFLIGHT_SKBS_PER_QP_LOW	= 16,
 
+	/* Max number of interations of each tasklet
+	 * before yielding the cpu to let other
+	 * work make progress
+	 */
+	RXE_MAX_ITERATIONS		= 1024,
+
 	/* Delay before calling arbiter timer */
 	RXE_NSEC_ARB_TIMER_DELAY	= 200,
 
diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c
index ed326d82725c..661b83d65af3 100644
--- a/drivers/infiniband/sw/rxe/rxe_qp.c
+++ b/drivers/infiniband/sw/rxe/rxe_qp.c
@@ -195,6 +195,14 @@ static void rxe_qp_init_misc(struct rxe_dev *rxe, struct rxe_qp *qp,
 	spin_lock_init(&qp->grp_lock);
 	spin_lock_init(&qp->state_lock);
 
+	spin_lock_init(&qp->req.task.state_lock);
+	spin_lock_init(&qp->resp.task.state_lock);
+	spin_lock_init(&qp->comp.task.state_lock);
+
+	spin_lock_init(&qp->sq.sq_lock);
+	spin_lock_init(&qp->rq.producer_lock);
+	spin_lock_init(&qp->rq.consumer_lock);
+
 	atomic_set(&qp->ssn, 0);
 	atomic_set(&qp->skb_out, 0);
 }
@@ -231,7 +239,7 @@ static int rxe_qp_init_req(struct rxe_dev *rxe, struct rxe_qp *qp,
 	qp->sq.max_inline = init->cap.max_inline_data = wqe_size;
 	wqe_size += sizeof(struct rxe_send_wqe);
 
-	type = uresp ? QUEUE_TYPE_FROM_USER : QUEUE_TYPE_KERNEL;
+	type = QUEUE_TYPE_FROM_CLIENT;
 	qp->sq.queue = rxe_queue_init(rxe, &qp->sq.max_wr,
 				wqe_size, type);
 	if (!qp->sq.queue)
@@ -248,18 +256,13 @@ static int rxe_qp_init_req(struct rxe_dev *rxe, struct rxe_qp *qp,
 		return err;
 	}
 
-	if (qp->is_user)
-		qp->req.wqe_index = producer_index(qp->sq.queue,
-						QUEUE_TYPE_FROM_USER);
-	else
-		qp->req.wqe_index = producer_index(qp->sq.queue,
-						QUEUE_TYPE_KERNEL);
+	qp->req.wqe_index = queue_get_producer(qp->sq.queue,
+					       QUEUE_TYPE_FROM_CLIENT);
 
 	qp->req.state		= QP_STATE_RESET;
 	qp->req.opcode		= -1;
 	qp->comp.opcode		= -1;
 
-	spin_lock_init(&qp->sq.sq_lock);
 	skb_queue_head_init(&qp->req_pkts);
 
 	rxe_init_task(rxe, &qp->req.task, qp,
@@ -293,7 +296,7 @@ static int rxe_qp_init_resp(struct rxe_dev *rxe, struct rxe_qp *qp,
 		pr_debug("qp#%d max_wr = %d, max_sge = %d, wqe_size = %d\n",
 			 qp_num(qp), qp->rq.max_wr, qp->rq.max_sge, wqe_size);
 
-		type = uresp ? QUEUE_TYPE_FROM_USER : QUEUE_TYPE_KERNEL;
+		type = QUEUE_TYPE_FROM_CLIENT;
 		qp->rq.queue = rxe_queue_init(rxe, &qp->rq.max_wr,
 					wqe_size, type);
 		if (!qp->rq.queue)
@@ -310,11 +313,6 @@ static int rxe_qp_init_resp(struct rxe_dev *rxe, struct rxe_qp *qp,
 		}
 	}
 
-	spin_lock_init(&qp->rq.producer_lock);
-	spin_lock_init(&qp->rq.consumer_lock);
-
-	qp->rq.is_user = qp->is_user;
-
 	skb_queue_head_init(&qp->resp_pkts);
 
 	rxe_init_task(rxe, &qp->resp.task, qp,
diff --git a/drivers/infiniband/sw/rxe/rxe_queue.c b/drivers/infiniband/sw/rxe/rxe_queue.c
index 72d95398e604..6e6e023c1b45 100644
--- a/drivers/infiniband/sw/rxe/rxe_queue.c
+++ b/drivers/infiniband/sw/rxe/rxe_queue.c
@@ -111,17 +111,33 @@ err1:
 static int resize_finish(struct rxe_queue *q, struct rxe_queue *new_q,
 			 unsigned int num_elem)
 {
-	if (!queue_empty(q, q->type) && (num_elem < queue_count(q, q->type)))
+	enum queue_type type = q->type;
+	u32 prod;
+	u32 cons;
+
+	if (!queue_empty(q, q->type) && (num_elem < queue_count(q, type)))
 		return -EINVAL;
 
-	while (!queue_empty(q, q->type)) {
-		memcpy(producer_addr(new_q, new_q->type),
-					consumer_addr(q, q->type),
-					new_q->elem_size);
-		advance_producer(new_q, new_q->type);
-		advance_consumer(q, q->type);
+	prod = queue_get_producer(new_q, type);
+	cons = queue_get_consumer(q, type);
+
+	while (!queue_empty(q, type)) {
+		memcpy(queue_addr_from_index(new_q, prod),
+		       queue_addr_from_index(q, cons), new_q->elem_size);
+		prod = queue_next_index(new_q, prod);
+		cons = queue_next_index(q, cons);
 	}
 
+	new_q->buf->producer_index = prod;
+	q->buf->consumer_index = cons;
+
+	/* update private index copies */
+	if (type == QUEUE_TYPE_TO_CLIENT)
+		new_q->index = new_q->buf->producer_index;
+	else
+		q->index = q->buf->consumer_index;
+
+	/* exchange rxe_queue headers */
 	swap(*q, *new_q);
 
 	return 0;
diff --git a/drivers/infiniband/sw/rxe/rxe_queue.h b/drivers/infiniband/sw/rxe/rxe_queue.h
index 2702b0e55fc3..6227112ef7a2 100644
--- a/drivers/infiniband/sw/rxe/rxe_queue.h
+++ b/drivers/infiniband/sw/rxe/rxe_queue.h
@@ -10,34 +10,47 @@
 /* for definition of shared struct rxe_queue_buf */
 #include <uapi/rdma/rdma_user_rxe.h>
 
-/* implements a simple circular buffer that can optionally be
- * shared between user space and the kernel and can be resized
- * the requested element size is rounded up to a power of 2
- * and the number of elements in the buffer is also rounded
- * up to a power of 2. Since the queue is empty when the
- * producer and consumer indices match the maximum capacity
- * of the queue is one less than the number of element slots
+/* Implements a simple circular buffer that is shared between user
+ * and the driver and can be resized. The requested element size is
+ * rounded up to a power of 2 and the number of elements in the buffer
+ * is also rounded up to a power of 2. Since the queue is empty when
+ * the producer and consumer indices match the maximum capacity of the
+ * queue is one less than the number of element slots.
  *
  * Notes:
- *   - Kernel space indices are always masked off to q->index_mask
- *   before storing so do not need to be checked on reads.
- *   - User space indices may be out of range and must be
- *   masked before use when read.
- *   - The kernel indices for shared queues must not be written
- *   by user space so a local copy is used and a shared copy is
- *   stored when the local copy changes.
+ *   - The driver indices are always masked off to q->index_mask
+ *     before storing so do not need to be checked on reads.
+ *   - The user whether user space or kernel is generally
+ *     not trusted so its parameters are masked to make sure
+ *     they do not access the queue out of bounds on reads.
+ *   - The driver indices for queues must not be written
+ *     by user so a local copy is used and a shared copy is
+ *     stored when the local copy is changed.
  *   - By passing the type in the parameter list separate from q
- *   the compiler can eliminate the switch statement when the
- *   actual queue type is known when the function is called.
- *   In the performance path this is done. In less critical
- *   paths just q->type is passed.
+ *     the compiler can eliminate the switch statement when the
+ *     actual queue type is known when the function is called at
+ *     compile time.
+ *   - These queues are lock free. The user and driver must protect
+ *     changes to their end of the queues with locks if more than one
+ *     CPU can be accessing it at the same time.
  */
 
-/* type of queue */
+/**
+ * enum queue_type - type of queue
+ * @QUEUE_TYPE_TO_CLIENT:	Queue is written by rxe driver and
+ *				read by client. Used by rxe driver only.
+ * @QUEUE_TYPE_FROM_CLIENT:	Queue is written by client and
+ *				read by rxe driver. Used by rxe driver only.
+ * @QUEUE_TYPE_TO_DRIVER:	Queue is written by client and
+ *				read by rxe driver. Used by kernel client only.
+ * @QUEUE_TYPE_FROM_DRIVER:	Queue is written by rxe driver and
+ *				read by client. Used by kernel client only.
+ */
 enum queue_type {
-	QUEUE_TYPE_KERNEL,
-	QUEUE_TYPE_TO_USER,
-	QUEUE_TYPE_FROM_USER,
+	QUEUE_TYPE_TO_CLIENT,
+	QUEUE_TYPE_FROM_CLIENT,
+	QUEUE_TYPE_TO_DRIVER,
+	QUEUE_TYPE_FROM_DRIVER,
 };
 
 struct rxe_queue {
@@ -69,238 +82,171 @@ struct rxe_queue *rxe_queue_init(struct rxe_dev *rxe, int *num_elem,
 int rxe_queue_resize(struct rxe_queue *q, unsigned int *num_elem_p,
 		     unsigned int elem_size, struct ib_udata *udata,
 		     struct mminfo __user *outbuf,
-		     /* Protect producers while resizing queue */
-		     spinlock_t *producer_lock,
-		     /* Protect consumers while resizing queue */
-		     spinlock_t *consumer_lock);
+		     spinlock_t *producer_lock, spinlock_t *consumer_lock);
 
 void rxe_queue_cleanup(struct rxe_queue *queue);
 
-static inline int next_index(struct rxe_queue *q, int index)
+static inline u32 queue_next_index(struct rxe_queue *q, int index)
 {
-	return (index + 1) & q->buf->index_mask;
+	return (index + 1) & q->index_mask;
 }
 
-static inline int queue_empty(struct rxe_queue *q, enum queue_type type)
+static inline u32 queue_get_producer(const struct rxe_queue *q,
+				     enum queue_type type)
 {
 	u32 prod;
-	u32 cons;
 
 	switch (type) {
-	case QUEUE_TYPE_FROM_USER:
-		/* protect user space index */
+	case QUEUE_TYPE_FROM_CLIENT:
+		/* protect user index */
 		prod = smp_load_acquire(&q->buf->producer_index);
-		cons = q->index;
 		break;
-	case QUEUE_TYPE_TO_USER:
+	case QUEUE_TYPE_TO_CLIENT:
 		prod = q->index;
-		/* protect user space index */
-		cons = smp_load_acquire(&q->buf->consumer_index);
 		break;
-	case QUEUE_TYPE_KERNEL:
+	case QUEUE_TYPE_FROM_DRIVER:
+		/* protect driver index */
+		prod = smp_load_acquire(&q->buf->producer_index);
+		break;
+	case QUEUE_TYPE_TO_DRIVER:
 		prod = q->buf->producer_index;
-		cons = q->buf->consumer_index;
 		break;
 	}
 
-	return ((prod - cons) & q->index_mask) == 0;
+	return prod;
 }
 
-static inline int queue_full(struct rxe_queue *q, enum queue_type type)
+static inline u32 queue_get_consumer(const struct rxe_queue *q,
+				     enum queue_type type)
 {
-	u32 prod;
 	u32 cons;
 
 	switch (type) {
-	case QUEUE_TYPE_FROM_USER:
-		/* protect user space index */
-		prod = smp_load_acquire(&q->buf->producer_index);
+	case QUEUE_TYPE_FROM_CLIENT:
 		cons = q->index;
 		break;
-	case QUEUE_TYPE_TO_USER:
-		prod = q->index;
-		/* protect user space index */
+	case QUEUE_TYPE_TO_CLIENT:
+		/* protect user index */
 		cons = smp_load_acquire(&q->buf->consumer_index);
 		break;
-	case QUEUE_TYPE_KERNEL:
-		prod = q->buf->producer_index;
+	case QUEUE_TYPE_FROM_DRIVER:
 		cons = q->buf->consumer_index;
 		break;
+	case QUEUE_TYPE_TO_DRIVER:
+		/* protect driver index */
+		cons = smp_load_acquire(&q->buf->consumer_index);
+		break;
 	}
 
-	return ((prod + 1 - cons) & q->index_mask) == 0;
+	return cons;
 }
 
-static inline unsigned int queue_count(const struct rxe_queue *q,
-					enum queue_type type)
+static inline int queue_empty(struct rxe_queue *q, enum queue_type type)
 {
-	u32 prod;
-	u32 cons;
-
-	switch (type) {
-	case QUEUE_TYPE_FROM_USER:
-		/* protect user space index */
-		prod = smp_load_acquire(&q->buf->producer_index);
-		cons = q->index;
-		break;
-	case QUEUE_TYPE_TO_USER:
-		prod = q->index;
-		/* protect user space index */
-		cons = smp_load_acquire(&q->buf->consumer_index);
-		break;
-	case QUEUE_TYPE_KERNEL:
-		prod = q->buf->producer_index;
-		cons = q->buf->consumer_index;
-		break;
-	}
+	u32 prod = queue_get_producer(q, type);
+	u32 cons = queue_get_consumer(q, type);
 
-	return (prod - cons) & q->index_mask;
+	return ((prod - cons) & q->index_mask) == 0;
 }
 
-static inline void advance_producer(struct rxe_queue *q, enum queue_type type)
+static inline int queue_full(struct rxe_queue *q, enum queue_type type)
 {
-	u32 prod;
+	u32 prod = queue_get_producer(q, type);
+	u32 cons = queue_get_consumer(q, type);
 
-	switch (type) {
-	case QUEUE_TYPE_FROM_USER:
-		pr_warn_once("Normally kernel should not write user space index\n");
-		/* protect user space index */
-		prod = smp_load_acquire(&q->buf->producer_index);
-		prod = (prod + 1) & q->index_mask;
-		/* same */
-		smp_store_release(&q->buf->producer_index, prod);
-		break;
-	case QUEUE_TYPE_TO_USER:
-		prod = q->index;
-		q->index = (prod + 1) & q->index_mask;
-		q->buf->producer_index = q->index;
-		break;
-	case QUEUE_TYPE_KERNEL:
-		prod = q->buf->producer_index;
-		q->buf->producer_index = (prod + 1) & q->index_mask;
-		break;
-	}
+	return ((prod + 1 - cons) & q->index_mask) == 0;
 }
 
-static inline void advance_consumer(struct rxe_queue *q, enum queue_type type)
+static inline u32 queue_count(const struct rxe_queue *q,
+					enum queue_type type)
 {
-	u32 cons;
+	u32 prod = queue_get_producer(q, type);
+	u32 cons = queue_get_consumer(q, type);
 
-	switch (type) {
-	case QUEUE_TYPE_FROM_USER:
-		cons = q->index;
-		q->index = (cons + 1) & q->index_mask;
-		q->buf->consumer_index = q->index;
-		break;
-	case QUEUE_TYPE_TO_USER:
-		pr_warn_once("Normally kernel should not write user space index\n");
-		/* protect user space index */
-		cons = smp_load_acquire(&q->buf->consumer_index);
-		cons = (cons + 1) & q->index_mask;
-		/* same */
-		smp_store_release(&q->buf->consumer_index, cons);
-		break;
-	case QUEUE_TYPE_KERNEL:
-		cons = q->buf->consumer_index;
-		q->buf->consumer_index = (cons + 1) & q->index_mask;
-		break;
-	}
+	return (prod - cons) & q->index_mask;
 }
 
-static inline void *producer_addr(struct rxe_queue *q, enum queue_type type)
+static inline void queue_advance_producer(struct rxe_queue *q,
+					  enum queue_type type)
 {
 	u32 prod;
 
 	switch (type) {
-	case QUEUE_TYPE_FROM_USER:
-		/* protect user space index */
-		prod = smp_load_acquire(&q->buf->producer_index);
-		prod &= q->index_mask;
+	case QUEUE_TYPE_FROM_CLIENT:
+		pr_warn("%s: attempt to advance client index\n",
+			__func__);
 		break;
-	case QUEUE_TYPE_TO_USER:
+	case QUEUE_TYPE_TO_CLIENT:
 		prod = q->index;
+		prod = (prod + 1) & q->index_mask;
+		q->index = prod;
+		/* protect user index */
+		smp_store_release(&q->buf->producer_index, prod);
+		break;
+	case QUEUE_TYPE_FROM_DRIVER:
+		pr_warn("%s: attempt to advance driver index\n",
+			__func__);
 		break;
-	case QUEUE_TYPE_KERNEL:
+	case QUEUE_TYPE_TO_DRIVER:
 		prod = q->buf->producer_index;
+		prod = (prod + 1) & q->index_mask;
+		q->buf->producer_index = prod;
 		break;
 	}
-
-	return q->buf->data + (prod << q->log2_elem_size);
 }
 
-static inline void *consumer_addr(struct rxe_queue *q, enum queue_type type)
+static inline void queue_advance_consumer(struct rxe_queue *q,
+					  enum queue_type type)
 {
 	u32 cons;
 
 	switch (type) {
-	case QUEUE_TYPE_FROM_USER:
+	case QUEUE_TYPE_FROM_CLIENT:
 		cons = q->index;
+		cons = (cons + 1) & q->index_mask;
+		q->index = cons;
+		/* protect user index */
+		smp_store_release(&q->buf->consumer_index, cons);
 		break;
-	case QUEUE_TYPE_TO_USER:
-		/* protect user space index */
-		cons = smp_load_acquire(&q->buf->consumer_index);
-		cons &= q->index_mask;
+	case QUEUE_TYPE_TO_CLIENT:
+		pr_warn("%s: attempt to advance client index\n",
+			__func__);
 		break;
-	case QUEUE_TYPE_KERNEL:
+	case QUEUE_TYPE_FROM_DRIVER:
 		cons = q->buf->consumer_index;
+		cons = (cons + 1) & q->index_mask;
+		q->buf->consumer_index = cons;
+		break;
+	case QUEUE_TYPE_TO_DRIVER:
+		pr_warn("%s: attempt to advance driver index\n",
+			__func__);
 		break;
 	}
-
-	return q->buf->data + (cons << q->log2_elem_size);
 }
 
-static inline unsigned int producer_index(struct rxe_queue *q,
-						enum queue_type type)
+static inline void *queue_producer_addr(struct rxe_queue *q,
+					enum queue_type type)
 {
-	u32 prod;
+	u32 prod = queue_get_producer(q, type);
 
-	switch (type) {
-	case QUEUE_TYPE_FROM_USER:
-		/* protect user space index */
-		prod = smp_load_acquire(&q->buf->producer_index);
-		prod &= q->index_mask;
-		break;
-	case QUEUE_TYPE_TO_USER:
-		prod = q->index;
-		break;
-	case QUEUE_TYPE_KERNEL:
-		prod = q->buf->producer_index;
-		break;
-	}
-
-	return prod;
+	return q->buf->data + (prod << q->log2_elem_size);
 }
 
-static inline unsigned int consumer_index(struct rxe_queue *q,
-						enum queue_type type)
+static inline void *queue_consumer_addr(struct rxe_queue *q,
+					enum queue_type type)
 {
-	u32 cons;
-
-	switch (type) {
-	case QUEUE_TYPE_FROM_USER:
-		cons = q->index;
-		break;
-	case QUEUE_TYPE_TO_USER:
-		/* protect user space index */
-		cons = smp_load_acquire(&q->buf->consumer_index);
-		cons &= q->index_mask;
-		break;
-	case QUEUE_TYPE_KERNEL:
-		cons = q->buf->consumer_index;
-		break;
-	}
+	u32 cons = queue_get_consumer(q, type);
 
-	return cons;
+	return q->buf->data + (cons << q->log2_elem_size);
 }
 
-static inline void *addr_from_index(struct rxe_queue *q,
-				unsigned int index)
+static inline void *queue_addr_from_index(struct rxe_queue *q, u32 index)
 {
 	return q->buf->data + ((index & q->index_mask)
-				<< q->buf->log2_elem_size);
+				<< q->log2_elem_size);
 }
 
-static inline unsigned int index_from_addr(const struct rxe_queue *q,
+static inline u32 queue_index_from_addr(const struct rxe_queue *q,
 				const void *addr)
 {
 	return (((u8 *)addr - q->buf->data) >> q->log2_elem_size)
@@ -309,7 +255,7 @@ static inline unsigned int index_from_addr(const struct rxe_queue *q,
 
 static inline void *queue_head(struct rxe_queue *q, enum queue_type type)
 {
-	return queue_empty(q, type) ? NULL : consumer_addr(q, type);
+	return queue_empty(q, type) ? NULL : queue_consumer_addr(q, type);
 }
 
 #endif /* RXE_QUEUE_H */
diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c
index 7812e3d6a6c2..8c0e7ecd4141 100644
--- a/drivers/infiniband/sw/rxe/rxe_req.c
+++ b/drivers/infiniband/sw/rxe/rxe_req.c
@@ -49,21 +49,16 @@ static void req_retry(struct rxe_qp *qp)
 	unsigned int cons;
 	unsigned int prod;
 
-	if (qp->is_user) {
-		cons = consumer_index(q, QUEUE_TYPE_FROM_USER);
-		prod = producer_index(q, QUEUE_TYPE_FROM_USER);
-	} else {
-		cons = consumer_index(q, QUEUE_TYPE_KERNEL);
-		prod = producer_index(q, QUEUE_TYPE_KERNEL);
-	}
+	cons = queue_get_consumer(q, QUEUE_TYPE_FROM_CLIENT);
+	prod = queue_get_producer(q, QUEUE_TYPE_FROM_CLIENT);
 
 	qp->req.wqe_index	= cons;
 	qp->req.psn		= qp->comp.psn;
 	qp->req.opcode		= -1;
 
 	for (wqe_index = cons; wqe_index != prod;
-			wqe_index = next_index(q, wqe_index)) {
-		wqe = addr_from_index(qp->sq.queue, wqe_index);
+			wqe_index = queue_next_index(q, wqe_index)) {
+		wqe = queue_addr_from_index(qp->sq.queue, wqe_index);
 		mask = wr_opcode_mask(wqe->wr.opcode, qp);
 
 		if (wqe->state == wqe_state_posted)
@@ -121,15 +116,9 @@ static struct rxe_send_wqe *req_next_wqe(struct rxe_qp *qp)
 	unsigned int cons;
 	unsigned int prod;
 
-	if (qp->is_user) {
-		wqe = queue_head(q, QUEUE_TYPE_FROM_USER);
-		cons = consumer_index(q, QUEUE_TYPE_FROM_USER);
-		prod = producer_index(q, QUEUE_TYPE_FROM_USER);
-	} else {
-		wqe = queue_head(q, QUEUE_TYPE_KERNEL);
-		cons = consumer_index(q, QUEUE_TYPE_KERNEL);
-		prod = producer_index(q, QUEUE_TYPE_KERNEL);
-	}
+	wqe = queue_head(q, QUEUE_TYPE_FROM_CLIENT);
+	cons = queue_get_consumer(q, QUEUE_TYPE_FROM_CLIENT);
+	prod = queue_get_producer(q, QUEUE_TYPE_FROM_CLIENT);
 
 	if (unlikely(qp->req.state == QP_STATE_DRAIN)) {
 		/* check to see if we are drained;
@@ -170,7 +159,7 @@ static struct rxe_send_wqe *req_next_wqe(struct rxe_qp *qp)
 	if (index == prod)
 		return NULL;
 
-	wqe = addr_from_index(q, index);
+	wqe = queue_addr_from_index(q, index);
 
 	if (unlikely((qp->req.state == QP_STATE_DRAIN ||
 		      qp->req.state == QP_STATE_DRAINED) &&
@@ -560,7 +549,8 @@ static void update_state(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
 	qp->req.opcode = pkt->opcode;
 
 	if (pkt->mask & RXE_END_MASK)
-		qp->req.wqe_index = next_index(qp->sq.queue, qp->req.wqe_index);
+		qp->req.wqe_index = queue_next_index(qp->sq.queue,
+						     qp->req.wqe_index);
 
 	qp->need_req_skb = 0;
 
@@ -610,11 +600,13 @@ static int rxe_do_local_ops(struct rxe_qp *qp, struct rxe_send_wqe *wqe)
 
 	wqe->state = wqe_state_done;
 	wqe->status = IB_WC_SUCCESS;
-	qp->req.wqe_index = next_index(qp->sq.queue, qp->req.wqe_index);
+	qp->req.wqe_index = queue_next_index(qp->sq.queue, qp->req.wqe_index);
 
-	if ((wqe->wr.send_flags & IB_SEND_SIGNALED) ||
-	    qp->sq_sig_type == IB_SIGNAL_ALL_WR)
-		rxe_run_task(&qp->comp.task, 1);
+	/* There is no ack coming for local work requests
+	 * which can lead to a deadlock. So go ahead and complete
+	 * it now.
+	 */
+	rxe_run_task(&qp->comp.task, 1);
 
 	return 0;
 }
@@ -641,7 +633,8 @@ next_wqe:
 		goto exit;
 
 	if (unlikely(qp->req.state == QP_STATE_RESET)) {
-		qp->req.wqe_index = consumer_index(q, q->type);
+		qp->req.wqe_index = queue_get_consumer(q,
+						QUEUE_TYPE_FROM_CLIENT);
 		qp->req.opcode = -1;
 		qp->req.need_rd_atomic = 0;
 		qp->req.wait_psn = 0;
@@ -707,7 +700,7 @@ next_wqe:
 			wqe->last_psn = qp->req.psn;
 			qp->req.psn = (qp->req.psn + 1) & BTH_PSN_MASK;
 			qp->req.opcode = IB_OPCODE_UD_SEND_ONLY;
-			qp->req.wqe_index = next_index(qp->sq.queue,
+			qp->req.wqe_index = queue_next_index(qp->sq.queue,
 						       qp->req.wqe_index);
 			wqe->state = wqe_state_done;
 			wqe->status = IB_WC_SUCCESS;
diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index 8ed172ab0beb..e7dec8481061 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -303,10 +303,7 @@ static enum resp_states get_srq_wqe(struct rxe_qp *qp)
 
 	spin_lock_bh(&srq->rq.consumer_lock);
 
-	if (qp->is_user)
-		wqe = queue_head(q, QUEUE_TYPE_FROM_USER);
-	else
-		wqe = queue_head(q, QUEUE_TYPE_KERNEL);
+	wqe = queue_head(q, QUEUE_TYPE_FROM_CLIENT);
 	if (!wqe) {
 		spin_unlock_bh(&srq->rq.consumer_lock);
 		return RESPST_ERR_RNR;
@@ -322,13 +319,8 @@ static enum resp_states get_srq_wqe(struct rxe_qp *qp)
 	memcpy(&qp->resp.srq_wqe, wqe, size);
 
 	qp->resp.wqe = &qp->resp.srq_wqe.wqe;
-	if (qp->is_user) {
-		advance_consumer(q, QUEUE_TYPE_FROM_USER);
-		count = queue_count(q, QUEUE_TYPE_FROM_USER);
-	} else {
-		advance_consumer(q, QUEUE_TYPE_KERNEL);
-		count = queue_count(q, QUEUE_TYPE_KERNEL);
-	}
+	queue_advance_consumer(q, QUEUE_TYPE_FROM_CLIENT);
+	count = queue_count(q, QUEUE_TYPE_FROM_CLIENT);
 
 	if (srq->limit && srq->ibsrq.event_handler && (count < srq->limit)) {
 		srq->limit = 0;
@@ -357,12 +349,8 @@ static enum resp_states check_resource(struct rxe_qp *qp,
 			qp->resp.status = IB_WC_WR_FLUSH_ERR;
 			return RESPST_COMPLETE;
 		} else if (!srq) {
-			if (qp->is_user)
-				qp->resp.wqe = queue_head(qp->rq.queue,
-						QUEUE_TYPE_FROM_USER);
-			else
-				qp->resp.wqe = queue_head(qp->rq.queue,
-						QUEUE_TYPE_KERNEL);
+			qp->resp.wqe = queue_head(qp->rq.queue,
+					QUEUE_TYPE_FROM_CLIENT);
 			if (qp->resp.wqe) {
 				qp->resp.status = IB_WC_WR_FLUSH_ERR;
 				return RESPST_COMPLETE;
@@ -389,12 +377,8 @@ static enum resp_states check_resource(struct rxe_qp *qp,
 		if (srq)
 			return get_srq_wqe(qp);
 
-		if (qp->is_user)
-			qp->resp.wqe = queue_head(qp->rq.queue,
-					QUEUE_TYPE_FROM_USER);
-		else
-			qp->resp.wqe = queue_head(qp->rq.queue,
-					QUEUE_TYPE_KERNEL);
+		qp->resp.wqe = queue_head(qp->rq.queue,
+				QUEUE_TYPE_FROM_CLIENT);
 		return (qp->resp.wqe) ? RESPST_CHK_LENGTH : RESPST_ERR_RNR;
 	}
 
@@ -938,12 +922,8 @@ static enum resp_states do_complete(struct rxe_qp *qp,
 	}
 
 	/* have copy for srq and reference for !srq */
-	if (!qp->srq) {
-		if (qp->is_user)
-			advance_consumer(qp->rq.queue, QUEUE_TYPE_FROM_USER);
-		else
-			advance_consumer(qp->rq.queue, QUEUE_TYPE_KERNEL);
-	}
+	if (!qp->srq)
+		queue_advance_consumer(qp->rq.queue, QUEUE_TYPE_FROM_CLIENT);
 
 	qp->resp.wqe = NULL;
 
@@ -1215,7 +1195,7 @@ static void rxe_drain_req_pkts(struct rxe_qp *qp, bool notify)
 		return;
 
 	while (!qp->srq && q && queue_head(q, q->type))
-		advance_consumer(q, q->type);
+		queue_advance_consumer(q, q->type);
 }
 
 int rxe_responder(void *arg)
diff --git a/drivers/infiniband/sw/rxe/rxe_srq.c b/drivers/infiniband/sw/rxe/rxe_srq.c
index 610c98d24b5c..eb1c4c3b3a78 100644
--- a/drivers/infiniband/sw/rxe/rxe_srq.c
+++ b/drivers/infiniband/sw/rxe/rxe_srq.c
@@ -86,14 +86,13 @@ int rxe_srq_from_init(struct rxe_dev *rxe, struct rxe_srq *srq,
 	srq->srq_num		= srq->pelem.index;
 	srq->rq.max_wr		= init->attr.max_wr;
 	srq->rq.max_sge		= init->attr.max_sge;
-	srq->rq.is_user		= srq->is_user;
 
 	srq_wqe_size		= rcv_wqe_size(srq->rq.max_sge);
 
 	spin_lock_init(&srq->rq.producer_lock);
 	spin_lock_init(&srq->rq.consumer_lock);
 
-	type = uresp ? QUEUE_TYPE_FROM_USER : QUEUE_TYPE_KERNEL;
+	type = QUEUE_TYPE_FROM_CLIENT;
 	q = rxe_queue_init(rxe, &srq->rq.max_wr,
 			srq_wqe_size, type);
 	if (!q) {
diff --git a/drivers/infiniband/sw/rxe/rxe_task.c b/drivers/infiniband/sw/rxe/rxe_task.c
index 6951fdcb31bf..568cf56c236b 100644
--- a/drivers/infiniband/sw/rxe/rxe_task.c
+++ b/drivers/infiniband/sw/rxe/rxe_task.c
@@ -8,7 +8,7 @@
 #include <linux/interrupt.h>
 #include <linux/hardirq.h>
 
-#include "rxe_task.h"
+#include "rxe.h"
 
 int __rxe_do_task(struct rxe_task *task)
 
@@ -34,6 +34,7 @@ void rxe_do_task(struct tasklet_struct *t)
 	int ret;
 	unsigned long flags;
 	struct rxe_task *task = from_tasklet(task, t, tasklet);
+	unsigned int iterations = RXE_MAX_ITERATIONS;
 
 	spin_lock_irqsave(&task->state_lock, flags);
 	switch (task->state) {
@@ -62,13 +63,20 @@ void rxe_do_task(struct tasklet_struct *t)
 		spin_lock_irqsave(&task->state_lock, flags);
 		switch (task->state) {
 		case TASK_STATE_BUSY:
-			if (ret)
+			if (ret) {
 				task->state = TASK_STATE_START;
-			else
+			} else if (iterations--) {
 				cont = 1;
+			} else {
+				/* reschedule the tasklet and exit
+				 * the loop to give up the cpu
+				 */
+				tasklet_schedule(&task->tasklet);
+				task->state = TASK_STATE_START;
+			}
 			break;
 
-		/* soneone tried to run the task since the last time we called
+		/* someone tried to run the task since the last time we called
 		 * func, so we will call one more time regardless of the
 		 * return value
 		 */
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index 267b5a9c345d..e40927cf5772 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -218,11 +218,7 @@ static int post_one_recv(struct rxe_rq *rq, const struct ib_recv_wr *ibwr)
 	int num_sge = ibwr->num_sge;
 	int full;
 
-	if (rq->is_user)
-		full = queue_full(rq->queue, QUEUE_TYPE_FROM_USER);
-	else
-		full = queue_full(rq->queue, QUEUE_TYPE_KERNEL);
-
+	full = queue_full(rq->queue, QUEUE_TYPE_TO_DRIVER);
 	if (unlikely(full)) {
 		err = -ENOMEM;
 		goto err1;
@@ -237,11 +233,7 @@ static int post_one_recv(struct rxe_rq *rq, const struct ib_recv_wr *ibwr)
 	for (i = 0; i < num_sge; i++)
 		length += ibwr->sg_list[i].length;
 
-	if (rq->is_user)
-		recv_wqe = producer_addr(rq->queue, QUEUE_TYPE_FROM_USER);
-	else
-		recv_wqe = producer_addr(rq->queue, QUEUE_TYPE_KERNEL);
-
+	recv_wqe = queue_producer_addr(rq->queue, QUEUE_TYPE_TO_DRIVER);
 	recv_wqe->wr_id = ibwr->wr_id;
 	recv_wqe->num_sge = num_sge;
 
@@ -254,10 +246,7 @@ static int post_one_recv(struct rxe_rq *rq, const struct ib_recv_wr *ibwr)
 	recv_wqe->dma.cur_sge		= 0;
 	recv_wqe->dma.sge_offset	= 0;
 
-	if (rq->is_user)
-		advance_producer(rq->queue, QUEUE_TYPE_FROM_USER);
-	else
-		advance_producer(rq->queue, QUEUE_TYPE_KERNEL);
+	queue_advance_producer(rq->queue, QUEUE_TYPE_TO_DRIVER);
 
 	return 0;
 
@@ -281,9 +270,6 @@ static int rxe_create_srq(struct ib_srq *ibsrq, struct ib_srq_init_attr *init,
 		if (udata->outlen < sizeof(*uresp))
 			return -EINVAL;
 		uresp = udata->outbuf;
-		srq->is_user = true;
-	} else {
-		srq->is_user = false;
 	}
 
 	err = rxe_srq_chk_attr(rxe, NULL, &init->attr, IB_SRQ_INIT_MASK);
@@ -633,27 +619,17 @@ static int post_one_send(struct rxe_qp *qp, const struct ib_send_wr *ibwr,
 
 	spin_lock_irqsave(&qp->sq.sq_lock, flags);
 
-	if (qp->is_user)
-		full = queue_full(sq->queue, QUEUE_TYPE_FROM_USER);
-	else
-		full = queue_full(sq->queue, QUEUE_TYPE_KERNEL);
+	full = queue_full(sq->queue, QUEUE_TYPE_TO_DRIVER);
 
 	if (unlikely(full)) {
 		spin_unlock_irqrestore(&qp->sq.sq_lock, flags);
 		return -ENOMEM;
 	}
 
-	if (qp->is_user)
-		send_wqe = producer_addr(sq->queue, QUEUE_TYPE_FROM_USER);
-	else
-		send_wqe = producer_addr(sq->queue, QUEUE_TYPE_KERNEL);
-
+	send_wqe = queue_producer_addr(sq->queue, QUEUE_TYPE_TO_DRIVER);
 	init_send_wqe(qp, ibwr, mask, length, send_wqe);
 
-	if (qp->is_user)
-		advance_producer(sq->queue, QUEUE_TYPE_FROM_USER);
-	else
-		advance_producer(sq->queue, QUEUE_TYPE_KERNEL);
+	queue_advance_producer(sq->queue, QUEUE_TYPE_TO_DRIVER);
 
 	spin_unlock_irqrestore(&qp->sq.sq_lock, flags);
 
@@ -845,18 +821,12 @@ static int rxe_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
 
 	spin_lock_irqsave(&cq->cq_lock, flags);
 	for (i = 0; i < num_entries; i++) {
-		if (cq->is_user)
-			cqe = queue_head(cq->queue, QUEUE_TYPE_TO_USER);
-		else
-			cqe = queue_head(cq->queue, QUEUE_TYPE_KERNEL);
+		cqe = queue_head(cq->queue, QUEUE_TYPE_FROM_DRIVER);
 		if (!cqe)
 			break;
 
 		memcpy(wc++, &cqe->ibwc, sizeof(*wc));
-		if (cq->is_user)
-			advance_consumer(cq->queue, QUEUE_TYPE_TO_USER);
-		else
-			advance_consumer(cq->queue, QUEUE_TYPE_KERNEL);
+		queue_advance_consumer(cq->queue, QUEUE_TYPE_FROM_DRIVER);
 	}
 	spin_unlock_irqrestore(&cq->cq_lock, flags);
 
@@ -868,10 +838,7 @@ static int rxe_peek_cq(struct ib_cq *ibcq, int wc_cnt)
 	struct rxe_cq *cq = to_rcq(ibcq);
 	int count;
 
-	if (cq->is_user)
-		count = queue_count(cq->queue, QUEUE_TYPE_TO_USER);
-	else
-		count = queue_count(cq->queue, QUEUE_TYPE_KERNEL);
+	count = queue_count(cq->queue, QUEUE_TYPE_FROM_DRIVER);
 
 	return (count > wc_cnt) ? wc_cnt : count;
 }
@@ -887,10 +854,7 @@ static int rxe_req_notify_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags)
 	if (cq->notify != IB_CQ_NEXT_COMP)
 		cq->notify = flags & IB_CQ_SOLICITED_MASK;
 
-	if (cq->is_user)
-		empty = queue_empty(cq->queue, QUEUE_TYPE_TO_USER);
-	else
-		empty = queue_empty(cq->queue, QUEUE_TYPE_KERNEL);
+	empty = queue_empty(cq->queue, QUEUE_TYPE_FROM_DRIVER);
 
 	if ((flags & IB_CQ_REPORT_MISSED_EVENTS) && !empty)
 		ret = 1;
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h
index d90b1d77de34..c852a9907bad 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.h
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.h
@@ -77,7 +77,6 @@ enum wqe_state {
 };
 
 struct rxe_sq {
-	bool			is_user;
 	int			max_wr;
 	int			max_sge;
 	int			max_inline;
@@ -86,7 +85,6 @@ struct rxe_sq {
 };
 
 struct rxe_rq {
-	bool			is_user;
 	int			max_wr;
 	int			max_sge;
 	spinlock_t		producer_lock; /* guard queue producer */
@@ -100,7 +98,6 @@ struct rxe_srq {
 	struct rxe_pd		*pd;
 	struct rxe_rq		rq;
 	u32			srq_num;
-	bool			is_user;
 
 	int			limit;
 	int			error;
diff --git a/drivers/infiniband/sw/siw/siw_cm.c b/drivers/infiniband/sw/siw/siw_cm.c
index 18a64ccbb0e5..69d639cab898 100644
--- a/drivers/infiniband/sw/siw/siw_cm.c
+++ b/drivers/infiniband/sw/siw/siw_cm.c
@@ -725,11 +725,11 @@ static int siw_proc_mpareply(struct siw_cep *cep)
 	enum mpa_v2_ctrl mpa_p2p_mode = MPA_V2_RDMA_NO_RTR;
 
 	rv = siw_recv_mpa_rr(cep);
-	if (rv != -EAGAIN)
-		siw_cancel_mpatimer(cep);
 	if (rv)
 		goto out_err;
 
+	siw_cancel_mpatimer(cep);
+
 	rep = &cep->mpa.hdr;
 
 	if (__mpa_rr_revision(rep->params.bits) > MPA_REVISION_2) {
@@ -895,7 +895,8 @@ static int siw_proc_mpareply(struct siw_cep *cep)
 	}
 
 out_err:
-	siw_cm_upcall(cep, IW_CM_EVENT_CONNECT_REPLY, -EINVAL);
+	if (rv != -EAGAIN)
+		siw_cm_upcall(cep, IW_CM_EVENT_CONNECT_REPLY, -EINVAL);
 
 	return rv;
 }
diff --git a/drivers/infiniband/sw/siw/siw_qp_tx.c b/drivers/infiniband/sw/siw/siw_qp_tx.c
index 1f4e60257700..7d47b521070b 100644
--- a/drivers/infiniband/sw/siw/siw_qp_tx.c
+++ b/drivers/infiniband/sw/siw/siw_qp_tx.c
@@ -29,7 +29,7 @@ static struct page *siw_get_pblpage(struct siw_mem *mem, u64 addr, int *idx)
 	dma_addr_t paddr = siw_pbl_get_buffer(pbl, offset, NULL, idx);
 
 	if (paddr)
-		return virt_to_page(paddr);
+		return virt_to_page((void *)paddr);
 
 	return NULL;
 }
@@ -533,13 +533,23 @@ static int siw_tx_hdt(struct siw_iwarp_tx *c_tx, struct socket *s)
 					kunmap_local(kaddr);
 				}
 			} else {
-				u64 va = sge->laddr + sge_off;
+				/*
+				 * Cast to an uintptr_t to preserve all 64 bits
+				 * in sge->laddr.
+				 */
+				uintptr_t va = (uintptr_t)(sge->laddr + sge_off);
 
-				page_array[seg] = virt_to_page(va & PAGE_MASK);
+				/*
+				 * virt_to_page() takes a (void *) pointer
+				 * so cast to a (void *) meaning it will be 64
+				 * bits on a 64 bit platform and 32 bits on a
+				 * 32 bit platform.
+				 */
+				page_array[seg] = virt_to_page((void *)(va & PAGE_MASK));
 				if (do_crc)
 					crypto_shash_update(
 						c_tx->mpa_crc_hd,
-						(void *)(uintptr_t)va,
+						(void *)va,
 						plen);
 			}
 
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c
index 776e46ee95da..ef2d165d15a8 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.c
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.c
@@ -584,7 +584,7 @@ iscsi_iser_session_destroy(struct iscsi_cls_session *cls_session)
 	struct Scsi_Host *shost = iscsi_session_to_shost(cls_session);
 
 	iscsi_session_teardown(cls_session);
-	iscsi_host_remove(shost);
+	iscsi_host_remove(shost, false);
 	iscsi_host_free(shost);
 }
 
@@ -702,7 +702,7 @@ iscsi_iser_session_create(struct iscsi_endpoint *ep,
 	return cls_session;
 
 remove_host:
-	iscsi_host_remove(shost);
+	iscsi_host_remove(shost, false);
 free_host:
 	iscsi_host_free(shost);
 	return NULL;
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt-stats.c b/drivers/infiniband/ulp/rtrs/rtrs-clt-stats.c
index 5e780bdd763d..e7b57bdfe3ea 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt-stats.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt-stats.c
@@ -13,8 +13,8 @@
 
 void rtrs_clt_update_wc_stats(struct rtrs_clt_con *con)
 {
-	struct rtrs_clt_sess *sess = to_clt_sess(con->c.sess);
-	struct rtrs_clt_stats *stats = sess->stats;
+	struct rtrs_clt_path *clt_path = to_clt_path(con->c.path);
+	struct rtrs_clt_stats *stats = clt_path->stats;
 	struct rtrs_clt_stats_pcpu *s;
 	int cpu;
 
@@ -174,8 +174,8 @@ static inline void rtrs_clt_update_rdma_stats(struct rtrs_clt_stats *stats,
 void rtrs_clt_update_all_stats(struct rtrs_clt_io_req *req, int dir)
 {
 	struct rtrs_clt_con *con = req->con;
-	struct rtrs_clt_sess *sess = to_clt_sess(con->c.sess);
-	struct rtrs_clt_stats *stats = sess->stats;
+	struct rtrs_clt_path *clt_path = to_clt_path(con->c.path);
+	struct rtrs_clt_stats *stats = clt_path->stats;
 	unsigned int len;
 
 	len = req->usr_len + req->data_len;
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt-sysfs.c b/drivers/infiniband/ulp/rtrs/rtrs-clt-sysfs.c
index 4ee592ccf979..dbf9a778c3bd 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt-sysfs.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt-sysfs.c
@@ -16,21 +16,21 @@
 #define MIN_MAX_RECONN_ATT -1
 #define MAX_MAX_RECONN_ATT 9999
 
-static void rtrs_clt_sess_release(struct kobject *kobj)
+static void rtrs_clt_path_release(struct kobject *kobj)
 {
-	struct rtrs_clt_sess *sess;
+	struct rtrs_clt_path *clt_path;
 
-	sess = container_of(kobj, struct rtrs_clt_sess, kobj);
+	clt_path = container_of(kobj, struct rtrs_clt_path, kobj);
 
-	free_sess(sess);
+	free_path(clt_path);
 }
 
 static struct kobj_type ktype_sess = {
 	.sysfs_ops = &kobj_sysfs_ops,
-	.release = rtrs_clt_sess_release
+	.release = rtrs_clt_path_release
 };
 
-static void rtrs_clt_sess_stats_release(struct kobject *kobj)
+static void rtrs_clt_path_stats_release(struct kobject *kobj)
 {
 	struct rtrs_clt_stats *stats;
 
@@ -43,7 +43,7 @@ static void rtrs_clt_sess_stats_release(struct kobject *kobj)
 
 static struct kobj_type ktype_stats = {
 	.sysfs_ops = &kobj_sysfs_ops,
-	.release = rtrs_clt_sess_stats_release,
+	.release = rtrs_clt_path_stats_release,
 };
 
 static ssize_t max_reconnect_attempts_show(struct device *dev,
@@ -197,10 +197,10 @@ static DEVICE_ATTR_RW(add_path);
 static ssize_t rtrs_clt_state_show(struct kobject *kobj,
 				    struct kobj_attribute *attr, char *page)
 {
-	struct rtrs_clt_sess *sess;
+	struct rtrs_clt_path *clt_path;
 
-	sess = container_of(kobj, struct rtrs_clt_sess, kobj);
-	if (sess->state == RTRS_CLT_CONNECTED)
+	clt_path = container_of(kobj, struct rtrs_clt_path, kobj);
+	if (clt_path->state == RTRS_CLT_CONNECTED)
 		return sysfs_emit(page, "connected\n");
 
 	return sysfs_emit(page, "disconnected\n");
@@ -219,16 +219,16 @@ static ssize_t rtrs_clt_reconnect_store(struct kobject *kobj,
 					 struct kobj_attribute *attr,
 					 const char *buf, size_t count)
 {
-	struct rtrs_clt_sess *sess;
+	struct rtrs_clt_path *clt_path;
 	int ret;
 
-	sess = container_of(kobj, struct rtrs_clt_sess, kobj);
+	clt_path = container_of(kobj, struct rtrs_clt_path, kobj);
 	if (!sysfs_streq(buf, "1")) {
-		rtrs_err(sess->clt, "%s: unknown value: '%s'\n",
+		rtrs_err(clt_path->clt, "%s: unknown value: '%s'\n",
 			  attr->attr.name, buf);
 		return -EINVAL;
 	}
-	ret = rtrs_clt_reconnect_from_sysfs(sess);
+	ret = rtrs_clt_reconnect_from_sysfs(clt_path);
 	if (ret)
 		return ret;
 
@@ -249,15 +249,15 @@ static ssize_t rtrs_clt_disconnect_store(struct kobject *kobj,
 					  struct kobj_attribute *attr,
 					  const char *buf, size_t count)
 {
-	struct rtrs_clt_sess *sess;
+	struct rtrs_clt_path *clt_path;
 
-	sess = container_of(kobj, struct rtrs_clt_sess, kobj);
+	clt_path = container_of(kobj, struct rtrs_clt_path, kobj);
 	if (!sysfs_streq(buf, "1")) {
-		rtrs_err(sess->clt, "%s: unknown value: '%s'\n",
+		rtrs_err(clt_path->clt, "%s: unknown value: '%s'\n",
 			  attr->attr.name, buf);
 		return -EINVAL;
 	}
-	rtrs_clt_close_conns(sess, true);
+	rtrs_clt_close_conns(clt_path, true);
 
 	return count;
 }
@@ -276,16 +276,16 @@ static ssize_t rtrs_clt_remove_path_store(struct kobject *kobj,
 					   struct kobj_attribute *attr,
 					   const char *buf, size_t count)
 {
-	struct rtrs_clt_sess *sess;
+	struct rtrs_clt_path *clt_path;
 	int ret;
 
-	sess = container_of(kobj, struct rtrs_clt_sess, kobj);
+	clt_path = container_of(kobj, struct rtrs_clt_path, kobj);
 	if (!sysfs_streq(buf, "1")) {
-		rtrs_err(sess->clt, "%s: unknown value: '%s'\n",
+		rtrs_err(clt_path->clt, "%s: unknown value: '%s'\n",
 			  attr->attr.name, buf);
 		return -EINVAL;
 	}
-	ret = rtrs_clt_remove_path_from_sysfs(sess, &attr->attr);
+	ret = rtrs_clt_remove_path_from_sysfs(clt_path, &attr->attr);
 	if (ret)
 		return ret;
 
@@ -328,11 +328,11 @@ static ssize_t rtrs_clt_hca_port_show(struct kobject *kobj,
 				       struct kobj_attribute *attr,
 				       char *page)
 {
-	struct rtrs_clt_sess *sess;
+	struct rtrs_clt_path *clt_path;
 
-	sess = container_of(kobj, typeof(*sess), kobj);
+	clt_path = container_of(kobj, typeof(*clt_path), kobj);
 
-	return sysfs_emit(page, "%u\n", sess->hca_port);
+	return sysfs_emit(page, "%u\n", clt_path->hca_port);
 }
 
 static struct kobj_attribute rtrs_clt_hca_port_attr =
@@ -342,11 +342,11 @@ static ssize_t rtrs_clt_hca_name_show(struct kobject *kobj,
 				       struct kobj_attribute *attr,
 				       char *page)
 {
-	struct rtrs_clt_sess *sess;
+	struct rtrs_clt_path *clt_path;
 
-	sess = container_of(kobj, struct rtrs_clt_sess, kobj);
+	clt_path = container_of(kobj, struct rtrs_clt_path, kobj);
 
-	return sysfs_emit(page, "%s\n", sess->hca_name);
+	return sysfs_emit(page, "%s\n", clt_path->hca_name);
 }
 
 static struct kobj_attribute rtrs_clt_hca_name_attr =
@@ -356,12 +356,12 @@ static ssize_t rtrs_clt_cur_latency_show(struct kobject *kobj,
 				    struct kobj_attribute *attr,
 				    char *page)
 {
-	struct rtrs_clt_sess *sess;
+	struct rtrs_clt_path *clt_path;
 
-	sess = container_of(kobj, struct rtrs_clt_sess, kobj);
+	clt_path = container_of(kobj, struct rtrs_clt_path, kobj);
 
 	return sysfs_emit(page, "%lld ns\n",
-			  ktime_to_ns(sess->s.hb_cur_latency));
+			  ktime_to_ns(clt_path->s.hb_cur_latency));
 }
 
 static struct kobj_attribute rtrs_clt_cur_latency_attr =
@@ -371,11 +371,11 @@ static ssize_t rtrs_clt_src_addr_show(struct kobject *kobj,
 				       struct kobj_attribute *attr,
 				       char *page)
 {
-	struct rtrs_clt_sess *sess;
+	struct rtrs_clt_path *clt_path;
 	int len;
 
-	sess = container_of(kobj, struct rtrs_clt_sess, kobj);
-	len = sockaddr_to_str((struct sockaddr *)&sess->s.src_addr, page,
+	clt_path = container_of(kobj, struct rtrs_clt_path, kobj);
+	len = sockaddr_to_str((struct sockaddr *)&clt_path->s.src_addr, page,
 			      PAGE_SIZE);
 	len += sysfs_emit_at(page, len, "\n");
 	return len;
@@ -388,11 +388,11 @@ static ssize_t rtrs_clt_dst_addr_show(struct kobject *kobj,
 				       struct kobj_attribute *attr,
 				       char *page)
 {
-	struct rtrs_clt_sess *sess;
+	struct rtrs_clt_path *clt_path;
 	int len;
 
-	sess = container_of(kobj, struct rtrs_clt_sess, kobj);
-	len = sockaddr_to_str((struct sockaddr *)&sess->s.dst_addr, page,
+	clt_path = container_of(kobj, struct rtrs_clt_path, kobj);
+	len = sockaddr_to_str((struct sockaddr *)&clt_path->s.dst_addr, page,
 			      PAGE_SIZE);
 	len += sysfs_emit_at(page, len, "\n");
 	return len;
@@ -401,7 +401,7 @@ static ssize_t rtrs_clt_dst_addr_show(struct kobject *kobj,
 static struct kobj_attribute rtrs_clt_dst_addr_attr =
 	__ATTR(dst_addr, 0444, rtrs_clt_dst_addr_show, NULL);
 
-static struct attribute *rtrs_clt_sess_attrs[] = {
+static struct attribute *rtrs_clt_path_attrs[] = {
 	&rtrs_clt_hca_name_attr.attr,
 	&rtrs_clt_hca_port_attr.attr,
 	&rtrs_clt_src_addr_attr.attr,
@@ -414,42 +414,43 @@ static struct attribute *rtrs_clt_sess_attrs[] = {
 	NULL,
 };
 
-static const struct attribute_group rtrs_clt_sess_attr_group = {
-	.attrs = rtrs_clt_sess_attrs,
+static const struct attribute_group rtrs_clt_path_attr_group = {
+	.attrs = rtrs_clt_path_attrs,
 };
 
-int rtrs_clt_create_sess_files(struct rtrs_clt_sess *sess)
+int rtrs_clt_create_path_files(struct rtrs_clt_path *clt_path)
 {
-	struct rtrs_clt *clt = sess->clt;
+	struct rtrs_clt *clt = clt_path->clt;
 	char str[NAME_MAX];
 	int err;
 	struct rtrs_addr path = {
-		.src = &sess->s.src_addr,
-		.dst = &sess->s.dst_addr,
+		.src = &clt_path->s.src_addr,
+		.dst = &clt_path->s.dst_addr,
 	};
 
 	rtrs_addr_to_str(&path, str, sizeof(str));
-	err = kobject_init_and_add(&sess->kobj, &ktype_sess, clt->kobj_paths,
+	err = kobject_init_and_add(&clt_path->kobj, &ktype_sess,
+				   clt->kobj_paths,
 				   "%s", str);
 	if (err) {
 		pr_err("kobject_init_and_add: %d\n", err);
-		kobject_put(&sess->kobj);
+		kobject_put(&clt_path->kobj);
 		return err;
 	}
-	err = sysfs_create_group(&sess->kobj, &rtrs_clt_sess_attr_group);
+	err = sysfs_create_group(&clt_path->kobj, &rtrs_clt_path_attr_group);
 	if (err) {
 		pr_err("sysfs_create_group(): %d\n", err);
 		goto put_kobj;
 	}
-	err = kobject_init_and_add(&sess->stats->kobj_stats, &ktype_stats,
-				   &sess->kobj, "stats");
+	err = kobject_init_and_add(&clt_path->stats->kobj_stats, &ktype_stats,
+				   &clt_path->kobj, "stats");
 	if (err) {
 		pr_err("kobject_init_and_add: %d\n", err);
-		kobject_put(&sess->stats->kobj_stats);
+		kobject_put(&clt_path->stats->kobj_stats);
 		goto remove_group;
 	}
 
-	err = sysfs_create_group(&sess->stats->kobj_stats,
+	err = sysfs_create_group(&clt_path->stats->kobj_stats,
 				 &rtrs_clt_stats_attr_group);
 	if (err) {
 		pr_err("failed to create stats sysfs group, err: %d\n", err);
@@ -459,25 +460,25 @@ int rtrs_clt_create_sess_files(struct rtrs_clt_sess *sess)
 	return 0;
 
 put_kobj_stats:
-	kobject_del(&sess->stats->kobj_stats);
-	kobject_put(&sess->stats->kobj_stats);
+	kobject_del(&clt_path->stats->kobj_stats);
+	kobject_put(&clt_path->stats->kobj_stats);
 remove_group:
-	sysfs_remove_group(&sess->kobj, &rtrs_clt_sess_attr_group);
+	sysfs_remove_group(&clt_path->kobj, &rtrs_clt_path_attr_group);
 put_kobj:
-	kobject_del(&sess->kobj);
-	kobject_put(&sess->kobj);
+	kobject_del(&clt_path->kobj);
+	kobject_put(&clt_path->kobj);
 
 	return err;
 }
 
-void rtrs_clt_destroy_sess_files(struct rtrs_clt_sess *sess,
+void rtrs_clt_destroy_path_files(struct rtrs_clt_path *clt_path,
 				  const struct attribute *sysfs_self)
 {
-	kobject_del(&sess->stats->kobj_stats);
-	kobject_put(&sess->stats->kobj_stats);
+	kobject_del(&clt_path->stats->kobj_stats);
+	kobject_put(&clt_path->stats->kobj_stats);
 	if (sysfs_self)
-		sysfs_remove_file_self(&sess->kobj, sysfs_self);
-	kobject_del(&sess->kobj);
+		sysfs_remove_file_self(&clt_path->kobj, sysfs_self);
+	kobject_del(&clt_path->kobj);
 }
 
 static struct attribute *rtrs_clt_attrs[] = {
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
index a23438bacf12..c644617725a8 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
@@ -48,12 +48,12 @@ static struct class *rtrs_clt_dev_class;
 
 static inline bool rtrs_clt_is_connected(const struct rtrs_clt *clt)
 {
-	struct rtrs_clt_sess *sess;
+	struct rtrs_clt_path *clt_path;
 	bool connected = false;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(sess, &clt->paths_list, s.entry)
-		connected |= READ_ONCE(sess->state) == RTRS_CLT_CONNECTED;
+	list_for_each_entry_rcu(clt_path, &clt->paths_list, s.entry)
+		connected |= READ_ONCE(clt_path->state) == RTRS_CLT_CONNECTED;
 	rcu_read_unlock();
 
 	return connected;
@@ -163,29 +163,29 @@ EXPORT_SYMBOL(rtrs_clt_put_permit);
 
 /**
  * rtrs_permit_to_clt_con() - returns RDMA connection pointer by the permit
- * @sess: client session pointer
+ * @clt_path: client path pointer
  * @permit: permit for the allocation of the RDMA buffer
  * Note:
  *     IO connection starts from 1.
  *     0 connection is for user messages.
  */
 static
-struct rtrs_clt_con *rtrs_permit_to_clt_con(struct rtrs_clt_sess *sess,
+struct rtrs_clt_con *rtrs_permit_to_clt_con(struct rtrs_clt_path *clt_path,
 					    struct rtrs_permit *permit)
 {
 	int id = 0;
 
 	if (permit->con_type == RTRS_IO_CON)
-		id = (permit->cpu_id % (sess->s.irq_con_num - 1)) + 1;
+		id = (permit->cpu_id % (clt_path->s.irq_con_num - 1)) + 1;
 
-	return to_clt_con(sess->s.con[id]);
+	return to_clt_con(clt_path->s.con[id]);
 }
 
 /**
  * rtrs_clt_change_state() - change the session state through session state
  * machine.
  *
- * @sess: client session to change the state of.
+ * @clt_path: client path to change the state of.
  * @new_state: state to change to.
  *
  * returns true if sess's state is changed to new state, otherwise return false.
@@ -193,15 +193,15 @@ struct rtrs_clt_con *rtrs_permit_to_clt_con(struct rtrs_clt_sess *sess,
  * Locks:
  * state_wq lock must be hold.
  */
-static bool rtrs_clt_change_state(struct rtrs_clt_sess *sess,
+static bool rtrs_clt_change_state(struct rtrs_clt_path *clt_path,
 				     enum rtrs_clt_state new_state)
 {
 	enum rtrs_clt_state old_state;
 	bool changed = false;
 
-	lockdep_assert_held(&sess->state_wq.lock);
+	lockdep_assert_held(&clt_path->state_wq.lock);
 
-	old_state = sess->state;
+	old_state = clt_path->state;
 	switch (new_state) {
 	case RTRS_CLT_CONNECTING:
 		switch (old_state) {
@@ -275,42 +275,42 @@ static bool rtrs_clt_change_state(struct rtrs_clt_sess *sess,
 		break;
 	}
 	if (changed) {
-		sess->state = new_state;
-		wake_up_locked(&sess->state_wq);
+		clt_path->state = new_state;
+		wake_up_locked(&clt_path->state_wq);
 	}
 
 	return changed;
 }
 
-static bool rtrs_clt_change_state_from_to(struct rtrs_clt_sess *sess,
+static bool rtrs_clt_change_state_from_to(struct rtrs_clt_path *clt_path,
 					   enum rtrs_clt_state old_state,
 					   enum rtrs_clt_state new_state)
 {
 	bool changed = false;
 
-	spin_lock_irq(&sess->state_wq.lock);
-	if (sess->state == old_state)
-		changed = rtrs_clt_change_state(sess, new_state);
-	spin_unlock_irq(&sess->state_wq.lock);
+	spin_lock_irq(&clt_path->state_wq.lock);
+	if (clt_path->state == old_state)
+		changed = rtrs_clt_change_state(clt_path, new_state);
+	spin_unlock_irq(&clt_path->state_wq.lock);
 
 	return changed;
 }
 
 static void rtrs_rdma_error_recovery(struct rtrs_clt_con *con)
 {
-	struct rtrs_clt_sess *sess = to_clt_sess(con->c.sess);
+	struct rtrs_clt_path *clt_path = to_clt_path(con->c.path);
 
-	if (rtrs_clt_change_state_from_to(sess,
+	if (rtrs_clt_change_state_from_to(clt_path,
 					   RTRS_CLT_CONNECTED,
 					   RTRS_CLT_RECONNECTING)) {
-		struct rtrs_clt *clt = sess->clt;
+		struct rtrs_clt *clt = clt_path->clt;
 		unsigned int delay_ms;
 
 		/*
 		 * Normal scenario, reconnect if we were successfully connected
 		 */
 		delay_ms = clt->reconnect_delay_sec * 1000;
-		queue_delayed_work(rtrs_wq, &sess->reconnect_dwork,
+		queue_delayed_work(rtrs_wq, &clt_path->reconnect_dwork,
 				   msecs_to_jiffies(delay_ms +
 						    prandom_u32() % RTRS_RECONNECT_SEED));
 	} else {
@@ -319,7 +319,7 @@ static void rtrs_rdma_error_recovery(struct rtrs_clt_con *con)
 		 * so notify waiter with error state, waiter is responsible
 		 * for cleaning the rest and reconnect if needed.
 		 */
-		rtrs_clt_change_state_from_to(sess,
+		rtrs_clt_change_state_from_to(clt_path,
 					       RTRS_CLT_CONNECTING,
 					       RTRS_CLT_CONNECTING_ERR);
 	}
@@ -330,7 +330,7 @@ static void rtrs_clt_fast_reg_done(struct ib_cq *cq, struct ib_wc *wc)
 	struct rtrs_clt_con *con = to_clt_con(wc->qp->qp_context);
 
 	if (wc->status != IB_WC_SUCCESS) {
-		rtrs_err(con->c.sess, "Failed IB_WR_REG_MR: %s\n",
+		rtrs_err(con->c.path, "Failed IB_WR_REG_MR: %s\n",
 			  ib_wc_status_msg(wc->status));
 		rtrs_rdma_error_recovery(con);
 	}
@@ -350,7 +350,7 @@ static void rtrs_clt_inv_rkey_done(struct ib_cq *cq, struct ib_wc *wc)
 	struct rtrs_clt_con *con = to_clt_con(wc->qp->qp_context);
 
 	if (wc->status != IB_WC_SUCCESS) {
-		rtrs_err(con->c.sess, "Failed IB_WR_LOCAL_INV: %s\n",
+		rtrs_err(con->c.path, "Failed IB_WR_LOCAL_INV: %s\n",
 			  ib_wc_status_msg(wc->status));
 		rtrs_rdma_error_recovery(con);
 	}
@@ -380,14 +380,14 @@ static void complete_rdma_req(struct rtrs_clt_io_req *req, int errno,
 			      bool notify, bool can_wait)
 {
 	struct rtrs_clt_con *con = req->con;
-	struct rtrs_clt_sess *sess;
+	struct rtrs_clt_path *clt_path;
 	int err;
 
 	if (WARN_ON(!req->in_use))
 		return;
 	if (WARN_ON(!req->con))
 		return;
-	sess = to_clt_sess(con->c.sess);
+	clt_path = to_clt_path(con->c.path);
 
 	if (req->sg_cnt) {
 		if (req->dir == DMA_FROM_DEVICE && req->need_inv) {
@@ -417,7 +417,7 @@ static void complete_rdma_req(struct rtrs_clt_io_req *req, int errno,
 			refcount_inc(&req->ref);
 			err = rtrs_inv_rkey(req);
 			if (err) {
-				rtrs_err(con->c.sess, "Send INV WR key=%#x: %d\n",
+				rtrs_err(con->c.path, "Send INV WR key=%#x: %d\n",
 					  req->mr->rkey, err);
 			} else if (can_wait) {
 				wait_for_completion(&req->inv_comp);
@@ -433,21 +433,21 @@ static void complete_rdma_req(struct rtrs_clt_io_req *req, int errno,
 			if (!refcount_dec_and_test(&req->ref))
 				return;
 		}
-		ib_dma_unmap_sg(sess->s.dev->ib_dev, req->sglist,
+		ib_dma_unmap_sg(clt_path->s.dev->ib_dev, req->sglist,
 				req->sg_cnt, req->dir);
 	}
 	if (!refcount_dec_and_test(&req->ref))
 		return;
 	if (req->mp_policy == MP_POLICY_MIN_INFLIGHT)
-		atomic_dec(&sess->stats->inflight);
+		atomic_dec(&clt_path->stats->inflight);
 
 	req->in_use = false;
 	req->con = NULL;
 
 	if (errno) {
-		rtrs_err_rl(con->c.sess, "IO request failed: error=%d path=%s [%s:%u] notify=%d\n",
-			    errno, kobject_name(&sess->kobj), sess->hca_name,
-			    sess->hca_port, notify);
+		rtrs_err_rl(con->c.path, "IO request failed: error=%d path=%s [%s:%u] notify=%d\n",
+			    errno, kobject_name(&clt_path->kobj), clt_path->hca_name,
+			    clt_path->hca_port, notify);
 	}
 
 	if (notify)
@@ -459,12 +459,12 @@ static int rtrs_post_send_rdma(struct rtrs_clt_con *con,
 				struct rtrs_rbuf *rbuf, u32 off,
 				u32 imm, struct ib_send_wr *wr)
 {
-	struct rtrs_clt_sess *sess = to_clt_sess(con->c.sess);
+	struct rtrs_clt_path *clt_path = to_clt_path(con->c.path);
 	enum ib_send_flags flags;
 	struct ib_sge sge;
 
 	if (!req->sg_size) {
-		rtrs_wrn(con->c.sess,
+		rtrs_wrn(con->c.path,
 			 "Doing RDMA Write failed, no data supplied\n");
 		return -EINVAL;
 	}
@@ -472,16 +472,17 @@ static int rtrs_post_send_rdma(struct rtrs_clt_con *con,
 	/* user data and user message in the first list element */
 	sge.addr   = req->iu->dma_addr;
 	sge.length = req->sg_size;
-	sge.lkey   = sess->s.dev->ib_pd->local_dma_lkey;
+	sge.lkey   = clt_path->s.dev->ib_pd->local_dma_lkey;
 
 	/*
 	 * From time to time we have to post signalled sends,
 	 * or send queue will fill up and only QP reset can help.
 	 */
-	flags = atomic_inc_return(&con->c.wr_cnt) % sess->s.signal_interval ?
+	flags = atomic_inc_return(&con->c.wr_cnt) % clt_path->s.signal_interval ?
 			0 : IB_SEND_SIGNALED;
 
-	ib_dma_sync_single_for_device(sess->s.dev->ib_dev, req->iu->dma_addr,
+	ib_dma_sync_single_for_device(clt_path->s.dev->ib_dev,
+				      req->iu->dma_addr,
 				      req->sg_size, DMA_TO_DEVICE);
 
 	return rtrs_iu_post_rdma_write_imm(&con->c, req->iu, &sge, 1,
@@ -489,15 +490,15 @@ static int rtrs_post_send_rdma(struct rtrs_clt_con *con,
 					    imm, flags, wr, NULL);
 }
 
-static void process_io_rsp(struct rtrs_clt_sess *sess, u32 msg_id,
+static void process_io_rsp(struct rtrs_clt_path *clt_path, u32 msg_id,
 			   s16 errno, bool w_inval)
 {
 	struct rtrs_clt_io_req *req;
 
-	if (WARN_ON(msg_id >= sess->queue_depth))
+	if (WARN_ON(msg_id >= clt_path->queue_depth))
 		return;
 
-	req = &sess->reqs[msg_id];
+	req = &clt_path->reqs[msg_id];
 	/* Drop need_inv if server responded with send with invalidation */
 	req->need_inv &= !w_inval;
 	complete_rdma_req(req, errno, true, false);
@@ -507,21 +508,21 @@ static void rtrs_clt_recv_done(struct rtrs_clt_con *con, struct ib_wc *wc)
 {
 	struct rtrs_iu *iu;
 	int err;
-	struct rtrs_clt_sess *sess = to_clt_sess(con->c.sess);
+	struct rtrs_clt_path *clt_path = to_clt_path(con->c.path);
 
-	WARN_ON((sess->flags & RTRS_MSG_NEW_RKEY_F) == 0);
+	WARN_ON((clt_path->flags & RTRS_MSG_NEW_RKEY_F) == 0);
 	iu = container_of(wc->wr_cqe, struct rtrs_iu,
 			  cqe);
 	err = rtrs_iu_post_recv(&con->c, iu);
 	if (err) {
-		rtrs_err(con->c.sess, "post iu failed %d\n", err);
+		rtrs_err(con->c.path, "post iu failed %d\n", err);
 		rtrs_rdma_error_recovery(con);
 	}
 }
 
 static void rtrs_clt_rkey_rsp_done(struct rtrs_clt_con *con, struct ib_wc *wc)
 {
-	struct rtrs_clt_sess *sess = to_clt_sess(con->c.sess);
+	struct rtrs_clt_path *clt_path = to_clt_path(con->c.path);
 	struct rtrs_msg_rkey_rsp *msg;
 	u32 imm_type, imm_payload;
 	bool w_inval = false;
@@ -529,25 +530,26 @@ static void rtrs_clt_rkey_rsp_done(struct rtrs_clt_con *con, struct ib_wc *wc)
 	u32 buf_id;
 	int err;
 
-	WARN_ON((sess->flags & RTRS_MSG_NEW_RKEY_F) == 0);
+	WARN_ON((clt_path->flags & RTRS_MSG_NEW_RKEY_F) == 0);
 
 	iu = container_of(wc->wr_cqe, struct rtrs_iu, cqe);
 
 	if (wc->byte_len < sizeof(*msg)) {
-		rtrs_err(con->c.sess, "rkey response is malformed: size %d\n",
+		rtrs_err(con->c.path, "rkey response is malformed: size %d\n",
 			  wc->byte_len);
 		goto out;
 	}
-	ib_dma_sync_single_for_cpu(sess->s.dev->ib_dev, iu->dma_addr,
+	ib_dma_sync_single_for_cpu(clt_path->s.dev->ib_dev, iu->dma_addr,
 				   iu->size, DMA_FROM_DEVICE);
 	msg = iu->buf;
 	if (le16_to_cpu(msg->type) != RTRS_MSG_RKEY_RSP) {
-		rtrs_err(sess->clt, "rkey response is malformed: type %d\n",
+		rtrs_err(clt_path->clt,
+			  "rkey response is malformed: type %d\n",
 			  le16_to_cpu(msg->type));
 		goto out;
 	}
 	buf_id = le16_to_cpu(msg->buf_id);
-	if (WARN_ON(buf_id >= sess->queue_depth))
+	if (WARN_ON(buf_id >= clt_path->queue_depth))
 		goto out;
 
 	rtrs_from_imm(be32_to_cpu(wc->ex.imm_data), &imm_type, &imm_payload);
@@ -560,10 +562,10 @@ static void rtrs_clt_rkey_rsp_done(struct rtrs_clt_con *con, struct ib_wc *wc)
 
 		if (WARN_ON(buf_id != msg_id))
 			goto out;
-		sess->rbufs[buf_id].rkey = le32_to_cpu(msg->rkey);
-		process_io_rsp(sess, msg_id, err, w_inval);
+		clt_path->rbufs[buf_id].rkey = le32_to_cpu(msg->rkey);
+		process_io_rsp(clt_path, msg_id, err, w_inval);
 	}
-	ib_dma_sync_single_for_device(sess->s.dev->ib_dev, iu->dma_addr,
+	ib_dma_sync_single_for_device(clt_path->s.dev->ib_dev, iu->dma_addr,
 				      iu->size, DMA_FROM_DEVICE);
 	return rtrs_clt_recv_done(con, wc);
 out:
@@ -600,14 +602,14 @@ static int rtrs_post_recv_empty_x2(struct rtrs_con *con, struct ib_cqe *cqe)
 static void rtrs_clt_rdma_done(struct ib_cq *cq, struct ib_wc *wc)
 {
 	struct rtrs_clt_con *con = to_clt_con(wc->qp->qp_context);
-	struct rtrs_clt_sess *sess = to_clt_sess(con->c.sess);
+	struct rtrs_clt_path *clt_path = to_clt_path(con->c.path);
 	u32 imm_type, imm_payload;
 	bool w_inval = false;
 	int err;
 
 	if (wc->status != IB_WC_SUCCESS) {
 		if (wc->status != IB_WC_WR_FLUSH_ERR) {
-			rtrs_err(sess->clt, "RDMA failed: %s\n",
+			rtrs_err(clt_path->clt, "RDMA failed: %s\n",
 				  ib_wc_status_msg(wc->status));
 			rtrs_rdma_error_recovery(con);
 		}
@@ -632,21 +634,21 @@ static void rtrs_clt_rdma_done(struct ib_cq *cq, struct ib_wc *wc)
 			w_inval = (imm_type == RTRS_IO_RSP_W_INV_IMM);
 			rtrs_from_io_rsp_imm(imm_payload, &msg_id, &err);
 
-			process_io_rsp(sess, msg_id, err, w_inval);
+			process_io_rsp(clt_path, msg_id, err, w_inval);
 		} else if (imm_type == RTRS_HB_MSG_IMM) {
 			WARN_ON(con->c.cid);
-			rtrs_send_hb_ack(&sess->s);
-			if (sess->flags & RTRS_MSG_NEW_RKEY_F)
+			rtrs_send_hb_ack(&clt_path->s);
+			if (clt_path->flags & RTRS_MSG_NEW_RKEY_F)
 				return  rtrs_clt_recv_done(con, wc);
 		} else if (imm_type == RTRS_HB_ACK_IMM) {
 			WARN_ON(con->c.cid);
-			sess->s.hb_missed_cnt = 0;
-			sess->s.hb_cur_latency =
-				ktime_sub(ktime_get(), sess->s.hb_last_sent);
-			if (sess->flags & RTRS_MSG_NEW_RKEY_F)
+			clt_path->s.hb_missed_cnt = 0;
+			clt_path->s.hb_cur_latency =
+				ktime_sub(ktime_get(), clt_path->s.hb_last_sent);
+			if (clt_path->flags & RTRS_MSG_NEW_RKEY_F)
 				return  rtrs_clt_recv_done(con, wc);
 		} else {
-			rtrs_wrn(con->c.sess, "Unknown IMM type %u\n",
+			rtrs_wrn(con->c.path, "Unknown IMM type %u\n",
 				  imm_type);
 		}
 		if (w_inval)
@@ -658,7 +660,7 @@ static void rtrs_clt_rdma_done(struct ib_cq *cq, struct ib_wc *wc)
 		else
 			err = rtrs_post_recv_empty(&con->c, &io_comp_cqe);
 		if (err) {
-			rtrs_err(con->c.sess, "rtrs_post_recv_empty(): %d\n",
+			rtrs_err(con->c.path, "rtrs_post_recv_empty(): %d\n",
 				  err);
 			rtrs_rdma_error_recovery(con);
 		}
@@ -670,7 +672,7 @@ static void rtrs_clt_rdma_done(struct ib_cq *cq, struct ib_wc *wc)
 		WARN_ON(!(wc->wc_flags & IB_WC_WITH_INVALIDATE ||
 			  wc->wc_flags & IB_WC_WITH_IMM));
 		WARN_ON(wc->wr_cqe->done != rtrs_clt_rdma_done);
-		if (sess->flags & RTRS_MSG_NEW_RKEY_F) {
+		if (clt_path->flags & RTRS_MSG_NEW_RKEY_F) {
 			if (wc->wc_flags & IB_WC_WITH_INVALIDATE)
 				return  rtrs_clt_recv_done(con, wc);
 
@@ -685,7 +687,7 @@ static void rtrs_clt_rdma_done(struct ib_cq *cq, struct ib_wc *wc)
 		break;
 
 	default:
-		rtrs_wrn(sess->clt, "Unexpected WC type: %d\n", wc->opcode);
+		rtrs_wrn(clt_path->clt, "Unexpected WC type: %d\n", wc->opcode);
 		return;
 	}
 }
@@ -693,10 +695,10 @@ static void rtrs_clt_rdma_done(struct ib_cq *cq, struct ib_wc *wc)
 static int post_recv_io(struct rtrs_clt_con *con, size_t q_size)
 {
 	int err, i;
-	struct rtrs_clt_sess *sess = to_clt_sess(con->c.sess);
+	struct rtrs_clt_path *clt_path = to_clt_path(con->c.path);
 
 	for (i = 0; i < q_size; i++) {
-		if (sess->flags & RTRS_MSG_NEW_RKEY_F) {
+		if (clt_path->flags & RTRS_MSG_NEW_RKEY_F) {
 			struct rtrs_iu *iu = &con->rsp_ius[i];
 
 			err = rtrs_iu_post_recv(&con->c, iu);
@@ -710,16 +712,16 @@ static int post_recv_io(struct rtrs_clt_con *con, size_t q_size)
 	return 0;
 }
 
-static int post_recv_sess(struct rtrs_clt_sess *sess)
+static int post_recv_path(struct rtrs_clt_path *clt_path)
 {
 	size_t q_size = 0;
 	int err, cid;
 
-	for (cid = 0; cid < sess->s.con_num; cid++) {
+	for (cid = 0; cid < clt_path->s.con_num; cid++) {
 		if (cid == 0)
 			q_size = SERVICE_CON_QUEUE_DEPTH;
 		else
-			q_size = sess->queue_depth;
+			q_size = clt_path->queue_depth;
 
 		/*
 		 * x2 for RDMA read responses + FR key invalidations,
@@ -727,9 +729,10 @@ static int post_recv_sess(struct rtrs_clt_sess *sess)
 		 */
 		q_size *= 2;
 
-		err = post_recv_io(to_clt_con(sess->s.con[cid]), q_size);
+		err = post_recv_io(to_clt_con(clt_path->s.con[cid]), q_size);
 		if (err) {
-			rtrs_err(sess->clt, "post_recv_io(), err: %d\n", err);
+			rtrs_err(clt_path->clt, "post_recv_io(), err: %d\n",
+				 err);
 			return err;
 		}
 	}
@@ -741,28 +744,28 @@ struct path_it {
 	int i;
 	struct list_head skip_list;
 	struct rtrs_clt *clt;
-	struct rtrs_clt_sess *(*next_path)(struct path_it *it);
+	struct rtrs_clt_path *(*next_path)(struct path_it *it);
 };
 
-/**
- * list_next_or_null_rr_rcu - get next list element in round-robin fashion.
+/*
+ * rtrs_clt_get_next_path_or_null - get clt path from the list or return NULL
  * @head:	the head for the list.
- * @ptr:        the list head to take the next element from.
- * @type:       the type of the struct this is embedded in.
- * @memb:       the name of the list_head within the struct.
+ * @clt_path:	The element to take the next clt_path from.
  *
- * Next element returned in round-robin fashion, i.e. head will be skipped,
+ * Next clt path returned in round-robin fashion, i.e. head will be skipped,
  * but if list is observed as empty, NULL will be returned.
  *
- * This primitive may safely run concurrently with the _rcu list-mutation
+ * This function may safely run concurrently with the _rcu list-mutation
  * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock().
  */
-#define list_next_or_null_rr_rcu(head, ptr, type, memb) \
-({ \
-	list_next_or_null_rcu(head, ptr, type, memb) ?: \
-		list_next_or_null_rcu(head, READ_ONCE((ptr)->next), \
-				      type, memb); \
-})
+static inline struct rtrs_clt_path *
+rtrs_clt_get_next_path_or_null(struct list_head *head, struct rtrs_clt_path *clt_path)
+{
+	return list_next_or_null_rcu(head, &clt_path->s.entry, typeof(*clt_path), s.entry) ?:
+				     list_next_or_null_rcu(head,
+							   READ_ONCE((&clt_path->s.entry)->next),
+							   typeof(*clt_path), s.entry);
+}
 
 /**
  * get_next_path_rr() - Returns path in round-robin fashion.
@@ -773,10 +776,10 @@ struct path_it {
  * Locks:
  *    rcu_read_lock() must be hold.
  */
-static struct rtrs_clt_sess *get_next_path_rr(struct path_it *it)
+static struct rtrs_clt_path *get_next_path_rr(struct path_it *it)
 {
-	struct rtrs_clt_sess __rcu **ppcpu_path;
-	struct rtrs_clt_sess *path;
+	struct rtrs_clt_path __rcu **ppcpu_path;
+	struct rtrs_clt_path *path;
 	struct rtrs_clt *clt;
 
 	clt = it->clt;
@@ -793,10 +796,8 @@ static struct rtrs_clt_sess *get_next_path_rr(struct path_it *it)
 		path = list_first_or_null_rcu(&clt->paths_list,
 					      typeof(*path), s.entry);
 	else
-		path = list_next_or_null_rr_rcu(&clt->paths_list,
-						&path->s.entry,
-						typeof(*path),
-						s.entry);
+		path = rtrs_clt_get_next_path_or_null(&clt->paths_list, path);
+
 	rcu_assign_pointer(*ppcpu_path, path);
 
 	return path;
@@ -811,26 +812,26 @@ static struct rtrs_clt_sess *get_next_path_rr(struct path_it *it)
  * Locks:
  *    rcu_read_lock() must be hold.
  */
-static struct rtrs_clt_sess *get_next_path_min_inflight(struct path_it *it)
+static struct rtrs_clt_path *get_next_path_min_inflight(struct path_it *it)
 {
-	struct rtrs_clt_sess *min_path = NULL;
+	struct rtrs_clt_path *min_path = NULL;
 	struct rtrs_clt *clt = it->clt;
-	struct rtrs_clt_sess *sess;
+	struct rtrs_clt_path *clt_path;
 	int min_inflight = INT_MAX;
 	int inflight;
 
-	list_for_each_entry_rcu(sess, &clt->paths_list, s.entry) {
-		if (READ_ONCE(sess->state) != RTRS_CLT_CONNECTED)
+	list_for_each_entry_rcu(clt_path, &clt->paths_list, s.entry) {
+		if (READ_ONCE(clt_path->state) != RTRS_CLT_CONNECTED)
 			continue;
 
-		if (!list_empty(raw_cpu_ptr(sess->mp_skip_entry)))
+		if (!list_empty(raw_cpu_ptr(clt_path->mp_skip_entry)))
 			continue;
 
-		inflight = atomic_read(&sess->stats->inflight);
+		inflight = atomic_read(&clt_path->stats->inflight);
 
 		if (inflight < min_inflight) {
 			min_inflight = inflight;
-			min_path = sess;
+			min_path = clt_path;
 		}
 	}
 
@@ -862,26 +863,26 @@ static struct rtrs_clt_sess *get_next_path_min_inflight(struct path_it *it)
  * Therefore the caller MUST check the returned
  * path is NULL and trigger the IO error.
  */
-static struct rtrs_clt_sess *get_next_path_min_latency(struct path_it *it)
+static struct rtrs_clt_path *get_next_path_min_latency(struct path_it *it)
 {
-	struct rtrs_clt_sess *min_path = NULL;
+	struct rtrs_clt_path *min_path = NULL;
 	struct rtrs_clt *clt = it->clt;
-	struct rtrs_clt_sess *sess;
+	struct rtrs_clt_path *clt_path;
 	ktime_t min_latency = KTIME_MAX;
 	ktime_t latency;
 
-	list_for_each_entry_rcu(sess, &clt->paths_list, s.entry) {
-		if (READ_ONCE(sess->state) != RTRS_CLT_CONNECTED)
+	list_for_each_entry_rcu(clt_path, &clt->paths_list, s.entry) {
+		if (READ_ONCE(clt_path->state) != RTRS_CLT_CONNECTED)
 			continue;
 
-		if (!list_empty(raw_cpu_ptr(sess->mp_skip_entry)))
+		if (!list_empty(raw_cpu_ptr(clt_path->mp_skip_entry)))
 			continue;
 
-		latency = sess->s.hb_cur_latency;
+		latency = clt_path->s.hb_cur_latency;
 
 		if (latency < min_latency) {
 			min_latency = latency;
-			min_path = sess;
+			min_path = clt_path;
 		}
 	}
 
@@ -928,7 +929,7 @@ static inline void path_it_deinit(struct path_it *it)
  * the corresponding buffer of rtrs_iu (req->iu->buf), which later on will
  * also hold the control message of rtrs.
  * @req: an io request holding information about IO.
- * @sess: client session
+ * @clt_path: client path
  * @conf: conformation callback function to notify upper layer.
  * @permit: permit for allocation of RDMA remote buffer
  * @priv: private pointer
@@ -940,7 +941,7 @@ static inline void path_it_deinit(struct path_it *it)
  * @dir: direction of the IO.
  */
 static void rtrs_clt_init_req(struct rtrs_clt_io_req *req,
-			      struct rtrs_clt_sess *sess,
+			      struct rtrs_clt_path *clt_path,
 			      void (*conf)(void *priv, int errno),
 			      struct rtrs_permit *permit, void *priv,
 			      const struct kvec *vec, size_t usr_len,
@@ -958,13 +959,13 @@ static void rtrs_clt_init_req(struct rtrs_clt_io_req *req,
 	req->sg_cnt = sg_cnt;
 	req->priv = priv;
 	req->dir = dir;
-	req->con = rtrs_permit_to_clt_con(sess, permit);
+	req->con = rtrs_permit_to_clt_con(clt_path, permit);
 	req->conf = conf;
 	req->need_inv = false;
 	req->need_inv_comp = false;
 	req->inv_errno = 0;
 	refcount_set(&req->ref, 1);
-	req->mp_policy = sess->clt->mp_policy;
+	req->mp_policy = clt_path->clt->mp_policy;
 
 	iov_iter_kvec(&iter, READ, vec, 1, usr_len);
 	len = _copy_from_iter(req->iu->buf, usr_len, &iter);
@@ -974,7 +975,7 @@ static void rtrs_clt_init_req(struct rtrs_clt_io_req *req,
 }
 
 static struct rtrs_clt_io_req *
-rtrs_clt_get_req(struct rtrs_clt_sess *sess,
+rtrs_clt_get_req(struct rtrs_clt_path *clt_path,
 		 void (*conf)(void *priv, int errno),
 		 struct rtrs_permit *permit, void *priv,
 		 const struct kvec *vec, size_t usr_len,
@@ -983,14 +984,14 @@ rtrs_clt_get_req(struct rtrs_clt_sess *sess,
 {
 	struct rtrs_clt_io_req *req;
 
-	req = &sess->reqs[permit->mem_id];
-	rtrs_clt_init_req(req, sess, conf, permit, priv, vec, usr_len,
+	req = &clt_path->reqs[permit->mem_id];
+	rtrs_clt_init_req(req, clt_path, conf, permit, priv, vec, usr_len,
 			   sg, sg_cnt, data_len, dir);
 	return req;
 }
 
 static struct rtrs_clt_io_req *
-rtrs_clt_get_copy_req(struct rtrs_clt_sess *alive_sess,
+rtrs_clt_get_copy_req(struct rtrs_clt_path *alive_path,
 		       struct rtrs_clt_io_req *fail_req)
 {
 	struct rtrs_clt_io_req *req;
@@ -999,8 +1000,8 @@ rtrs_clt_get_copy_req(struct rtrs_clt_sess *alive_sess,
 		.iov_len  = fail_req->usr_len
 	};
 
-	req = &alive_sess->reqs[fail_req->permit->mem_id];
-	rtrs_clt_init_req(req, alive_sess, fail_req->conf, fail_req->permit,
+	req = &alive_path->reqs[fail_req->permit->mem_id];
+	rtrs_clt_init_req(req, alive_path, fail_req->conf, fail_req->permit,
 			   fail_req->priv, &vec, fail_req->usr_len,
 			   fail_req->sglist, fail_req->sg_cnt,
 			   fail_req->data_len, fail_req->dir);
@@ -1010,10 +1011,11 @@ rtrs_clt_get_copy_req(struct rtrs_clt_sess *alive_sess,
 static int rtrs_post_rdma_write_sg(struct rtrs_clt_con *con,
 				   struct rtrs_clt_io_req *req,
 				   struct rtrs_rbuf *rbuf, bool fr_en,
-				   u32 size, u32 imm, struct ib_send_wr *wr,
+				   u32 count, u32 size, u32 imm,
+				   struct ib_send_wr *wr,
 				   struct ib_send_wr *tail)
 {
-	struct rtrs_clt_sess *sess = to_clt_sess(con->c.sess);
+	struct rtrs_clt_path *clt_path = to_clt_path(con->c.path);
 	struct ib_sge *sge = req->sge;
 	enum ib_send_flags flags;
 	struct scatterlist *sg;
@@ -1030,25 +1032,26 @@ static int rtrs_post_rdma_write_sg(struct rtrs_clt_con *con,
 		num_sge = 2;
 		ptail = tail;
 	} else {
-		for_each_sg(req->sglist, sg, req->sg_cnt, i) {
+		for_each_sg(req->sglist, sg, count, i) {
 			sge[i].addr   = sg_dma_address(sg);
 			sge[i].length = sg_dma_len(sg);
-			sge[i].lkey   = sess->s.dev->ib_pd->local_dma_lkey;
+			sge[i].lkey   = clt_path->s.dev->ib_pd->local_dma_lkey;
 		}
-		num_sge = 1 + req->sg_cnt;
+		num_sge = 1 + count;
 	}
 	sge[i].addr   = req->iu->dma_addr;
 	sge[i].length = size;
-	sge[i].lkey   = sess->s.dev->ib_pd->local_dma_lkey;
+	sge[i].lkey   = clt_path->s.dev->ib_pd->local_dma_lkey;
 
 	/*
 	 * From time to time we have to post signalled sends,
 	 * or send queue will fill up and only QP reset can help.
 	 */
-	flags = atomic_inc_return(&con->c.wr_cnt) % sess->s.signal_interval ?
+	flags = atomic_inc_return(&con->c.wr_cnt) % clt_path->s.signal_interval ?
 			0 : IB_SEND_SIGNALED;
 
-	ib_dma_sync_single_for_device(sess->s.dev->ib_dev, req->iu->dma_addr,
+	ib_dma_sync_single_for_device(clt_path->s.dev->ib_dev,
+				      req->iu->dma_addr,
 				      size, DMA_TO_DEVICE);
 
 	return rtrs_iu_post_rdma_write_imm(&con->c, req->iu, sge, num_sge,
@@ -1074,8 +1077,8 @@ static int rtrs_map_sg_fr(struct rtrs_clt_io_req *req, size_t count)
 static int rtrs_clt_write_req(struct rtrs_clt_io_req *req)
 {
 	struct rtrs_clt_con *con = req->con;
-	struct rtrs_sess *s = con->c.sess;
-	struct rtrs_clt_sess *sess = to_clt_sess(s);
+	struct rtrs_path *s = con->c.path;
+	struct rtrs_clt_path *clt_path = to_clt_path(s);
 	struct rtrs_msg_rdma_write *msg;
 
 	struct rtrs_rbuf *rbuf;
@@ -1088,13 +1091,13 @@ static int rtrs_clt_write_req(struct rtrs_clt_io_req *req)
 
 	const size_t tsize = sizeof(*msg) + req->data_len + req->usr_len;
 
-	if (tsize > sess->chunk_size) {
+	if (tsize > clt_path->chunk_size) {
 		rtrs_wrn(s, "Write request failed, size too big %zu > %d\n",
-			  tsize, sess->chunk_size);
+			  tsize, clt_path->chunk_size);
 		return -EMSGSIZE;
 	}
 	if (req->sg_cnt) {
-		count = ib_dma_map_sg(sess->s.dev->ib_dev, req->sglist,
+		count = ib_dma_map_sg(clt_path->s.dev->ib_dev, req->sglist,
 				      req->sg_cnt, req->dir);
 		if (!count) {
 			rtrs_wrn(s, "Write request failed, map failed\n");
@@ -1111,7 +1114,7 @@ static int rtrs_clt_write_req(struct rtrs_clt_io_req *req)
 	imm = rtrs_to_io_req_imm(imm);
 	buf_id = req->permit->mem_id;
 	req->sg_size = tsize;
-	rbuf = &sess->rbufs[buf_id];
+	rbuf = &clt_path->rbufs[buf_id];
 
 	if (count) {
 		ret = rtrs_map_sg_fr(req, count);
@@ -1119,7 +1122,7 @@ static int rtrs_clt_write_req(struct rtrs_clt_io_req *req)
 			rtrs_err_rl(s,
 				    "Write request failed, failed to map fast reg. data, err: %d\n",
 				    ret);
-			ib_dma_unmap_sg(sess->s.dev->ib_dev, req->sglist,
+			ib_dma_unmap_sg(clt_path->s.dev->ib_dev, req->sglist,
 					req->sg_cnt, req->dir);
 			return ret;
 		}
@@ -1147,18 +1150,18 @@ static int rtrs_clt_write_req(struct rtrs_clt_io_req *req)
 	 */
 	rtrs_clt_update_all_stats(req, WRITE);
 
-	ret = rtrs_post_rdma_write_sg(req->con, req, rbuf, fr_en,
+	ret = rtrs_post_rdma_write_sg(req->con, req, rbuf, fr_en, count,
 				      req->usr_len + sizeof(*msg),
 				      imm, wr, &inv_wr);
 	if (ret) {
 		rtrs_err_rl(s,
 			    "Write request failed: error=%d path=%s [%s:%u]\n",
-			    ret, kobject_name(&sess->kobj), sess->hca_name,
-			    sess->hca_port);
+			    ret, kobject_name(&clt_path->kobj), clt_path->hca_name,
+			    clt_path->hca_port);
 		if (req->mp_policy == MP_POLICY_MIN_INFLIGHT)
-			atomic_dec(&sess->stats->inflight);
+			atomic_dec(&clt_path->stats->inflight);
 		if (req->sg_cnt)
-			ib_dma_unmap_sg(sess->s.dev->ib_dev, req->sglist,
+			ib_dma_unmap_sg(clt_path->s.dev->ib_dev, req->sglist,
 					req->sg_cnt, req->dir);
 	}
 
@@ -1168,10 +1171,10 @@ static int rtrs_clt_write_req(struct rtrs_clt_io_req *req)
 static int rtrs_clt_read_req(struct rtrs_clt_io_req *req)
 {
 	struct rtrs_clt_con *con = req->con;
-	struct rtrs_sess *s = con->c.sess;
-	struct rtrs_clt_sess *sess = to_clt_sess(s);
+	struct rtrs_path *s = con->c.path;
+	struct rtrs_clt_path *clt_path = to_clt_path(s);
 	struct rtrs_msg_rdma_read *msg;
-	struct rtrs_ib_dev *dev = sess->s.dev;
+	struct rtrs_ib_dev *dev = clt_path->s.dev;
 
 	struct ib_reg_wr rwr;
 	struct ib_send_wr *wr = NULL;
@@ -1181,10 +1184,10 @@ static int rtrs_clt_read_req(struct rtrs_clt_io_req *req)
 
 	const size_t tsize = sizeof(*msg) + req->data_len + req->usr_len;
 
-	if (tsize > sess->chunk_size) {
+	if (tsize > clt_path->chunk_size) {
 		rtrs_wrn(s,
 			  "Read request failed, message size is %zu, bigger than CHUNK_SIZE %d\n",
-			  tsize, sess->chunk_size);
+			  tsize, clt_path->chunk_size);
 		return -EMSGSIZE;
 	}
 
@@ -1254,15 +1257,15 @@ static int rtrs_clt_read_req(struct rtrs_clt_io_req *req)
 	 */
 	rtrs_clt_update_all_stats(req, READ);
 
-	ret = rtrs_post_send_rdma(req->con, req, &sess->rbufs[buf_id],
+	ret = rtrs_post_send_rdma(req->con, req, &clt_path->rbufs[buf_id],
 				   req->data_len, imm, wr);
 	if (ret) {
 		rtrs_err_rl(s,
 			    "Read request failed: error=%d path=%s [%s:%u]\n",
-			    ret, kobject_name(&sess->kobj), sess->hca_name,
-			    sess->hca_port);
+			    ret, kobject_name(&clt_path->kobj), clt_path->hca_name,
+			    clt_path->hca_port);
 		if (req->mp_policy == MP_POLICY_MIN_INFLIGHT)
-			atomic_dec(&sess->stats->inflight);
+			atomic_dec(&clt_path->stats->inflight);
 		req->need_inv = false;
 		if (req->sg_cnt)
 			ib_dma_unmap_sg(dev->ib_dev, req->sglist,
@@ -1280,18 +1283,18 @@ static int rtrs_clt_read_req(struct rtrs_clt_io_req *req)
 static int rtrs_clt_failover_req(struct rtrs_clt *clt,
 				 struct rtrs_clt_io_req *fail_req)
 {
-	struct rtrs_clt_sess *alive_sess;
+	struct rtrs_clt_path *alive_path;
 	struct rtrs_clt_io_req *req;
 	int err = -ECONNABORTED;
 	struct path_it it;
 
 	rcu_read_lock();
 	for (path_it_init(&it, clt);
-	     (alive_sess = it.next_path(&it)) && it.i < it.clt->paths_num;
+	     (alive_path = it.next_path(&it)) && it.i < it.clt->paths_num;
 	     it.i++) {
-		if (READ_ONCE(alive_sess->state) != RTRS_CLT_CONNECTED)
+		if (READ_ONCE(alive_path->state) != RTRS_CLT_CONNECTED)
 			continue;
-		req = rtrs_clt_get_copy_req(alive_sess, fail_req);
+		req = rtrs_clt_get_copy_req(alive_path, fail_req);
 		if (req->dir == DMA_TO_DEVICE)
 			err = rtrs_clt_write_req(req);
 		else
@@ -1301,7 +1304,7 @@ static int rtrs_clt_failover_req(struct rtrs_clt *clt,
 			continue;
 		}
 		/* Success path */
-		rtrs_clt_inc_failover_cnt(alive_sess->stats);
+		rtrs_clt_inc_failover_cnt(alive_path->stats);
 		break;
 	}
 	path_it_deinit(&it);
@@ -1310,16 +1313,16 @@ static int rtrs_clt_failover_req(struct rtrs_clt *clt,
 	return err;
 }
 
-static void fail_all_outstanding_reqs(struct rtrs_clt_sess *sess)
+static void fail_all_outstanding_reqs(struct rtrs_clt_path *clt_path)
 {
-	struct rtrs_clt *clt = sess->clt;
+	struct rtrs_clt *clt = clt_path->clt;
 	struct rtrs_clt_io_req *req;
 	int i, err;
 
-	if (!sess->reqs)
+	if (!clt_path->reqs)
 		return;
-	for (i = 0; i < sess->queue_depth; ++i) {
-		req = &sess->reqs[i];
+	for (i = 0; i < clt_path->queue_depth; ++i) {
+		req = &clt_path->reqs[i];
 		if (!req->in_use)
 			continue;
 
@@ -1337,38 +1340,39 @@ static void fail_all_outstanding_reqs(struct rtrs_clt_sess *sess)
 	}
 }
 
-static void free_sess_reqs(struct rtrs_clt_sess *sess)
+static void free_path_reqs(struct rtrs_clt_path *clt_path)
 {
 	struct rtrs_clt_io_req *req;
 	int i;
 
-	if (!sess->reqs)
+	if (!clt_path->reqs)
 		return;
-	for (i = 0; i < sess->queue_depth; ++i) {
-		req = &sess->reqs[i];
+	for (i = 0; i < clt_path->queue_depth; ++i) {
+		req = &clt_path->reqs[i];
 		if (req->mr)
 			ib_dereg_mr(req->mr);
 		kfree(req->sge);
-		rtrs_iu_free(req->iu, sess->s.dev->ib_dev, 1);
+		rtrs_iu_free(req->iu, clt_path->s.dev->ib_dev, 1);
 	}
-	kfree(sess->reqs);
-	sess->reqs = NULL;
+	kfree(clt_path->reqs);
+	clt_path->reqs = NULL;
 }
 
-static int alloc_sess_reqs(struct rtrs_clt_sess *sess)
+static int alloc_path_reqs(struct rtrs_clt_path *clt_path)
 {
 	struct rtrs_clt_io_req *req;
 	int i, err = -ENOMEM;
 
-	sess->reqs = kcalloc(sess->queue_depth, sizeof(*sess->reqs),
-			     GFP_KERNEL);
-	if (!sess->reqs)
+	clt_path->reqs = kcalloc(clt_path->queue_depth,
+				 sizeof(*clt_path->reqs),
+				 GFP_KERNEL);
+	if (!clt_path->reqs)
 		return -ENOMEM;
 
-	for (i = 0; i < sess->queue_depth; ++i) {
-		req = &sess->reqs[i];
-		req->iu = rtrs_iu_alloc(1, sess->max_hdr_size, GFP_KERNEL,
-					 sess->s.dev->ib_dev,
+	for (i = 0; i < clt_path->queue_depth; ++i) {
+		req = &clt_path->reqs[i];
+		req->iu = rtrs_iu_alloc(1, clt_path->max_hdr_size, GFP_KERNEL,
+					 clt_path->s.dev->ib_dev,
 					 DMA_TO_DEVICE,
 					 rtrs_clt_rdma_done);
 		if (!req->iu)
@@ -1378,13 +1382,14 @@ static int alloc_sess_reqs(struct rtrs_clt_sess *sess)
 		if (!req->sge)
 			goto out;
 
-		req->mr = ib_alloc_mr(sess->s.dev->ib_pd, IB_MR_TYPE_MEM_REG,
-				      sess->max_pages_per_mr);
+		req->mr = ib_alloc_mr(clt_path->s.dev->ib_pd,
+				      IB_MR_TYPE_MEM_REG,
+				      clt_path->max_pages_per_mr);
 		if (IS_ERR(req->mr)) {
 			err = PTR_ERR(req->mr);
 			req->mr = NULL;
-			pr_err("Failed to alloc sess->max_pages_per_mr %d\n",
-			       sess->max_pages_per_mr);
+			pr_err("Failed to alloc clt_path->max_pages_per_mr %d\n",
+			       clt_path->max_pages_per_mr);
 			goto out;
 		}
 
@@ -1394,7 +1399,7 @@ static int alloc_sess_reqs(struct rtrs_clt_sess *sess)
 	return 0;
 
 out:
-	free_sess_reqs(sess);
+	free_path_reqs(clt_path);
 
 	return err;
 }
@@ -1447,13 +1452,13 @@ static void free_permits(struct rtrs_clt *clt)
 	clt->permits = NULL;
 }
 
-static void query_fast_reg_mode(struct rtrs_clt_sess *sess)
+static void query_fast_reg_mode(struct rtrs_clt_path *clt_path)
 {
 	struct ib_device *ib_dev;
 	u64 max_pages_per_mr;
 	int mr_page_shift;
 
-	ib_dev = sess->s.dev->ib_dev;
+	ib_dev = clt_path->s.dev->ib_dev;
 
 	/*
 	 * Use the smallest page size supported by the HCA, down to a
@@ -1463,24 +1468,24 @@ static void query_fast_reg_mode(struct rtrs_clt_sess *sess)
 	mr_page_shift      = max(12, ffs(ib_dev->attrs.page_size_cap) - 1);
 	max_pages_per_mr   = ib_dev->attrs.max_mr_size;
 	do_div(max_pages_per_mr, (1ull << mr_page_shift));
-	sess->max_pages_per_mr =
-		min3(sess->max_pages_per_mr, (u32)max_pages_per_mr,
+	clt_path->max_pages_per_mr =
+		min3(clt_path->max_pages_per_mr, (u32)max_pages_per_mr,
 		     ib_dev->attrs.max_fast_reg_page_list_len);
-	sess->clt->max_segments =
-		min(sess->max_pages_per_mr, sess->clt->max_segments);
+	clt_path->clt->max_segments =
+		min(clt_path->max_pages_per_mr, clt_path->clt->max_segments);
 }
 
-static bool rtrs_clt_change_state_get_old(struct rtrs_clt_sess *sess,
+static bool rtrs_clt_change_state_get_old(struct rtrs_clt_path *clt_path,
 					   enum rtrs_clt_state new_state,
 					   enum rtrs_clt_state *old_state)
 {
 	bool changed;
 
-	spin_lock_irq(&sess->state_wq.lock);
+	spin_lock_irq(&clt_path->state_wq.lock);
 	if (old_state)
-		*old_state = sess->state;
-	changed = rtrs_clt_change_state(sess, new_state);
-	spin_unlock_irq(&sess->state_wq.lock);
+		*old_state = clt_path->state;
+	changed = rtrs_clt_change_state(clt_path, new_state);
+	spin_unlock_irq(&clt_path->state_wq.lock);
 
 	return changed;
 }
@@ -1492,9 +1497,9 @@ static void rtrs_clt_hb_err_handler(struct rtrs_con *c)
 	rtrs_rdma_error_recovery(con);
 }
 
-static void rtrs_clt_init_hb(struct rtrs_clt_sess *sess)
+static void rtrs_clt_init_hb(struct rtrs_clt_path *clt_path)
 {
-	rtrs_init_hb(&sess->s, &io_comp_cqe,
+	rtrs_init_hb(&clt_path->s, &io_comp_cqe,
 		      RTRS_HB_INTERVAL_MS,
 		      RTRS_HB_MISSED_MAX,
 		      rtrs_clt_hb_err_handler,
@@ -1504,17 +1509,17 @@ static void rtrs_clt_init_hb(struct rtrs_clt_sess *sess)
 static void rtrs_clt_reconnect_work(struct work_struct *work);
 static void rtrs_clt_close_work(struct work_struct *work);
 
-static struct rtrs_clt_sess *alloc_sess(struct rtrs_clt *clt,
+static struct rtrs_clt_path *alloc_path(struct rtrs_clt *clt,
 					const struct rtrs_addr *path,
 					size_t con_num, u32 nr_poll_queues)
 {
-	struct rtrs_clt_sess *sess;
+	struct rtrs_clt_path *clt_path;
 	int err = -ENOMEM;
 	int cpu;
 	size_t total_con;
 
-	sess = kzalloc(sizeof(*sess), GFP_KERNEL);
-	if (!sess)
+	clt_path = kzalloc(sizeof(*clt_path), GFP_KERNEL);
+	if (!clt_path)
 		goto err;
 
 	/*
@@ -1522,20 +1527,21 @@ static struct rtrs_clt_sess *alloc_sess(struct rtrs_clt *clt,
 	 * +1: Extra connection for user messages
 	 */
 	total_con = con_num + nr_poll_queues + 1;
-	sess->s.con = kcalloc(total_con, sizeof(*sess->s.con), GFP_KERNEL);
-	if (!sess->s.con)
-		goto err_free_sess;
+	clt_path->s.con = kcalloc(total_con, sizeof(*clt_path->s.con),
+				  GFP_KERNEL);
+	if (!clt_path->s.con)
+		goto err_free_path;
 
-	sess->s.con_num = total_con;
-	sess->s.irq_con_num = con_num + 1;
+	clt_path->s.con_num = total_con;
+	clt_path->s.irq_con_num = con_num + 1;
 
-	sess->stats = kzalloc(sizeof(*sess->stats), GFP_KERNEL);
-	if (!sess->stats)
+	clt_path->stats = kzalloc(sizeof(*clt_path->stats), GFP_KERNEL);
+	if (!clt_path->stats)
 		goto err_free_con;
 
-	mutex_init(&sess->init_mutex);
-	uuid_gen(&sess->s.uuid);
-	memcpy(&sess->s.dst_addr, path->dst,
+	mutex_init(&clt_path->init_mutex);
+	uuid_gen(&clt_path->s.uuid);
+	memcpy(&clt_path->s.dst_addr, path->dst,
 	       rdma_addr_size((struct sockaddr *)path->dst));
 
 	/*
@@ -1544,53 +1550,54 @@ static struct rtrs_clt_sess *alloc_sess(struct rtrs_clt *clt,
 	 * the sess->src_addr will contain only zeros, which is then fine.
 	 */
 	if (path->src)
-		memcpy(&sess->s.src_addr, path->src,
+		memcpy(&clt_path->s.src_addr, path->src,
 		       rdma_addr_size((struct sockaddr *)path->src));
-	strscpy(sess->s.sessname, clt->sessname, sizeof(sess->s.sessname));
-	sess->clt = clt;
-	sess->max_pages_per_mr = RTRS_MAX_SEGMENTS;
-	init_waitqueue_head(&sess->state_wq);
-	sess->state = RTRS_CLT_CONNECTING;
-	atomic_set(&sess->connected_cnt, 0);
-	INIT_WORK(&sess->close_work, rtrs_clt_close_work);
-	INIT_DELAYED_WORK(&sess->reconnect_dwork, rtrs_clt_reconnect_work);
-	rtrs_clt_init_hb(sess);
-
-	sess->mp_skip_entry = alloc_percpu(typeof(*sess->mp_skip_entry));
-	if (!sess->mp_skip_entry)
+	strscpy(clt_path->s.sessname, clt->sessname,
+		sizeof(clt_path->s.sessname));
+	clt_path->clt = clt;
+	clt_path->max_pages_per_mr = RTRS_MAX_SEGMENTS;
+	init_waitqueue_head(&clt_path->state_wq);
+	clt_path->state = RTRS_CLT_CONNECTING;
+	atomic_set(&clt_path->connected_cnt, 0);
+	INIT_WORK(&clt_path->close_work, rtrs_clt_close_work);
+	INIT_DELAYED_WORK(&clt_path->reconnect_dwork, rtrs_clt_reconnect_work);
+	rtrs_clt_init_hb(clt_path);
+
+	clt_path->mp_skip_entry = alloc_percpu(typeof(*clt_path->mp_skip_entry));
+	if (!clt_path->mp_skip_entry)
 		goto err_free_stats;
 
 	for_each_possible_cpu(cpu)
-		INIT_LIST_HEAD(per_cpu_ptr(sess->mp_skip_entry, cpu));
+		INIT_LIST_HEAD(per_cpu_ptr(clt_path->mp_skip_entry, cpu));
 
-	err = rtrs_clt_init_stats(sess->stats);
+	err = rtrs_clt_init_stats(clt_path->stats);
 	if (err)
 		goto err_free_percpu;
 
-	return sess;
+	return clt_path;
 
 err_free_percpu:
-	free_percpu(sess->mp_skip_entry);
+	free_percpu(clt_path->mp_skip_entry);
 err_free_stats:
-	kfree(sess->stats);
+	kfree(clt_path->stats);
 err_free_con:
-	kfree(sess->s.con);
-err_free_sess:
-	kfree(sess);
+	kfree(clt_path->s.con);
+err_free_path:
+	kfree(clt_path);
 err:
 	return ERR_PTR(err);
 }
 
-void free_sess(struct rtrs_clt_sess *sess)
+void free_path(struct rtrs_clt_path *clt_path)
 {
-	free_percpu(sess->mp_skip_entry);
-	mutex_destroy(&sess->init_mutex);
-	kfree(sess->s.con);
-	kfree(sess->rbufs);
-	kfree(sess);
+	free_percpu(clt_path->mp_skip_entry);
+	mutex_destroy(&clt_path->init_mutex);
+	kfree(clt_path->s.con);
+	kfree(clt_path->rbufs);
+	kfree(clt_path);
 }
 
-static int create_con(struct rtrs_clt_sess *sess, unsigned int cid)
+static int create_con(struct rtrs_clt_path *clt_path, unsigned int cid)
 {
 	struct rtrs_clt_con *con;
 
@@ -1601,28 +1608,28 @@ static int create_con(struct rtrs_clt_sess *sess, unsigned int cid)
 	/* Map first two connections to the first CPU */
 	con->cpu  = (cid ? cid - 1 : 0) % nr_cpu_ids;
 	con->c.cid = cid;
-	con->c.sess = &sess->s;
+	con->c.path = &clt_path->s;
 	/* Align with srv, init as 1 */
 	atomic_set(&con->c.wr_cnt, 1);
 	mutex_init(&con->con_mutex);
 
-	sess->s.con[cid] = &con->c;
+	clt_path->s.con[cid] = &con->c;
 
 	return 0;
 }
 
 static void destroy_con(struct rtrs_clt_con *con)
 {
-	struct rtrs_clt_sess *sess = to_clt_sess(con->c.sess);
+	struct rtrs_clt_path *clt_path = to_clt_path(con->c.path);
 
-	sess->s.con[con->c.cid] = NULL;
+	clt_path->s.con[con->c.cid] = NULL;
 	mutex_destroy(&con->con_mutex);
 	kfree(con);
 }
 
 static int create_con_cq_qp(struct rtrs_clt_con *con)
 {
-	struct rtrs_clt_sess *sess = to_clt_sess(con->c.sess);
+	struct rtrs_clt_path *clt_path = to_clt_path(con->c.path);
 	u32 max_send_wr, max_recv_wr, cq_num, max_send_sge, wr_limit;
 	int err, cq_vector;
 	struct rtrs_msg_rkey_rsp *rsp;
@@ -1631,7 +1638,7 @@ static int create_con_cq_qp(struct rtrs_clt_con *con)
 	if (con->c.cid == 0) {
 		max_send_sge = 1;
 		/* We must be the first here */
-		if (WARN_ON(sess->s.dev))
+		if (WARN_ON(clt_path->s.dev))
 			return -EINVAL;
 
 		/*
@@ -1639,16 +1646,16 @@ static int create_con_cq_qp(struct rtrs_clt_con *con)
 		 * Be careful not to close user connection before ib dev
 		 * is gracefully put.
 		 */
-		sess->s.dev = rtrs_ib_dev_find_or_add(con->c.cm_id->device,
+		clt_path->s.dev = rtrs_ib_dev_find_or_add(con->c.cm_id->device,
 						       &dev_pd);
-		if (!sess->s.dev) {
-			rtrs_wrn(sess->clt,
+		if (!clt_path->s.dev) {
+			rtrs_wrn(clt_path->clt,
 				  "rtrs_ib_dev_find_get_or_add(): no memory\n");
 			return -ENOMEM;
 		}
-		sess->s.dev_ref = 1;
-		query_fast_reg_mode(sess);
-		wr_limit = sess->s.dev->ib_dev->attrs.max_qp_wr;
+		clt_path->s.dev_ref = 1;
+		query_fast_reg_mode(clt_path);
+		wr_limit = clt_path->s.dev->ib_dev->attrs.max_qp_wr;
 		/*
 		 * Two (request + registration) completion for send
 		 * Two for recv if always_invalidate is set on server
@@ -1665,27 +1672,28 @@ static int create_con_cq_qp(struct rtrs_clt_con *con)
 		 * This is always true if user connection (cid == 0) is
 		 * established first.
 		 */
-		if (WARN_ON(!sess->s.dev))
+		if (WARN_ON(!clt_path->s.dev))
 			return -EINVAL;
-		if (WARN_ON(!sess->queue_depth))
+		if (WARN_ON(!clt_path->queue_depth))
 			return -EINVAL;
 
-		wr_limit = sess->s.dev->ib_dev->attrs.max_qp_wr;
+		wr_limit = clt_path->s.dev->ib_dev->attrs.max_qp_wr;
 		/* Shared between connections */
-		sess->s.dev_ref++;
+		clt_path->s.dev_ref++;
 		max_send_wr = min_t(int, wr_limit,
 			      /* QD * (REQ + RSP + FR REGS or INVS) + drain */
-			      sess->queue_depth * 3 + 1);
+			      clt_path->queue_depth * 3 + 1);
 		max_recv_wr = min_t(int, wr_limit,
-			      sess->queue_depth * 3 + 1);
+			      clt_path->queue_depth * 3 + 1);
 		max_send_sge = 2;
 	}
 	atomic_set(&con->c.sq_wr_avail, max_send_wr);
 	cq_num = max_send_wr + max_recv_wr;
 	/* alloc iu to recv new rkey reply when server reports flags set */
-	if (sess->flags & RTRS_MSG_NEW_RKEY_F || con->c.cid == 0) {
+	if (clt_path->flags & RTRS_MSG_NEW_RKEY_F || con->c.cid == 0) {
 		con->rsp_ius = rtrs_iu_alloc(cq_num, sizeof(*rsp),
-					      GFP_KERNEL, sess->s.dev->ib_dev,
+					      GFP_KERNEL,
+					      clt_path->s.dev->ib_dev,
 					      DMA_FROM_DEVICE,
 					      rtrs_clt_rdma_done);
 		if (!con->rsp_ius)
@@ -1693,13 +1701,13 @@ static int create_con_cq_qp(struct rtrs_clt_con *con)
 		con->queue_num = cq_num;
 	}
 	cq_num = max_send_wr + max_recv_wr;
-	cq_vector = con->cpu % sess->s.dev->ib_dev->num_comp_vectors;
-	if (con->c.cid >= sess->s.irq_con_num)
-		err = rtrs_cq_qp_create(&sess->s, &con->c, max_send_sge,
+	cq_vector = con->cpu % clt_path->s.dev->ib_dev->num_comp_vectors;
+	if (con->c.cid >= clt_path->s.irq_con_num)
+		err = rtrs_cq_qp_create(&clt_path->s, &con->c, max_send_sge,
 					cq_vector, cq_num, max_send_wr,
 					max_recv_wr, IB_POLL_DIRECT);
 	else
-		err = rtrs_cq_qp_create(&sess->s, &con->c, max_send_sge,
+		err = rtrs_cq_qp_create(&clt_path->s, &con->c, max_send_sge,
 					cq_vector, cq_num, max_send_wr,
 					max_recv_wr, IB_POLL_SOFTIRQ);
 	/*
@@ -1711,7 +1719,7 @@ static int create_con_cq_qp(struct rtrs_clt_con *con)
 
 static void destroy_con_cq_qp(struct rtrs_clt_con *con)
 {
-	struct rtrs_clt_sess *sess = to_clt_sess(con->c.sess);
+	struct rtrs_clt_path *clt_path = to_clt_path(con->c.path);
 
 	/*
 	 * Be careful here: destroy_con_cq_qp() can be called even
@@ -1720,13 +1728,14 @@ static void destroy_con_cq_qp(struct rtrs_clt_con *con)
 	lockdep_assert_held(&con->con_mutex);
 	rtrs_cq_qp_destroy(&con->c);
 	if (con->rsp_ius) {
-		rtrs_iu_free(con->rsp_ius, sess->s.dev->ib_dev, con->queue_num);
+		rtrs_iu_free(con->rsp_ius, clt_path->s.dev->ib_dev,
+			     con->queue_num);
 		con->rsp_ius = NULL;
 		con->queue_num = 0;
 	}
-	if (sess->s.dev_ref && !--sess->s.dev_ref) {
-		rtrs_ib_dev_put(sess->s.dev);
-		sess->s.dev = NULL;
+	if (clt_path->s.dev_ref && !--clt_path->s.dev_ref) {
+		rtrs_ib_dev_put(clt_path->s.dev);
+		clt_path->s.dev = NULL;
 	}
 }
 
@@ -1745,7 +1754,7 @@ static void destroy_cm(struct rtrs_clt_con *con)
 
 static int rtrs_rdma_addr_resolved(struct rtrs_clt_con *con)
 {
-	struct rtrs_sess *s = con->c.sess;
+	struct rtrs_path *s = con->c.path;
 	int err;
 
 	mutex_lock(&con->con_mutex);
@@ -1764,8 +1773,8 @@ static int rtrs_rdma_addr_resolved(struct rtrs_clt_con *con)
 
 static int rtrs_rdma_route_resolved(struct rtrs_clt_con *con)
 {
-	struct rtrs_clt_sess *sess = to_clt_sess(con->c.sess);
-	struct rtrs_clt *clt = sess->clt;
+	struct rtrs_clt_path *clt_path = to_clt_path(con->c.path);
+	struct rtrs_clt *clt = clt_path->clt;
 	struct rtrs_msg_conn_req msg;
 	struct rdma_conn_param param;
 
@@ -1782,11 +1791,11 @@ static int rtrs_rdma_route_resolved(struct rtrs_clt_con *con)
 		.magic = cpu_to_le16(RTRS_MAGIC),
 		.version = cpu_to_le16(RTRS_PROTO_VER),
 		.cid = cpu_to_le16(con->c.cid),
-		.cid_num = cpu_to_le16(sess->s.con_num),
-		.recon_cnt = cpu_to_le16(sess->s.recon_cnt),
+		.cid_num = cpu_to_le16(clt_path->s.con_num),
+		.recon_cnt = cpu_to_le16(clt_path->s.recon_cnt),
 	};
-	msg.first_conn = sess->for_new_clt ? FIRST_CONN : 0;
-	uuid_copy(&msg.sess_uuid, &sess->s.uuid);
+	msg.first_conn = clt_path->for_new_clt ? FIRST_CONN : 0;
+	uuid_copy(&msg.sess_uuid, &clt_path->s.uuid);
 	uuid_copy(&msg.paths_uuid, &clt->paths_uuid);
 
 	err = rdma_connect_locked(con->c.cm_id, &param);
@@ -1799,8 +1808,8 @@ static int rtrs_rdma_route_resolved(struct rtrs_clt_con *con)
 static int rtrs_rdma_conn_established(struct rtrs_clt_con *con,
 				       struct rdma_cm_event *ev)
 {
-	struct rtrs_clt_sess *sess = to_clt_sess(con->c.sess);
-	struct rtrs_clt *clt = sess->clt;
+	struct rtrs_clt_path *clt_path = to_clt_path(con->c.path);
+	struct rtrs_clt *clt = clt_path->clt;
 	const struct rtrs_msg_conn_rsp *msg;
 	u16 version, queue_depth;
 	int errno;
@@ -1831,31 +1840,32 @@ static int rtrs_rdma_conn_established(struct rtrs_clt_con *con,
 	if (con->c.cid == 0) {
 		queue_depth = le16_to_cpu(msg->queue_depth);
 
-		if (sess->queue_depth > 0 && queue_depth != sess->queue_depth) {
+		if (clt_path->queue_depth > 0 && queue_depth != clt_path->queue_depth) {
 			rtrs_err(clt, "Error: queue depth changed\n");
 
 			/*
 			 * Stop any more reconnection attempts
 			 */
-			sess->reconnect_attempts = -1;
+			clt_path->reconnect_attempts = -1;
 			rtrs_err(clt,
 				"Disabling auto-reconnect. Trigger a manual reconnect after issue is resolved\n");
 			return -ECONNRESET;
 		}
 
-		if (!sess->rbufs) {
-			sess->rbufs = kcalloc(queue_depth, sizeof(*sess->rbufs),
-					      GFP_KERNEL);
-			if (!sess->rbufs)
+		if (!clt_path->rbufs) {
+			clt_path->rbufs = kcalloc(queue_depth,
+						  sizeof(*clt_path->rbufs),
+						  GFP_KERNEL);
+			if (!clt_path->rbufs)
 				return -ENOMEM;
 		}
-		sess->queue_depth = queue_depth;
-		sess->s.signal_interval = min_not_zero(queue_depth,
+		clt_path->queue_depth = queue_depth;
+		clt_path->s.signal_interval = min_not_zero(queue_depth,
 						(unsigned short) SERVICE_CON_QUEUE_DEPTH);
-		sess->max_hdr_size = le32_to_cpu(msg->max_hdr_size);
-		sess->max_io_size = le32_to_cpu(msg->max_io_size);
-		sess->flags = le32_to_cpu(msg->flags);
-		sess->chunk_size = sess->max_io_size + sess->max_hdr_size;
+		clt_path->max_hdr_size = le32_to_cpu(msg->max_hdr_size);
+		clt_path->max_io_size = le32_to_cpu(msg->max_io_size);
+		clt_path->flags = le32_to_cpu(msg->flags);
+		clt_path->chunk_size = clt_path->max_io_size + clt_path->max_hdr_size;
 
 		/*
 		 * Global IO size is always a minimum.
@@ -1866,20 +1876,20 @@ static int rtrs_rdma_conn_established(struct rtrs_clt_con *con,
 		 * connections in parallel, use lock.
 		 */
 		mutex_lock(&clt->paths_mutex);
-		clt->queue_depth = sess->queue_depth;
-		clt->max_io_size = min_not_zero(sess->max_io_size,
+		clt->queue_depth = clt_path->queue_depth;
+		clt->max_io_size = min_not_zero(clt_path->max_io_size,
 						clt->max_io_size);
 		mutex_unlock(&clt->paths_mutex);
 
 		/*
 		 * Cache the hca_port and hca_name for sysfs
 		 */
-		sess->hca_port = con->c.cm_id->port_num;
-		scnprintf(sess->hca_name, sizeof(sess->hca_name),
-			  sess->s.dev->ib_dev->name);
-		sess->s.src_addr = con->c.cm_id->route.addr.src_addr;
+		clt_path->hca_port = con->c.cm_id->port_num;
+		scnprintf(clt_path->hca_name, sizeof(clt_path->hca_name),
+			  clt_path->s.dev->ib_dev->name);
+		clt_path->s.src_addr = con->c.cm_id->route.addr.src_addr;
 		/* set for_new_clt, to allow future reconnect on any path */
-		sess->for_new_clt = 1;
+		clt_path->for_new_clt = 1;
 	}
 
 	return 0;
@@ -1887,16 +1897,16 @@ static int rtrs_rdma_conn_established(struct rtrs_clt_con *con,
 
 static inline void flag_success_on_conn(struct rtrs_clt_con *con)
 {
-	struct rtrs_clt_sess *sess = to_clt_sess(con->c.sess);
+	struct rtrs_clt_path *clt_path = to_clt_path(con->c.path);
 
-	atomic_inc(&sess->connected_cnt);
+	atomic_inc(&clt_path->connected_cnt);
 	con->cm_err = 1;
 }
 
 static int rtrs_rdma_conn_rejected(struct rtrs_clt_con *con,
 				    struct rdma_cm_event *ev)
 {
-	struct rtrs_sess *s = con->c.sess;
+	struct rtrs_path *s = con->c.path;
 	const struct rtrs_msg_conn_rsp *msg;
 	const char *rej_msg;
 	int status, errno;
@@ -1924,23 +1934,23 @@ static int rtrs_rdma_conn_rejected(struct rtrs_clt_con *con,
 	return -ECONNRESET;
 }
 
-void rtrs_clt_close_conns(struct rtrs_clt_sess *sess, bool wait)
+void rtrs_clt_close_conns(struct rtrs_clt_path *clt_path, bool wait)
 {
-	if (rtrs_clt_change_state_get_old(sess, RTRS_CLT_CLOSING, NULL))
-		queue_work(rtrs_wq, &sess->close_work);
+	if (rtrs_clt_change_state_get_old(clt_path, RTRS_CLT_CLOSING, NULL))
+		queue_work(rtrs_wq, &clt_path->close_work);
 	if (wait)
-		flush_work(&sess->close_work);
+		flush_work(&clt_path->close_work);
 }
 
 static inline void flag_error_on_conn(struct rtrs_clt_con *con, int cm_err)
 {
 	if (con->cm_err == 1) {
-		struct rtrs_clt_sess *sess;
+		struct rtrs_clt_path *clt_path;
 
-		sess = to_clt_sess(con->c.sess);
-		if (atomic_dec_and_test(&sess->connected_cnt))
+		clt_path = to_clt_path(con->c.path);
+		if (atomic_dec_and_test(&clt_path->connected_cnt))
 
-			wake_up(&sess->state_wq);
+			wake_up(&clt_path->state_wq);
 	}
 	con->cm_err = cm_err;
 }
@@ -1949,8 +1959,8 @@ static int rtrs_clt_rdma_cm_handler(struct rdma_cm_id *cm_id,
 				     struct rdma_cm_event *ev)
 {
 	struct rtrs_clt_con *con = cm_id->context;
-	struct rtrs_sess *s = con->c.sess;
-	struct rtrs_clt_sess *sess = to_clt_sess(s);
+	struct rtrs_path *s = con->c.path;
+	struct rtrs_clt_path *clt_path = to_clt_path(s);
 	int cm_err = 0;
 
 	switch (ev->event) {
@@ -1968,7 +1978,7 @@ static int rtrs_clt_rdma_cm_handler(struct rdma_cm_id *cm_id,
 			 * i.e. wake up without state change, but we set cm_err.
 			 */
 			flag_success_on_conn(con);
-			wake_up(&sess->state_wq);
+			wake_up(&clt_path->state_wq);
 			return 0;
 		}
 		break;
@@ -1997,7 +2007,7 @@ static int rtrs_clt_rdma_cm_handler(struct rdma_cm_id *cm_id,
 		/*
 		 * Device removal is a special case.  Queue close and return 0.
 		 */
-		rtrs_clt_close_conns(sess, false);
+		rtrs_clt_close_conns(clt_path, false);
 		return 0;
 	default:
 		rtrs_err(s, "Unexpected RDMA CM error (CM event: %s, err: %d)\n",
@@ -2020,13 +2030,13 @@ static int rtrs_clt_rdma_cm_handler(struct rdma_cm_id *cm_id,
 
 static int create_cm(struct rtrs_clt_con *con)
 {
-	struct rtrs_sess *s = con->c.sess;
-	struct rtrs_clt_sess *sess = to_clt_sess(s);
+	struct rtrs_path *s = con->c.path;
+	struct rtrs_clt_path *clt_path = to_clt_path(s);
 	struct rdma_cm_id *cm_id;
 	int err;
 
 	cm_id = rdma_create_id(&init_net, rtrs_clt_rdma_cm_handler, con,
-			       sess->s.dst_addr.ss_family == AF_IB ?
+			       clt_path->s.dst_addr.ss_family == AF_IB ?
 			       RDMA_PS_IB : RDMA_PS_TCP, IB_QPT_RC);
 	if (IS_ERR(cm_id)) {
 		err = PTR_ERR(cm_id);
@@ -2042,8 +2052,8 @@ static int create_cm(struct rtrs_clt_con *con)
 		rtrs_err(s, "Set address reuse failed, err: %d\n", err);
 		goto destroy_cm;
 	}
-	err = rdma_resolve_addr(cm_id, (struct sockaddr *)&sess->s.src_addr,
-				(struct sockaddr *)&sess->s.dst_addr,
+	err = rdma_resolve_addr(cm_id, (struct sockaddr *)&clt_path->s.src_addr,
+				(struct sockaddr *)&clt_path->s.dst_addr,
 				RTRS_CONNECT_TIMEOUT_MS);
 	if (err) {
 		rtrs_err(s, "Failed to resolve address, err: %d\n", err);
@@ -2055,8 +2065,8 @@ static int create_cm(struct rtrs_clt_con *con)
 	 * or session state was really changed to error by device removal.
 	 */
 	err = wait_event_interruptible_timeout(
-			sess->state_wq,
-			con->cm_err || sess->state != RTRS_CLT_CONNECTING,
+			clt_path->state_wq,
+			con->cm_err || clt_path->state != RTRS_CLT_CONNECTING,
 			msecs_to_jiffies(RTRS_CONNECT_TIMEOUT_MS));
 	if (err == 0 || err == -ERESTARTSYS) {
 		if (err == 0)
@@ -2068,7 +2078,7 @@ static int create_cm(struct rtrs_clt_con *con)
 		err = con->cm_err;
 		goto errr;
 	}
-	if (READ_ONCE(sess->state) != RTRS_CLT_CONNECTING) {
+	if (READ_ONCE(clt_path->state) != RTRS_CLT_CONNECTING) {
 		/* Device removal */
 		err = -ECONNABORTED;
 		goto errr;
@@ -2087,9 +2097,9 @@ destroy_cm:
 	return err;
 }
 
-static void rtrs_clt_sess_up(struct rtrs_clt_sess *sess)
+static void rtrs_clt_path_up(struct rtrs_clt_path *clt_path)
 {
-	struct rtrs_clt *clt = sess->clt;
+	struct rtrs_clt *clt = clt_path->clt;
 	int up;
 
 	/*
@@ -2113,19 +2123,19 @@ static void rtrs_clt_sess_up(struct rtrs_clt_sess *sess)
 	mutex_unlock(&clt->paths_ev_mutex);
 
 	/* Mark session as established */
-	sess->established = true;
-	sess->reconnect_attempts = 0;
-	sess->stats->reconnects.successful_cnt++;
+	clt_path->established = true;
+	clt_path->reconnect_attempts = 0;
+	clt_path->stats->reconnects.successful_cnt++;
 }
 
-static void rtrs_clt_sess_down(struct rtrs_clt_sess *sess)
+static void rtrs_clt_path_down(struct rtrs_clt_path *clt_path)
 {
-	struct rtrs_clt *clt = sess->clt;
+	struct rtrs_clt *clt = clt_path->clt;
 
-	if (!sess->established)
+	if (!clt_path->established)
 		return;
 
-	sess->established = false;
+	clt_path->established = false;
 	mutex_lock(&clt->paths_ev_mutex);
 	WARN_ON(!clt->paths_up);
 	if (--clt->paths_up == 0)
@@ -2133,19 +2143,19 @@ static void rtrs_clt_sess_down(struct rtrs_clt_sess *sess)
 	mutex_unlock(&clt->paths_ev_mutex);
 }
 
-static void rtrs_clt_stop_and_destroy_conns(struct rtrs_clt_sess *sess)
+static void rtrs_clt_stop_and_destroy_conns(struct rtrs_clt_path *clt_path)
 {
 	struct rtrs_clt_con *con;
 	unsigned int cid;
 
-	WARN_ON(READ_ONCE(sess->state) == RTRS_CLT_CONNECTED);
+	WARN_ON(READ_ONCE(clt_path->state) == RTRS_CLT_CONNECTED);
 
 	/*
 	 * Possible race with rtrs_clt_open(), when DEVICE_REMOVAL comes
 	 * exactly in between.  Start destroying after it finishes.
 	 */
-	mutex_lock(&sess->init_mutex);
-	mutex_unlock(&sess->init_mutex);
+	mutex_lock(&clt_path->init_mutex);
+	mutex_unlock(&clt_path->init_mutex);
 
 	/*
 	 * All IO paths must observe !CONNECTED state before we
@@ -2153,7 +2163,7 @@ static void rtrs_clt_stop_and_destroy_conns(struct rtrs_clt_sess *sess)
 	 */
 	synchronize_rcu();
 
-	rtrs_stop_hb(&sess->s);
+	rtrs_stop_hb(&clt_path->s);
 
 	/*
 	 * The order it utterly crucial: firstly disconnect and complete all
@@ -2162,15 +2172,15 @@ static void rtrs_clt_stop_and_destroy_conns(struct rtrs_clt_sess *sess)
 	 * eventually notify upper layer about session disconnection.
 	 */
 
-	for (cid = 0; cid < sess->s.con_num; cid++) {
-		if (!sess->s.con[cid])
+	for (cid = 0; cid < clt_path->s.con_num; cid++) {
+		if (!clt_path->s.con[cid])
 			break;
-		con = to_clt_con(sess->s.con[cid]);
+		con = to_clt_con(clt_path->s.con[cid]);
 		stop_cm(con);
 	}
-	fail_all_outstanding_reqs(sess);
-	free_sess_reqs(sess);
-	rtrs_clt_sess_down(sess);
+	fail_all_outstanding_reqs(clt_path);
+	free_path_reqs(clt_path);
+	rtrs_clt_path_down(clt_path);
 
 	/*
 	 * Wait for graceful shutdown, namely when peer side invokes
@@ -2180,13 +2190,14 @@ static void rtrs_clt_stop_and_destroy_conns(struct rtrs_clt_sess *sess)
 	 * since CM does not fire anything.  That is fine, we are not in
 	 * hurry.
 	 */
-	wait_event_timeout(sess->state_wq, !atomic_read(&sess->connected_cnt),
+	wait_event_timeout(clt_path->state_wq,
+			   !atomic_read(&clt_path->connected_cnt),
 			   msecs_to_jiffies(RTRS_CONNECT_TIMEOUT_MS));
 
-	for (cid = 0; cid < sess->s.con_num; cid++) {
-		if (!sess->s.con[cid])
+	for (cid = 0; cid < clt_path->s.con_num; cid++) {
+		if (!clt_path->s.con[cid])
 			break;
-		con = to_clt_con(sess->s.con[cid]);
+		con = to_clt_con(clt_path->s.con[cid]);
 		mutex_lock(&con->con_mutex);
 		destroy_con_cq_qp(con);
 		mutex_unlock(&con->con_mutex);
@@ -2195,26 +2206,26 @@ static void rtrs_clt_stop_and_destroy_conns(struct rtrs_clt_sess *sess)
 	}
 }
 
-static inline bool xchg_sessions(struct rtrs_clt_sess __rcu **rcu_ppcpu_path,
-				 struct rtrs_clt_sess *sess,
-				 struct rtrs_clt_sess *next)
+static inline bool xchg_paths(struct rtrs_clt_path __rcu **rcu_ppcpu_path,
+			      struct rtrs_clt_path *clt_path,
+			      struct rtrs_clt_path *next)
 {
-	struct rtrs_clt_sess **ppcpu_path;
+	struct rtrs_clt_path **ppcpu_path;
 
 	/* Call cmpxchg() without sparse warnings */
 	ppcpu_path = (typeof(ppcpu_path))rcu_ppcpu_path;
-	return sess == cmpxchg(ppcpu_path, sess, next);
+	return clt_path == cmpxchg(ppcpu_path, clt_path, next);
 }
 
-static void rtrs_clt_remove_path_from_arr(struct rtrs_clt_sess *sess)
+static void rtrs_clt_remove_path_from_arr(struct rtrs_clt_path *clt_path)
 {
-	struct rtrs_clt *clt = sess->clt;
-	struct rtrs_clt_sess *next;
+	struct rtrs_clt *clt = clt_path->clt;
+	struct rtrs_clt_path *next;
 	bool wait_for_grace = false;
 	int cpu;
 
 	mutex_lock(&clt->paths_mutex);
-	list_del_rcu(&sess->s.entry);
+	list_del_rcu(&clt_path->s.entry);
 
 	/* Make sure everybody observes path removal. */
 	synchronize_rcu();
@@ -2255,8 +2266,7 @@ static void rtrs_clt_remove_path_from_arr(struct rtrs_clt_sess *sess)
 	 * removed.  If @sess is the last element, then @next is NULL.
 	 */
 	rcu_read_lock();
-	next = list_next_or_null_rr_rcu(&clt->paths_list, &sess->s.entry,
-					typeof(*next), s.entry);
+	next = rtrs_clt_get_next_path_or_null(&clt->paths_list, clt_path);
 	rcu_read_unlock();
 
 	/*
@@ -2264,11 +2274,11 @@ static void rtrs_clt_remove_path_from_arr(struct rtrs_clt_sess *sess)
 	 * removed, so change the pointer manually.
 	 */
 	for_each_possible_cpu(cpu) {
-		struct rtrs_clt_sess __rcu **ppcpu_path;
+		struct rtrs_clt_path __rcu **ppcpu_path;
 
 		ppcpu_path = per_cpu_ptr(clt->pcpu_path, cpu);
 		if (rcu_dereference_protected(*ppcpu_path,
-			lockdep_is_held(&clt->paths_mutex)) != sess)
+			lockdep_is_held(&clt->paths_mutex)) != clt_path)
 			/*
 			 * synchronize_rcu() was called just after deleting
 			 * entry from the list, thus IO code path cannot
@@ -2281,7 +2291,7 @@ static void rtrs_clt_remove_path_from_arr(struct rtrs_clt_sess *sess)
 		 * We race with IO code path, which also changes pointer,
 		 * thus we have to be careful not to overwrite it.
 		 */
-		if (xchg_sessions(ppcpu_path, sess, next))
+		if (xchg_paths(ppcpu_path, clt_path, next))
 			/*
 			 * @ppcpu_path was successfully replaced with @next,
 			 * that means that someone could also pick up the
@@ -2296,29 +2306,29 @@ static void rtrs_clt_remove_path_from_arr(struct rtrs_clt_sess *sess)
 	mutex_unlock(&clt->paths_mutex);
 }
 
-static void rtrs_clt_add_path_to_arr(struct rtrs_clt_sess *sess)
+static void rtrs_clt_add_path_to_arr(struct rtrs_clt_path *clt_path)
 {
-	struct rtrs_clt *clt = sess->clt;
+	struct rtrs_clt *clt = clt_path->clt;
 
 	mutex_lock(&clt->paths_mutex);
 	clt->paths_num++;
 
-	list_add_tail_rcu(&sess->s.entry, &clt->paths_list);
+	list_add_tail_rcu(&clt_path->s.entry, &clt->paths_list);
 	mutex_unlock(&clt->paths_mutex);
 }
 
 static void rtrs_clt_close_work(struct work_struct *work)
 {
-	struct rtrs_clt_sess *sess;
+	struct rtrs_clt_path *clt_path;
 
-	sess = container_of(work, struct rtrs_clt_sess, close_work);
+	clt_path = container_of(work, struct rtrs_clt_path, close_work);
 
-	cancel_delayed_work_sync(&sess->reconnect_dwork);
-	rtrs_clt_stop_and_destroy_conns(sess);
-	rtrs_clt_change_state_get_old(sess, RTRS_CLT_CLOSED, NULL);
+	cancel_delayed_work_sync(&clt_path->reconnect_dwork);
+	rtrs_clt_stop_and_destroy_conns(clt_path);
+	rtrs_clt_change_state_get_old(clt_path, RTRS_CLT_CLOSED, NULL);
 }
 
-static int init_conns(struct rtrs_clt_sess *sess)
+static int init_conns(struct rtrs_clt_path *clt_path)
 {
 	unsigned int cid;
 	int err;
@@ -2328,31 +2338,31 @@ static int init_conns(struct rtrs_clt_sess *sess)
 	 * to avoid clashes with previous sessions not yet closed
 	 * sessions on a server side.
 	 */
-	sess->s.recon_cnt++;
+	clt_path->s.recon_cnt++;
 
 	/* Establish all RDMA connections  */
-	for (cid = 0; cid < sess->s.con_num; cid++) {
-		err = create_con(sess, cid);
+	for (cid = 0; cid < clt_path->s.con_num; cid++) {
+		err = create_con(clt_path, cid);
 		if (err)
 			goto destroy;
 
-		err = create_cm(to_clt_con(sess->s.con[cid]));
+		err = create_cm(to_clt_con(clt_path->s.con[cid]));
 		if (err) {
-			destroy_con(to_clt_con(sess->s.con[cid]));
+			destroy_con(to_clt_con(clt_path->s.con[cid]));
 			goto destroy;
 		}
 	}
-	err = alloc_sess_reqs(sess);
+	err = alloc_path_reqs(clt_path);
 	if (err)
 		goto destroy;
 
-	rtrs_start_hb(&sess->s);
+	rtrs_start_hb(&clt_path->s);
 
 	return 0;
 
 destroy:
 	while (cid--) {
-		struct rtrs_clt_con *con = to_clt_con(sess->s.con[cid]);
+		struct rtrs_clt_con *con = to_clt_con(clt_path->s.con[cid]);
 
 		stop_cm(con);
 
@@ -2367,7 +2377,7 @@ destroy:
 	 * doing rdma_resolve_addr(), switch to CONNECTION_ERR state
 	 * manually to keep reconnecting.
 	 */
-	rtrs_clt_change_state_get_old(sess, RTRS_CLT_CONNECTING_ERR, NULL);
+	rtrs_clt_change_state_get_old(clt_path, RTRS_CLT_CONNECTING_ERR, NULL);
 
 	return err;
 }
@@ -2375,31 +2385,32 @@ destroy:
 static void rtrs_clt_info_req_done(struct ib_cq *cq, struct ib_wc *wc)
 {
 	struct rtrs_clt_con *con = to_clt_con(wc->qp->qp_context);
-	struct rtrs_clt_sess *sess = to_clt_sess(con->c.sess);
+	struct rtrs_clt_path *clt_path = to_clt_path(con->c.path);
 	struct rtrs_iu *iu;
 
 	iu = container_of(wc->wr_cqe, struct rtrs_iu, cqe);
-	rtrs_iu_free(iu, sess->s.dev->ib_dev, 1);
+	rtrs_iu_free(iu, clt_path->s.dev->ib_dev, 1);
 
 	if (wc->status != IB_WC_SUCCESS) {
-		rtrs_err(sess->clt, "Sess info request send failed: %s\n",
+		rtrs_err(clt_path->clt, "Path info request send failed: %s\n",
 			  ib_wc_status_msg(wc->status));
-		rtrs_clt_change_state_get_old(sess, RTRS_CLT_CONNECTING_ERR, NULL);
+		rtrs_clt_change_state_get_old(clt_path, RTRS_CLT_CONNECTING_ERR, NULL);
 		return;
 	}
 
 	rtrs_clt_update_wc_stats(con);
 }
 
-static int process_info_rsp(struct rtrs_clt_sess *sess,
+static int process_info_rsp(struct rtrs_clt_path *clt_path,
 			    const struct rtrs_msg_info_rsp *msg)
 {
 	unsigned int sg_cnt, total_len;
 	int i, sgi;
 
 	sg_cnt = le16_to_cpu(msg->sg_cnt);
-	if (!sg_cnt || (sess->queue_depth % sg_cnt)) {
-		rtrs_err(sess->clt, "Incorrect sg_cnt %d, is not multiple\n",
+	if (!sg_cnt || (clt_path->queue_depth % sg_cnt)) {
+		rtrs_err(clt_path->clt,
+			  "Incorrect sg_cnt %d, is not multiple\n",
 			  sg_cnt);
 		return -EINVAL;
 	}
@@ -2408,15 +2419,15 @@ static int process_info_rsp(struct rtrs_clt_sess *sess,
 	 * Check if IB immediate data size is enough to hold the mem_id and
 	 * the offset inside the memory chunk.
 	 */
-	if ((ilog2(sg_cnt - 1) + 1) + (ilog2(sess->chunk_size - 1) + 1) >
+	if ((ilog2(sg_cnt - 1) + 1) + (ilog2(clt_path->chunk_size - 1) + 1) >
 	    MAX_IMM_PAYL_BITS) {
-		rtrs_err(sess->clt,
+		rtrs_err(clt_path->clt,
 			  "RDMA immediate size (%db) not enough to encode %d buffers of size %dB\n",
-			  MAX_IMM_PAYL_BITS, sg_cnt, sess->chunk_size);
+			  MAX_IMM_PAYL_BITS, sg_cnt, clt_path->chunk_size);
 		return -EINVAL;
 	}
 	total_len = 0;
-	for (sgi = 0, i = 0; sgi < sg_cnt && i < sess->queue_depth; sgi++) {
+	for (sgi = 0, i = 0; sgi < sg_cnt && i < clt_path->queue_depth; sgi++) {
 		const struct rtrs_sg_desc *desc = &msg->desc[sgi];
 		u32 len, rkey;
 		u64 addr;
@@ -2427,26 +2438,28 @@ static int process_info_rsp(struct rtrs_clt_sess *sess,
 
 		total_len += len;
 
-		if (!len || (len % sess->chunk_size)) {
-			rtrs_err(sess->clt, "Incorrect [%d].len %d\n", sgi,
+		if (!len || (len % clt_path->chunk_size)) {
+			rtrs_err(clt_path->clt, "Incorrect [%d].len %d\n",
+				  sgi,
 				  len);
 			return -EINVAL;
 		}
-		for ( ; len && i < sess->queue_depth; i++) {
-			sess->rbufs[i].addr = addr;
-			sess->rbufs[i].rkey = rkey;
+		for ( ; len && i < clt_path->queue_depth; i++) {
+			clt_path->rbufs[i].addr = addr;
+			clt_path->rbufs[i].rkey = rkey;
 
-			len  -= sess->chunk_size;
-			addr += sess->chunk_size;
+			len  -= clt_path->chunk_size;
+			addr += clt_path->chunk_size;
 		}
 	}
 	/* Sanity check */
-	if (sgi != sg_cnt || i != sess->queue_depth) {
-		rtrs_err(sess->clt, "Incorrect sg vector, not fully mapped\n");
+	if (sgi != sg_cnt || i != clt_path->queue_depth) {
+		rtrs_err(clt_path->clt,
+			 "Incorrect sg vector, not fully mapped\n");
 		return -EINVAL;
 	}
-	if (total_len != sess->chunk_size * sess->queue_depth) {
-		rtrs_err(sess->clt, "Incorrect total_len %d\n", total_len);
+	if (total_len != clt_path->chunk_size * clt_path->queue_depth) {
+		rtrs_err(clt_path->clt, "Incorrect total_len %d\n", total_len);
 		return -EINVAL;
 	}
 
@@ -2456,7 +2469,7 @@ static int process_info_rsp(struct rtrs_clt_sess *sess,
 static void rtrs_clt_info_rsp_done(struct ib_cq *cq, struct ib_wc *wc)
 {
 	struct rtrs_clt_con *con = to_clt_con(wc->qp->qp_context);
-	struct rtrs_clt_sess *sess = to_clt_sess(con->c.sess);
+	struct rtrs_clt_path *clt_path = to_clt_path(con->c.path);
 	struct rtrs_msg_info_rsp *msg;
 	enum rtrs_clt_state state;
 	struct rtrs_iu *iu;
@@ -2468,37 +2481,37 @@ static void rtrs_clt_info_rsp_done(struct ib_cq *cq, struct ib_wc *wc)
 	WARN_ON(con->c.cid);
 	iu = container_of(wc->wr_cqe, struct rtrs_iu, cqe);
 	if (wc->status != IB_WC_SUCCESS) {
-		rtrs_err(sess->clt, "Sess info response recv failed: %s\n",
+		rtrs_err(clt_path->clt, "Path info response recv failed: %s\n",
 			  ib_wc_status_msg(wc->status));
 		goto out;
 	}
 	WARN_ON(wc->opcode != IB_WC_RECV);
 
 	if (wc->byte_len < sizeof(*msg)) {
-		rtrs_err(sess->clt, "Sess info response is malformed: size %d\n",
+		rtrs_err(clt_path->clt, "Path info response is malformed: size %d\n",
 			  wc->byte_len);
 		goto out;
 	}
-	ib_dma_sync_single_for_cpu(sess->s.dev->ib_dev, iu->dma_addr,
+	ib_dma_sync_single_for_cpu(clt_path->s.dev->ib_dev, iu->dma_addr,
 				   iu->size, DMA_FROM_DEVICE);
 	msg = iu->buf;
 	if (le16_to_cpu(msg->type) != RTRS_MSG_INFO_RSP) {
-		rtrs_err(sess->clt, "Sess info response is malformed: type %d\n",
+		rtrs_err(clt_path->clt, "Path info response is malformed: type %d\n",
 			  le16_to_cpu(msg->type));
 		goto out;
 	}
 	rx_sz  = sizeof(*msg);
 	rx_sz += sizeof(msg->desc[0]) * le16_to_cpu(msg->sg_cnt);
 	if (wc->byte_len < rx_sz) {
-		rtrs_err(sess->clt, "Sess info response is malformed: size %d\n",
+		rtrs_err(clt_path->clt, "Path info response is malformed: size %d\n",
 			  wc->byte_len);
 		goto out;
 	}
-	err = process_info_rsp(sess, msg);
+	err = process_info_rsp(clt_path, msg);
 	if (err)
 		goto out;
 
-	err = post_recv_sess(sess);
+	err = post_recv_path(clt_path);
 	if (err)
 		goto out;
 
@@ -2506,25 +2519,25 @@ static void rtrs_clt_info_rsp_done(struct ib_cq *cq, struct ib_wc *wc)
 
 out:
 	rtrs_clt_update_wc_stats(con);
-	rtrs_iu_free(iu, sess->s.dev->ib_dev, 1);
-	rtrs_clt_change_state_get_old(sess, state, NULL);
+	rtrs_iu_free(iu, clt_path->s.dev->ib_dev, 1);
+	rtrs_clt_change_state_get_old(clt_path, state, NULL);
 }
 
-static int rtrs_send_sess_info(struct rtrs_clt_sess *sess)
+static int rtrs_send_path_info(struct rtrs_clt_path *clt_path)
 {
-	struct rtrs_clt_con *usr_con = to_clt_con(sess->s.con[0]);
+	struct rtrs_clt_con *usr_con = to_clt_con(clt_path->s.con[0]);
 	struct rtrs_msg_info_req *msg;
 	struct rtrs_iu *tx_iu, *rx_iu;
 	size_t rx_sz;
 	int err;
 
 	rx_sz  = sizeof(struct rtrs_msg_info_rsp);
-	rx_sz += sizeof(struct rtrs_sg_desc) * sess->queue_depth;
+	rx_sz += sizeof(struct rtrs_sg_desc) * clt_path->queue_depth;
 
 	tx_iu = rtrs_iu_alloc(1, sizeof(struct rtrs_msg_info_req), GFP_KERNEL,
-			       sess->s.dev->ib_dev, DMA_TO_DEVICE,
+			       clt_path->s.dev->ib_dev, DMA_TO_DEVICE,
 			       rtrs_clt_info_req_done);
-	rx_iu = rtrs_iu_alloc(1, rx_sz, GFP_KERNEL, sess->s.dev->ib_dev,
+	rx_iu = rtrs_iu_alloc(1, rx_sz, GFP_KERNEL, clt_path->s.dev->ib_dev,
 			       DMA_FROM_DEVICE, rtrs_clt_info_rsp_done);
 	if (!tx_iu || !rx_iu) {
 		err = -ENOMEM;
@@ -2533,33 +2546,34 @@ static int rtrs_send_sess_info(struct rtrs_clt_sess *sess)
 	/* Prepare for getting info response */
 	err = rtrs_iu_post_recv(&usr_con->c, rx_iu);
 	if (err) {
-		rtrs_err(sess->clt, "rtrs_iu_post_recv(), err: %d\n", err);
+		rtrs_err(clt_path->clt, "rtrs_iu_post_recv(), err: %d\n", err);
 		goto out;
 	}
 	rx_iu = NULL;
 
 	msg = tx_iu->buf;
 	msg->type = cpu_to_le16(RTRS_MSG_INFO_REQ);
-	memcpy(msg->sessname, sess->s.sessname, sizeof(msg->sessname));
+	memcpy(msg->pathname, clt_path->s.sessname, sizeof(msg->pathname));
 
-	ib_dma_sync_single_for_device(sess->s.dev->ib_dev, tx_iu->dma_addr,
+	ib_dma_sync_single_for_device(clt_path->s.dev->ib_dev,
+				      tx_iu->dma_addr,
 				      tx_iu->size, DMA_TO_DEVICE);
 
 	/* Send info request */
 	err = rtrs_iu_post_send(&usr_con->c, tx_iu, sizeof(*msg), NULL);
 	if (err) {
-		rtrs_err(sess->clt, "rtrs_iu_post_send(), err: %d\n", err);
+		rtrs_err(clt_path->clt, "rtrs_iu_post_send(), err: %d\n", err);
 		goto out;
 	}
 	tx_iu = NULL;
 
 	/* Wait for state change */
-	wait_event_interruptible_timeout(sess->state_wq,
-					 sess->state != RTRS_CLT_CONNECTING,
+	wait_event_interruptible_timeout(clt_path->state_wq,
+					 clt_path->state != RTRS_CLT_CONNECTING,
 					 msecs_to_jiffies(
 						 RTRS_CONNECT_TIMEOUT_MS));
-	if (READ_ONCE(sess->state) != RTRS_CLT_CONNECTED) {
-		if (READ_ONCE(sess->state) == RTRS_CLT_CONNECTING_ERR)
+	if (READ_ONCE(clt_path->state) != RTRS_CLT_CONNECTED) {
+		if (READ_ONCE(clt_path->state) == RTRS_CLT_CONNECTING_ERR)
 			err = -ECONNRESET;
 		else
 			err = -ETIMEDOUT;
@@ -2567,82 +2581,82 @@ static int rtrs_send_sess_info(struct rtrs_clt_sess *sess)
 
 out:
 	if (tx_iu)
-		rtrs_iu_free(tx_iu, sess->s.dev->ib_dev, 1);
+		rtrs_iu_free(tx_iu, clt_path->s.dev->ib_dev, 1);
 	if (rx_iu)
-		rtrs_iu_free(rx_iu, sess->s.dev->ib_dev, 1);
+		rtrs_iu_free(rx_iu, clt_path->s.dev->ib_dev, 1);
 	if (err)
 		/* If we've never taken async path because of malloc problems */
-		rtrs_clt_change_state_get_old(sess, RTRS_CLT_CONNECTING_ERR, NULL);
+		rtrs_clt_change_state_get_old(clt_path,
+					      RTRS_CLT_CONNECTING_ERR, NULL);
 
 	return err;
 }
 
 /**
- * init_sess() - establishes all session connections and does handshake
- * @sess: client session.
+ * init_path() - establishes all path connections and does handshake
+ * @clt_path: client path.
  * In case of error full close or reconnect procedure should be taken,
  * because reconnect or close async works can be started.
  */
-static int init_sess(struct rtrs_clt_sess *sess)
+static int init_path(struct rtrs_clt_path *clt_path)
 {
 	int err;
 	char str[NAME_MAX];
 	struct rtrs_addr path = {
-		.src = &sess->s.src_addr,
-		.dst = &sess->s.dst_addr,
+		.src = &clt_path->s.src_addr,
+		.dst = &clt_path->s.dst_addr,
 	};
 
 	rtrs_addr_to_str(&path, str, sizeof(str));
 
-	mutex_lock(&sess->init_mutex);
-	err = init_conns(sess);
+	mutex_lock(&clt_path->init_mutex);
+	err = init_conns(clt_path);
 	if (err) {
-		rtrs_err(sess->clt,
+		rtrs_err(clt_path->clt,
 			 "init_conns() failed: err=%d path=%s [%s:%u]\n", err,
-			 str, sess->hca_name, sess->hca_port);
+			 str, clt_path->hca_name, clt_path->hca_port);
 		goto out;
 	}
-	err = rtrs_send_sess_info(sess);
+	err = rtrs_send_path_info(clt_path);
 	if (err) {
-		rtrs_err(
-			sess->clt,
-			"rtrs_send_sess_info() failed: err=%d path=%s [%s:%u]\n",
-			err, str, sess->hca_name, sess->hca_port);
+		rtrs_err(clt_path->clt,
+			 "rtrs_send_path_info() failed: err=%d path=%s [%s:%u]\n",
+			 err, str, clt_path->hca_name, clt_path->hca_port);
 		goto out;
 	}
-	rtrs_clt_sess_up(sess);
+	rtrs_clt_path_up(clt_path);
 out:
-	mutex_unlock(&sess->init_mutex);
+	mutex_unlock(&clt_path->init_mutex);
 
 	return err;
 }
 
 static void rtrs_clt_reconnect_work(struct work_struct *work)
 {
-	struct rtrs_clt_sess *sess;
+	struct rtrs_clt_path *clt_path;
 	struct rtrs_clt *clt;
 	unsigned int delay_ms;
 	int err;
 
-	sess = container_of(to_delayed_work(work), struct rtrs_clt_sess,
-			    reconnect_dwork);
-	clt = sess->clt;
+	clt_path = container_of(to_delayed_work(work), struct rtrs_clt_path,
+				reconnect_dwork);
+	clt = clt_path->clt;
 
-	if (READ_ONCE(sess->state) != RTRS_CLT_RECONNECTING)
+	if (READ_ONCE(clt_path->state) != RTRS_CLT_RECONNECTING)
 		return;
 
-	if (sess->reconnect_attempts >= clt->max_reconnect_attempts) {
-		/* Close a session completely if max attempts is reached */
-		rtrs_clt_close_conns(sess, false);
+	if (clt_path->reconnect_attempts >= clt->max_reconnect_attempts) {
+		/* Close a path completely if max attempts is reached */
+		rtrs_clt_close_conns(clt_path, false);
 		return;
 	}
-	sess->reconnect_attempts++;
+	clt_path->reconnect_attempts++;
 
 	/* Stop everything */
-	rtrs_clt_stop_and_destroy_conns(sess);
+	rtrs_clt_stop_and_destroy_conns(clt_path);
 	msleep(RTRS_RECONNECT_BACKOFF);
-	if (rtrs_clt_change_state_get_old(sess, RTRS_CLT_CONNECTING, NULL)) {
-		err = init_sess(sess);
+	if (rtrs_clt_change_state_get_old(clt_path, RTRS_CLT_CONNECTING, NULL)) {
+		err = init_path(clt_path);
 		if (err)
 			goto reconnect_again;
 	}
@@ -2650,10 +2664,10 @@ static void rtrs_clt_reconnect_work(struct work_struct *work)
 	return;
 
 reconnect_again:
-	if (rtrs_clt_change_state_get_old(sess, RTRS_CLT_RECONNECTING, NULL)) {
-		sess->stats->reconnects.fail_cnt++;
+	if (rtrs_clt_change_state_get_old(clt_path, RTRS_CLT_RECONNECTING, NULL)) {
+		clt_path->stats->reconnects.fail_cnt++;
 		delay_ms = clt->reconnect_delay_sec * 1000;
-		queue_delayed_work(rtrs_wq, &sess->reconnect_dwork,
+		queue_delayed_work(rtrs_wq, &clt_path->reconnect_dwork,
 				   msecs_to_jiffies(delay_ms +
 						    prandom_u32() %
 						    RTRS_RECONNECT_SEED));
@@ -2762,7 +2776,7 @@ static void free_clt(struct rtrs_clt *clt)
 }
 
 /**
- * rtrs_clt_open() - Open a session to an RTRS server
+ * rtrs_clt_open() - Open a path to an RTRS server
  * @ops: holds the link event callback and the private pointer.
  * @sessname: name of the session
  * @paths: Paths to be established defined by their src and dst addresses
@@ -2780,17 +2794,23 @@ static void free_clt(struct rtrs_clt *clt)
  * Return a valid pointer on success otherwise PTR_ERR.
  */
 struct rtrs_clt *rtrs_clt_open(struct rtrs_clt_ops *ops,
-				 const char *sessname,
+				 const char *pathname,
 				 const struct rtrs_addr *paths,
 				 size_t paths_num, u16 port,
 				 size_t pdu_sz, u8 reconnect_delay_sec,
 				 s16 max_reconnect_attempts, u32 nr_poll_queues)
 {
-	struct rtrs_clt_sess *sess, *tmp;
+	struct rtrs_clt_path *clt_path, *tmp;
 	struct rtrs_clt *clt;
 	int err, i;
 
-	clt = alloc_clt(sessname, paths_num, port, pdu_sz, ops->priv,
+	if (strchr(pathname, '/') || strchr(pathname, '.')) {
+		pr_err("pathname cannot contain / and .\n");
+		err = -EINVAL;
+		goto out;
+	}
+
+	clt = alloc_clt(pathname, paths_num, port, pdu_sz, ops->priv,
 			ops->link_ev,
 			reconnect_delay_sec,
 			max_reconnect_attempts);
@@ -2799,49 +2819,49 @@ struct rtrs_clt *rtrs_clt_open(struct rtrs_clt_ops *ops,
 		goto out;
 	}
 	for (i = 0; i < paths_num; i++) {
-		struct rtrs_clt_sess *sess;
+		struct rtrs_clt_path *clt_path;
 
-		sess = alloc_sess(clt, &paths[i], nr_cpu_ids,
+		clt_path = alloc_path(clt, &paths[i], nr_cpu_ids,
 				  nr_poll_queues);
-		if (IS_ERR(sess)) {
-			err = PTR_ERR(sess);
-			goto close_all_sess;
+		if (IS_ERR(clt_path)) {
+			err = PTR_ERR(clt_path);
+			goto close_all_path;
 		}
 		if (!i)
-			sess->for_new_clt = 1;
-		list_add_tail_rcu(&sess->s.entry, &clt->paths_list);
+			clt_path->for_new_clt = 1;
+		list_add_tail_rcu(&clt_path->s.entry, &clt->paths_list);
 
-		err = init_sess(sess);
+		err = init_path(clt_path);
 		if (err) {
-			list_del_rcu(&sess->s.entry);
-			rtrs_clt_close_conns(sess, true);
-			free_percpu(sess->stats->pcpu_stats);
-			kfree(sess->stats);
-			free_sess(sess);
-			goto close_all_sess;
+			list_del_rcu(&clt_path->s.entry);
+			rtrs_clt_close_conns(clt_path, true);
+			free_percpu(clt_path->stats->pcpu_stats);
+			kfree(clt_path->stats);
+			free_path(clt_path);
+			goto close_all_path;
 		}
 
-		err = rtrs_clt_create_sess_files(sess);
+		err = rtrs_clt_create_path_files(clt_path);
 		if (err) {
-			list_del_rcu(&sess->s.entry);
-			rtrs_clt_close_conns(sess, true);
-			free_percpu(sess->stats->pcpu_stats);
-			kfree(sess->stats);
-			free_sess(sess);
-			goto close_all_sess;
+			list_del_rcu(&clt_path->s.entry);
+			rtrs_clt_close_conns(clt_path, true);
+			free_percpu(clt_path->stats->pcpu_stats);
+			kfree(clt_path->stats);
+			free_path(clt_path);
+			goto close_all_path;
 		}
 	}
 	err = alloc_permits(clt);
 	if (err)
-		goto close_all_sess;
+		goto close_all_path;
 
 	return clt;
 
-close_all_sess:
-	list_for_each_entry_safe(sess, tmp, &clt->paths_list, s.entry) {
-		rtrs_clt_destroy_sess_files(sess, NULL);
-		rtrs_clt_close_conns(sess, true);
-		kobject_put(&sess->kobj);
+close_all_path:
+	list_for_each_entry_safe(clt_path, tmp, &clt->paths_list, s.entry) {
+		rtrs_clt_destroy_path_files(clt_path, NULL);
+		rtrs_clt_close_conns(clt_path, true);
+		kobject_put(&clt_path->kobj);
 	}
 	rtrs_clt_destroy_sysfs_root(clt);
 	free_clt(clt);
@@ -2852,38 +2872,39 @@ out:
 EXPORT_SYMBOL(rtrs_clt_open);
 
 /**
- * rtrs_clt_close() - Close a session
+ * rtrs_clt_close() - Close a path
  * @clt: Session handle. Session is freed upon return.
  */
 void rtrs_clt_close(struct rtrs_clt *clt)
 {
-	struct rtrs_clt_sess *sess, *tmp;
+	struct rtrs_clt_path *clt_path, *tmp;
 
 	/* Firstly forbid sysfs access */
 	rtrs_clt_destroy_sysfs_root(clt);
 
 	/* Now it is safe to iterate over all paths without locks */
-	list_for_each_entry_safe(sess, tmp, &clt->paths_list, s.entry) {
-		rtrs_clt_close_conns(sess, true);
-		rtrs_clt_destroy_sess_files(sess, NULL);
-		kobject_put(&sess->kobj);
+	list_for_each_entry_safe(clt_path, tmp, &clt->paths_list, s.entry) {
+		rtrs_clt_close_conns(clt_path, true);
+		rtrs_clt_destroy_path_files(clt_path, NULL);
+		kobject_put(&clt_path->kobj);
 	}
 	free_permits(clt);
 	free_clt(clt);
 }
 EXPORT_SYMBOL(rtrs_clt_close);
 
-int rtrs_clt_reconnect_from_sysfs(struct rtrs_clt_sess *sess)
+int rtrs_clt_reconnect_from_sysfs(struct rtrs_clt_path *clt_path)
 {
 	enum rtrs_clt_state old_state;
 	int err = -EBUSY;
 	bool changed;
 
-	changed = rtrs_clt_change_state_get_old(sess, RTRS_CLT_RECONNECTING,
+	changed = rtrs_clt_change_state_get_old(clt_path,
+						 RTRS_CLT_RECONNECTING,
 						 &old_state);
 	if (changed) {
-		sess->reconnect_attempts = 0;
-		queue_delayed_work(rtrs_wq, &sess->reconnect_dwork, 0);
+		clt_path->reconnect_attempts = 0;
+		queue_delayed_work(rtrs_wq, &clt_path->reconnect_dwork, 0);
 	}
 	if (changed || old_state == RTRS_CLT_RECONNECTING) {
 		/*
@@ -2891,15 +2912,15 @@ int rtrs_clt_reconnect_from_sysfs(struct rtrs_clt_sess *sess)
 		 * execution, so do the flush if we have queued something
 		 * right now or work is pending.
 		 */
-		flush_delayed_work(&sess->reconnect_dwork);
-		err = (READ_ONCE(sess->state) ==
+		flush_delayed_work(&clt_path->reconnect_dwork);
+		err = (READ_ONCE(clt_path->state) ==
 		       RTRS_CLT_CONNECTED ? 0 : -ENOTCONN);
 	}
 
 	return err;
 }
 
-int rtrs_clt_remove_path_from_sysfs(struct rtrs_clt_sess *sess,
+int rtrs_clt_remove_path_from_sysfs(struct rtrs_clt_path *clt_path,
 				     const struct attribute *sysfs_self)
 {
 	enum rtrs_clt_state old_state;
@@ -2915,16 +2936,16 @@ int rtrs_clt_remove_path_from_sysfs(struct rtrs_clt_sess *sess,
 	 *    removing the path.
 	 */
 	do {
-		rtrs_clt_close_conns(sess, true);
-		changed = rtrs_clt_change_state_get_old(sess,
+		rtrs_clt_close_conns(clt_path, true);
+		changed = rtrs_clt_change_state_get_old(clt_path,
 							RTRS_CLT_DEAD,
 							&old_state);
 	} while (!changed && old_state != RTRS_CLT_DEAD);
 
 	if (changed) {
-		rtrs_clt_remove_path_from_arr(sess);
-		rtrs_clt_destroy_sess_files(sess, sysfs_self);
-		kobject_put(&sess->kobj);
+		rtrs_clt_remove_path_from_arr(clt_path);
+		rtrs_clt_destroy_path_files(clt_path, sysfs_self);
+		kobject_put(&clt_path->kobj);
 	}
 
 	return 0;
@@ -2970,7 +2991,7 @@ int rtrs_clt_request(int dir, struct rtrs_clt_req_ops *ops,
 		      struct scatterlist *sg, unsigned int sg_cnt)
 {
 	struct rtrs_clt_io_req *req;
-	struct rtrs_clt_sess *sess;
+	struct rtrs_clt_path *clt_path;
 
 	enum dma_data_direction dma_dir;
 	int err = -ECONNABORTED, i;
@@ -2992,19 +3013,19 @@ int rtrs_clt_request(int dir, struct rtrs_clt_req_ops *ops,
 
 	rcu_read_lock();
 	for (path_it_init(&it, clt);
-	     (sess = it.next_path(&it)) && it.i < it.clt->paths_num; it.i++) {
-		if (READ_ONCE(sess->state) != RTRS_CLT_CONNECTED)
+	     (clt_path = it.next_path(&it)) && it.i < it.clt->paths_num; it.i++) {
+		if (READ_ONCE(clt_path->state) != RTRS_CLT_CONNECTED)
 			continue;
 
-		if (usr_len + hdr_len > sess->max_hdr_size) {
-			rtrs_wrn_rl(sess->clt,
+		if (usr_len + hdr_len > clt_path->max_hdr_size) {
+			rtrs_wrn_rl(clt_path->clt,
 				     "%s request failed, user message size is %zu and header length %zu, but max size is %u\n",
 				     dir == READ ? "Read" : "Write",
-				     usr_len, hdr_len, sess->max_hdr_size);
+				     usr_len, hdr_len, clt_path->max_hdr_size);
 			err = -EMSGSIZE;
 			break;
 		}
-		req = rtrs_clt_get_req(sess, ops->conf_fn, permit, ops->priv,
+		req = rtrs_clt_get_req(clt_path, ops->conf_fn, permit, ops->priv,
 				       vec, usr_len, sg, sg_cnt, data_len,
 				       dma_dir);
 		if (dir == READ)
@@ -3030,16 +3051,16 @@ int rtrs_clt_rdma_cq_direct(struct rtrs_clt *clt, unsigned int index)
 	/* If no path, return -1 for block layer not to try again */
 	int cnt = -1;
 	struct rtrs_con *con;
-	struct rtrs_clt_sess *sess;
+	struct rtrs_clt_path *clt_path;
 	struct path_it it;
 
 	rcu_read_lock();
 	for (path_it_init(&it, clt);
-	     (sess = it.next_path(&it)) && it.i < it.clt->paths_num; it.i++) {
-		if (READ_ONCE(sess->state) != RTRS_CLT_CONNECTED)
+	     (clt_path = it.next_path(&it)) && it.i < it.clt->paths_num; it.i++) {
+		if (READ_ONCE(clt_path->state) != RTRS_CLT_CONNECTED)
 			continue;
 
-		con = sess->s.con[index + 1];
+		con = clt_path->s.con[index + 1];
 		cnt = ib_process_cq_direct(con->cq, -1);
 		if (cnt)
 			break;
@@ -3077,12 +3098,12 @@ EXPORT_SYMBOL(rtrs_clt_query);
 int rtrs_clt_create_path_from_sysfs(struct rtrs_clt *clt,
 				     struct rtrs_addr *addr)
 {
-	struct rtrs_clt_sess *sess;
+	struct rtrs_clt_path *clt_path;
 	int err;
 
-	sess = alloc_sess(clt, addr, nr_cpu_ids, 0);
-	if (IS_ERR(sess))
-		return PTR_ERR(sess);
+	clt_path = alloc_path(clt, addr, nr_cpu_ids, 0);
+	if (IS_ERR(clt_path))
+		return PTR_ERR(clt_path);
 
 	mutex_lock(&clt->paths_mutex);
 	if (clt->paths_num == 0) {
@@ -3091,7 +3112,7 @@ int rtrs_clt_create_path_from_sysfs(struct rtrs_clt *clt,
 		 * the addition of the first path is like a new session for
 		 * the storage server
 		 */
-		sess->for_new_clt = 1;
+		clt_path->for_new_clt = 1;
 	}
 
 	mutex_unlock(&clt->paths_mutex);
@@ -3101,24 +3122,24 @@ int rtrs_clt_create_path_from_sysfs(struct rtrs_clt *clt,
 	 * IO will never grab it.  Also it is very important to add
 	 * path before init, since init fires LINK_CONNECTED event.
 	 */
-	rtrs_clt_add_path_to_arr(sess);
+	rtrs_clt_add_path_to_arr(clt_path);
 
-	err = init_sess(sess);
+	err = init_path(clt_path);
 	if (err)
-		goto close_sess;
+		goto close_path;
 
-	err = rtrs_clt_create_sess_files(sess);
+	err = rtrs_clt_create_path_files(clt_path);
 	if (err)
-		goto close_sess;
+		goto close_path;
 
 	return 0;
 
-close_sess:
-	rtrs_clt_remove_path_from_arr(sess);
-	rtrs_clt_close_conns(sess, true);
-	free_percpu(sess->stats->pcpu_stats);
-	kfree(sess->stats);
-	free_sess(sess);
+close_path:
+	rtrs_clt_remove_path_from_arr(clt_path);
+	rtrs_clt_close_conns(clt_path, true);
+	free_percpu(clt_path->stats->pcpu_stats);
+	kfree(clt_path->stats);
+	free_path(clt_path);
 
 	return err;
 }
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.h b/drivers/infiniband/ulp/rtrs/rtrs-clt.h
index 9dc819885ec7..7f2a64995fb6 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.h
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.h
@@ -124,8 +124,8 @@ struct rtrs_rbuf {
 	u32 rkey;
 };
 
-struct rtrs_clt_sess {
-	struct rtrs_sess	s;
+struct rtrs_clt_path {
+	struct rtrs_path	s;
 	struct rtrs_clt	*clt;
 	wait_queue_head_t	state_wq;
 	enum rtrs_clt_state	state;
@@ -156,7 +156,7 @@ struct rtrs_clt_sess {
 struct rtrs_clt {
 	struct list_head	paths_list; /* rcu protected list */
 	size_t			paths_num;
-	struct rtrs_clt_sess
+	struct rtrs_clt_path
 	__rcu * __percpu	*pcpu_path;
 	uuid_t			paths_uuid;
 	int			paths_up;
@@ -186,9 +186,9 @@ static inline struct rtrs_clt_con *to_clt_con(struct rtrs_con *c)
 	return container_of(c, struct rtrs_clt_con, c);
 }
 
-static inline struct rtrs_clt_sess *to_clt_sess(struct rtrs_sess *s)
+static inline struct rtrs_clt_path *to_clt_path(struct rtrs_path *s)
 {
-	return container_of(s, struct rtrs_clt_sess, s);
+	return container_of(s, struct rtrs_clt_path, s);
 }
 
 static inline int permit_size(struct rtrs_clt *clt)
@@ -201,16 +201,16 @@ static inline struct rtrs_permit *get_permit(struct rtrs_clt *clt, int idx)
 	return (struct rtrs_permit *)(clt->permits + permit_size(clt) * idx);
 }
 
-int rtrs_clt_reconnect_from_sysfs(struct rtrs_clt_sess *sess);
-void rtrs_clt_close_conns(struct rtrs_clt_sess *sess, bool wait);
+int rtrs_clt_reconnect_from_sysfs(struct rtrs_clt_path *path);
+void rtrs_clt_close_conns(struct rtrs_clt_path *clt_path, bool wait);
 int rtrs_clt_create_path_from_sysfs(struct rtrs_clt *clt,
 				     struct rtrs_addr *addr);
-int rtrs_clt_remove_path_from_sysfs(struct rtrs_clt_sess *sess,
+int rtrs_clt_remove_path_from_sysfs(struct rtrs_clt_path *path,
 				     const struct attribute *sysfs_self);
 
 void rtrs_clt_set_max_reconnect_attempts(struct rtrs_clt *clt, int value);
 int rtrs_clt_get_max_reconnect_attempts(const struct rtrs_clt *clt);
-void free_sess(struct rtrs_clt_sess *sess);
+void free_path(struct rtrs_clt_path *clt_path);
 
 /* rtrs-clt-stats.c */
 
@@ -243,8 +243,8 @@ ssize_t rtrs_clt_reset_all_help(struct rtrs_clt_stats *stats,
 int rtrs_clt_create_sysfs_root_files(struct rtrs_clt *clt);
 void rtrs_clt_destroy_sysfs_root(struct rtrs_clt *clt);
 
-int rtrs_clt_create_sess_files(struct rtrs_clt_sess *sess);
-void rtrs_clt_destroy_sess_files(struct rtrs_clt_sess *sess,
+int rtrs_clt_create_path_files(struct rtrs_clt_path *clt_path);
+void rtrs_clt_destroy_path_files(struct rtrs_clt_path *clt_path,
 				  const struct attribute *sysfs_self);
 
 #endif /* RTRS_CLT_H */
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-pri.h b/drivers/infiniband/ulp/rtrs/rtrs-pri.h
index d12ddfa50747..b69fa1fe9a70 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-pri.h
+++ b/drivers/infiniband/ulp/rtrs/rtrs-pri.h
@@ -23,6 +23,17 @@
 #define RTRS_PROTO_VER_STRING __stringify(RTRS_PROTO_VER_MAJOR) "." \
 			       __stringify(RTRS_PROTO_VER_MINOR)
 
+/*
+ * Max IB immediate data size is 2^28 (MAX_IMM_PAYL_BITS)
+ * and the minimum chunk size is 4096 (2^12).
+ * So the maximum sess_queue_depth is 65536 (2^16) in theory.
+ * But mempool_create, create_qp and ib_post_send fail with
+ * "cannot allocate memory" error if sess_queue_depth is too big.
+ * Therefore the pratical max value of sess_queue_depth is
+ * somewhere between 1 and 65534 and it depends on the system.
+ */
+#define MAX_SESS_QUEUE_DEPTH 65535
+
 enum rtrs_imm_const {
 	MAX_IMM_TYPE_BITS = 4,
 	MAX_IMM_TYPE_MASK = ((1 << MAX_IMM_TYPE_BITS) - 1),
@@ -46,16 +57,6 @@ enum {
 
 	MAX_PATHS_NUM = 128,
 
-	/*
-	 * Max IB immediate data size is 2^28 (MAX_IMM_PAYL_BITS)
-	 * and the minimum chunk size is 4096 (2^12).
-	 * So the maximum sess_queue_depth is 65536 (2^16) in theory.
-	 * But mempool_create, create_qp and ib_post_send fail with
-	 * "cannot allocate memory" error if sess_queue_depth is too big.
-	 * Therefore the pratical max value of sess_queue_depth is
-	 * somewhere between 1 and 65534 and it depends on the system.
-	 */
-	MAX_SESS_QUEUE_DEPTH = 65535,
 	MIN_CHUNK_SIZE = 8192,
 
 	RTRS_HB_INTERVAL_MS = 5000,
@@ -90,7 +91,7 @@ struct rtrs_ib_dev {
 };
 
 struct rtrs_con {
-	struct rtrs_sess	*sess;
+	struct rtrs_path	*path;
 	struct ib_qp		*qp;
 	struct ib_cq		*cq;
 	struct rdma_cm_id	*cm_id;
@@ -100,7 +101,7 @@ struct rtrs_con {
 	atomic_t		sq_wr_avail;
 };
 
-struct rtrs_sess {
+struct rtrs_path {
 	struct list_head	entry;
 	struct sockaddr_storage dst_addr;
 	struct sockaddr_storage src_addr;
@@ -229,11 +230,11 @@ struct rtrs_msg_conn_rsp {
 /**
  * struct rtrs_msg_info_req
  * @type:		@RTRS_MSG_INFO_REQ
- * @sessname:		Session name chosen by client
+ * @pathname:		Path name chosen by client
  */
 struct rtrs_msg_info_req {
 	__le16		type;
-	u8		sessname[NAME_MAX];
+	u8		pathname[NAME_MAX];
 	u8		reserved[15];
 };
 
@@ -313,19 +314,19 @@ int rtrs_iu_post_rdma_write_imm(struct rtrs_con *con, struct rtrs_iu *iu,
 
 int rtrs_post_recv_empty(struct rtrs_con *con, struct ib_cqe *cqe);
 
-int rtrs_cq_qp_create(struct rtrs_sess *sess, struct rtrs_con *con,
+int rtrs_cq_qp_create(struct rtrs_path *path, struct rtrs_con *con,
 		      u32 max_send_sge, int cq_vector, int nr_cqe,
 		      u32 max_send_wr, u32 max_recv_wr,
 		      enum ib_poll_context poll_ctx);
 void rtrs_cq_qp_destroy(struct rtrs_con *con);
 
-void rtrs_init_hb(struct rtrs_sess *sess, struct ib_cqe *cqe,
+void rtrs_init_hb(struct rtrs_path *path, struct ib_cqe *cqe,
 		  unsigned int interval_ms, unsigned int missed_max,
 		  void (*err_handler)(struct rtrs_con *con),
 		  struct workqueue_struct *wq);
-void rtrs_start_hb(struct rtrs_sess *sess);
-void rtrs_stop_hb(struct rtrs_sess *sess);
-void rtrs_send_hb_ack(struct rtrs_sess *sess);
+void rtrs_start_hb(struct rtrs_path *path);
+void rtrs_stop_hb(struct rtrs_path *path);
+void rtrs_send_hb_ack(struct rtrs_path *path);
 
 void rtrs_rdma_dev_pd_init(enum ib_pd_flags pd_flags,
 			   struct rtrs_rdma_dev_pd *pool);
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv-sysfs.c b/drivers/infiniband/ulp/rtrs/rtrs-srv-sysfs.c
index 20efd44297fb..309080184aac 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-srv-sysfs.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-srv-sysfs.c
@@ -15,10 +15,10 @@
 
 static void rtrs_srv_release(struct kobject *kobj)
 {
-	struct rtrs_srv_sess *sess;
+	struct rtrs_srv_path *srv_path;
 
-	sess = container_of(kobj, struct rtrs_srv_sess, kobj);
-	kfree(sess);
+	srv_path = container_of(kobj, struct rtrs_srv_path, kobj);
+	kfree(srv_path);
 }
 
 static struct kobj_type ktype = {
@@ -36,24 +36,25 @@ static ssize_t rtrs_srv_disconnect_store(struct kobject *kobj,
 					  struct kobj_attribute *attr,
 					  const char *buf, size_t count)
 {
-	struct rtrs_srv_sess *sess;
-	struct rtrs_sess *s;
+	struct rtrs_srv_path *srv_path;
+	struct rtrs_path *s;
 	char str[MAXHOSTNAMELEN];
 
-	sess = container_of(kobj, struct rtrs_srv_sess, kobj);
-	s = &sess->s;
+	srv_path = container_of(kobj, struct rtrs_srv_path, kobj);
+	s = &srv_path->s;
 	if (!sysfs_streq(buf, "1")) {
 		rtrs_err(s, "%s: invalid value: '%s'\n",
 			  attr->attr.name, buf);
 		return -EINVAL;
 	}
 
-	sockaddr_to_str((struct sockaddr *)&sess->s.dst_addr, str, sizeof(str));
+	sockaddr_to_str((struct sockaddr *)&srv_path->s.dst_addr, str,
+			sizeof(str));
 
 	rtrs_info(s, "disconnect for path %s requested\n", str);
 	/* first remove sysfs itself to avoid deadlock */
-	sysfs_remove_file_self(&sess->kobj, &attr->attr);
-	close_sess(sess);
+	sysfs_remove_file_self(&srv_path->kobj, &attr->attr);
+	close_path(srv_path);
 
 	return count;
 }
@@ -66,11 +67,11 @@ static ssize_t rtrs_srv_hca_port_show(struct kobject *kobj,
 				       struct kobj_attribute *attr,
 				       char *page)
 {
-	struct rtrs_srv_sess *sess;
+	struct rtrs_srv_path *srv_path;
 	struct rtrs_con *usr_con;
 
-	sess = container_of(kobj, typeof(*sess), kobj);
-	usr_con = sess->s.con[0];
+	srv_path = container_of(kobj, typeof(*srv_path), kobj);
+	usr_con = srv_path->s.con[0];
 
 	return sysfs_emit(page, "%u\n", usr_con->cm_id->port_num);
 }
@@ -82,11 +83,11 @@ static ssize_t rtrs_srv_hca_name_show(struct kobject *kobj,
 				       struct kobj_attribute *attr,
 				       char *page)
 {
-	struct rtrs_srv_sess *sess;
+	struct rtrs_srv_path *srv_path;
 
-	sess = container_of(kobj, struct rtrs_srv_sess, kobj);
+	srv_path = container_of(kobj, struct rtrs_srv_path, kobj);
 
-	return sysfs_emit(page, "%s\n", sess->s.dev->ib_dev->name);
+	return sysfs_emit(page, "%s\n", srv_path->s.dev->ib_dev->name);
 }
 
 static struct kobj_attribute rtrs_srv_hca_name_attr =
@@ -96,11 +97,11 @@ static ssize_t rtrs_srv_src_addr_show(struct kobject *kobj,
 				       struct kobj_attribute *attr,
 				       char *page)
 {
-	struct rtrs_srv_sess *sess;
+	struct rtrs_srv_path *srv_path;
 	int cnt;
 
-	sess = container_of(kobj, struct rtrs_srv_sess, kobj);
-	cnt = sockaddr_to_str((struct sockaddr *)&sess->s.dst_addr,
+	srv_path = container_of(kobj, struct rtrs_srv_path, kobj);
+	cnt = sockaddr_to_str((struct sockaddr *)&srv_path->s.dst_addr,
 			      page, PAGE_SIZE);
 	return cnt + scnprintf(page + cnt, PAGE_SIZE - cnt, "\n");
 }
@@ -112,11 +113,11 @@ static ssize_t rtrs_srv_dst_addr_show(struct kobject *kobj,
 				       struct kobj_attribute *attr,
 				       char *page)
 {
-	struct rtrs_srv_sess *sess;
+	struct rtrs_srv_path *srv_path;
 	int len;
 
-	sess = container_of(kobj, struct rtrs_srv_sess, kobj);
-	len = sockaddr_to_str((struct sockaddr *)&sess->s.src_addr, page,
+	srv_path = container_of(kobj, struct rtrs_srv_path, kobj);
+	len = sockaddr_to_str((struct sockaddr *)&srv_path->s.src_addr, page,
 			      PAGE_SIZE);
 	len += sysfs_emit_at(page, len, "\n");
 	return len;
@@ -125,7 +126,7 @@ static ssize_t rtrs_srv_dst_addr_show(struct kobject *kobj,
 static struct kobj_attribute rtrs_srv_dst_addr_attr =
 	__ATTR(dst_addr, 0444, rtrs_srv_dst_addr_show, NULL);
 
-static struct attribute *rtrs_srv_sess_attrs[] = {
+static struct attribute *rtrs_srv_path_attrs[] = {
 	&rtrs_srv_hca_name_attr.attr,
 	&rtrs_srv_hca_port_attr.attr,
 	&rtrs_srv_src_addr_attr.attr,
@@ -134,8 +135,8 @@ static struct attribute *rtrs_srv_sess_attrs[] = {
 	NULL,
 };
 
-static const struct attribute_group rtrs_srv_sess_attr_group = {
-	.attrs = rtrs_srv_sess_attrs,
+static const struct attribute_group rtrs_srv_path_attr_group = {
+	.attrs = rtrs_srv_path_attrs,
 };
 
 STAT_ATTR(struct rtrs_srv_stats, rdma,
@@ -151,9 +152,9 @@ static const struct attribute_group rtrs_srv_stats_attr_group = {
 	.attrs = rtrs_srv_stats_attrs,
 };
 
-static int rtrs_srv_create_once_sysfs_root_folders(struct rtrs_srv_sess *sess)
+static int rtrs_srv_create_once_sysfs_root_folders(struct rtrs_srv_path *srv_path)
 {
-	struct rtrs_srv *srv = sess->srv;
+	struct rtrs_srv *srv = srv_path->srv;
 	int err = 0;
 
 	mutex_lock(&srv->paths_mutex);
@@ -164,7 +165,7 @@ static int rtrs_srv_create_once_sysfs_root_folders(struct rtrs_srv_sess *sess)
 		goto unlock;
 	}
 	srv->dev.class = rtrs_dev_class;
-	err = dev_set_name(&srv->dev, "%s", sess->s.sessname);
+	err = dev_set_name(&srv->dev, "%s", srv_path->s.sessname);
 	if (err)
 		goto unlock;
 
@@ -196,9 +197,9 @@ unlock:
 }
 
 static void
-rtrs_srv_destroy_once_sysfs_root_folders(struct rtrs_srv_sess *sess)
+rtrs_srv_destroy_once_sysfs_root_folders(struct rtrs_srv_path *srv_path)
 {
-	struct rtrs_srv *srv = sess->srv;
+	struct rtrs_srv *srv = srv_path->srv;
 
 	mutex_lock(&srv->paths_mutex);
 	if (!--srv->dev_ref) {
@@ -213,7 +214,7 @@ rtrs_srv_destroy_once_sysfs_root_folders(struct rtrs_srv_sess *sess)
 	}
 }
 
-static void rtrs_srv_sess_stats_release(struct kobject *kobj)
+static void rtrs_srv_path_stats_release(struct kobject *kobj)
 {
 	struct rtrs_srv_stats *stats;
 
@@ -224,22 +225,22 @@ static void rtrs_srv_sess_stats_release(struct kobject *kobj)
 
 static struct kobj_type ktype_stats = {
 	.sysfs_ops = &kobj_sysfs_ops,
-	.release = rtrs_srv_sess_stats_release,
+	.release = rtrs_srv_path_stats_release,
 };
 
-static int rtrs_srv_create_stats_files(struct rtrs_srv_sess *sess)
+static int rtrs_srv_create_stats_files(struct rtrs_srv_path *srv_path)
 {
 	int err;
-	struct rtrs_sess *s = &sess->s;
+	struct rtrs_path *s = &srv_path->s;
 
-	err = kobject_init_and_add(&sess->stats->kobj_stats, &ktype_stats,
-				   &sess->kobj, "stats");
+	err = kobject_init_and_add(&srv_path->stats->kobj_stats, &ktype_stats,
+				   &srv_path->kobj, "stats");
 	if (err) {
 		rtrs_err(s, "kobject_init_and_add(): %d\n", err);
-		kobject_put(&sess->stats->kobj_stats);
+		kobject_put(&srv_path->stats->kobj_stats);
 		return err;
 	}
-	err = sysfs_create_group(&sess->stats->kobj_stats,
+	err = sysfs_create_group(&srv_path->stats->kobj_stats,
 				 &rtrs_srv_stats_attr_group);
 	if (err) {
 		rtrs_err(s, "sysfs_create_group(): %d\n", err);
@@ -249,64 +250,64 @@ static int rtrs_srv_create_stats_files(struct rtrs_srv_sess *sess)
 	return 0;
 
 err:
-	kobject_del(&sess->stats->kobj_stats);
-	kobject_put(&sess->stats->kobj_stats);
+	kobject_del(&srv_path->stats->kobj_stats);
+	kobject_put(&srv_path->stats->kobj_stats);
 
 	return err;
 }
 
-int rtrs_srv_create_sess_files(struct rtrs_srv_sess *sess)
+int rtrs_srv_create_path_files(struct rtrs_srv_path *srv_path)
 {
-	struct rtrs_srv *srv = sess->srv;
-	struct rtrs_sess *s = &sess->s;
+	struct rtrs_srv *srv = srv_path->srv;
+	struct rtrs_path *s = &srv_path->s;
 	char str[NAME_MAX];
 	int err;
 	struct rtrs_addr path = {
-		.src = &sess->s.dst_addr,
-		.dst = &sess->s.src_addr,
+		.src = &srv_path->s.dst_addr,
+		.dst = &srv_path->s.src_addr,
 	};
 
 	rtrs_addr_to_str(&path, str, sizeof(str));
-	err = rtrs_srv_create_once_sysfs_root_folders(sess);
+	err = rtrs_srv_create_once_sysfs_root_folders(srv_path);
 	if (err)
 		return err;
 
-	err = kobject_init_and_add(&sess->kobj, &ktype, srv->kobj_paths,
+	err = kobject_init_and_add(&srv_path->kobj, &ktype, srv->kobj_paths,
 				   "%s", str);
 	if (err) {
 		rtrs_err(s, "kobject_init_and_add(): %d\n", err);
 		goto destroy_root;
 	}
-	err = sysfs_create_group(&sess->kobj, &rtrs_srv_sess_attr_group);
+	err = sysfs_create_group(&srv_path->kobj, &rtrs_srv_path_attr_group);
 	if (err) {
 		rtrs_err(s, "sysfs_create_group(): %d\n", err);
 		goto put_kobj;
 	}
-	err = rtrs_srv_create_stats_files(sess);
+	err = rtrs_srv_create_stats_files(srv_path);
 	if (err)
 		goto remove_group;
 
 	return 0;
 
 remove_group:
-	sysfs_remove_group(&sess->kobj, &rtrs_srv_sess_attr_group);
+	sysfs_remove_group(&srv_path->kobj, &rtrs_srv_path_attr_group);
 put_kobj:
-	kobject_del(&sess->kobj);
+	kobject_del(&srv_path->kobj);
 destroy_root:
-	kobject_put(&sess->kobj);
-	rtrs_srv_destroy_once_sysfs_root_folders(sess);
+	kobject_put(&srv_path->kobj);
+	rtrs_srv_destroy_once_sysfs_root_folders(srv_path);
 
 	return err;
 }
 
-void rtrs_srv_destroy_sess_files(struct rtrs_srv_sess *sess)
+void rtrs_srv_destroy_path_files(struct rtrs_srv_path *srv_path)
 {
-	if (sess->kobj.state_in_sysfs) {
-		kobject_del(&sess->stats->kobj_stats);
-		kobject_put(&sess->stats->kobj_stats);
-		sysfs_remove_group(&sess->kobj, &rtrs_srv_sess_attr_group);
-		kobject_put(&sess->kobj);
+	if (srv_path->kobj.state_in_sysfs) {
+		kobject_del(&srv_path->stats->kobj_stats);
+		kobject_put(&srv_path->stats->kobj_stats);
+		sysfs_remove_group(&srv_path->kobj, &rtrs_srv_path_attr_group);
+		kobject_put(&srv_path->kobj);
 
-		rtrs_srv_destroy_once_sysfs_root_folders(sess);
+		rtrs_srv_destroy_once_sysfs_root_folders(srv_path);
 	}
 }
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv.c b/drivers/infiniband/ulp/rtrs/rtrs-srv.c
index 716ef7b23558..733116554e0b 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-srv.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-srv.c
@@ -62,19 +62,19 @@ static inline struct rtrs_srv_con *to_srv_con(struct rtrs_con *c)
 	return container_of(c, struct rtrs_srv_con, c);
 }
 
-static inline struct rtrs_srv_sess *to_srv_sess(struct rtrs_sess *s)
+static inline struct rtrs_srv_path *to_srv_path(struct rtrs_path *s)
 {
-	return container_of(s, struct rtrs_srv_sess, s);
+	return container_of(s, struct rtrs_srv_path, s);
 }
 
-static bool rtrs_srv_change_state(struct rtrs_srv_sess *sess,
+static bool rtrs_srv_change_state(struct rtrs_srv_path *srv_path,
 				  enum rtrs_srv_state new_state)
 {
 	enum rtrs_srv_state old_state;
 	bool changed = false;
 
-	spin_lock_irq(&sess->state_lock);
-	old_state = sess->state;
+	spin_lock_irq(&srv_path->state_lock);
+	old_state = srv_path->state;
 	switch (new_state) {
 	case RTRS_SRV_CONNECTED:
 		if (old_state == RTRS_SRV_CONNECTING)
@@ -93,8 +93,8 @@ static bool rtrs_srv_change_state(struct rtrs_srv_sess *sess,
 		break;
 	}
 	if (changed)
-		sess->state = new_state;
-	spin_unlock_irq(&sess->state_lock);
+		srv_path->state = new_state;
+	spin_unlock_irq(&srv_path->state_lock);
 
 	return changed;
 }
@@ -106,16 +106,16 @@ static void free_id(struct rtrs_srv_op *id)
 	kfree(id);
 }
 
-static void rtrs_srv_free_ops_ids(struct rtrs_srv_sess *sess)
+static void rtrs_srv_free_ops_ids(struct rtrs_srv_path *srv_path)
 {
-	struct rtrs_srv *srv = sess->srv;
+	struct rtrs_srv *srv = srv_path->srv;
 	int i;
 
-	if (sess->ops_ids) {
+	if (srv_path->ops_ids) {
 		for (i = 0; i < srv->queue_depth; i++)
-			free_id(sess->ops_ids[i]);
-		kfree(sess->ops_ids);
-		sess->ops_ids = NULL;
+			free_id(srv_path->ops_ids[i]);
+		kfree(srv_path->ops_ids);
+		srv_path->ops_ids = NULL;
 	}
 }
 
@@ -127,21 +127,24 @@ static struct ib_cqe io_comp_cqe = {
 
 static inline void rtrs_srv_inflight_ref_release(struct percpu_ref *ref)
 {
-	struct rtrs_srv_sess *sess = container_of(ref, struct rtrs_srv_sess, ids_inflight_ref);
+	struct rtrs_srv_path *srv_path = container_of(ref,
+						      struct rtrs_srv_path,
+						      ids_inflight_ref);
 
-	percpu_ref_exit(&sess->ids_inflight_ref);
-	complete(&sess->complete_done);
+	percpu_ref_exit(&srv_path->ids_inflight_ref);
+	complete(&srv_path->complete_done);
 }
 
-static int rtrs_srv_alloc_ops_ids(struct rtrs_srv_sess *sess)
+static int rtrs_srv_alloc_ops_ids(struct rtrs_srv_path *srv_path)
 {
-	struct rtrs_srv *srv = sess->srv;
+	struct rtrs_srv *srv = srv_path->srv;
 	struct rtrs_srv_op *id;
 	int i, ret;
 
-	sess->ops_ids = kcalloc(srv->queue_depth, sizeof(*sess->ops_ids),
-				GFP_KERNEL);
-	if (!sess->ops_ids)
+	srv_path->ops_ids = kcalloc(srv->queue_depth,
+				    sizeof(*srv_path->ops_ids),
+				    GFP_KERNEL);
+	if (!srv_path->ops_ids)
 		goto err;
 
 	for (i = 0; i < srv->queue_depth; ++i) {
@@ -149,44 +152,44 @@ static int rtrs_srv_alloc_ops_ids(struct rtrs_srv_sess *sess)
 		if (!id)
 			goto err;
 
-		sess->ops_ids[i] = id;
+		srv_path->ops_ids[i] = id;
 	}
 
-	ret = percpu_ref_init(&sess->ids_inflight_ref,
+	ret = percpu_ref_init(&srv_path->ids_inflight_ref,
 			      rtrs_srv_inflight_ref_release, 0, GFP_KERNEL);
 	if (ret) {
 		pr_err("Percpu reference init failed\n");
 		goto err;
 	}
-	init_completion(&sess->complete_done);
+	init_completion(&srv_path->complete_done);
 
 	return 0;
 
 err:
-	rtrs_srv_free_ops_ids(sess);
+	rtrs_srv_free_ops_ids(srv_path);
 	return -ENOMEM;
 }
 
-static inline void rtrs_srv_get_ops_ids(struct rtrs_srv_sess *sess)
+static inline void rtrs_srv_get_ops_ids(struct rtrs_srv_path *srv_path)
 {
-	percpu_ref_get(&sess->ids_inflight_ref);
+	percpu_ref_get(&srv_path->ids_inflight_ref);
 }
 
-static inline void rtrs_srv_put_ops_ids(struct rtrs_srv_sess *sess)
+static inline void rtrs_srv_put_ops_ids(struct rtrs_srv_path *srv_path)
 {
-	percpu_ref_put(&sess->ids_inflight_ref);
+	percpu_ref_put(&srv_path->ids_inflight_ref);
 }
 
 static void rtrs_srv_reg_mr_done(struct ib_cq *cq, struct ib_wc *wc)
 {
 	struct rtrs_srv_con *con = to_srv_con(wc->qp->qp_context);
-	struct rtrs_sess *s = con->c.sess;
-	struct rtrs_srv_sess *sess = to_srv_sess(s);
+	struct rtrs_path *s = con->c.path;
+	struct rtrs_srv_path *srv_path = to_srv_path(s);
 
 	if (wc->status != IB_WC_SUCCESS) {
 		rtrs_err(s, "REG MR failed: %s\n",
 			  ib_wc_status_msg(wc->status));
-		close_sess(sess);
+		close_path(srv_path);
 		return;
 	}
 }
@@ -197,9 +200,9 @@ static struct ib_cqe local_reg_cqe = {
 
 static int rdma_write_sg(struct rtrs_srv_op *id)
 {
-	struct rtrs_sess *s = id->con->c.sess;
-	struct rtrs_srv_sess *sess = to_srv_sess(s);
-	dma_addr_t dma_addr = sess->dma_addr[id->msg_id];
+	struct rtrs_path *s = id->con->c.path;
+	struct rtrs_srv_path *srv_path = to_srv_path(s);
+	dma_addr_t dma_addr = srv_path->dma_addr[id->msg_id];
 	struct rtrs_srv_mr *srv_mr;
 	struct ib_send_wr inv_wr;
 	struct ib_rdma_wr imm_wr;
@@ -233,7 +236,7 @@ static int rdma_write_sg(struct rtrs_srv_op *id)
 		return -EINVAL;
 	}
 
-	plist->lkey = sess->s.dev->ib_pd->local_dma_lkey;
+	plist->lkey = srv_path->s.dev->ib_pd->local_dma_lkey;
 	offset += plist->length;
 
 	wr->wr.sg_list	= plist;
@@ -284,7 +287,7 @@ static int rdma_write_sg(struct rtrs_srv_op *id)
 	if (always_invalidate) {
 		struct rtrs_msg_rkey_rsp *msg;
 
-		srv_mr = &sess->mrs[id->msg_id];
+		srv_mr = &srv_path->mrs[id->msg_id];
 		rwr.wr.opcode = IB_WR_REG_MR;
 		rwr.wr.wr_cqe = &local_reg_cqe;
 		rwr.wr.num_sge = 0;
@@ -300,11 +303,11 @@ static int rdma_write_sg(struct rtrs_srv_op *id)
 
 		list.addr   = srv_mr->iu->dma_addr;
 		list.length = sizeof(*msg);
-		list.lkey   = sess->s.dev->ib_pd->local_dma_lkey;
+		list.lkey   = srv_path->s.dev->ib_pd->local_dma_lkey;
 		imm_wr.wr.sg_list = &list;
 		imm_wr.wr.num_sge = 1;
 		imm_wr.wr.opcode = IB_WR_SEND_WITH_IMM;
-		ib_dma_sync_single_for_device(sess->s.dev->ib_dev,
+		ib_dma_sync_single_for_device(srv_path->s.dev->ib_dev,
 					      srv_mr->iu->dma_addr,
 					      srv_mr->iu->size, DMA_TO_DEVICE);
 	} else {
@@ -317,7 +320,7 @@ static int rdma_write_sg(struct rtrs_srv_op *id)
 							     0, need_inval));
 
 	imm_wr.wr.wr_cqe   = &io_comp_cqe;
-	ib_dma_sync_single_for_device(sess->s.dev->ib_dev, dma_addr,
+	ib_dma_sync_single_for_device(srv_path->s.dev->ib_dev, dma_addr,
 				      offset, DMA_BIDIRECTIONAL);
 
 	err = ib_post_send(id->con->c.qp, &id->tx_wr.wr, NULL);
@@ -341,8 +344,8 @@ static int rdma_write_sg(struct rtrs_srv_op *id)
 static int send_io_resp_imm(struct rtrs_srv_con *con, struct rtrs_srv_op *id,
 			    int errno)
 {
-	struct rtrs_sess *s = con->c.sess;
-	struct rtrs_srv_sess *sess = to_srv_sess(s);
+	struct rtrs_path *s = con->c.path;
+	struct rtrs_srv_path *srv_path = to_srv_path(s);
 	struct ib_send_wr inv_wr, *wr = NULL;
 	struct ib_rdma_wr imm_wr;
 	struct ib_reg_wr rwr;
@@ -402,7 +405,7 @@ static int send_io_resp_imm(struct rtrs_srv_con *con, struct rtrs_srv_op *id,
 		struct ib_sge list;
 		struct rtrs_msg_rkey_rsp *msg;
 
-		srv_mr = &sess->mrs[id->msg_id];
+		srv_mr = &srv_path->mrs[id->msg_id];
 		rwr.wr.next = &imm_wr.wr;
 		rwr.wr.opcode = IB_WR_REG_MR;
 		rwr.wr.wr_cqe = &local_reg_cqe;
@@ -419,11 +422,11 @@ static int send_io_resp_imm(struct rtrs_srv_con *con, struct rtrs_srv_op *id,
 
 		list.addr   = srv_mr->iu->dma_addr;
 		list.length = sizeof(*msg);
-		list.lkey   = sess->s.dev->ib_pd->local_dma_lkey;
+		list.lkey   = srv_path->s.dev->ib_pd->local_dma_lkey;
 		imm_wr.wr.sg_list = &list;
 		imm_wr.wr.num_sge = 1;
 		imm_wr.wr.opcode = IB_WR_SEND_WITH_IMM;
-		ib_dma_sync_single_for_device(sess->s.dev->ib_dev,
+		ib_dma_sync_single_for_device(srv_path->s.dev->ib_dev,
 					      srv_mr->iu->dma_addr,
 					      srv_mr->iu->size, DMA_TO_DEVICE);
 	} else {
@@ -444,11 +447,11 @@ static int send_io_resp_imm(struct rtrs_srv_con *con, struct rtrs_srv_op *id,
 	return err;
 }
 
-void close_sess(struct rtrs_srv_sess *sess)
+void close_path(struct rtrs_srv_path *srv_path)
 {
-	if (rtrs_srv_change_state(sess, RTRS_SRV_CLOSING))
-		queue_work(rtrs_wq, &sess->close_work);
-	WARN_ON(sess->state != RTRS_SRV_CLOSING);
+	if (rtrs_srv_change_state(srv_path, RTRS_SRV_CLOSING))
+		queue_work(rtrs_wq, &srv_path->close_work);
+	WARN_ON(srv_path->state != RTRS_SRV_CLOSING);
 }
 
 static inline const char *rtrs_srv_state_str(enum rtrs_srv_state state)
@@ -480,35 +483,35 @@ static inline const char *rtrs_srv_state_str(enum rtrs_srv_state state)
  */
 bool rtrs_srv_resp_rdma(struct rtrs_srv_op *id, int status)
 {
-	struct rtrs_srv_sess *sess;
+	struct rtrs_srv_path *srv_path;
 	struct rtrs_srv_con *con;
-	struct rtrs_sess *s;
+	struct rtrs_path *s;
 	int err;
 
 	if (WARN_ON(!id))
 		return true;
 
 	con = id->con;
-	s = con->c.sess;
-	sess = to_srv_sess(s);
+	s = con->c.path;
+	srv_path = to_srv_path(s);
 
 	id->status = status;
 
-	if (sess->state != RTRS_SRV_CONNECTED) {
+	if (srv_path->state != RTRS_SRV_CONNECTED) {
 		rtrs_err_rl(s,
-			    "Sending I/O response failed,  session %s is disconnected, sess state %s\n",
-			    kobject_name(&sess->kobj),
-			    rtrs_srv_state_str(sess->state));
+			    "Sending I/O response failed,  server path %s is disconnected, path state %s\n",
+			    kobject_name(&srv_path->kobj),
+			    rtrs_srv_state_str(srv_path->state));
 		goto out;
 	}
 	if (always_invalidate) {
-		struct rtrs_srv_mr *mr = &sess->mrs[id->msg_id];
+		struct rtrs_srv_mr *mr = &srv_path->mrs[id->msg_id];
 
 		ib_update_fast_reg_key(mr->mr, ib_inc_rkey(mr->mr->rkey));
 	}
 	if (atomic_sub_return(1, &con->c.sq_wr_avail) < 0) {
-		rtrs_err(s, "IB send queue full: sess=%s cid=%d\n",
-			 kobject_name(&sess->kobj),
+		rtrs_err(s, "IB send queue full: srv_path=%s cid=%d\n",
+			 kobject_name(&srv_path->kobj),
 			 con->c.cid);
 		atomic_add(1, &con->c.sq_wr_avail);
 		spin_lock(&con->rsp_wr_wait_lock);
@@ -523,12 +526,12 @@ bool rtrs_srv_resp_rdma(struct rtrs_srv_op *id, int status)
 		err = rdma_write_sg(id);
 
 	if (err) {
-		rtrs_err_rl(s, "IO response failed: %d: sess=%s\n", err,
-			    kobject_name(&sess->kobj));
-		close_sess(sess);
+		rtrs_err_rl(s, "IO response failed: %d: srv_path=%s\n", err,
+			    kobject_name(&srv_path->kobj));
+		close_path(srv_path);
 	}
 out:
-	rtrs_srv_put_ops_ids(sess);
+	rtrs_srv_put_ops_ids(srv_path);
 	return true;
 }
 EXPORT_SYMBOL(rtrs_srv_resp_rdma);
@@ -544,27 +547,27 @@ void rtrs_srv_set_sess_priv(struct rtrs_srv *srv, void *priv)
 }
 EXPORT_SYMBOL(rtrs_srv_set_sess_priv);
 
-static void unmap_cont_bufs(struct rtrs_srv_sess *sess)
+static void unmap_cont_bufs(struct rtrs_srv_path *srv_path)
 {
 	int i;
 
-	for (i = 0; i < sess->mrs_num; i++) {
+	for (i = 0; i < srv_path->mrs_num; i++) {
 		struct rtrs_srv_mr *srv_mr;
 
-		srv_mr = &sess->mrs[i];
-		rtrs_iu_free(srv_mr->iu, sess->s.dev->ib_dev, 1);
+		srv_mr = &srv_path->mrs[i];
+		rtrs_iu_free(srv_mr->iu, srv_path->s.dev->ib_dev, 1);
 		ib_dereg_mr(srv_mr->mr);
-		ib_dma_unmap_sg(sess->s.dev->ib_dev, srv_mr->sgt.sgl,
+		ib_dma_unmap_sg(srv_path->s.dev->ib_dev, srv_mr->sgt.sgl,
 				srv_mr->sgt.nents, DMA_BIDIRECTIONAL);
 		sg_free_table(&srv_mr->sgt);
 	}
-	kfree(sess->mrs);
+	kfree(srv_path->mrs);
 }
 
-static int map_cont_bufs(struct rtrs_srv_sess *sess)
+static int map_cont_bufs(struct rtrs_srv_path *srv_path)
 {
-	struct rtrs_srv *srv = sess->srv;
-	struct rtrs_sess *ss = &sess->s;
+	struct rtrs_srv *srv = srv_path->srv;
+	struct rtrs_path *ss = &srv_path->s;
 	int i, mri, err, mrs_num;
 	unsigned int chunk_bits;
 	int chunks_per_mr = 1;
@@ -581,23 +584,23 @@ static int map_cont_bufs(struct rtrs_srv_sess *sess)
 		mrs_num = srv->queue_depth;
 	} else {
 		chunks_per_mr =
-			sess->s.dev->ib_dev->attrs.max_fast_reg_page_list_len;
+			srv_path->s.dev->ib_dev->attrs.max_fast_reg_page_list_len;
 		mrs_num = DIV_ROUND_UP(srv->queue_depth, chunks_per_mr);
 		chunks_per_mr = DIV_ROUND_UP(srv->queue_depth, mrs_num);
 	}
 
-	sess->mrs = kcalloc(mrs_num, sizeof(*sess->mrs), GFP_KERNEL);
-	if (!sess->mrs)
+	srv_path->mrs = kcalloc(mrs_num, sizeof(*srv_path->mrs), GFP_KERNEL);
+	if (!srv_path->mrs)
 		return -ENOMEM;
 
-	sess->mrs_num = mrs_num;
+	srv_path->mrs_num = mrs_num;
 
 	for (mri = 0; mri < mrs_num; mri++) {
-		struct rtrs_srv_mr *srv_mr = &sess->mrs[mri];
+		struct rtrs_srv_mr *srv_mr = &srv_path->mrs[mri];
 		struct sg_table *sgt = &srv_mr->sgt;
 		struct scatterlist *s;
 		struct ib_mr *mr;
-		int nr, chunks;
+		int nr, nr_sgt, chunks;
 
 		chunks = chunks_per_mr * mri;
 		if (!always_invalidate)
@@ -612,19 +615,19 @@ static int map_cont_bufs(struct rtrs_srv_sess *sess)
 			sg_set_page(s, srv->chunks[chunks + i],
 				    max_chunk_size, 0);
 
-		nr = ib_dma_map_sg(sess->s.dev->ib_dev, sgt->sgl,
+		nr_sgt = ib_dma_map_sg(srv_path->s.dev->ib_dev, sgt->sgl,
 				   sgt->nents, DMA_BIDIRECTIONAL);
-		if (nr < sgt->nents) {
-			err = nr < 0 ? nr : -EINVAL;
+		if (!nr_sgt) {
+			err = -EINVAL;
 			goto free_sg;
 		}
-		mr = ib_alloc_mr(sess->s.dev->ib_pd, IB_MR_TYPE_MEM_REG,
-				 sgt->nents);
+		mr = ib_alloc_mr(srv_path->s.dev->ib_pd, IB_MR_TYPE_MEM_REG,
+				 nr_sgt);
 		if (IS_ERR(mr)) {
 			err = PTR_ERR(mr);
 			goto unmap_sg;
 		}
-		nr = ib_map_mr_sg(mr, sgt->sgl, sgt->nents,
+		nr = ib_map_mr_sg(mr, sgt->sgl, nr_sgt,
 				  NULL, max_chunk_size);
 		if (nr < 0 || nr < sgt->nents) {
 			err = nr < 0 ? nr : -EINVAL;
@@ -634,7 +637,7 @@ static int map_cont_bufs(struct rtrs_srv_sess *sess)
 		if (always_invalidate) {
 			srv_mr->iu = rtrs_iu_alloc(1,
 					sizeof(struct rtrs_msg_rkey_rsp),
-					GFP_KERNEL, sess->s.dev->ib_dev,
+					GFP_KERNEL, srv_path->s.dev->ib_dev,
 					DMA_TO_DEVICE, rtrs_srv_rdma_done);
 			if (!srv_mr->iu) {
 				err = -ENOMEM;
@@ -643,8 +646,8 @@ static int map_cont_bufs(struct rtrs_srv_sess *sess)
 			}
 		}
 		/* Eventually dma addr for each chunk can be cached */
-		for_each_sg(sgt->sgl, s, sgt->orig_nents, i)
-			sess->dma_addr[chunks + i] = sg_dma_address(s);
+		for_each_sg(sgt->sgl, s, nr_sgt, i)
+			srv_path->dma_addr[chunks + i] = sg_dma_address(s);
 
 		ib_update_fast_reg_key(mr, ib_inc_rkey(mr->rkey));
 		srv_mr->mr = mr;
@@ -652,75 +655,75 @@ static int map_cont_bufs(struct rtrs_srv_sess *sess)
 		continue;
 err:
 		while (mri--) {
-			srv_mr = &sess->mrs[mri];
+			srv_mr = &srv_path->mrs[mri];
 			sgt = &srv_mr->sgt;
 			mr = srv_mr->mr;
-			rtrs_iu_free(srv_mr->iu, sess->s.dev->ib_dev, 1);
+			rtrs_iu_free(srv_mr->iu, srv_path->s.dev->ib_dev, 1);
 dereg_mr:
 			ib_dereg_mr(mr);
 unmap_sg:
-			ib_dma_unmap_sg(sess->s.dev->ib_dev, sgt->sgl,
+			ib_dma_unmap_sg(srv_path->s.dev->ib_dev, sgt->sgl,
 					sgt->nents, DMA_BIDIRECTIONAL);
 free_sg:
 			sg_free_table(sgt);
 		}
-		kfree(sess->mrs);
+		kfree(srv_path->mrs);
 
 		return err;
 	}
 
 	chunk_bits = ilog2(srv->queue_depth - 1) + 1;
-	sess->mem_bits = (MAX_IMM_PAYL_BITS - chunk_bits);
+	srv_path->mem_bits = (MAX_IMM_PAYL_BITS - chunk_bits);
 
 	return 0;
 }
 
 static void rtrs_srv_hb_err_handler(struct rtrs_con *c)
 {
-	close_sess(to_srv_sess(c->sess));
+	close_path(to_srv_path(c->path));
 }
 
-static void rtrs_srv_init_hb(struct rtrs_srv_sess *sess)
+static void rtrs_srv_init_hb(struct rtrs_srv_path *srv_path)
 {
-	rtrs_init_hb(&sess->s, &io_comp_cqe,
+	rtrs_init_hb(&srv_path->s, &io_comp_cqe,
 		      RTRS_HB_INTERVAL_MS,
 		      RTRS_HB_MISSED_MAX,
 		      rtrs_srv_hb_err_handler,
 		      rtrs_wq);
 }
 
-static void rtrs_srv_start_hb(struct rtrs_srv_sess *sess)
+static void rtrs_srv_start_hb(struct rtrs_srv_path *srv_path)
 {
-	rtrs_start_hb(&sess->s);
+	rtrs_start_hb(&srv_path->s);
 }
 
-static void rtrs_srv_stop_hb(struct rtrs_srv_sess *sess)
+static void rtrs_srv_stop_hb(struct rtrs_srv_path *srv_path)
 {
-	rtrs_stop_hb(&sess->s);
+	rtrs_stop_hb(&srv_path->s);
 }
 
 static void rtrs_srv_info_rsp_done(struct ib_cq *cq, struct ib_wc *wc)
 {
 	struct rtrs_srv_con *con = to_srv_con(wc->qp->qp_context);
-	struct rtrs_sess *s = con->c.sess;
-	struct rtrs_srv_sess *sess = to_srv_sess(s);
+	struct rtrs_path *s = con->c.path;
+	struct rtrs_srv_path *srv_path = to_srv_path(s);
 	struct rtrs_iu *iu;
 
 	iu = container_of(wc->wr_cqe, struct rtrs_iu, cqe);
-	rtrs_iu_free(iu, sess->s.dev->ib_dev, 1);
+	rtrs_iu_free(iu, srv_path->s.dev->ib_dev, 1);
 
 	if (wc->status != IB_WC_SUCCESS) {
 		rtrs_err(s, "Sess info response send failed: %s\n",
 			  ib_wc_status_msg(wc->status));
-		close_sess(sess);
+		close_path(srv_path);
 		return;
 	}
 	WARN_ON(wc->opcode != IB_WC_SEND);
 }
 
-static void rtrs_srv_sess_up(struct rtrs_srv_sess *sess)
+static void rtrs_srv_path_up(struct rtrs_srv_path *srv_path)
 {
-	struct rtrs_srv *srv = sess->srv;
+	struct rtrs_srv *srv = srv_path->srv;
 	struct rtrs_srv_ctx *ctx = srv->ctx;
 	int up;
 
@@ -731,18 +734,18 @@ static void rtrs_srv_sess_up(struct rtrs_srv_sess *sess)
 	mutex_unlock(&srv->paths_ev_mutex);
 
 	/* Mark session as established */
-	sess->established = true;
+	srv_path->established = true;
 }
 
-static void rtrs_srv_sess_down(struct rtrs_srv_sess *sess)
+static void rtrs_srv_path_down(struct rtrs_srv_path *srv_path)
 {
-	struct rtrs_srv *srv = sess->srv;
+	struct rtrs_srv *srv = srv_path->srv;
 	struct rtrs_srv_ctx *ctx = srv->ctx;
 
-	if (!sess->established)
+	if (!srv_path->established)
 		return;
 
-	sess->established = false;
+	srv_path->established = false;
 	mutex_lock(&srv->paths_ev_mutex);
 	WARN_ON(!srv->paths_up);
 	if (--srv->paths_up == 0)
@@ -750,11 +753,11 @@ static void rtrs_srv_sess_down(struct rtrs_srv_sess *sess)
 	mutex_unlock(&srv->paths_ev_mutex);
 }
 
-static bool exist_sessname(struct rtrs_srv_ctx *ctx,
-			   const char *sessname, const uuid_t *path_uuid)
+static bool exist_pathname(struct rtrs_srv_ctx *ctx,
+			   const char *pathname, const uuid_t *path_uuid)
 {
 	struct rtrs_srv *srv;
-	struct rtrs_srv_sess *sess;
+	struct rtrs_srv_path *srv_path;
 	bool found = false;
 
 	mutex_lock(&ctx->srv_mutex);
@@ -767,9 +770,9 @@ static bool exist_sessname(struct rtrs_srv_ctx *ctx,
 			continue;
 		}
 
-		list_for_each_entry(sess, &srv->paths_list, s.entry) {
-			if (strlen(sess->s.sessname) == strlen(sessname) &&
-			    !strcmp(sess->s.sessname, sessname)) {
+		list_for_each_entry(srv_path, &srv->paths_list, s.entry) {
+			if (strlen(srv_path->s.sessname) == strlen(pathname) &&
+			    !strcmp(srv_path->s.sessname, pathname)) {
 				found = true;
 				break;
 			}
@@ -782,14 +785,14 @@ static bool exist_sessname(struct rtrs_srv_ctx *ctx,
 	return found;
 }
 
-static int post_recv_sess(struct rtrs_srv_sess *sess);
+static int post_recv_path(struct rtrs_srv_path *srv_path);
 static int rtrs_rdma_do_reject(struct rdma_cm_id *cm_id, int errno);
 
 static int process_info_req(struct rtrs_srv_con *con,
 			    struct rtrs_msg_info_req *msg)
 {
-	struct rtrs_sess *s = con->c.sess;
-	struct rtrs_srv_sess *sess = to_srv_sess(s);
+	struct rtrs_path *s = con->c.path;
+	struct rtrs_srv_path *srv_path = to_srv_path(s);
 	struct ib_send_wr *reg_wr = NULL;
 	struct rtrs_msg_info_rsp *rsp;
 	struct rtrs_iu *tx_iu;
@@ -797,26 +800,32 @@ static int process_info_req(struct rtrs_srv_con *con,
 	int mri, err;
 	size_t tx_sz;
 
-	err = post_recv_sess(sess);
+	err = post_recv_path(srv_path);
 	if (err) {
-		rtrs_err(s, "post_recv_sess(), err: %d\n", err);
+		rtrs_err(s, "post_recv_path(), err: %d\n", err);
 		return err;
 	}
 
-	if (exist_sessname(sess->srv->ctx,
-			   msg->sessname, &sess->srv->paths_uuid)) {
-		rtrs_err(s, "sessname is duplicated: %s\n", msg->sessname);
+	if (strchr(msg->pathname, '/') || strchr(msg->pathname, '.')) {
+		rtrs_err(s, "pathname cannot contain / and .\n");
+		return -EINVAL;
+	}
+
+	if (exist_pathname(srv_path->srv->ctx,
+			   msg->pathname, &srv_path->srv->paths_uuid)) {
+		rtrs_err(s, "pathname is duplicated: %s\n", msg->pathname);
 		return -EPERM;
 	}
-	strscpy(sess->s.sessname, msg->sessname, sizeof(sess->s.sessname));
+	strscpy(srv_path->s.sessname, msg->pathname,
+		sizeof(srv_path->s.sessname));
 
-	rwr = kcalloc(sess->mrs_num, sizeof(*rwr), GFP_KERNEL);
+	rwr = kcalloc(srv_path->mrs_num, sizeof(*rwr), GFP_KERNEL);
 	if (!rwr)
 		return -ENOMEM;
 
 	tx_sz  = sizeof(*rsp);
-	tx_sz += sizeof(rsp->desc[0]) * sess->mrs_num;
-	tx_iu = rtrs_iu_alloc(1, tx_sz, GFP_KERNEL, sess->s.dev->ib_dev,
+	tx_sz += sizeof(rsp->desc[0]) * srv_path->mrs_num;
+	tx_iu = rtrs_iu_alloc(1, tx_sz, GFP_KERNEL, srv_path->s.dev->ib_dev,
 			       DMA_TO_DEVICE, rtrs_srv_info_rsp_done);
 	if (!tx_iu) {
 		err = -ENOMEM;
@@ -825,10 +834,10 @@ static int process_info_req(struct rtrs_srv_con *con,
 
 	rsp = tx_iu->buf;
 	rsp->type = cpu_to_le16(RTRS_MSG_INFO_RSP);
-	rsp->sg_cnt = cpu_to_le16(sess->mrs_num);
+	rsp->sg_cnt = cpu_to_le16(srv_path->mrs_num);
 
-	for (mri = 0; mri < sess->mrs_num; mri++) {
-		struct ib_mr *mr = sess->mrs[mri].mr;
+	for (mri = 0; mri < srv_path->mrs_num; mri++) {
+		struct ib_mr *mr = srv_path->mrs[mri].mr;
 
 		rsp->desc[mri].addr = cpu_to_le64(mr->iova);
 		rsp->desc[mri].key  = cpu_to_le32(mr->rkey);
@@ -849,13 +858,13 @@ static int process_info_req(struct rtrs_srv_con *con,
 		reg_wr = &rwr[mri].wr;
 	}
 
-	err = rtrs_srv_create_sess_files(sess);
+	err = rtrs_srv_create_path_files(srv_path);
 	if (err)
 		goto iu_free;
-	kobject_get(&sess->kobj);
-	get_device(&sess->srv->dev);
-	rtrs_srv_change_state(sess, RTRS_SRV_CONNECTED);
-	rtrs_srv_start_hb(sess);
+	kobject_get(&srv_path->kobj);
+	get_device(&srv_path->srv->dev);
+	rtrs_srv_change_state(srv_path, RTRS_SRV_CONNECTED);
+	rtrs_srv_start_hb(srv_path);
 
 	/*
 	 * We do not account number of established connections at the current
@@ -863,9 +872,10 @@ static int process_info_req(struct rtrs_srv_con *con,
 	 * all connections are successfully established.  Thus, simply notify
 	 * listener with a proper event if we are the first path.
 	 */
-	rtrs_srv_sess_up(sess);
+	rtrs_srv_path_up(srv_path);
 
-	ib_dma_sync_single_for_device(sess->s.dev->ib_dev, tx_iu->dma_addr,
+	ib_dma_sync_single_for_device(srv_path->s.dev->ib_dev,
+				      tx_iu->dma_addr,
 				      tx_iu->size, DMA_TO_DEVICE);
 
 	/* Send info response */
@@ -873,7 +883,7 @@ static int process_info_req(struct rtrs_srv_con *con,
 	if (err) {
 		rtrs_err(s, "rtrs_iu_post_send(), err: %d\n", err);
 iu_free:
-		rtrs_iu_free(tx_iu, sess->s.dev->ib_dev, 1);
+		rtrs_iu_free(tx_iu, srv_path->s.dev->ib_dev, 1);
 	}
 rwr_free:
 	kfree(rwr);
@@ -884,8 +894,8 @@ rwr_free:
 static void rtrs_srv_info_req_done(struct ib_cq *cq, struct ib_wc *wc)
 {
 	struct rtrs_srv_con *con = to_srv_con(wc->qp->qp_context);
-	struct rtrs_sess *s = con->c.sess;
-	struct rtrs_srv_sess *sess = to_srv_sess(s);
+	struct rtrs_path *s = con->c.path;
+	struct rtrs_srv_path *srv_path = to_srv_path(s);
 	struct rtrs_msg_info_req *msg;
 	struct rtrs_iu *iu;
 	int err;
@@ -905,7 +915,7 @@ static void rtrs_srv_info_req_done(struct ib_cq *cq, struct ib_wc *wc)
 			  wc->byte_len);
 		goto close;
 	}
-	ib_dma_sync_single_for_cpu(sess->s.dev->ib_dev, iu->dma_addr,
+	ib_dma_sync_single_for_cpu(srv_path->s.dev->ib_dev, iu->dma_addr,
 				   iu->size, DMA_FROM_DEVICE);
 	msg = iu->buf;
 	if (le16_to_cpu(msg->type) != RTRS_MSG_INFO_REQ) {
@@ -918,22 +928,22 @@ static void rtrs_srv_info_req_done(struct ib_cq *cq, struct ib_wc *wc)
 		goto close;
 
 out:
-	rtrs_iu_free(iu, sess->s.dev->ib_dev, 1);
+	rtrs_iu_free(iu, srv_path->s.dev->ib_dev, 1);
 	return;
 close:
-	close_sess(sess);
+	close_path(srv_path);
 	goto out;
 }
 
 static int post_recv_info_req(struct rtrs_srv_con *con)
 {
-	struct rtrs_sess *s = con->c.sess;
-	struct rtrs_srv_sess *sess = to_srv_sess(s);
+	struct rtrs_path *s = con->c.path;
+	struct rtrs_srv_path *srv_path = to_srv_path(s);
 	struct rtrs_iu *rx_iu;
 	int err;
 
 	rx_iu = rtrs_iu_alloc(1, sizeof(struct rtrs_msg_info_req),
-			       GFP_KERNEL, sess->s.dev->ib_dev,
+			       GFP_KERNEL, srv_path->s.dev->ib_dev,
 			       DMA_FROM_DEVICE, rtrs_srv_info_req_done);
 	if (!rx_iu)
 		return -ENOMEM;
@@ -941,7 +951,7 @@ static int post_recv_info_req(struct rtrs_srv_con *con)
 	err = rtrs_iu_post_recv(&con->c, rx_iu);
 	if (err) {
 		rtrs_err(s, "rtrs_iu_post_recv(), err: %d\n", err);
-		rtrs_iu_free(rx_iu, sess->s.dev->ib_dev, 1);
+		rtrs_iu_free(rx_iu, srv_path->s.dev->ib_dev, 1);
 		return err;
 	}
 
@@ -961,20 +971,20 @@ static int post_recv_io(struct rtrs_srv_con *con, size_t q_size)
 	return 0;
 }
 
-static int post_recv_sess(struct rtrs_srv_sess *sess)
+static int post_recv_path(struct rtrs_srv_path *srv_path)
 {
-	struct rtrs_srv *srv = sess->srv;
-	struct rtrs_sess *s = &sess->s;
+	struct rtrs_srv *srv = srv_path->srv;
+	struct rtrs_path *s = &srv_path->s;
 	size_t q_size;
 	int err, cid;
 
-	for (cid = 0; cid < sess->s.con_num; cid++) {
+	for (cid = 0; cid < srv_path->s.con_num; cid++) {
 		if (cid == 0)
 			q_size = SERVICE_CON_QUEUE_DEPTH;
 		else
 			q_size = srv->queue_depth;
 
-		err = post_recv_io(to_srv_con(sess->s.con[cid]), q_size);
+		err = post_recv_io(to_srv_con(srv_path->s.con[cid]), q_size);
 		if (err) {
 			rtrs_err(s, "post_recv_io(), err: %d\n", err);
 			return err;
@@ -988,9 +998,9 @@ static void process_read(struct rtrs_srv_con *con,
 			 struct rtrs_msg_rdma_read *msg,
 			 u32 buf_id, u32 off)
 {
-	struct rtrs_sess *s = con->c.sess;
-	struct rtrs_srv_sess *sess = to_srv_sess(s);
-	struct rtrs_srv *srv = sess->srv;
+	struct rtrs_path *s = con->c.path;
+	struct rtrs_srv_path *srv_path = to_srv_path(s);
+	struct rtrs_srv *srv = srv_path->srv;
 	struct rtrs_srv_ctx *ctx = srv->ctx;
 	struct rtrs_srv_op *id;
 
@@ -998,10 +1008,10 @@ static void process_read(struct rtrs_srv_con *con,
 	void *data;
 	int ret;
 
-	if (sess->state != RTRS_SRV_CONNECTED) {
+	if (srv_path->state != RTRS_SRV_CONNECTED) {
 		rtrs_err_rl(s,
 			     "Processing read request failed,  session is disconnected, sess state %s\n",
-			     rtrs_srv_state_str(sess->state));
+			     rtrs_srv_state_str(srv_path->state));
 		return;
 	}
 	if (msg->sg_cnt != 1 && msg->sg_cnt != 0) {
@@ -1009,9 +1019,9 @@ static void process_read(struct rtrs_srv_con *con,
 			    "Processing read request failed, invalid message\n");
 		return;
 	}
-	rtrs_srv_get_ops_ids(sess);
-	rtrs_srv_update_rdma_stats(sess->stats, off, READ);
-	id = sess->ops_ids[buf_id];
+	rtrs_srv_get_ops_ids(srv_path);
+	rtrs_srv_update_rdma_stats(srv_path->stats, off, READ);
+	id = srv_path->ops_ids[buf_id];
 	id->con		= con;
 	id->dir		= READ;
 	id->msg_id	= buf_id;
@@ -1037,18 +1047,18 @@ send_err_msg:
 		rtrs_err_rl(s,
 			     "Sending err msg for failed RDMA-Write-Req failed, msg_id %d, err: %d\n",
 			     buf_id, ret);
-		close_sess(sess);
+		close_path(srv_path);
 	}
-	rtrs_srv_put_ops_ids(sess);
+	rtrs_srv_put_ops_ids(srv_path);
 }
 
 static void process_write(struct rtrs_srv_con *con,
 			  struct rtrs_msg_rdma_write *req,
 			  u32 buf_id, u32 off)
 {
-	struct rtrs_sess *s = con->c.sess;
-	struct rtrs_srv_sess *sess = to_srv_sess(s);
-	struct rtrs_srv *srv = sess->srv;
+	struct rtrs_path *s = con->c.path;
+	struct rtrs_srv_path *srv_path = to_srv_path(s);
+	struct rtrs_srv *srv = srv_path->srv;
 	struct rtrs_srv_ctx *ctx = srv->ctx;
 	struct rtrs_srv_op *id;
 
@@ -1056,15 +1066,15 @@ static void process_write(struct rtrs_srv_con *con,
 	void *data;
 	int ret;
 
-	if (sess->state != RTRS_SRV_CONNECTED) {
+	if (srv_path->state != RTRS_SRV_CONNECTED) {
 		rtrs_err_rl(s,
 			     "Processing write request failed,  session is disconnected, sess state %s\n",
-			     rtrs_srv_state_str(sess->state));
+			     rtrs_srv_state_str(srv_path->state));
 		return;
 	}
-	rtrs_srv_get_ops_ids(sess);
-	rtrs_srv_update_rdma_stats(sess->stats, off, WRITE);
-	id = sess->ops_ids[buf_id];
+	rtrs_srv_get_ops_ids(srv_path);
+	rtrs_srv_update_rdma_stats(srv_path->stats, off, WRITE);
+	id = srv_path->ops_ids[buf_id];
 	id->con    = con;
 	id->dir    = WRITE;
 	id->msg_id = buf_id;
@@ -1089,20 +1099,21 @@ send_err_msg:
 		rtrs_err_rl(s,
 			     "Processing write request failed, sending I/O response failed, msg_id %d, err: %d\n",
 			     buf_id, ret);
-		close_sess(sess);
+		close_path(srv_path);
 	}
-	rtrs_srv_put_ops_ids(sess);
+	rtrs_srv_put_ops_ids(srv_path);
 }
 
 static void process_io_req(struct rtrs_srv_con *con, void *msg,
 			   u32 id, u32 off)
 {
-	struct rtrs_sess *s = con->c.sess;
-	struct rtrs_srv_sess *sess = to_srv_sess(s);
+	struct rtrs_path *s = con->c.path;
+	struct rtrs_srv_path *srv_path = to_srv_path(s);
 	struct rtrs_msg_rdma_hdr *hdr;
 	unsigned int type;
 
-	ib_dma_sync_single_for_cpu(sess->s.dev->ib_dev, sess->dma_addr[id],
+	ib_dma_sync_single_for_cpu(srv_path->s.dev->ib_dev,
+				   srv_path->dma_addr[id],
 				   max_chunk_size, DMA_BIDIRECTIONAL);
 	hdr = msg;
 	type = le16_to_cpu(hdr->type);
@@ -1124,7 +1135,7 @@ static void process_io_req(struct rtrs_srv_con *con, void *msg,
 	return;
 
 err:
-	close_sess(sess);
+	close_path(srv_path);
 }
 
 static void rtrs_srv_inv_rkey_done(struct ib_cq *cq, struct ib_wc *wc)
@@ -1132,16 +1143,16 @@ static void rtrs_srv_inv_rkey_done(struct ib_cq *cq, struct ib_wc *wc)
 	struct rtrs_srv_mr *mr =
 		container_of(wc->wr_cqe, typeof(*mr), inv_cqe);
 	struct rtrs_srv_con *con = to_srv_con(wc->qp->qp_context);
-	struct rtrs_sess *s = con->c.sess;
-	struct rtrs_srv_sess *sess = to_srv_sess(s);
-	struct rtrs_srv *srv = sess->srv;
+	struct rtrs_path *s = con->c.path;
+	struct rtrs_srv_path *srv_path = to_srv_path(s);
+	struct rtrs_srv *srv = srv_path->srv;
 	u32 msg_id, off;
 	void *data;
 
 	if (wc->status != IB_WC_SUCCESS) {
 		rtrs_err(s, "Failed IB_WR_LOCAL_INV: %s\n",
 			  ib_wc_status_msg(wc->status));
-		close_sess(sess);
+		close_path(srv_path);
 	}
 	msg_id = mr->msg_id;
 	off = mr->msg_off;
@@ -1189,9 +1200,9 @@ static void rtrs_rdma_process_wr_wait_list(struct rtrs_srv_con *con)
 static void rtrs_srv_rdma_done(struct ib_cq *cq, struct ib_wc *wc)
 {
 	struct rtrs_srv_con *con = to_srv_con(wc->qp->qp_context);
-	struct rtrs_sess *s = con->c.sess;
-	struct rtrs_srv_sess *sess = to_srv_sess(s);
-	struct rtrs_srv *srv = sess->srv;
+	struct rtrs_path *s = con->c.path;
+	struct rtrs_srv_path *srv_path = to_srv_path(s);
+	struct rtrs_srv *srv = srv_path->srv;
 	u32 imm_type, imm_payload;
 	int err;
 
@@ -1201,7 +1212,7 @@ static void rtrs_srv_rdma_done(struct ib_cq *cq, struct ib_wc *wc)
 				  "%s (wr_cqe: %p, type: %d, vendor_err: 0x%x, len: %u)\n",
 				  ib_wc_status_msg(wc->status), wc->wr_cqe,
 				  wc->opcode, wc->vendor_err, wc->byte_len);
-			close_sess(sess);
+			close_path(srv_path);
 		}
 		return;
 	}
@@ -1217,7 +1228,7 @@ static void rtrs_srv_rdma_done(struct ib_cq *cq, struct ib_wc *wc)
 		err = rtrs_post_recv_empty(&con->c, &io_comp_cqe);
 		if (err) {
 			rtrs_err(s, "rtrs_post_recv(), err: %d\n", err);
-			close_sess(sess);
+			close_path(srv_path);
 			break;
 		}
 		rtrs_from_imm(be32_to_cpu(wc->ex.imm_data),
@@ -1226,16 +1237,16 @@ static void rtrs_srv_rdma_done(struct ib_cq *cq, struct ib_wc *wc)
 			u32 msg_id, off;
 			void *data;
 
-			msg_id = imm_payload >> sess->mem_bits;
-			off = imm_payload & ((1 << sess->mem_bits) - 1);
+			msg_id = imm_payload >> srv_path->mem_bits;
+			off = imm_payload & ((1 << srv_path->mem_bits) - 1);
 			if (msg_id >= srv->queue_depth || off >= max_chunk_size) {
 				rtrs_err(s, "Wrong msg_id %u, off %u\n",
 					  msg_id, off);
-				close_sess(sess);
+				close_path(srv_path);
 				return;
 			}
 			if (always_invalidate) {
-				struct rtrs_srv_mr *mr = &sess->mrs[msg_id];
+				struct rtrs_srv_mr *mr = &srv_path->mrs[msg_id];
 
 				mr->msg_off = off;
 				mr->msg_id = msg_id;
@@ -1243,7 +1254,7 @@ static void rtrs_srv_rdma_done(struct ib_cq *cq, struct ib_wc *wc)
 				if (err) {
 					rtrs_err(s, "rtrs_post_recv(), err: %d\n",
 						  err);
-					close_sess(sess);
+					close_path(srv_path);
 					break;
 				}
 			} else {
@@ -1252,10 +1263,10 @@ static void rtrs_srv_rdma_done(struct ib_cq *cq, struct ib_wc *wc)
 			}
 		} else if (imm_type == RTRS_HB_MSG_IMM) {
 			WARN_ON(con->c.cid);
-			rtrs_send_hb_ack(&sess->s);
+			rtrs_send_hb_ack(&srv_path->s);
 		} else if (imm_type == RTRS_HB_ACK_IMM) {
 			WARN_ON(con->c.cid);
-			sess->s.hb_missed_cnt = 0;
+			srv_path->s.hb_missed_cnt = 0;
 		} else {
 			rtrs_wrn(s, "Unknown IMM type %u\n", imm_type);
 		}
@@ -1279,22 +1290,23 @@ static void rtrs_srv_rdma_done(struct ib_cq *cq, struct ib_wc *wc)
 }
 
 /**
- * rtrs_srv_get_sess_name() - Get rtrs_srv peer hostname.
+ * rtrs_srv_get_path_name() - Get rtrs_srv peer hostname.
  * @srv:	Session
- * @sessname:	Sessname buffer
+ * @pathname:	Pathname buffer
  * @len:	Length of sessname buffer
  */
-int rtrs_srv_get_sess_name(struct rtrs_srv *srv, char *sessname, size_t len)
+int rtrs_srv_get_path_name(struct rtrs_srv *srv, char *pathname,
+			   size_t len)
 {
-	struct rtrs_srv_sess *sess;
+	struct rtrs_srv_path *srv_path;
 	int err = -ENOTCONN;
 
 	mutex_lock(&srv->paths_mutex);
-	list_for_each_entry(sess, &srv->paths_list, s.entry) {
-		if (sess->state != RTRS_SRV_CONNECTED)
+	list_for_each_entry(srv_path, &srv->paths_list, s.entry) {
+		if (srv_path->state != RTRS_SRV_CONNECTED)
 			continue;
-		strscpy(sessname, sess->s.sessname,
-		       min_t(size_t, sizeof(sess->s.sessname), len));
+		strscpy(pathname, srv_path->s.sessname,
+			min_t(size_t, sizeof(srv_path->s.sessname), len));
 		err = 0;
 		break;
 	}
@@ -1302,7 +1314,7 @@ int rtrs_srv_get_sess_name(struct rtrs_srv *srv, char *sessname, size_t len)
 
 	return err;
 }
-EXPORT_SYMBOL(rtrs_srv_get_sess_name);
+EXPORT_SYMBOL(rtrs_srv_get_path_name);
 
 /**
  * rtrs_srv_get_queue_depth() - Get rtrs_srv qdepth.
@@ -1314,22 +1326,22 @@ int rtrs_srv_get_queue_depth(struct rtrs_srv *srv)
 }
 EXPORT_SYMBOL(rtrs_srv_get_queue_depth);
 
-static int find_next_bit_ring(struct rtrs_srv_sess *sess)
+static int find_next_bit_ring(struct rtrs_srv_path *srv_path)
 {
-	struct ib_device *ib_dev = sess->s.dev->ib_dev;
+	struct ib_device *ib_dev = srv_path->s.dev->ib_dev;
 	int v;
 
-	v = cpumask_next(sess->cur_cq_vector, &cq_affinity_mask);
+	v = cpumask_next(srv_path->cur_cq_vector, &cq_affinity_mask);
 	if (v >= nr_cpu_ids || v >= ib_dev->num_comp_vectors)
 		v = cpumask_first(&cq_affinity_mask);
 	return v;
 }
 
-static int rtrs_srv_get_next_cq_vector(struct rtrs_srv_sess *sess)
+static int rtrs_srv_get_next_cq_vector(struct rtrs_srv_path *srv_path)
 {
-	sess->cur_cq_vector = find_next_bit_ring(sess);
+	srv_path->cur_cq_vector = find_next_bit_ring(srv_path);
 
-	return sess->cur_cq_vector;
+	return srv_path->cur_cq_vector;
 }
 
 static void rtrs_srv_dev_release(struct device *dev)
@@ -1434,22 +1446,22 @@ static void put_srv(struct rtrs_srv *srv)
 }
 
 static void __add_path_to_srv(struct rtrs_srv *srv,
-			      struct rtrs_srv_sess *sess)
+			      struct rtrs_srv_path *srv_path)
 {
-	list_add_tail(&sess->s.entry, &srv->paths_list);
+	list_add_tail(&srv_path->s.entry, &srv->paths_list);
 	srv->paths_num++;
 	WARN_ON(srv->paths_num >= MAX_PATHS_NUM);
 }
 
-static void del_path_from_srv(struct rtrs_srv_sess *sess)
+static void del_path_from_srv(struct rtrs_srv_path *srv_path)
 {
-	struct rtrs_srv *srv = sess->srv;
+	struct rtrs_srv *srv = srv_path->srv;
 
 	if (WARN_ON(!srv))
 		return;
 
 	mutex_lock(&srv->paths_mutex);
-	list_del(&sess->s.entry);
+	list_del(&srv_path->s.entry);
 	WARN_ON(!srv->paths_num);
 	srv->paths_num--;
 	mutex_unlock(&srv->paths_mutex);
@@ -1482,44 +1494,44 @@ static int sockaddr_cmp(const struct sockaddr *a, const struct sockaddr *b)
 static bool __is_path_w_addr_exists(struct rtrs_srv *srv,
 				    struct rdma_addr *addr)
 {
-	struct rtrs_srv_sess *sess;
+	struct rtrs_srv_path *srv_path;
 
-	list_for_each_entry(sess, &srv->paths_list, s.entry)
-		if (!sockaddr_cmp((struct sockaddr *)&sess->s.dst_addr,
+	list_for_each_entry(srv_path, &srv->paths_list, s.entry)
+		if (!sockaddr_cmp((struct sockaddr *)&srv_path->s.dst_addr,
 				  (struct sockaddr *)&addr->dst_addr) &&
-		    !sockaddr_cmp((struct sockaddr *)&sess->s.src_addr,
+		    !sockaddr_cmp((struct sockaddr *)&srv_path->s.src_addr,
 				  (struct sockaddr *)&addr->src_addr))
 			return true;
 
 	return false;
 }
 
-static void free_sess(struct rtrs_srv_sess *sess)
+static void free_path(struct rtrs_srv_path *srv_path)
 {
-	if (sess->kobj.state_in_sysfs) {
-		kobject_del(&sess->kobj);
-		kobject_put(&sess->kobj);
+	if (srv_path->kobj.state_in_sysfs) {
+		kobject_del(&srv_path->kobj);
+		kobject_put(&srv_path->kobj);
 	} else {
-		kfree(sess->stats);
-		kfree(sess);
+		kfree(srv_path->stats);
+		kfree(srv_path);
 	}
 }
 
 static void rtrs_srv_close_work(struct work_struct *work)
 {
-	struct rtrs_srv_sess *sess;
+	struct rtrs_srv_path *srv_path;
 	struct rtrs_srv_con *con;
 	int i;
 
-	sess = container_of(work, typeof(*sess), close_work);
+	srv_path = container_of(work, typeof(*srv_path), close_work);
 
-	rtrs_srv_destroy_sess_files(sess);
-	rtrs_srv_stop_hb(sess);
+	rtrs_srv_destroy_path_files(srv_path);
+	rtrs_srv_stop_hb(srv_path);
 
-	for (i = 0; i < sess->s.con_num; i++) {
-		if (!sess->s.con[i])
+	for (i = 0; i < srv_path->s.con_num; i++) {
+		if (!srv_path->s.con[i])
 			continue;
-		con = to_srv_con(sess->s.con[i]);
+		con = to_srv_con(srv_path->s.con[i]);
 		rdma_disconnect(con->c.cm_id);
 		ib_drain_qp(con->c.qp);
 	}
@@ -1528,41 +1540,41 @@ static void rtrs_srv_close_work(struct work_struct *work)
 	 * Degrade ref count to the usual model with a single shared
 	 * atomic_t counter
 	 */
-	percpu_ref_kill(&sess->ids_inflight_ref);
+	percpu_ref_kill(&srv_path->ids_inflight_ref);
 
 	/* Wait for all completion */
-	wait_for_completion(&sess->complete_done);
+	wait_for_completion(&srv_path->complete_done);
 
 	/* Notify upper layer if we are the last path */
-	rtrs_srv_sess_down(sess);
+	rtrs_srv_path_down(srv_path);
 
-	unmap_cont_bufs(sess);
-	rtrs_srv_free_ops_ids(sess);
+	unmap_cont_bufs(srv_path);
+	rtrs_srv_free_ops_ids(srv_path);
 
-	for (i = 0; i < sess->s.con_num; i++) {
-		if (!sess->s.con[i])
+	for (i = 0; i < srv_path->s.con_num; i++) {
+		if (!srv_path->s.con[i])
 			continue;
-		con = to_srv_con(sess->s.con[i]);
+		con = to_srv_con(srv_path->s.con[i]);
 		rtrs_cq_qp_destroy(&con->c);
 		rdma_destroy_id(con->c.cm_id);
 		kfree(con);
 	}
-	rtrs_ib_dev_put(sess->s.dev);
+	rtrs_ib_dev_put(srv_path->s.dev);
 
-	del_path_from_srv(sess);
-	put_srv(sess->srv);
-	sess->srv = NULL;
-	rtrs_srv_change_state(sess, RTRS_SRV_CLOSED);
+	del_path_from_srv(srv_path);
+	put_srv(srv_path->srv);
+	srv_path->srv = NULL;
+	rtrs_srv_change_state(srv_path, RTRS_SRV_CLOSED);
 
-	kfree(sess->dma_addr);
-	kfree(sess->s.con);
-	free_sess(sess);
+	kfree(srv_path->dma_addr);
+	kfree(srv_path->s.con);
+	free_path(srv_path);
 }
 
-static int rtrs_rdma_do_accept(struct rtrs_srv_sess *sess,
+static int rtrs_rdma_do_accept(struct rtrs_srv_path *srv_path,
 			       struct rdma_cm_id *cm_id)
 {
-	struct rtrs_srv *srv = sess->srv;
+	struct rtrs_srv *srv = srv_path->srv;
 	struct rtrs_msg_conn_rsp msg;
 	struct rdma_conn_param param;
 	int err;
@@ -1610,25 +1622,25 @@ static int rtrs_rdma_do_reject(struct rdma_cm_id *cm_id, int errno)
 	return errno;
 }
 
-static struct rtrs_srv_sess *
-__find_sess(struct rtrs_srv *srv, const uuid_t *sess_uuid)
+static struct rtrs_srv_path *
+__find_path(struct rtrs_srv *srv, const uuid_t *sess_uuid)
 {
-	struct rtrs_srv_sess *sess;
+	struct rtrs_srv_path *srv_path;
 
-	list_for_each_entry(sess, &srv->paths_list, s.entry) {
-		if (uuid_equal(&sess->s.uuid, sess_uuid))
-			return sess;
+	list_for_each_entry(srv_path, &srv->paths_list, s.entry) {
+		if (uuid_equal(&srv_path->s.uuid, sess_uuid))
+			return srv_path;
 	}
 
 	return NULL;
 }
 
-static int create_con(struct rtrs_srv_sess *sess,
+static int create_con(struct rtrs_srv_path *srv_path,
 		      struct rdma_cm_id *cm_id,
 		      unsigned int cid)
 {
-	struct rtrs_srv *srv = sess->srv;
-	struct rtrs_sess *s = &sess->s;
+	struct rtrs_srv *srv = srv_path->srv;
+	struct rtrs_path *s = &srv_path->s;
 	struct rtrs_srv_con *con;
 
 	u32 cq_num, max_send_wr, max_recv_wr, wr_limit;
@@ -1643,10 +1655,10 @@ static int create_con(struct rtrs_srv_sess *sess,
 	spin_lock_init(&con->rsp_wr_wait_lock);
 	INIT_LIST_HEAD(&con->rsp_wr_wait_list);
 	con->c.cm_id = cm_id;
-	con->c.sess = &sess->s;
+	con->c.path = &srv_path->s;
 	con->c.cid = cid;
 	atomic_set(&con->c.wr_cnt, 1);
-	wr_limit = sess->s.dev->ib_dev->attrs.max_qp_wr;
+	wr_limit = srv_path->s.dev->ib_dev->attrs.max_qp_wr;
 
 	if (con->c.cid == 0) {
 		/*
@@ -1679,10 +1691,10 @@ static int create_con(struct rtrs_srv_sess *sess,
 	}
 	cq_num = max_send_wr + max_recv_wr;
 	atomic_set(&con->c.sq_wr_avail, max_send_wr);
-	cq_vector = rtrs_srv_get_next_cq_vector(sess);
+	cq_vector = rtrs_srv_get_next_cq_vector(srv_path);
 
 	/* TODO: SOFTIRQ can be faster, but be careful with softirq context */
-	err = rtrs_cq_qp_create(&sess->s, &con->c, 1, cq_vector, cq_num,
+	err = rtrs_cq_qp_create(&srv_path->s, &con->c, 1, cq_vector, cq_num,
 				 max_send_wr, max_recv_wr,
 				 IB_POLL_WORKQUEUE);
 	if (err) {
@@ -1694,8 +1706,8 @@ static int create_con(struct rtrs_srv_sess *sess,
 		if (err)
 			goto free_cqqp;
 	}
-	WARN_ON(sess->s.con[cid]);
-	sess->s.con[cid] = &con->c;
+	WARN_ON(srv_path->s.con[cid]);
+	srv_path->s.con[cid] = &con->c;
 
 	/*
 	 * Change context from server to current connection.  The other
@@ -1714,13 +1726,13 @@ err:
 	return err;
 }
 
-static struct rtrs_srv_sess *__alloc_sess(struct rtrs_srv *srv,
+static struct rtrs_srv_path *__alloc_path(struct rtrs_srv *srv,
 					   struct rdma_cm_id *cm_id,
 					   unsigned int con_num,
 					   unsigned int recon_cnt,
 					   const uuid_t *uuid)
 {
-	struct rtrs_srv_sess *sess;
+	struct rtrs_srv_path *srv_path;
 	int err = -ENOMEM;
 	char str[NAME_MAX];
 	struct rtrs_addr path;
@@ -1734,73 +1746,76 @@ static struct rtrs_srv_sess *__alloc_sess(struct rtrs_srv *srv,
 		pr_err("Path with same addr exists\n");
 		goto err;
 	}
-	sess = kzalloc(sizeof(*sess), GFP_KERNEL);
-	if (!sess)
+	srv_path = kzalloc(sizeof(*srv_path), GFP_KERNEL);
+	if (!srv_path)
 		goto err;
 
-	sess->stats = kzalloc(sizeof(*sess->stats), GFP_KERNEL);
-	if (!sess->stats)
+	srv_path->stats = kzalloc(sizeof(*srv_path->stats), GFP_KERNEL);
+	if (!srv_path->stats)
 		goto err_free_sess;
 
-	sess->stats->sess = sess;
+	srv_path->stats->srv_path = srv_path;
 
-	sess->dma_addr = kcalloc(srv->queue_depth, sizeof(*sess->dma_addr),
-				 GFP_KERNEL);
-	if (!sess->dma_addr)
+	srv_path->dma_addr = kcalloc(srv->queue_depth,
+				     sizeof(*srv_path->dma_addr),
+				     GFP_KERNEL);
+	if (!srv_path->dma_addr)
 		goto err_free_stats;
 
-	sess->s.con = kcalloc(con_num, sizeof(*sess->s.con), GFP_KERNEL);
-	if (!sess->s.con)
+	srv_path->s.con = kcalloc(con_num, sizeof(*srv_path->s.con),
+				  GFP_KERNEL);
+	if (!srv_path->s.con)
 		goto err_free_dma_addr;
 
-	sess->state = RTRS_SRV_CONNECTING;
-	sess->srv = srv;
-	sess->cur_cq_vector = -1;
-	sess->s.dst_addr = cm_id->route.addr.dst_addr;
-	sess->s.src_addr = cm_id->route.addr.src_addr;
+	srv_path->state = RTRS_SRV_CONNECTING;
+	srv_path->srv = srv;
+	srv_path->cur_cq_vector = -1;
+	srv_path->s.dst_addr = cm_id->route.addr.dst_addr;
+	srv_path->s.src_addr = cm_id->route.addr.src_addr;
 
 	/* temporary until receiving session-name from client */
-	path.src = &sess->s.src_addr;
-	path.dst = &sess->s.dst_addr;
+	path.src = &srv_path->s.src_addr;
+	path.dst = &srv_path->s.dst_addr;
 	rtrs_addr_to_str(&path, str, sizeof(str));
-	strscpy(sess->s.sessname, str, sizeof(sess->s.sessname));
-
-	sess->s.con_num = con_num;
-	sess->s.recon_cnt = recon_cnt;
-	uuid_copy(&sess->s.uuid, uuid);
-	spin_lock_init(&sess->state_lock);
-	INIT_WORK(&sess->close_work, rtrs_srv_close_work);
-	rtrs_srv_init_hb(sess);
-
-	sess->s.dev = rtrs_ib_dev_find_or_add(cm_id->device, &dev_pd);
-	if (!sess->s.dev) {
+	strscpy(srv_path->s.sessname, str, sizeof(srv_path->s.sessname));
+
+	srv_path->s.con_num = con_num;
+	srv_path->s.irq_con_num = con_num;
+	srv_path->s.recon_cnt = recon_cnt;
+	uuid_copy(&srv_path->s.uuid, uuid);
+	spin_lock_init(&srv_path->state_lock);
+	INIT_WORK(&srv_path->close_work, rtrs_srv_close_work);
+	rtrs_srv_init_hb(srv_path);
+
+	srv_path->s.dev = rtrs_ib_dev_find_or_add(cm_id->device, &dev_pd);
+	if (!srv_path->s.dev) {
 		err = -ENOMEM;
 		goto err_free_con;
 	}
-	err = map_cont_bufs(sess);
+	err = map_cont_bufs(srv_path);
 	if (err)
 		goto err_put_dev;
 
-	err = rtrs_srv_alloc_ops_ids(sess);
+	err = rtrs_srv_alloc_ops_ids(srv_path);
 	if (err)
 		goto err_unmap_bufs;
 
-	__add_path_to_srv(srv, sess);
+	__add_path_to_srv(srv, srv_path);
 
-	return sess;
+	return srv_path;
 
 err_unmap_bufs:
-	unmap_cont_bufs(sess);
+	unmap_cont_bufs(srv_path);
 err_put_dev:
-	rtrs_ib_dev_put(sess->s.dev);
+	rtrs_ib_dev_put(srv_path->s.dev);
 err_free_con:
-	kfree(sess->s.con);
+	kfree(srv_path->s.con);
 err_free_dma_addr:
-	kfree(sess->dma_addr);
+	kfree(srv_path->dma_addr);
 err_free_stats:
-	kfree(sess->stats);
+	kfree(srv_path->stats);
 err_free_sess:
-	kfree(sess);
+	kfree(srv_path);
 err:
 	return ERR_PTR(err);
 }
@@ -1810,7 +1825,7 @@ static int rtrs_rdma_connect(struct rdma_cm_id *cm_id,
 			      size_t len)
 {
 	struct rtrs_srv_ctx *ctx = cm_id->context;
-	struct rtrs_srv_sess *sess;
+	struct rtrs_srv_path *srv_path;
 	struct rtrs_srv *srv;
 
 	u16 version, con_num, cid;
@@ -1851,16 +1866,16 @@ static int rtrs_rdma_connect(struct rdma_cm_id *cm_id,
 		goto reject_w_err;
 	}
 	mutex_lock(&srv->paths_mutex);
-	sess = __find_sess(srv, &msg->sess_uuid);
-	if (sess) {
-		struct rtrs_sess *s = &sess->s;
+	srv_path = __find_path(srv, &msg->sess_uuid);
+	if (srv_path) {
+		struct rtrs_path *s = &srv_path->s;
 
 		/* Session already holds a reference */
 		put_srv(srv);
 
-		if (sess->state != RTRS_SRV_CONNECTING) {
+		if (srv_path->state != RTRS_SRV_CONNECTING) {
 			rtrs_err(s, "Session in wrong state: %s\n",
-				  rtrs_srv_state_str(sess->state));
+				  rtrs_srv_state_str(srv_path->state));
 			mutex_unlock(&srv->paths_mutex);
 			goto reject_w_err;
 		}
@@ -1880,19 +1895,19 @@ static int rtrs_rdma_connect(struct rdma_cm_id *cm_id,
 			goto reject_w_err;
 		}
 	} else {
-		sess = __alloc_sess(srv, cm_id, con_num, recon_cnt,
+		srv_path = __alloc_path(srv, cm_id, con_num, recon_cnt,
 				    &msg->sess_uuid);
-		if (IS_ERR(sess)) {
+		if (IS_ERR(srv_path)) {
 			mutex_unlock(&srv->paths_mutex);
 			put_srv(srv);
-			err = PTR_ERR(sess);
+			err = PTR_ERR(srv_path);
 			pr_err("RTRS server session allocation failed: %d\n", err);
 			goto reject_w_err;
 		}
 	}
-	err = create_con(sess, cm_id, cid);
+	err = create_con(srv_path, cm_id, cid);
 	if (err) {
-		rtrs_err((&sess->s), "create_con(), error %d\n", err);
+		rtrs_err((&srv_path->s), "create_con(), error %d\n", err);
 		rtrs_rdma_do_reject(cm_id, err);
 		/*
 		 * Since session has other connections we follow normal way
@@ -1901,9 +1916,9 @@ static int rtrs_rdma_connect(struct rdma_cm_id *cm_id,
 		 */
 		goto close_and_return_err;
 	}
-	err = rtrs_rdma_do_accept(sess, cm_id);
+	err = rtrs_rdma_do_accept(srv_path, cm_id);
 	if (err) {
-		rtrs_err((&sess->s), "rtrs_rdma_do_accept(), error %d\n", err);
+		rtrs_err((&srv_path->s), "rtrs_rdma_do_accept(), error %d\n", err);
 		rtrs_rdma_do_reject(cm_id, err);
 		/*
 		 * Since current connection was successfully added to the
@@ -1923,7 +1938,7 @@ reject_w_err:
 
 close_and_return_err:
 	mutex_unlock(&srv->paths_mutex);
-	close_sess(sess);
+	close_path(srv_path);
 
 	return err;
 }
@@ -1931,14 +1946,14 @@ close_and_return_err:
 static int rtrs_srv_rdma_cm_handler(struct rdma_cm_id *cm_id,
 				     struct rdma_cm_event *ev)
 {
-	struct rtrs_srv_sess *sess = NULL;
-	struct rtrs_sess *s = NULL;
+	struct rtrs_srv_path *srv_path = NULL;
+	struct rtrs_path *s = NULL;
 
 	if (ev->event != RDMA_CM_EVENT_CONNECT_REQUEST) {
 		struct rtrs_con *c = cm_id->context;
 
-		s = c->sess;
-		sess = to_srv_sess(s);
+		s = c->path;
+		srv_path = to_srv_path(s);
 	}
 
 	switch (ev->event) {
@@ -1962,7 +1977,7 @@ static int rtrs_srv_rdma_cm_handler(struct rdma_cm_id *cm_id,
 	case RDMA_CM_EVENT_ADDR_CHANGE:
 	case RDMA_CM_EVENT_TIMEWAIT_EXIT:
 	case RDMA_CM_EVENT_DEVICE_REMOVAL:
-		close_sess(sess);
+		close_path(srv_path);
 		break;
 	default:
 		pr_err("Ignoring unexpected CM event %s, err %d\n",
@@ -2170,13 +2185,13 @@ struct rtrs_srv_ctx *rtrs_srv_open(struct rtrs_srv_ops *ops, u16 port)
 }
 EXPORT_SYMBOL(rtrs_srv_open);
 
-static void close_sessions(struct rtrs_srv *srv)
+static void close_paths(struct rtrs_srv *srv)
 {
-	struct rtrs_srv_sess *sess;
+	struct rtrs_srv_path *srv_path;
 
 	mutex_lock(&srv->paths_mutex);
-	list_for_each_entry(sess, &srv->paths_list, s.entry)
-		close_sess(sess);
+	list_for_each_entry(srv_path, &srv->paths_list, s.entry)
+		close_path(srv_path);
 	mutex_unlock(&srv->paths_mutex);
 }
 
@@ -2186,7 +2201,7 @@ static void close_ctx(struct rtrs_srv_ctx *ctx)
 
 	mutex_lock(&ctx->srv_mutex);
 	list_for_each_entry(srv, &ctx->srv_list, ctx_list)
-		close_sessions(srv);
+		close_paths(srv);
 	mutex_unlock(&ctx->srv_mutex);
 	flush_workqueue(rtrs_wq);
 }
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv.h b/drivers/infiniband/ulp/rtrs/rtrs-srv.h
index 9d8d2a91a235..ee3578b9aa01 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-srv.h
+++ b/drivers/infiniband/ulp/rtrs/rtrs-srv.h
@@ -37,7 +37,7 @@ struct rtrs_srv_stats_rdma_stats {
 struct rtrs_srv_stats {
 	struct kobject				kobj_stats;
 	struct rtrs_srv_stats_rdma_stats	rdma_stats;
-	struct rtrs_srv_sess			*sess;
+	struct rtrs_srv_path			*srv_path;
 };
 
 struct rtrs_srv_con {
@@ -71,8 +71,8 @@ struct rtrs_srv_mr {
 	struct rtrs_iu	*iu;		/* send buffer for new rkey msg */
 };
 
-struct rtrs_srv_sess {
-	struct rtrs_sess	s;
+struct rtrs_srv_path {
+	struct rtrs_path	s;
 	struct rtrs_srv	*srv;
 	struct work_struct	close_work;
 	enum rtrs_srv_state	state;
@@ -125,7 +125,7 @@ struct rtrs_srv_ib_ctx {
 
 extern struct class *rtrs_dev_class;
 
-void close_sess(struct rtrs_srv_sess *sess);
+void close_path(struct rtrs_srv_path *srv_path);
 
 static inline void rtrs_srv_update_rdma_stats(struct rtrs_srv_stats *s,
 					      size_t size, int d)
@@ -143,7 +143,7 @@ ssize_t rtrs_srv_reset_all_help(struct rtrs_srv_stats *stats,
 				 char *page, size_t len);
 
 /* functions which are implemented in rtrs-srv-sysfs.c */
-int rtrs_srv_create_sess_files(struct rtrs_srv_sess *sess);
-void rtrs_srv_destroy_sess_files(struct rtrs_srv_sess *sess);
+int rtrs_srv_create_path_files(struct rtrs_srv_path *srv_path);
+void rtrs_srv_destroy_path_files(struct rtrs_srv_path *srv_path);
 
 #endif /* RTRS_SRV_H */
diff --git a/drivers/infiniband/ulp/rtrs/rtrs.c b/drivers/infiniband/ulp/rtrs/rtrs.c
index ca542e477d38..4da889103a5f 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs.c
@@ -69,16 +69,16 @@ EXPORT_SYMBOL_GPL(rtrs_iu_free);
 
 int rtrs_iu_post_recv(struct rtrs_con *con, struct rtrs_iu *iu)
 {
-	struct rtrs_sess *sess = con->sess;
+	struct rtrs_path *path = con->path;
 	struct ib_recv_wr wr;
 	struct ib_sge list;
 
 	list.addr   = iu->dma_addr;
 	list.length = iu->size;
-	list.lkey   = sess->dev->ib_pd->local_dma_lkey;
+	list.lkey   = path->dev->ib_pd->local_dma_lkey;
 
 	if (list.length == 0) {
-		rtrs_wrn(con->sess,
+		rtrs_wrn(con->path,
 			  "Posting receive work request failed, sg list is empty\n");
 		return -EINVAL;
 	}
@@ -126,7 +126,7 @@ static int rtrs_post_send(struct ib_qp *qp, struct ib_send_wr *head,
 int rtrs_iu_post_send(struct rtrs_con *con, struct rtrs_iu *iu, size_t size,
 		       struct ib_send_wr *head)
 {
-	struct rtrs_sess *sess = con->sess;
+	struct rtrs_path *path = con->path;
 	struct ib_send_wr wr;
 	struct ib_sge list;
 
@@ -135,7 +135,7 @@ int rtrs_iu_post_send(struct rtrs_con *con, struct rtrs_iu *iu, size_t size,
 
 	list.addr   = iu->dma_addr;
 	list.length = size;
-	list.lkey   = sess->dev->ib_pd->local_dma_lkey;
+	list.lkey   = path->dev->ib_pd->local_dma_lkey;
 
 	wr = (struct ib_send_wr) {
 		.wr_cqe     = &iu->cqe,
@@ -188,11 +188,11 @@ static int rtrs_post_rdma_write_imm_empty(struct rtrs_con *con,
 					  struct ib_send_wr *head)
 {
 	struct ib_rdma_wr wr;
-	struct rtrs_sess *sess = con->sess;
+	struct rtrs_path *path = con->path;
 	enum ib_send_flags sflags;
 
 	atomic_dec_if_positive(&con->sq_wr_avail);
-	sflags = (atomic_inc_return(&con->wr_cnt) % sess->signal_interval) ?
+	sflags = (atomic_inc_return(&con->wr_cnt) % path->signal_interval) ?
 		0 : IB_SEND_SIGNALED;
 
 	wr = (struct ib_rdma_wr) {
@@ -211,26 +211,36 @@ static void qp_event_handler(struct ib_event *ev, void *ctx)
 
 	switch (ev->event) {
 	case IB_EVENT_COMM_EST:
-		rtrs_info(con->sess, "QP event %s (%d) received\n",
+		rtrs_info(con->path, "QP event %s (%d) received\n",
 			   ib_event_msg(ev->event), ev->event);
 		rdma_notify(con->cm_id, IB_EVENT_COMM_EST);
 		break;
 	default:
-		rtrs_info(con->sess, "Unhandled QP event %s (%d) received\n",
+		rtrs_info(con->path, "Unhandled QP event %s (%d) received\n",
 			   ib_event_msg(ev->event), ev->event);
 		break;
 	}
 }
 
+static bool is_pollqueue(struct rtrs_con *con)
+{
+	return con->cid >= con->path->irq_con_num;
+}
+
 static int create_cq(struct rtrs_con *con, int cq_vector, int nr_cqe,
 		     enum ib_poll_context poll_ctx)
 {
 	struct rdma_cm_id *cm_id = con->cm_id;
 	struct ib_cq *cq;
 
-	cq = ib_cq_pool_get(cm_id->device, nr_cqe, cq_vector, poll_ctx);
+	if (is_pollqueue(con))
+		cq = ib_alloc_cq(cm_id->device, con, nr_cqe, cq_vector,
+				 poll_ctx);
+	else
+		cq = ib_cq_pool_get(cm_id->device, nr_cqe, cq_vector, poll_ctx);
+
 	if (IS_ERR(cq)) {
-		rtrs_err(con->sess, "Creating completion queue failed, errno: %ld\n",
+		rtrs_err(con->path, "Creating completion queue failed, errno: %ld\n",
 			  PTR_ERR(cq));
 		return PTR_ERR(cq);
 	}
@@ -261,7 +271,7 @@ static int create_qp(struct rtrs_con *con, struct ib_pd *pd,
 
 	ret = rdma_create_qp(cm_id, pd, &init_attr);
 	if (ret) {
-		rtrs_err(con->sess, "Creating QP failed, err: %d\n", ret);
+		rtrs_err(con->path, "Creating QP failed, err: %d\n", ret);
 		return ret;
 	}
 	con->qp = cm_id->qp;
@@ -269,7 +279,18 @@ static int create_qp(struct rtrs_con *con, struct ib_pd *pd,
 	return ret;
 }
 
-int rtrs_cq_qp_create(struct rtrs_sess *sess, struct rtrs_con *con,
+static void destroy_cq(struct rtrs_con *con)
+{
+	if (con->cq) {
+		if (is_pollqueue(con))
+			ib_free_cq(con->cq);
+		else
+			ib_cq_pool_put(con->cq, con->nr_cqe);
+	}
+	con->cq = NULL;
+}
+
+int rtrs_cq_qp_create(struct rtrs_path *path, struct rtrs_con *con,
 		       u32 max_send_sge, int cq_vector, int nr_cqe,
 		       u32 max_send_wr, u32 max_recv_wr,
 		       enum ib_poll_context poll_ctx)
@@ -280,14 +301,13 @@ int rtrs_cq_qp_create(struct rtrs_sess *sess, struct rtrs_con *con,
 	if (err)
 		return err;
 
-	err = create_qp(con, sess->dev->ib_pd, max_send_wr, max_recv_wr,
+	err = create_qp(con, path->dev->ib_pd, max_send_wr, max_recv_wr,
 			max_send_sge);
 	if (err) {
-		ib_cq_pool_put(con->cq, con->nr_cqe);
-		con->cq = NULL;
+		destroy_cq(con);
 		return err;
 	}
-	con->sess = sess;
+	con->path = path;
 
 	return 0;
 }
@@ -299,31 +319,28 @@ void rtrs_cq_qp_destroy(struct rtrs_con *con)
 		rdma_destroy_qp(con->cm_id);
 		con->qp = NULL;
 	}
-	if (con->cq) {
-		ib_cq_pool_put(con->cq, con->nr_cqe);
-		con->cq = NULL;
-	}
+	destroy_cq(con);
 }
 EXPORT_SYMBOL_GPL(rtrs_cq_qp_destroy);
 
-static void schedule_hb(struct rtrs_sess *sess)
+static void schedule_hb(struct rtrs_path *path)
 {
-	queue_delayed_work(sess->hb_wq, &sess->hb_dwork,
-			   msecs_to_jiffies(sess->hb_interval_ms));
+	queue_delayed_work(path->hb_wq, &path->hb_dwork,
+			   msecs_to_jiffies(path->hb_interval_ms));
 }
 
-void rtrs_send_hb_ack(struct rtrs_sess *sess)
+void rtrs_send_hb_ack(struct rtrs_path *path)
 {
-	struct rtrs_con *usr_con = sess->con[0];
+	struct rtrs_con *usr_con = path->con[0];
 	u32 imm;
 	int err;
 
 	imm = rtrs_to_imm(RTRS_HB_ACK_IMM, 0);
-	err = rtrs_post_rdma_write_imm_empty(usr_con, sess->hb_cqe, imm,
+	err = rtrs_post_rdma_write_imm_empty(usr_con, path->hb_cqe, imm,
 					     NULL);
 	if (err) {
-		rtrs_err(sess, "send HB ACK failed, errno: %d\n", err);
-		sess->hb_err_handler(usr_con);
+		rtrs_err(path, "send HB ACK failed, errno: %d\n", err);
+		path->hb_err_handler(usr_con);
 		return;
 	}
 }
@@ -332,63 +349,63 @@ EXPORT_SYMBOL_GPL(rtrs_send_hb_ack);
 static void hb_work(struct work_struct *work)
 {
 	struct rtrs_con *usr_con;
-	struct rtrs_sess *sess;
+	struct rtrs_path *path;
 	u32 imm;
 	int err;
 
-	sess = container_of(to_delayed_work(work), typeof(*sess), hb_dwork);
-	usr_con = sess->con[0];
+	path = container_of(to_delayed_work(work), typeof(*path), hb_dwork);
+	usr_con = path->con[0];
 
-	if (sess->hb_missed_cnt > sess->hb_missed_max) {
-		rtrs_err(sess, "HB missed max reached.\n");
-		sess->hb_err_handler(usr_con);
+	if (path->hb_missed_cnt > path->hb_missed_max) {
+		rtrs_err(path, "HB missed max reached.\n");
+		path->hb_err_handler(usr_con);
 		return;
 	}
-	if (sess->hb_missed_cnt++) {
+	if (path->hb_missed_cnt++) {
 		/* Reschedule work without sending hb */
-		schedule_hb(sess);
+		schedule_hb(path);
 		return;
 	}
 
-	sess->hb_last_sent = ktime_get();
+	path->hb_last_sent = ktime_get();
 
 	imm = rtrs_to_imm(RTRS_HB_MSG_IMM, 0);
-	err = rtrs_post_rdma_write_imm_empty(usr_con, sess->hb_cqe, imm,
+	err = rtrs_post_rdma_write_imm_empty(usr_con, path->hb_cqe, imm,
 					     NULL);
 	if (err) {
-		rtrs_err(sess, "HB send failed, errno: %d\n", err);
-		sess->hb_err_handler(usr_con);
+		rtrs_err(path, "HB send failed, errno: %d\n", err);
+		path->hb_err_handler(usr_con);
 		return;
 	}
 
-	schedule_hb(sess);
+	schedule_hb(path);
 }
 
-void rtrs_init_hb(struct rtrs_sess *sess, struct ib_cqe *cqe,
+void rtrs_init_hb(struct rtrs_path *path, struct ib_cqe *cqe,
 		  unsigned int interval_ms, unsigned int missed_max,
 		  void (*err_handler)(struct rtrs_con *con),
 		  struct workqueue_struct *wq)
 {
-	sess->hb_cqe = cqe;
-	sess->hb_interval_ms = interval_ms;
-	sess->hb_err_handler = err_handler;
-	sess->hb_wq = wq;
-	sess->hb_missed_max = missed_max;
-	sess->hb_missed_cnt = 0;
-	INIT_DELAYED_WORK(&sess->hb_dwork, hb_work);
+	path->hb_cqe = cqe;
+	path->hb_interval_ms = interval_ms;
+	path->hb_err_handler = err_handler;
+	path->hb_wq = wq;
+	path->hb_missed_max = missed_max;
+	path->hb_missed_cnt = 0;
+	INIT_DELAYED_WORK(&path->hb_dwork, hb_work);
 }
 EXPORT_SYMBOL_GPL(rtrs_init_hb);
 
-void rtrs_start_hb(struct rtrs_sess *sess)
+void rtrs_start_hb(struct rtrs_path *path)
 {
-	schedule_hb(sess);
+	schedule_hb(path);
 }
 EXPORT_SYMBOL_GPL(rtrs_start_hb);
 
-void rtrs_stop_hb(struct rtrs_sess *sess)
+void rtrs_stop_hb(struct rtrs_path *path)
 {
-	cancel_delayed_work_sync(&sess->hb_dwork);
-	sess->hb_missed_cnt = 0;
+	cancel_delayed_work_sync(&path->hb_dwork);
+	path->hb_missed_cnt = 0;
 }
 EXPORT_SYMBOL_GPL(rtrs_stop_hb);
 
diff --git a/drivers/infiniband/ulp/rtrs/rtrs.h b/drivers/infiniband/ulp/rtrs/rtrs.h
index 859c79685daf..c529b6d63c9a 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs.h
+++ b/drivers/infiniband/ulp/rtrs/rtrs.h
@@ -53,13 +53,13 @@ struct rtrs_clt_ops {
 };
 
 struct rtrs_clt *rtrs_clt_open(struct rtrs_clt_ops *ops,
-				 const char *sessname,
+				 const char *pathname,
 				 const struct rtrs_addr *paths,
 				 size_t path_cnt, u16 port,
 				 size_t pdu_sz, u8 reconnect_delay_sec,
 				 s16 max_reconnect_attempts, u32 nr_poll_queues);
 
-void rtrs_clt_close(struct rtrs_clt *sess);
+void rtrs_clt_close(struct rtrs_clt *clt_path);
 
 enum wait_type {
 	RTRS_PERMIT_NOWAIT = 0,
@@ -175,7 +175,8 @@ bool rtrs_srv_resp_rdma(struct rtrs_srv_op *id, int errno);
 
 void rtrs_srv_set_sess_priv(struct rtrs_srv *sess, void *priv);
 
-int rtrs_srv_get_sess_name(struct rtrs_srv *sess, char *sessname, size_t len);
+int rtrs_srv_get_path_name(struct rtrs_srv *sess, char *pathname,
+			   size_t len);
 
 int rtrs_srv_get_queue_depth(struct rtrs_srv *sess);
 
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 5d416ec22871..473b3a08cf96 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -1955,7 +1955,8 @@ static void srp_process_rsp(struct srp_rdma_ch *ch, struct srp_rsp *rsp)
 		if (scmnd) {
 			req = scsi_cmd_priv(scmnd);
 			scmnd = srp_claim_req(ch, req, NULL, scmnd);
-		} else {
+		}
+		if (!scmnd) {
 			shost_printk(KERN_ERR, target->scsi_host,
 				     "Null scmnd for RSP w/tag %#016llx received on ch %td / QP %#x\n",
 				     rsp->tag, ch - target->ch, ch->qp->qp_num);
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 3cadf1295417..7b69b0c9e48d 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -565,12 +565,9 @@ static int srpt_refresh_port(struct srpt_port *sport)
 	if (ret)
 		return ret;
 
-	sport->port_guid_id.wwn.priv = sport;
-	srpt_format_guid(sport->port_guid_id.name,
-			 sizeof(sport->port_guid_id.name),
+	srpt_format_guid(sport->guid_name, ARRAY_SIZE(sport->guid_name),
 			 &sport->gid.global.interface_id);
-	sport->port_gid_id.wwn.priv = sport;
-	snprintf(sport->port_gid_id.name, sizeof(sport->port_gid_id.name),
+	snprintf(sport->gid_name, ARRAY_SIZE(sport->gid_name),
 		 "0x%016llx%016llx",
 		 be64_to_cpu(sport->gid.global.subnet_prefix),
 		 be64_to_cpu(sport->gid.global.interface_id));
@@ -2314,31 +2311,35 @@ static int srpt_cm_req_recv(struct srpt_device *const sdev,
 	tag_num = ch->rq_size;
 	tag_size = 1; /* ib_srpt does not use se_sess->sess_cmd_map */
 
-	mutex_lock(&sport->port_guid_id.mutex);
-	list_for_each_entry(stpg, &sport->port_guid_id.tpg_list, entry) {
-		if (!IS_ERR_OR_NULL(ch->sess))
-			break;
-		ch->sess = target_setup_session(&stpg->tpg, tag_num,
+	if (sport->guid_id) {
+		mutex_lock(&sport->guid_id->mutex);
+		list_for_each_entry(stpg, &sport->guid_id->tpg_list, entry) {
+			if (!IS_ERR_OR_NULL(ch->sess))
+				break;
+			ch->sess = target_setup_session(&stpg->tpg, tag_num,
 						tag_size, TARGET_PROT_NORMAL,
 						ch->sess_name, ch, NULL);
+		}
+		mutex_unlock(&sport->guid_id->mutex);
 	}
-	mutex_unlock(&sport->port_guid_id.mutex);
 
-	mutex_lock(&sport->port_gid_id.mutex);
-	list_for_each_entry(stpg, &sport->port_gid_id.tpg_list, entry) {
-		if (!IS_ERR_OR_NULL(ch->sess))
-			break;
-		ch->sess = target_setup_session(&stpg->tpg, tag_num,
+	if (sport->gid_id) {
+		mutex_lock(&sport->gid_id->mutex);
+		list_for_each_entry(stpg, &sport->gid_id->tpg_list, entry) {
+			if (!IS_ERR_OR_NULL(ch->sess))
+				break;
+			ch->sess = target_setup_session(&stpg->tpg, tag_num,
 					tag_size, TARGET_PROT_NORMAL, i_port_id,
 					ch, NULL);
-		if (!IS_ERR_OR_NULL(ch->sess))
-			break;
-		/* Retry without leading "0x" */
-		ch->sess = target_setup_session(&stpg->tpg, tag_num,
+			if (!IS_ERR_OR_NULL(ch->sess))
+				break;
+			/* Retry without leading "0x" */
+			ch->sess = target_setup_session(&stpg->tpg, tag_num,
 						tag_size, TARGET_PROT_NORMAL,
 						i_port_id + 2, ch, NULL);
+		}
+		mutex_unlock(&sport->gid_id->mutex);
 	}
-	mutex_unlock(&sport->port_gid_id.mutex);
 
 	if (IS_ERR_OR_NULL(ch->sess)) {
 		WARN_ON_ONCE(ch->sess == NULL);
@@ -2983,7 +2984,12 @@ static int srpt_release_sport(struct srpt_port *sport)
 	return 0;
 }
 
-static struct se_wwn *__srpt_lookup_wwn(const char *name)
+struct port_and_port_id {
+	struct srpt_port *sport;
+	struct srpt_port_id **port_id;
+};
+
+static struct port_and_port_id __srpt_lookup_port(const char *name)
 {
 	struct ib_device *dev;
 	struct srpt_device *sdev;
@@ -2998,25 +3004,38 @@ static struct se_wwn *__srpt_lookup_wwn(const char *name)
 		for (i = 0; i < dev->phys_port_cnt; i++) {
 			sport = &sdev->port[i];
 
-			if (strcmp(sport->port_guid_id.name, name) == 0)
-				return &sport->port_guid_id.wwn;
-			if (strcmp(sport->port_gid_id.name, name) == 0)
-				return &sport->port_gid_id.wwn;
+			if (strcmp(sport->guid_name, name) == 0) {
+				kref_get(&sdev->refcnt);
+				return (struct port_and_port_id){
+					sport, &sport->guid_id};
+			}
+			if (strcmp(sport->gid_name, name) == 0) {
+				kref_get(&sdev->refcnt);
+				return (struct port_and_port_id){
+					sport, &sport->gid_id};
+			}
 		}
 	}
 
-	return NULL;
+	return (struct port_and_port_id){};
 }
 
-static struct se_wwn *srpt_lookup_wwn(const char *name)
+/**
+ * srpt_lookup_port() - Look up an RDMA port by name
+ * @name: ASCII port name
+ *
+ * Increments the RDMA port reference count if an RDMA port pointer is returned.
+ * The caller must drop that reference count by calling srpt_port_put_ref().
+ */
+static struct port_and_port_id srpt_lookup_port(const char *name)
 {
-	struct se_wwn *wwn;
+	struct port_and_port_id papi;
 
 	spin_lock(&srpt_dev_lock);
-	wwn = __srpt_lookup_wwn(name);
+	papi = __srpt_lookup_port(name);
 	spin_unlock(&srpt_dev_lock);
 
-	return wwn;
+	return papi;
 }
 
 static void srpt_free_srq(struct srpt_device *sdev)
@@ -3101,6 +3120,18 @@ static int srpt_use_srq(struct srpt_device *sdev, bool use_srq)
 	return ret;
 }
 
+static void srpt_free_sdev(struct kref *refcnt)
+{
+	struct srpt_device *sdev = container_of(refcnt, typeof(*sdev), refcnt);
+
+	kfree(sdev);
+}
+
+static void srpt_sdev_put(struct srpt_device *sdev)
+{
+	kref_put(&sdev->refcnt, srpt_free_sdev);
+}
+
 /**
  * srpt_add_one - InfiniBand device addition callback function
  * @device: Describes a HCA.
@@ -3119,6 +3150,7 @@ static int srpt_add_one(struct ib_device *device)
 	if (!sdev)
 		return -ENOMEM;
 
+	kref_init(&sdev->refcnt);
 	sdev->device = device;
 	mutex_init(&sdev->sdev_mutex);
 
@@ -3182,10 +3214,6 @@ static int srpt_add_one(struct ib_device *device)
 		sport->port_attrib.srp_sq_size = DEF_SRPT_SQ_SIZE;
 		sport->port_attrib.use_srq = false;
 		INIT_WORK(&sport->work, srpt_refresh_port_work);
-		mutex_init(&sport->port_guid_id.mutex);
-		INIT_LIST_HEAD(&sport->port_guid_id.tpg_list);
-		mutex_init(&sport->port_gid_id.mutex);
-		INIT_LIST_HEAD(&sport->port_gid_id.tpg_list);
 
 		ret = srpt_refresh_port(sport);
 		if (ret) {
@@ -3214,7 +3242,7 @@ err_ring:
 	srpt_free_srq(sdev);
 	ib_dealloc_pd(sdev->pd);
 free_dev:
-	kfree(sdev);
+	srpt_sdev_put(sdev);
 	pr_info("%s(%s) failed.\n", __func__, dev_name(&device->dev));
 	return ret;
 }
@@ -3258,7 +3286,7 @@ static void srpt_remove_one(struct ib_device *device, void *client_data)
 
 	ib_dealloc_pd(sdev->pd);
 
-	kfree(sdev);
+	srpt_sdev_put(sdev);
 }
 
 static struct ib_client srpt_client = {
@@ -3286,10 +3314,10 @@ static struct srpt_port_id *srpt_wwn_to_sport_id(struct se_wwn *wwn)
 {
 	struct srpt_port *sport = wwn->priv;
 
-	if (wwn == &sport->port_guid_id.wwn)
-		return &sport->port_guid_id;
-	if (wwn == &sport->port_gid_id.wwn)
-		return &sport->port_gid_id;
+	if (sport->guid_id && &sport->guid_id->wwn == wwn)
+		return sport->guid_id;
+	if (sport->gid_id && &sport->gid_id->wwn == wwn)
+		return sport->gid_id;
 	WARN_ON_ONCE(true);
 	return NULL;
 }
@@ -3804,7 +3832,31 @@ static struct se_wwn *srpt_make_tport(struct target_fabric_configfs *tf,
 				      struct config_group *group,
 				      const char *name)
 {
-	return srpt_lookup_wwn(name) ? : ERR_PTR(-EINVAL);
+	struct port_and_port_id papi = srpt_lookup_port(name);
+	struct srpt_port *sport = papi.sport;
+	struct srpt_port_id *port_id;
+
+	if (!papi.port_id)
+		return ERR_PTR(-EINVAL);
+	if (*papi.port_id) {
+		/* Attempt to create a directory that already exists. */
+		WARN_ON_ONCE(true);
+		return &(*papi.port_id)->wwn;
+	}
+	port_id = kzalloc(sizeof(*port_id), GFP_KERNEL);
+	if (!port_id) {
+		srpt_sdev_put(sport->sdev);
+		return ERR_PTR(-ENOMEM);
+	}
+	mutex_init(&port_id->mutex);
+	INIT_LIST_HEAD(&port_id->tpg_list);
+	port_id->wwn.priv = sport;
+	memcpy(port_id->name, port_id == sport->guid_id ? sport->guid_name :
+	       sport->gid_name, ARRAY_SIZE(port_id->name));
+
+	*papi.port_id = port_id;
+
+	return &port_id->wwn;
 }
 
 /**
@@ -3813,6 +3865,18 @@ static struct se_wwn *srpt_make_tport(struct target_fabric_configfs *tf,
  */
 static void srpt_drop_tport(struct se_wwn *wwn)
 {
+	struct srpt_port_id *port_id = container_of(wwn, typeof(*port_id), wwn);
+	struct srpt_port *sport = wwn->priv;
+
+	if (sport->guid_id == port_id)
+		sport->guid_id = NULL;
+	else if (sport->gid_id == port_id)
+		sport->gid_id = NULL;
+	else
+		WARN_ON_ONCE(true);
+
+	srpt_sdev_put(sport->sdev);
+	kfree(port_id);
 }
 
 static ssize_t srpt_wwn_version_show(struct config_item *item, char *buf)
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.h b/drivers/infiniband/ulp/srpt/ib_srpt.h
index 76e66f630c17..4c46b301eea1 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.h
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.h
@@ -376,7 +376,7 @@ struct srpt_tpg {
 };
 
 /**
- * struct srpt_port_id - information about an RDMA port name
+ * struct srpt_port_id - LIO RDMA port information
  * @mutex:	Protects @tpg_list changes.
  * @tpg_list:	TPGs associated with the RDMA port name.
  * @wwn:	WWN associated with the RDMA port name.
@@ -393,7 +393,7 @@ struct srpt_port_id {
 };
 
 /**
- * struct srpt_port - information associated by SRPT with a single IB port
+ * struct srpt_port - SRPT RDMA port information
  * @sdev:      backpointer to the HCA information.
  * @mad_agent: per-port management datagram processing information.
  * @enabled:   Whether or not this target port is enabled.
@@ -402,8 +402,10 @@ struct srpt_port_id {
  * @lid:       cached value of the port's lid.
  * @gid:       cached value of the port's gid.
  * @work:      work structure for refreshing the aforementioned cached values.
- * @port_guid_id: target port GUID
- * @port_gid_id: target port GID
+ * @guid_name: port name in GUID format.
+ * @guid_id:   LIO target port information for the port name in GUID format.
+ * @gid_name:  port name in GID format.
+ * @gid_id:    LIO target port information for the port name in GID format.
  * @port_attrib:   Port attributes that can be accessed through configfs.
  * @refcount:	   Number of objects associated with this port.
  * @freed_channels: Completion that will be signaled once @refcount becomes 0.
@@ -419,8 +421,10 @@ struct srpt_port {
 	u32			lid;
 	union ib_gid		gid;
 	struct work_struct	work;
-	struct srpt_port_id	port_guid_id;
-	struct srpt_port_id	port_gid_id;
+	char			guid_name[64];
+	struct srpt_port_id	*guid_id;
+	char			gid_name[64];
+	struct srpt_port_id	*gid_id;
 	struct srpt_port_attrib port_attrib;
 	atomic_t		refcount;
 	struct completion	*freed_channels;
@@ -430,6 +434,7 @@ struct srpt_port {
 
 /**
  * struct srpt_device - information associated by SRPT with a single HCA
+ * @refcnt:	   Reference count for this device.
  * @device:        Backpointer to the struct ib_device managed by the IB core.
  * @pd:            IB protection domain.
  * @lkey:          L_Key (local key) with write access to all local memory.
@@ -445,6 +450,7 @@ struct srpt_port {
  * @port:          Information about the ports owned by this HCA.
  */
 struct srpt_device {
+	struct kref		refcnt;
 	struct ib_device	*device;
 	struct ib_pd		*pd;
 	u32			lkey;
diff --git a/drivers/input/joystick/iforce/iforce-main.c b/drivers/input/joystick/iforce/iforce-main.c
index b2a68bc9f0b4..b86de1312512 100644
--- a/drivers/input/joystick/iforce/iforce-main.c
+++ b/drivers/input/joystick/iforce/iforce-main.c
@@ -50,6 +50,7 @@ static struct iforce_device iforce_device[] = {
 	{ 0x046d, 0xc291, "Logitech WingMan Formula Force",		btn_wheel, abs_wheel, ff_iforce },
 	{ 0x05ef, 0x020a, "AVB Top Shot Pegasus",			btn_joystick_avb, abs_avb_pegasus, ff_iforce },
 	{ 0x05ef, 0x8884, "AVB Mag Turbo Force",			btn_wheel, abs_wheel, ff_iforce },
+	{ 0x05ef, 0x8886, "Boeder Force Feedback Wheel",		btn_wheel, abs_wheel, ff_iforce },
 	{ 0x05ef, 0x8888, "AVB Top Shot Force Feedback Racing Wheel",	btn_wheel, abs_wheel, ff_iforce }, //?
 	{ 0x061c, 0xc0a4, "ACT LABS Force RS",                          btn_wheel, abs_wheel, ff_iforce }, //?
 	{ 0x061c, 0xc084, "ACT LABS Force RS",				btn_wheel, abs_wheel, ff_iforce },
diff --git a/drivers/input/joystick/iforce/iforce-serio.c b/drivers/input/joystick/iforce/iforce-serio.c
index f95a81b9fac7..2380546d7978 100644
--- a/drivers/input/joystick/iforce/iforce-serio.c
+++ b/drivers/input/joystick/iforce/iforce-serio.c
@@ -39,7 +39,7 @@ static void iforce_serio_xmit(struct iforce *iforce)
 
 again:
 	if (iforce->xmit.head == iforce->xmit.tail) {
-		clear_bit(IFORCE_XMIT_RUNNING, iforce->xmit_flags);
+		iforce_clear_xmit_and_wake(iforce);
 		spin_unlock_irqrestore(&iforce->xmit_lock, flags);
 		return;
 	}
@@ -64,7 +64,7 @@ again:
 	if (test_and_clear_bit(IFORCE_XMIT_AGAIN, iforce->xmit_flags))
 		goto again;
 
-	clear_bit(IFORCE_XMIT_RUNNING, iforce->xmit_flags);
+	iforce_clear_xmit_and_wake(iforce);
 
 	spin_unlock_irqrestore(&iforce->xmit_lock, flags);
 }
@@ -169,7 +169,7 @@ static irqreturn_t iforce_serio_irq(struct serio *serio,
 			iforce_serio->cmd_response_len = iforce_serio->len;
 
 			/* Signal that command is done */
-			wake_up(&iforce->wait);
+			wake_up_all(&iforce->wait);
 		} else if (likely(iforce->type)) {
 			iforce_process_packet(iforce, iforce_serio->id,
 					      iforce_serio->data_in,
diff --git a/drivers/input/joystick/iforce/iforce-usb.c b/drivers/input/joystick/iforce/iforce-usb.c
index ea58805c480f..cba92bd590a8 100644
--- a/drivers/input/joystick/iforce/iforce-usb.c
+++ b/drivers/input/joystick/iforce/iforce-usb.c
@@ -30,7 +30,7 @@ static void __iforce_usb_xmit(struct iforce *iforce)
 	spin_lock_irqsave(&iforce->xmit_lock, flags);
 
 	if (iforce->xmit.head == iforce->xmit.tail) {
-		clear_bit(IFORCE_XMIT_RUNNING, iforce->xmit_flags);
+		iforce_clear_xmit_and_wake(iforce);
 		spin_unlock_irqrestore(&iforce->xmit_lock, flags);
 		return;
 	}
@@ -58,9 +58,9 @@ static void __iforce_usb_xmit(struct iforce *iforce)
 	XMIT_INC(iforce->xmit.tail, n);
 
 	if ( (n=usb_submit_urb(iforce_usb->out, GFP_ATOMIC)) ) {
-		clear_bit(IFORCE_XMIT_RUNNING, iforce->xmit_flags);
 		dev_warn(&iforce_usb->intf->dev,
 			 "usb_submit_urb failed %d\n", n);
+		iforce_clear_xmit_and_wake(iforce);
 	}
 
 	/* The IFORCE_XMIT_RUNNING bit is not cleared here. That's intended.
@@ -175,15 +175,15 @@ static void iforce_usb_out(struct urb *urb)
 	struct iforce *iforce = &iforce_usb->iforce;
 
 	if (urb->status) {
-		clear_bit(IFORCE_XMIT_RUNNING, iforce->xmit_flags);
 		dev_dbg(&iforce_usb->intf->dev, "urb->status %d, exiting\n",
 			urb->status);
+		iforce_clear_xmit_and_wake(iforce);
 		return;
 	}
 
 	__iforce_usb_xmit(iforce);
 
-	wake_up(&iforce->wait);
+	wake_up_all(&iforce->wait);
 }
 
 static int iforce_usb_probe(struct usb_interface *intf,
diff --git a/drivers/input/joystick/iforce/iforce.h b/drivers/input/joystick/iforce/iforce.h
index 6aa761ebbdf7..9ccb9107ccbe 100644
--- a/drivers/input/joystick/iforce/iforce.h
+++ b/drivers/input/joystick/iforce/iforce.h
@@ -119,6 +119,12 @@ static inline int iforce_get_id_packet(struct iforce *iforce, u8 id,
 					 response_data, response_len);
 }
 
+static inline void iforce_clear_xmit_and_wake(struct iforce *iforce)
+{
+	clear_bit(IFORCE_XMIT_RUNNING, iforce->xmit_flags);
+	wake_up_all(&iforce->wait);
+}
+
 /* Public functions */
 /* iforce-main.c */
 int iforce_init_device(struct device *parent, u16 bustype,
diff --git a/drivers/input/misc/cpcap-pwrbutton.c b/drivers/input/misc/cpcap-pwrbutton.c
index 0abef63217e2..372cb44d0635 100644
--- a/drivers/input/misc/cpcap-pwrbutton.c
+++ b/drivers/input/misc/cpcap-pwrbutton.c
@@ -54,9 +54,13 @@ static irqreturn_t powerbutton_irq(int irq, void *_button)
 static int cpcap_power_button_probe(struct platform_device *pdev)
 {
 	struct cpcap_power_button *button;
-	int irq = platform_get_irq(pdev, 0);
+	int irq;
 	int err;
 
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
 	button = devm_kmalloc(&pdev->dev, sizeof(*button), GFP_KERNEL);
 	if (!button)
 		return -ENOMEM;
diff --git a/drivers/input/misc/rk805-pwrkey.c b/drivers/input/misc/rk805-pwrkey.c
index 3fb64dbda1a2..76873aa005b4 100644
--- a/drivers/input/misc/rk805-pwrkey.c
+++ b/drivers/input/misc/rk805-pwrkey.c
@@ -98,6 +98,7 @@ static struct platform_driver rk805_pwrkey_driver = {
 };
 module_platform_driver(rk805_pwrkey_driver);
 
+MODULE_ALIAS("platform:rk805-pwrkey");
 MODULE_AUTHOR("Joseph Chen <chenjh@rock-chips.com>");
 MODULE_DESCRIPTION("RK805 PMIC Power Key driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/input/serio/gscps2.c b/drivers/input/serio/gscps2.c
index a9065c6ab550..da2c67cb8642 100644
--- a/drivers/input/serio/gscps2.c
+++ b/drivers/input/serio/gscps2.c
@@ -350,6 +350,10 @@ static int __init gscps2_probe(struct parisc_device *dev)
 	ps2port->port = serio;
 	ps2port->padev = dev;
 	ps2port->addr = ioremap(hpa, GSC_STATUS + 4);
+	if (!ps2port->addr) {
+		ret = -ENOMEM;
+		goto fail_nomem;
+	}
 	spin_lock_init(&ps2port->lock);
 
 	gscps2_reset(ps2port);
diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h
index 148a7c5fd0e2..4b0201cf71f5 100644
--- a/drivers/input/serio/i8042-x86ia64io.h
+++ b/drivers/input/serio/i8042-x86ia64io.h
@@ -67,25 +67,84 @@ static inline void i8042_write_command(int val)
 
 #include <linux/dmi.h>
 
-static const struct dmi_system_id __initconst i8042_dmi_noloop_table[] = {
+#define SERIO_QUIRK_NOKBD		BIT(0)
+#define SERIO_QUIRK_NOAUX		BIT(1)
+#define SERIO_QUIRK_NOMUX		BIT(2)
+#define SERIO_QUIRK_FORCEMUX		BIT(3)
+#define SERIO_QUIRK_UNLOCK		BIT(4)
+#define SERIO_QUIRK_PROBE_DEFER		BIT(5)
+#define SERIO_QUIRK_RESET_ALWAYS	BIT(6)
+#define SERIO_QUIRK_RESET_NEVER		BIT(7)
+#define SERIO_QUIRK_DIECT		BIT(8)
+#define SERIO_QUIRK_DUMBKBD		BIT(9)
+#define SERIO_QUIRK_NOLOOP		BIT(10)
+#define SERIO_QUIRK_NOTIMEOUT		BIT(11)
+#define SERIO_QUIRK_KBDRESET		BIT(12)
+#define SERIO_QUIRK_DRITEK		BIT(13)
+#define SERIO_QUIRK_NOPNP		BIT(14)
+
+/* Quirk table for different mainboards. Options similar or identical to i8042
+ * module parameters.
+ * ORDERING IS IMPORTANT! The first match will be apllied and the rest ignored.
+ * This allows entries to overwrite vendor wide quirks on a per device basis.
+ * Where this is irrelevant, entries are sorted case sensitive by DMI_SYS_VENDOR
+ * and/or DMI_BOARD_VENDOR to make it easier to avoid dublicate entries.
+ */
+static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 	{
-		/*
-		 * Arima-Rioworks HDAMB -
-		 * AUX LOOP command does not raise AUX IRQ
-		 */
 		.matches = {
-			DMI_MATCH(DMI_BOARD_VENDOR, "RIOWORKS"),
-			DMI_MATCH(DMI_BOARD_NAME, "HDAMB"),
-			DMI_MATCH(DMI_BOARD_VERSION, "Rev E"),
+			DMI_MATCH(DMI_SYS_VENDOR, "ALIENWARE"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Sentia"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
-		/* ASUS G1S */
 		.matches = {
-			DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer Inc."),
-			DMI_MATCH(DMI_BOARD_NAME, "G1S"),
-			DMI_MATCH(DMI_BOARD_VERSION, "1.0"),
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X750LN"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_NOLOOP)
+	},
+	{
+		/* Asus X450LCP */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X450LCP"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_NEVER)
+	},
+	{
+		/* ASUS ZenBook UX425UA */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ZenBook UX425UA"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_PROBE_DEFER | SERIO_QUIRK_RESET_NEVER)
+	},
+	{
+		/* ASUS ZenBook UM325UA */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ZenBook UX325UA_UM325UA"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_PROBE_DEFER | SERIO_QUIRK_RESET_NEVER)
+	},
+	/*
+	 * On some Asus laptops, just running self tests cause problems.
+	 */
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_CHASSIS_TYPE, "10"), /* Notebook */
+		},
+		.driver_data = (void *)(SERIO_QUIRK_RESET_NEVER)
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_CHASSIS_TYPE, "31"), /* Convertible Notebook */
+		},
+		.driver_data = (void *)(SERIO_QUIRK_RESET_NEVER)
 	},
 	{
 		/* ASUS P65UP5 - AUX LOOP command does not raise AUX IRQ */
@@ -94,585 +153,681 @@ static const struct dmi_system_id __initconst i8042_dmi_noloop_table[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "P/I-P65UP5"),
 			DMI_MATCH(DMI_BOARD_VERSION, "REV 2.X"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOLOOP)
 	},
 	{
+		/* ASUS G1S */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "X750LN"),
+			DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer Inc."),
+			DMI_MATCH(DMI_BOARD_NAME, "G1S"),
+			DMI_MATCH(DMI_BOARD_VERSION, "1.0"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOLOOP)
 	},
 	{
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Compaq"),
-			DMI_MATCH(DMI_PRODUCT_NAME , "ProLiant"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "8500"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 1360"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
+		/* Acer Aspire 5710 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Compaq"),
-			DMI_MATCH(DMI_PRODUCT_NAME , "ProLiant"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "DL760"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5710"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
-		/* Dell Embedded Box PC 3000 */
+		/* Acer Aspire 7738 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Embedded Box PC 3000"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 7738"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
-		/* OQO Model 01 */
+		/* Acer Aspire 5536 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "OQO"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "ZEPTO"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "00"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5536"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "0100"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
-		/* ULI EV4873 - AUX LOOP does not work properly */
+		/*
+		 * Acer Aspire 5738z
+		 * Touchpad stops working in mux mode when dis- + re-enabled
+		 * with the touchpad enable/disable toggle hotkey
+		 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ULI"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "EV4873"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "5a"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5738"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
-		/* Microsoft Virtual Machine */
+		/* Acer Aspire One 150 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Microsoft Corporation"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Virtual Machine"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "VS2005R2"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "AOA150"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS)
 	},
 	{
-		/* Medion MAM 2070 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Notebook"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "MAM 2070"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "5a"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A114-31"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS)
 	},
 	{
-		/* Medion Akoya E7225 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Medion"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Akoya E7225"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A314-31"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS)
 	},
 	{
-		/* Blue FB5601 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "blue"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "FB5601"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "M606"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A315-31"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS)
 	},
 	{
-		/* Gigabyte M912 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "M912"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "01"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire ES1-132"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS)
 	},
 	{
-		/* Gigabyte M1022M netbook */
 		.matches = {
-			DMI_MATCH(DMI_BOARD_VENDOR, "Gigabyte Technology Co.,Ltd."),
-			DMI_MATCH(DMI_BOARD_NAME, "M1022E"),
-			DMI_MATCH(DMI_BOARD_VERSION, "1.02"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire ES1-332"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS)
 	},
 	{
-		/* Gigabyte Spring Peak - defines wrong chassis type */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Spring Peak"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire ES1-432"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS)
 	},
 	{
-		/* Gigabyte T1005 - defines wrong chassis type ("Other") */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "T1005"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate Spin B118-RN"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS)
 	},
+	/*
+	 * Some Wistron based laptops need us to explicitly enable the 'Dritek
+	 * keyboard extension' to make their extra keys start generating scancodes.
+	 * Originally, this was just confined to older laptops, but a few Acer laptops
+	 * have turned up in 2007 that also need this again.
+	 */
 	{
-		/* Gigabyte T1005M/P - defines wrong chassis type ("Other") */
+		/* Acer Aspire 5100 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "T1005M/P"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5100"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_DRITEK)
 	},
 	{
+		/* Acer Aspire 5610 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv9700"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "Rev 1"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5610"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_DRITEK)
 	},
 	{
+		/* Acer Aspire 5630 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "PEGATRON CORPORATION"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "C15B"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5630"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_DRITEK)
 	},
 	{
+		/* Acer Aspire 5650 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ByteSpeed LLC"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "ByteSpeed Laptop C15B"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5650"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_DRITEK)
 	},
-	{ }
-};
-
-/*
- * Some Fujitsu notebooks are having trouble with touchpads if
- * active multiplexing mode is activated. Luckily they don't have
- * external PS/2 ports so we can safely disable it.
- * ... apparently some Toshibas don't like MUX mode either and
- * die horrible death on reboot.
- */
-static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = {
 	{
-		/* Fujitsu Lifebook P7010/P7010D */
+		/* Acer Aspire 5680 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "P7010"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5680"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_DRITEK)
 	},
 	{
-		/* Fujitsu Lifebook P7010 */
+		/* Acer Aspire 5720 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "0000000000"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5720"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_DRITEK)
 	},
 	{
-		/* Fujitsu Lifebook P5020D */
+		/* Acer Aspire 9110 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "LifeBook P Series"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 9110"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_DRITEK)
 	},
 	{
-		/* Fujitsu Lifebook S2000 */
+		/* Acer TravelMate 660 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "LifeBook S Series"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 660"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_DRITEK)
 	},
 	{
-		/* Fujitsu Lifebook S6230 */
+		/* Acer TravelMate 2490 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "LifeBook S6230"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 2490"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_DRITEK)
 	},
 	{
-		/* Fujitsu Lifebook T725 laptop */
+		/* Acer TravelMate 4280 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK T725"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 4280"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_DRITEK)
 	},
 	{
-		/* Fujitsu Lifebook U745 */
+		/* Amoi M636/A737 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK U745"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Amoi Electronics CO.,LTD."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "M636/A737 platform"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
-		/* Fujitsu T70H */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "FMVLT70H"),
+			DMI_MATCH(DMI_SYS_VENDOR, "ByteSpeed LLC"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ByteSpeed Laptop C15B"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOLOOP)
 	},
 	{
-		/* Fujitsu-Siemens Lifebook T3010 */
+		/* Compal HEL80I */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK T3010"),
+			DMI_MATCH(DMI_SYS_VENDOR, "COMPAL"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HEL80I"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
-		/* Fujitsu-Siemens Lifebook E4010 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E4010"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Compaq"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "8500"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOLOOP)
 	},
 	{
-		/* Fujitsu-Siemens Amilo Pro 2010 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "AMILO Pro V2010"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Compaq"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "DL760"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOLOOP)
 	},
 	{
-		/* Fujitsu-Siemens Amilo Pro 2030 */
+		/* Advent 4211 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "AMILO PRO V2030"),
+			DMI_MATCH(DMI_SYS_VENDOR, "DIXONSXP"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Advent 4211"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS)
 	},
 	{
-		/*
-		 * No data is coming from the touchscreen unless KBC
-		 * is in legacy mode.
-		 */
-		/* Panasonic CF-29 */
+		/* Dell Embedded Box PC 3000 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Matsushita"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "CF-29"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Embedded Box PC 3000"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOLOOP)
 	},
 	{
-		/*
-		 * HP Pavilion DV4017EA -
-		 * errors on MUX ports are reported without raising AUXDATA
-		 * causing "spurious NAK" messages.
-		 */
+		/* Dell XPS M1530 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Pavilion dv4000 (EA032EA#ABF)"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "XPS M1530"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
-		/*
-		 * HP Pavilion ZT1000 -
-		 * like DV4017EA does not raise AUXERR for errors on MUX ports.
-		 */
+		/* Dell Vostro 1510 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion Notebook PC"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "HP Pavilion Notebook ZT1000"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Vostro1510"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
-		/*
-		 * HP Pavilion DV4270ca -
-		 * like DV4017EA does not raise AUXERR for errors on MUX ports.
-		 */
+		/* Dell Vostro V13 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Pavilion dv4000 (EH476UA#ABL)"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Vostro V13"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_NOTIMEOUT)
 	},
 	{
+		/* Dell Vostro 1320 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Satellite P10"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 1320"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS)
 	},
 	{
+		/* Dell Vostro 1520 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "EQUIUM A110"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 1520"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS)
 	},
 	{
+		/* Dell Vostro 1720 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "SATELLITE C850D"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 1720"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS)
 	},
 	{
+		/* Entroware Proteus */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ALIENWARE"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Sentia"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Entroware"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Proteus"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "EL07R4"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS)
 	},
+	/*
+	 * Some Fujitsu notebooks are having trouble with touchpads if
+	 * active multiplexing mode is activated. Luckily they don't have
+	 * external PS/2 ports so we can safely disable it.
+	 * ... apparently some Toshibas don't like MUX mode either and
+	 * die horrible death on reboot.
+	 */
 	{
-		/* Sharp Actius MM20 */
+		/* Fujitsu Lifebook P7010/P7010D */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "SHARP"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "PC-MM20 Series"),
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "P7010"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
-		/* Sony Vaio FS-115b */
+		/* Fujitsu Lifebook P5020D */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "VGN-FS115B"),
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LifeBook P Series"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
-		/*
-		 * Sony Vaio FZ-240E -
-		 * reset and GET ID commands issued via KBD port are
-		 * sometimes being delivered to AUX3.
-		 */
+		/* Fujitsu Lifebook S2000 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "VGN-FZ240E"),
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LifeBook S Series"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
-		/*
-		 * Most (all?) VAIOs do not have external PS/2 ports nor
-		 * they implement active multiplexing properly, and
-		 * MUX discovery usually messes up keyboard/touchpad.
-		 */
+		/* Fujitsu Lifebook S6230 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"),
-			DMI_MATCH(DMI_BOARD_NAME, "VAIO"),
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LifeBook S6230"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
-		/* Amoi M636/A737 */
+		/* Fujitsu Lifebook T725 laptop */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Amoi Electronics CO.,LTD."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "M636/A737 platform"),
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK T725"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_NOTIMEOUT)
 	},
 	{
-		/* Lenovo 3000 n100 */
+		/* Fujitsu Lifebook U745 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "076804U"),
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK U745"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
-		/* Lenovo XiaoXin Air 12 */
+		/* Fujitsu T70H */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "80UN"),
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "FMVLT70H"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
+		/* Fujitsu A544 laptop */
+		/* https://bugzilla.redhat.com/show_bug.cgi?id=1111138 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 1360"),
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK A544"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOTIMEOUT)
 	},
 	{
-		/* Acer Aspire 5710 */
+		/* Fujitsu AH544 laptop */
+		/* https://bugzilla.kernel.org/show_bug.cgi?id=69731 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5710"),
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK AH544"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOTIMEOUT)
 	},
 	{
-		/* Acer Aspire 7738 */
+		/* Fujitsu U574 laptop */
+		/* https://bugzilla.kernel.org/show_bug.cgi?id=69731 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 7738"),
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK U574"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOTIMEOUT)
 	},
 	{
-		/* Gericom Bellagio */
+		/* Fujitsu UH554 laptop */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Gericom"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "N34AS6"),
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK UH544"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOTIMEOUT)
 	},
 	{
-		/* IBM 2656 */
+		/* Fujitsu Lifebook P7010 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "IBM"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "2656"),
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "0000000000"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
-		/* Dell XPS M1530 */
+		/* Fujitsu-Siemens Lifebook T3010 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "XPS M1530"),
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK T3010"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
-		/* Compal HEL80I */
+		/* Fujitsu-Siemens Lifebook E4010 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "COMPAL"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "HEL80I"),
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E4010"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
-		/* Dell Vostro 1510 */
+		/* Fujitsu-Siemens Amilo Pro 2010 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Vostro1510"),
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "AMILO Pro V2010"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
-		/* Acer Aspire 5536 */
+		/* Fujitsu-Siemens Amilo Pro 2030 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5536"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "0100"),
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "AMILO PRO V2030"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
-		/* Dell Vostro V13 */
+		/* Gigabyte M912 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Vostro V13"),
+			DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "M912"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "01"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOLOOP)
 	},
 	{
-		/* Newer HP Pavilion dv4 models */
+		/* Gigabyte Spring Peak - defines wrong chassis type */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv4 Notebook PC"),
+			DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Spring Peak"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOLOOP)
 	},
 	{
-		/* Asus X450LCP */
+		/* Gigabyte T1005 - defines wrong chassis type ("Other") */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "X450LCP"),
+			DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "T1005"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOLOOP)
 	},
 	{
-		/* Avatar AVIU-145A6 */
+		/* Gigabyte T1005M/P - defines wrong chassis type ("Other") */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Intel"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "IC4I"),
+			DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "T1005M/P"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOLOOP)
 	},
+	/*
+	 * Some laptops need keyboard reset before probing for the trackpad to get
+	 * it detected, initialised & finally work.
+	 */
 	{
-		/* TUXEDO BU1406 */
+		/* Gigabyte P35 v2 - Elantech touchpad */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Notebook"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "N24_25BU"),
+			DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "P35V2"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_KBDRESET)
+	},
+		{
+		/* Aorus branded Gigabyte X3 Plus - Elantech touchpad */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X3"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_KBDRESET)
 	},
 	{
-		/* Lenovo LaVie Z */
+		/* Gigabyte P34 - Elantech touchpad */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo LaVie Z"),
+			DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "P34"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_KBDRESET)
 	},
 	{
-		/*
-		 * Acer Aspire 5738z
-		 * Touchpad stops working in mux mode when dis- + re-enabled
-		 * with the touchpad enable/disable toggle hotkey
-		 */
+		/* Gigabyte P57 - Elantech touchpad */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5738"),
+			DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "P57"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_KBDRESET)
 	},
 	{
-		/* Entroware Proteus */
+		/* Gericom Bellagio */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Entroware"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Proteus"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "EL07R4"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Gericom"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "N34AS6"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
+	},
+	{
+		/* Gigabyte M1022M netbook */
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Gigabyte Technology Co.,Ltd."),
+			DMI_MATCH(DMI_BOARD_NAME, "M1022E"),
+			DMI_MATCH(DMI_BOARD_VERSION, "1.02"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_NOLOOP)
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv9700"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "Rev 1"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_NOLOOP)
 	},
-	{ }
-};
-
-static const struct dmi_system_id i8042_dmi_forcemux_table[] __initconst = {
 	{
 		/*
-		 * Sony Vaio VGN-CS series require MUX or the touch sensor
-		 * buttons will disturb touchpad operation
+		 * HP Pavilion DV4017EA -
+		 * errors on MUX ports are reported without raising AUXDATA
+		 * causing "spurious NAK" messages.
 		 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "VGN-CS"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Pavilion dv4000 (EA032EA#ABF)"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
-	{ }
-};
-
-/*
- * On some Asus laptops, just running self tests cause problems.
- */
-static const struct dmi_system_id i8042_dmi_noselftest_table[] = {
 	{
+		/*
+		 * HP Pavilion ZT1000 -
+		 * like DV4017EA does not raise AUXERR for errors on MUX ports.
+		 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_CHASSIS_TYPE, "10"), /* Notebook */
+			DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion Notebook PC"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "HP Pavilion Notebook ZT1000"),
 		},
-	}, {
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
+	},
+	{
+		/*
+		 * HP Pavilion DV4270ca -
+		 * like DV4017EA does not raise AUXERR for errors on MUX ports.
+		 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_CHASSIS_TYPE, "31"), /* Convertible Notebook */
+			DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Pavilion dv4000 (EH476UA#ABL)"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
-	{ }
-};
-static const struct dmi_system_id __initconst i8042_dmi_reset_table[] = {
 	{
-		/* MSI Wind U-100 */
+		/* Newer HP Pavilion dv4 models */
 		.matches = {
-			DMI_MATCH(DMI_BOARD_NAME, "U-100"),
-			DMI_MATCH(DMI_BOARD_VENDOR, "MICRO-STAR INTERNATIONAL CO., LTD"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv4 Notebook PC"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_NOTIMEOUT)
 	},
 	{
-		/* LG Electronics X110 */
+		/* IBM 2656 */
 		.matches = {
-			DMI_MATCH(DMI_BOARD_NAME, "X110"),
-			DMI_MATCH(DMI_BOARD_VENDOR, "LG Electronics Inc."),
+			DMI_MATCH(DMI_SYS_VENDOR, "IBM"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "2656"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
-		/* Acer Aspire One 150 */
+		/* Avatar AVIU-145A6 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "AOA150"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Intel"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "IC4I"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
+		/* Intel MBO Desktop D845PESV */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A114-31"),
+			DMI_MATCH(DMI_BOARD_VENDOR, "Intel Corporation"),
+			DMI_MATCH(DMI_BOARD_NAME, "D845PESV"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOPNP)
 	},
 	{
+		/*
+		 * Intel NUC D54250WYK - does not have i8042 controller but
+		 * declares PS/2 devices in DSDT.
+		 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A314-31"),
+			DMI_MATCH(DMI_BOARD_VENDOR, "Intel Corporation"),
+			DMI_MATCH(DMI_BOARD_NAME, "D54250WYK"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOPNP)
 	},
 	{
+		/* Lenovo 3000 n100 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A315-31"),
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "076804U"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
+		/* Lenovo XiaoXin Air 12 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire ES1-132"),
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "80UN"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
+		/* Lenovo LaVie Z */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire ES1-332"),
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo LaVie Z"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
+		/* Lenovo Ideapad U455 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire ES1-432"),
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "20046"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS)
 	},
 	{
+		/* Lenovo ThinkPad L460 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate Spin B118-RN"),
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad L460"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS)
 	},
 	{
-		/* Advent 4211 */
+		/* Lenovo ThinkPad Twist S230u */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "DIXONSXP"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Advent 4211"),
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "33474HU"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS)
+	},
+	{
+		/* LG Electronics X110 */
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LG Electronics Inc."),
+			DMI_MATCH(DMI_BOARD_NAME, "X110"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS)
 	},
 	{
 		/* Medion Akoya Mini E1210 */
@@ -680,6 +835,7 @@ static const struct dmi_system_id __initconst i8042_dmi_reset_table[] = {
 			DMI_MATCH(DMI_SYS_VENDOR, "MEDION"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "E1210"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS)
 	},
 	{
 		/* Medion Akoya E1222 */
@@ -687,331 +843,434 @@ static const struct dmi_system_id __initconst i8042_dmi_reset_table[] = {
 			DMI_MATCH(DMI_SYS_VENDOR, "MEDION"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "E122X"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS)
 	},
 	{
-		/* Mivvy M310 */
+		/* MSI Wind U-100 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "VIOOO"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "N10"),
+			DMI_MATCH(DMI_BOARD_VENDOR, "MICRO-STAR INTERNATIONAL CO., LTD"),
+			DMI_MATCH(DMI_BOARD_NAME, "U-100"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS | SERIO_QUIRK_NOPNP)
 	},
 	{
-		/* Dell Vostro 1320 */
+		/*
+		 * No data is coming from the touchscreen unless KBC
+		 * is in legacy mode.
+		 */
+		/* Panasonic CF-29 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 1320"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Matsushita"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "CF-29"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
-		/* Dell Vostro 1520 */
+		/* Medion Akoya E7225 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 1520"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Medion"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Akoya E7225"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOLOOP)
 	},
 	{
-		/* Dell Vostro 1720 */
+		/* Microsoft Virtual Machine */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 1720"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Microsoft Corporation"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Virtual Machine"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "VS2005R2"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOLOOP)
 	},
 	{
-		/* Lenovo Ideapad U455 */
+		/* Medion MAM 2070 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "20046"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Notebook"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "MAM 2070"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "5a"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOLOOP)
 	},
 	{
-		/* Lenovo ThinkPad L460 */
+		/* TUXEDO BU1406 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad L460"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Notebook"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "N24_25BU"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
-		/* Clevo P650RS, 650RP6, Sager NP8152-S, and others */
+		/* OQO Model 01 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Notebook"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "P65xRP"),
+			DMI_MATCH(DMI_SYS_VENDOR, "OQO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ZEPTO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "00"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOLOOP)
 	},
 	{
-		/* Lenovo ThinkPad Twist S230u */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "33474HU"),
+			DMI_MATCH(DMI_SYS_VENDOR, "PEGATRON CORPORATION"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "C15B"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOLOOP)
 	},
 	{
-		/* Entroware Proteus */
+		/* Acer Aspire 5 A515 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Entroware"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Proteus"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "EL07R4"),
+			DMI_MATCH(DMI_BOARD_VENDOR, "PK"),
+			DMI_MATCH(DMI_BOARD_NAME, "Grumpy_PK"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOPNP)
 	},
-	{ }
-};
-
-#ifdef CONFIG_PNP
-static const struct dmi_system_id __initconst i8042_dmi_nopnp_table[] = {
 	{
-		/* Intel MBO Desktop D845PESV */
+		/* ULI EV4873 - AUX LOOP does not work properly */
 		.matches = {
-			DMI_MATCH(DMI_BOARD_NAME, "D845PESV"),
-			DMI_MATCH(DMI_BOARD_VENDOR, "Intel Corporation"),
+			DMI_MATCH(DMI_SYS_VENDOR, "ULI"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "EV4873"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "5a"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOLOOP)
 	},
 	{
 		/*
-		 * Intel NUC D54250WYK - does not have i8042 controller but
-		 * declares PS/2 devices in DSDT.
+		 * Arima-Rioworks HDAMB -
+		 * AUX LOOP command does not raise AUX IRQ
 		 */
 		.matches = {
-			DMI_MATCH(DMI_BOARD_NAME, "D54250WYK"),
-			DMI_MATCH(DMI_BOARD_VENDOR, "Intel Corporation"),
+			DMI_MATCH(DMI_BOARD_VENDOR, "RIOWORKS"),
+			DMI_MATCH(DMI_BOARD_NAME, "HDAMB"),
+			DMI_MATCH(DMI_BOARD_VERSION, "Rev E"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOLOOP)
 	},
 	{
-		/* MSI Wind U-100 */
+		/* Sharp Actius MM20 */
 		.matches = {
-			DMI_MATCH(DMI_BOARD_NAME, "U-100"),
-			DMI_MATCH(DMI_BOARD_VENDOR, "MICRO-STAR INTERNATIONAL CO., LTD"),
+			DMI_MATCH(DMI_SYS_VENDOR, "SHARP"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PC-MM20 Series"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
-		/* Acer Aspire 5 A515 */
+		/*
+		 * Sony Vaio FZ-240E -
+		 * reset and GET ID commands issued via KBD port are
+		 * sometimes being delivered to AUX3.
+		 */
 		.matches = {
-			DMI_MATCH(DMI_BOARD_NAME, "Grumpy_PK"),
-			DMI_MATCH(DMI_BOARD_VENDOR, "PK"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "VGN-FZ240E"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
-	{ }
-};
-
-static const struct dmi_system_id __initconst i8042_dmi_laptop_table[] = {
 	{
+		/*
+		 * Most (all?) VAIOs do not have external PS/2 ports nor
+		 * they implement active multiplexing properly, and
+		 * MUX discovery usually messes up keyboard/touchpad.
+		 */
 		.matches = {
-			DMI_MATCH(DMI_CHASSIS_TYPE, "8"), /* Portable */
+			DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"),
+			DMI_MATCH(DMI_BOARD_NAME, "VAIO"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
+		/* Sony Vaio FS-115b */
 		.matches = {
-			DMI_MATCH(DMI_CHASSIS_TYPE, "9"), /* Laptop */
+			DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "VGN-FS115B"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
+		/*
+		 * Sony Vaio VGN-CS series require MUX or the touch sensor
+		 * buttons will disturb touchpad operation
+		 */
 		.matches = {
-			DMI_MATCH(DMI_CHASSIS_TYPE, "10"), /* Notebook */
+			DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "VGN-CS"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_FORCEMUX)
 	},
 	{
 		.matches = {
-			DMI_MATCH(DMI_CHASSIS_TYPE, "14"), /* Sub-Notebook */
+			DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Satellite P10"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
-	{ }
-};
-#endif
-
-static const struct dmi_system_id __initconst i8042_dmi_notimeout_table[] = {
 	{
-		/* Dell Vostro V13 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Vostro V13"),
+			DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "EQUIUM A110"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
 	{
-		/* Newer HP Pavilion dv4 models */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv4 Notebook PC"),
+			DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "SATELLITE C850D"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
+	/*
+	 * A lot of modern Clevo barebones have touchpad and/or keyboard issues
+	 * after suspend fixable with nomux + reset + noloop + nopnp. Luckily,
+	 * none of them have an external PS/2 port so this can safely be set for
+	 * all of them. These two are based on a Clevo design, but have the
+	 * board_name changed.
+	 */
 	{
-		/* Fujitsu A544 laptop */
-		/* https://bugzilla.redhat.com/show_bug.cgi?id=1111138 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK A544"),
+			DMI_MATCH(DMI_BOARD_VENDOR, "TUXEDO"),
+			DMI_MATCH(DMI_BOARD_NAME, "AURA1501"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
+					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
 	},
 	{
-		/* Fujitsu AH544 laptop */
-		/* https://bugzilla.kernel.org/show_bug.cgi?id=69731 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK AH544"),
+			DMI_MATCH(DMI_BOARD_VENDOR, "TUXEDO"),
+			DMI_MATCH(DMI_BOARD_NAME, "EDUBOOK1502"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
+					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
 	},
 	{
-		/* Fujitsu Lifebook T725 laptop */
+		/* Mivvy M310 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK T725"),
+			DMI_MATCH(DMI_SYS_VENDOR, "VIOOO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "N10"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS)
 	},
+	/*
+	 * Some laptops need keyboard reset before probing for the trackpad to get
+	 * it detected, initialised & finally work.
+	 */
 	{
-		/* Fujitsu U574 laptop */
-		/* https://bugzilla.kernel.org/show_bug.cgi?id=69731 */
+		/* Schenker XMG C504 - Elantech touchpad */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK U574"),
+			DMI_MATCH(DMI_SYS_VENDOR, "XMG"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "C504"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_KBDRESET)
 	},
 	{
-		/* Fujitsu UH554 laptop */
+		/* Blue FB5601 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK UH544"),
+			DMI_MATCH(DMI_SYS_VENDOR, "blue"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "FB5601"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "M606"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOLOOP)
 	},
-	{ }
-};
-
-/*
- * Some Wistron based laptops need us to explicitly enable the 'Dritek
- * keyboard extension' to make their extra keys start generating scancodes.
- * Originally, this was just confined to older laptops, but a few Acer laptops
- * have turned up in 2007 that also need this again.
- */
-static const struct dmi_system_id __initconst i8042_dmi_dritek_table[] = {
+	/*
+	 * A lot of modern Clevo barebones have touchpad and/or keyboard issues
+	 * after suspend fixable with nomux + reset + noloop + nopnp. Luckily,
+	 * none of them have an external PS/2 port so this can safely be set for
+	 * all of them.
+	 * Clevo barebones come with board_vendor and/or system_vendor set to
+	 * either the very generic string "Notebook" and/or a different value
+	 * for each individual reseller. The only somewhat universal way to
+	 * identify them is by board_name.
+	 */
 	{
-		/* Acer Aspire 5100 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5100"),
+			DMI_MATCH(DMI_BOARD_NAME, "LAPQC71A"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
+					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
 	},
 	{
-		/* Acer Aspire 5610 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5610"),
+			DMI_MATCH(DMI_BOARD_NAME, "LAPQC71B"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
+					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
 	},
 	{
-		/* Acer Aspire 5630 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5630"),
+			DMI_MATCH(DMI_BOARD_NAME, "N140CU"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
+					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
 	},
 	{
-		/* Acer Aspire 5650 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5650"),
+			DMI_MATCH(DMI_BOARD_NAME, "N141CU"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
+					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
 	},
 	{
-		/* Acer Aspire 5680 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5680"),
+			DMI_MATCH(DMI_BOARD_NAME, "NH5xAx"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
+					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
 	},
 	{
-		/* Acer Aspire 5720 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5720"),
+			DMI_MATCH(DMI_BOARD_NAME, "NL5xRU"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
+					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
 	},
+	/*
+	 * At least one modern Clevo barebone has the touchpad connected both
+	 * via PS/2 and i2c interface. This causes a race condition between the
+	 * psmouse and i2c-hid driver. Since the full capability of the touchpad
+	 * is available via the i2c interface and the device has no external
+	 * PS/2 port, it is safe to just ignore all ps2 mouses here to avoid
+	 * this issue. The known affected device is the
+	 * TUXEDO InfinityBook S17 Gen6 / Clevo NS70MU which comes with one of
+	 * the two different dmi strings below. NS50MU is not a typo!
+	 */
 	{
-		/* Acer Aspire 9110 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 9110"),
+			DMI_MATCH(DMI_BOARD_NAME, "NS50MU"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOAUX | SERIO_QUIRK_NOMUX |
+					SERIO_QUIRK_RESET_ALWAYS | SERIO_QUIRK_NOLOOP |
+					SERIO_QUIRK_NOPNP)
 	},
 	{
-		/* Acer TravelMate 660 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 660"),
+			DMI_MATCH(DMI_BOARD_NAME, "NS50_70MU"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOAUX | SERIO_QUIRK_NOMUX |
+					SERIO_QUIRK_RESET_ALWAYS | SERIO_QUIRK_NOLOOP |
+					SERIO_QUIRK_NOPNP)
 	},
 	{
-		/* Acer TravelMate 2490 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 2490"),
+			DMI_MATCH(DMI_BOARD_NAME, "NJ50_70CU"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
+					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
 	},
 	{
-		/* Acer TravelMate 4280 */
+		/*
+		 * This is only a partial board_name and might be followed by
+		 * another letter or number. DMI_MATCH however does do partial
+		 * matching.
+		 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 4280"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "P65xH"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
+					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
 	},
-	{ }
-};
-
-/*
- * Some laptops need keyboard reset before probing for the trackpad to get
- * it detected, initialised & finally work.
- */
-static const struct dmi_system_id __initconst i8042_dmi_kbdreset_table[] = {
 	{
-		/* Gigabyte P35 v2 - Elantech touchpad */
+		/* Clevo P650RS, 650RP6, Sager NP8152-S, and others */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "P35V2"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "P65xRP"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
+					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
 	},
-		{
-		/* Aorus branded Gigabyte X3 Plus - Elantech touchpad */
+	{
+		/*
+		 * This is only a partial board_name and might be followed by
+		 * another letter or number. DMI_MATCH however does do partial
+		 * matching.
+		 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "X3"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "P65_P67H"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
+					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
 	},
 	{
-		/* Gigabyte P34 - Elantech touchpad */
+		/*
+		 * This is only a partial board_name and might be followed by
+		 * another letter or number. DMI_MATCH however does do partial
+		 * matching.
+		 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "P34"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "P65_67RP"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
+					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
 	},
 	{
-		/* Gigabyte P57 - Elantech touchpad */
+		/*
+		 * This is only a partial board_name and might be followed by
+		 * another letter or number. DMI_MATCH however does do partial
+		 * matching.
+		 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "P57"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "P65_67RS"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
+					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
 	},
 	{
-		/* Schenker XMG C504 - Elantech touchpad */
+		/*
+		 * This is only a partial board_name and might be followed by
+		 * another letter or number. DMI_MATCH however does do partial
+		 * matching.
+		 */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "XMG"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "C504"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "P67xRP"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
+					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "PB50_70DFx,DDx"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
+					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "X170SM"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
+					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "X170KM-G"),
 		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
+					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
 	},
 	{ }
 };
 
-static const struct dmi_system_id i8042_dmi_probe_defer_table[] __initconst = {
+#ifdef CONFIG_PNP
+static const struct dmi_system_id i8042_dmi_laptop_table[] __initconst = {
 	{
-		/* ASUS ZenBook UX425UA */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "ZenBook UX425UA"),
+			DMI_MATCH(DMI_CHASSIS_TYPE, "8"), /* Portable */
 		},
 	},
 	{
-		/* ASUS ZenBook UM325UA */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "ZenBook UX325UA_UM325UA"),
+			DMI_MATCH(DMI_CHASSIS_TYPE, "9"), /* Laptop */
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_CHASSIS_TYPE, "10"), /* Notebook */
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_CHASSIS_TYPE, "14"), /* Sub-Notebook */
 		},
 	},
 	{ }
 };
+#endif
 
 #endif /* CONFIG_X86 */
 
@@ -1167,11 +1426,6 @@ static int __init i8042_pnp_init(void)
 	bool pnp_data_busted = false;
 	int err;
 
-#ifdef CONFIG_X86
-	if (dmi_check_system(i8042_dmi_nopnp_table))
-		i8042_nopnp = true;
-#endif
-
 	if (i8042_nopnp) {
 		pr_info("PNP detection disabled\n");
 		return 0;
@@ -1275,6 +1529,59 @@ static inline int i8042_pnp_init(void) { return 0; }
 static inline void i8042_pnp_exit(void) { }
 #endif /* CONFIG_PNP */
 
+
+#ifdef CONFIG_X86
+static void __init i8042_check_quirks(void)
+{
+	const struct dmi_system_id *device_quirk_info;
+	uintptr_t quirks;
+
+	device_quirk_info = dmi_first_match(i8042_dmi_quirk_table);
+	if (!device_quirk_info)
+		return;
+
+	quirks = (uintptr_t)device_quirk_info->driver_data;
+
+	if (quirks & SERIO_QUIRK_NOKBD)
+		i8042_nokbd = true;
+	if (quirks & SERIO_QUIRK_NOAUX)
+		i8042_noaux = true;
+	if (quirks & SERIO_QUIRK_NOMUX)
+		i8042_nomux = true;
+	if (quirks & SERIO_QUIRK_FORCEMUX)
+		i8042_nomux = false;
+	if (quirks & SERIO_QUIRK_UNLOCK)
+		i8042_unlock = true;
+	if (quirks & SERIO_QUIRK_PROBE_DEFER)
+		i8042_probe_defer = true;
+	/* Honor module parameter when value is not default */
+	if (i8042_reset == I8042_RESET_DEFAULT) {
+		if (quirks & SERIO_QUIRK_RESET_ALWAYS)
+			i8042_reset = I8042_RESET_ALWAYS;
+		if (quirks & SERIO_QUIRK_RESET_NEVER)
+			i8042_reset = I8042_RESET_NEVER;
+	}
+	if (quirks & SERIO_QUIRK_DIECT)
+		i8042_direct = true;
+	if (quirks & SERIO_QUIRK_DUMBKBD)
+		i8042_dumbkbd = true;
+	if (quirks & SERIO_QUIRK_NOLOOP)
+		i8042_noloop = true;
+	if (quirks & SERIO_QUIRK_NOTIMEOUT)
+		i8042_notimeout = true;
+	if (quirks & SERIO_QUIRK_KBDRESET)
+		i8042_kbdreset = true;
+	if (quirks & SERIO_QUIRK_DRITEK)
+		i8042_dritek = true;
+#ifdef CONFIG_PNP
+	if (quirks & SERIO_QUIRK_NOPNP)
+		i8042_nopnp = true;
+#endif
+}
+#else
+static inline void i8042_check_quirks(void) {}
+#endif
+
 static int __init i8042_platform_init(void)
 {
 	int retval;
@@ -1297,45 +1604,17 @@ static int __init i8042_platform_init(void)
 	i8042_kbd_irq = I8042_MAP_IRQ(1);
 	i8042_aux_irq = I8042_MAP_IRQ(12);
 
-	retval = i8042_pnp_init();
-	if (retval)
-		return retval;
-
 #if defined(__ia64__)
-        i8042_reset = I8042_RESET_ALWAYS;
+	i8042_reset = I8042_RESET_ALWAYS;
 #endif
 
-#ifdef CONFIG_X86
-	/* Honor module parameter when value is not default */
-	if (i8042_reset == I8042_RESET_DEFAULT) {
-		if (dmi_check_system(i8042_dmi_reset_table))
-			i8042_reset = I8042_RESET_ALWAYS;
-
-		if (dmi_check_system(i8042_dmi_noselftest_table))
-			i8042_reset = I8042_RESET_NEVER;
-	}
-
-	if (dmi_check_system(i8042_dmi_noloop_table))
-		i8042_noloop = true;
-
-	if (dmi_check_system(i8042_dmi_nomux_table))
-		i8042_nomux = true;
-
-	if (dmi_check_system(i8042_dmi_forcemux_table))
-		i8042_nomux = false;
-
-	if (dmi_check_system(i8042_dmi_notimeout_table))
-		i8042_notimeout = true;
-
-	if (dmi_check_system(i8042_dmi_dritek_table))
-		i8042_dritek = true;
+	i8042_check_quirks();
 
-	if (dmi_check_system(i8042_dmi_kbdreset_table))
-		i8042_kbdreset = true;
-
-	if (dmi_check_system(i8042_dmi_probe_defer_table))
-		i8042_probe_defer = true;
+	retval = i8042_pnp_init();
+	if (retval)
+		return retval;
 
+#ifdef CONFIG_X86
 	/*
 	 * A20 was already enabled during early kernel init. But some buggy
 	 * BIOSes (in MSI Laptops) require A20 to be enabled using 8042 to
diff --git a/drivers/input/touchscreen/exc3000.c b/drivers/input/touchscreen/exc3000.c
index cbe0dd412912..4b7eee01c6aa 100644
--- a/drivers/input/touchscreen/exc3000.c
+++ b/drivers/input/touchscreen/exc3000.c
@@ -220,6 +220,7 @@ static int exc3000_vendor_data_request(struct exc3000_data *data, u8 *request,
 {
 	u8 buf[EXC3000_LEN_VENDOR_REQUEST] = { 0x67, 0x00, 0x42, 0x00, 0x03 };
 	int ret;
+	unsigned long time_left;
 
 	mutex_lock(&data->query_lock);
 
@@ -233,9 +234,9 @@ static int exc3000_vendor_data_request(struct exc3000_data *data, u8 *request,
 		goto out_unlock;
 
 	if (response) {
-		ret = wait_for_completion_timeout(&data->wait_event,
-						  timeout * HZ);
-		if (ret <= 0) {
+		time_left = wait_for_completion_timeout(&data->wait_event,
+							timeout * HZ);
+		if (time_left == 0) {
 			ret = -ETIMEDOUT;
 			goto out_unlock;
 		}
diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c
index b77969a16986..1c7270b59eff 100644
--- a/drivers/input/touchscreen/goodix.c
+++ b/drivers/input/touchscreen/goodix.c
@@ -14,20 +14,15 @@
 #include <linux/kernel.h>
 #include <linux/dmi.h>
 #include <linux/firmware.h>
-#include <linux/gpio/consumer.h>
-#include <linux/i2c.h>
-#include <linux/input.h>
-#include <linux/input/mt.h>
-#include <linux/input/touchscreen.h>
 #include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/irq.h>
 #include <linux/interrupt.h>
-#include <linux/regulator/consumer.h>
 #include <linux/slab.h>
 #include <linux/acpi.h>
 #include <linux/of.h>
 #include <asm/unaligned.h>
+#include "goodix.h"
 
 #define GOODIX_GPIO_INT_NAME		"irq"
 #define GOODIX_GPIO_RST_NAME		"reset"
@@ -38,22 +33,11 @@
 #define GOODIX_CONTACT_SIZE		8
 #define GOODIX_MAX_CONTACT_SIZE		9
 #define GOODIX_MAX_CONTACTS		10
-#define GOODIX_MAX_KEYS			7
 
 #define GOODIX_CONFIG_MIN_LENGTH	186
 #define GOODIX_CONFIG_911_LENGTH	186
 #define GOODIX_CONFIG_967_LENGTH	228
 #define GOODIX_CONFIG_GT9X_LENGTH	240
-#define GOODIX_CONFIG_MAX_LENGTH	240
-
-/* Register defines */
-#define GOODIX_REG_COMMAND		0x8040
-#define GOODIX_CMD_SCREEN_OFF		0x05
-
-#define GOODIX_READ_COOR_ADDR		0x814E
-#define GOODIX_GT1X_REG_CONFIG_DATA	0x8050
-#define GOODIX_GT9X_REG_CONFIG_DATA	0x8047
-#define GOODIX_REG_ID			0x8140
 
 #define GOODIX_BUFFER_STATUS_READY	BIT(7)
 #define GOODIX_HAVE_KEY			BIT(4)
@@ -68,55 +52,11 @@
 #define ACPI_GPIO_SUPPORT
 #endif
 
-struct goodix_ts_data;
-
-enum goodix_irq_pin_access_method {
-	IRQ_PIN_ACCESS_NONE,
-	IRQ_PIN_ACCESS_GPIO,
-	IRQ_PIN_ACCESS_ACPI_GPIO,
-	IRQ_PIN_ACCESS_ACPI_METHOD,
-};
-
-struct goodix_chip_data {
-	u16 config_addr;
-	int config_len;
-	int (*check_config)(struct goodix_ts_data *ts, const u8 *cfg, int len);
-	void (*calc_config_checksum)(struct goodix_ts_data *ts);
-};
-
 struct goodix_chip_id {
 	const char *id;
 	const struct goodix_chip_data *data;
 };
 
-#define GOODIX_ID_MAX_LEN	4
-
-struct goodix_ts_data {
-	struct i2c_client *client;
-	struct input_dev *input_dev;
-	const struct goodix_chip_data *chip;
-	struct touchscreen_properties prop;
-	unsigned int max_touch_num;
-	unsigned int int_trigger_type;
-	struct regulator *avdd28;
-	struct regulator *vddio;
-	struct gpio_desc *gpiod_int;
-	struct gpio_desc *gpiod_rst;
-	int gpio_count;
-	int gpio_int_idx;
-	char id[GOODIX_ID_MAX_LEN + 1];
-	u16 version;
-	const char *cfg_name;
-	bool reset_controller_at_probe;
-	bool load_cfg_from_disk;
-	struct completion firmware_loading_complete;
-	unsigned long irq_flags;
-	enum goodix_irq_pin_access_method irq_pin_access_method;
-	unsigned int contact_size;
-	u8 config[GOODIX_CONFIG_MAX_LENGTH];
-	unsigned short keymap[GOODIX_MAX_KEYS];
-};
-
 static int goodix_check_cfg_8(struct goodix_ts_data *ts,
 			      const u8 *cfg, int len);
 static int goodix_check_cfg_16(struct goodix_ts_data *ts,
@@ -154,6 +94,7 @@ static const struct goodix_chip_data gt9x_chip_data = {
 
 static const struct goodix_chip_id goodix_chip_ids[] = {
 	{ .id = "1151", .data = &gt1x_chip_data },
+	{ .id = "1158", .data = &gt1x_chip_data },
 	{ .id = "5663", .data = &gt1x_chip_data },
 	{ .id = "5688", .data = &gt1x_chip_data },
 	{ .id = "917S", .data = &gt1x_chip_data },
@@ -216,8 +157,7 @@ static const struct dmi_system_id inverted_x_screen[] = {
  * @buf: raw write data buffer.
  * @len: length of the buffer to write
  */
-static int goodix_i2c_read(struct i2c_client *client,
-			   u16 reg, u8 *buf, int len)
+int goodix_i2c_read(struct i2c_client *client, u16 reg, u8 *buf, int len)
 {
 	struct i2c_msg msgs[2];
 	__be16 wbuf = cpu_to_be16(reg);
@@ -245,8 +185,7 @@ static int goodix_i2c_read(struct i2c_client *client,
  * @buf: raw data buffer to write.
  * @len: length of the buffer to write
  */
-static int goodix_i2c_write(struct i2c_client *client, u16 reg, const u8 *buf,
-			    unsigned len)
+int goodix_i2c_write(struct i2c_client *client, u16 reg, const u8 *buf, int len)
 {
 	u8 *addr_buf;
 	struct i2c_msg msg;
@@ -270,7 +209,7 @@ static int goodix_i2c_write(struct i2c_client *client, u16 reg, const u8 *buf,
 	return ret < 0 ? ret : (ret != 1 ? -EIO : 0);
 }
 
-static int goodix_i2c_write_u8(struct i2c_client *client, u16 reg, u8 value)
+int goodix_i2c_write_u8(struct i2c_client *client, u16 reg, u8 value)
 {
 	return goodix_i2c_write(client, reg, &value, sizeof(value));
 }
@@ -563,7 +502,7 @@ static int goodix_check_cfg(struct goodix_ts_data *ts, const u8 *cfg, int len)
  * @cfg: config firmware to write to device
  * @len: config data length
  */
-static int goodix_send_cfg(struct goodix_ts_data *ts, const u8 *cfg, int len)
+int goodix_send_cfg(struct goodix_ts_data *ts, const u8 *cfg, int len)
 {
 	int error;
 
@@ -661,62 +600,88 @@ static int goodix_irq_direction_input(struct goodix_ts_data *ts)
 	return -EINVAL; /* Never reached */
 }
 
-static int goodix_int_sync(struct goodix_ts_data *ts)
+int goodix_int_sync(struct goodix_ts_data *ts)
 {
 	int error;
 
 	error = goodix_irq_direction_output(ts, 0);
 	if (error)
-		return error;
+		goto error;
 
 	msleep(50);				/* T5: 50ms */
 
 	error = goodix_irq_direction_input(ts);
 	if (error)
-		return error;
+		goto error;
 
 	return 0;
+
+error:
+	dev_err(&ts->client->dev, "Controller irq sync failed.\n");
+	return error;
 }
 
 /**
- * goodix_reset - Reset device during power on
+ * goodix_reset_no_int_sync - Reset device, leaving interrupt line in output mode
  *
  * @ts: goodix_ts_data pointer
  */
-static int goodix_reset(struct goodix_ts_data *ts)
+int goodix_reset_no_int_sync(struct goodix_ts_data *ts)
 {
 	int error;
 
 	/* begin select I2C slave addr */
 	error = gpiod_direction_output(ts->gpiod_rst, 0);
 	if (error)
-		return error;
+		goto error;
 
 	msleep(20);				/* T2: > 10ms */
 
 	/* HIGH: 0x28/0x29, LOW: 0xBA/0xBB */
 	error = goodix_irq_direction_output(ts, ts->client->addr == 0x14);
 	if (error)
-		return error;
+		goto error;
 
 	usleep_range(100, 2000);		/* T3: > 100us */
 
 	error = gpiod_direction_output(ts->gpiod_rst, 1);
 	if (error)
-		return error;
+		goto error;
 
 	usleep_range(6000, 10000);		/* T4: > 5ms */
 
-	/* end select I2C slave addr */
-	error = gpiod_direction_input(ts->gpiod_rst);
-	if (error)
-		return error;
+	/*
+	 * Put the reset pin back in to input / high-impedance mode to save
+	 * power. Only do this in the non ACPI case since some ACPI boards
+	 * don't have a pull-up, so there the reset pin must stay active-high.
+	 */
+	if (ts->irq_pin_access_method == IRQ_PIN_ACCESS_GPIO) {
+		error = gpiod_direction_input(ts->gpiod_rst);
+		if (error)
+			goto error;
+	}
 
-	error = goodix_int_sync(ts);
+	return 0;
+
+error:
+	dev_err(&ts->client->dev, "Controller reset failed.\n");
+	return error;
+}
+
+/**
+ * goodix_reset - Reset device during power on
+ *
+ * @ts: goodix_ts_data pointer
+ */
+static int goodix_reset(struct goodix_ts_data *ts)
+{
+	int error;
+
+	error = goodix_reset_no_int_sync(ts);
 	if (error)
 		return error;
 
-	return 0;
+	return goodix_int_sync(ts);
 }
 
 #ifdef ACPI_GPIO_SUPPORT
@@ -828,6 +793,14 @@ static int goodix_add_acpi_gpio_mappings(struct goodix_ts_data *ts)
 		return -EINVAL;
 	}
 
+	/*
+	 * Normally we put the reset pin in input / high-impedance mode to save
+	 * power. But some x86/ACPI boards don't have a pull-up, so for the ACPI
+	 * case, leave the pin as is. This results in the pin not being touched
+	 * at all on x86/ACPI boards, except when needed for error-recover.
+	 */
+	ts->gpiod_rst_flags = GPIOD_ASIS;
+
 	return devm_acpi_dev_add_driver_gpios(dev, gpio_mapping);
 }
 #else
@@ -853,6 +826,12 @@ static int goodix_get_gpio_config(struct goodix_ts_data *ts)
 		return -EINVAL;
 	dev = &ts->client->dev;
 
+	/*
+	 * By default we request the reset pin as input, leaving it in
+	 * high-impedance when not resetting the controller to save power.
+	 */
+	ts->gpiod_rst_flags = GPIOD_IN;
+
 	ts->avdd28 = devm_regulator_get(dev, "AVDD28");
 	if (IS_ERR(ts->avdd28)) {
 		error = PTR_ERR(ts->avdd28);
@@ -890,7 +869,7 @@ retry_get_irq_gpio:
 	ts->gpiod_int = gpiod;
 
 	/* Get the reset line GPIO pin number */
-	gpiod = devm_gpiod_get_optional(dev, GOODIX_GPIO_RST_NAME, GPIOD_IN);
+	gpiod = devm_gpiod_get_optional(dev, GOODIX_GPIO_RST_NAME, ts->gpiod_rst_flags);
 	if (IS_ERR(gpiod)) {
 		error = PTR_ERR(gpiod);
 		if (error != -EPROBE_DEFER)
@@ -1218,10 +1197,8 @@ reset:
 	if (ts->reset_controller_at_probe) {
 		/* reset the controller */
 		error = goodix_reset(ts);
-		if (error) {
-			dev_err(&client->dev, "Controller reset failed.\n");
+		if (error)
 			return error;
-		}
 	}
 
 	error = goodix_i2c_test(client);
@@ -1363,10 +1340,8 @@ static int __maybe_unused goodix_resume(struct device *dev)
 
 	if (error != 0 || config_ver != ts->config[0]) {
 		error = goodix_reset(ts);
-		if (error) {
-			dev_err(dev, "Controller reset failed.\n");
+		if (error)
 			return error;
-		}
 
 		if (ts->load_cfg_from_disk) {
 			error = goodix_send_cfg(ts, ts->config, ts->chip->config_len);
@@ -1402,6 +1377,7 @@ MODULE_DEVICE_TABLE(acpi, goodix_acpi_match);
 #ifdef CONFIG_OF
 static const struct of_device_id goodix_of_match[] = {
 	{ .compatible = "goodix,gt1151" },
+	{ .compatible = "goodix,gt1158" },
 	{ .compatible = "goodix,gt5663" },
 	{ .compatible = "goodix,gt5688" },
 	{ .compatible = "goodix,gt911" },
diff --git a/drivers/input/touchscreen/goodix.h b/drivers/input/touchscreen/goodix.h
new file mode 100644
index 000000000000..1a1571ad2cd2
--- /dev/null
+++ b/drivers/input/touchscreen/goodix.h
@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __GOODIX_H__
+#define __GOODIX_H__
+
+#include <linux/gpio/consumer.h>
+#include <linux/i2c.h>
+#include <linux/input.h>
+#include <linux/input/mt.h>
+#include <linux/input/touchscreen.h>
+#include <linux/regulator/consumer.h>
+
+/* Register defines */
+#define GOODIX_REG_COMMAND			0x8040
+#define GOODIX_CMD_SCREEN_OFF			0x05
+
+#define GOODIX_GT1X_REG_CONFIG_DATA		0x8050
+#define GOODIX_GT9X_REG_CONFIG_DATA		0x8047
+#define GOODIX_REG_ID				0x8140
+#define GOODIX_READ_COOR_ADDR			0x814E
+
+#define GOODIX_ID_MAX_LEN			4
+#define GOODIX_CONFIG_MAX_LENGTH		240
+#define GOODIX_MAX_KEYS				7
+
+enum goodix_irq_pin_access_method {
+	IRQ_PIN_ACCESS_NONE,
+	IRQ_PIN_ACCESS_GPIO,
+	IRQ_PIN_ACCESS_ACPI_GPIO,
+	IRQ_PIN_ACCESS_ACPI_METHOD,
+};
+
+struct goodix_ts_data;
+
+struct goodix_chip_data {
+	u16 config_addr;
+	int config_len;
+	int (*check_config)(struct goodix_ts_data *ts, const u8 *cfg, int len);
+	void (*calc_config_checksum)(struct goodix_ts_data *ts);
+};
+
+struct goodix_ts_data {
+	struct i2c_client *client;
+	struct input_dev *input_dev;
+	const struct goodix_chip_data *chip;
+	struct touchscreen_properties prop;
+	unsigned int max_touch_num;
+	unsigned int int_trigger_type;
+	struct regulator *avdd28;
+	struct regulator *vddio;
+	struct gpio_desc *gpiod_int;
+	struct gpio_desc *gpiod_rst;
+	int gpio_count;
+	int gpio_int_idx;
+	enum gpiod_flags gpiod_rst_flags;
+	char id[GOODIX_ID_MAX_LEN + 1];
+	u16 version;
+	const char *cfg_name;
+	bool reset_controller_at_probe;
+	bool load_cfg_from_disk;
+	struct completion firmware_loading_complete;
+	unsigned long irq_flags;
+	enum goodix_irq_pin_access_method irq_pin_access_method;
+	unsigned int contact_size;
+	u8 config[GOODIX_CONFIG_MAX_LENGTH];
+	unsigned short keymap[GOODIX_MAX_KEYS];
+};
+
+int goodix_i2c_read(struct i2c_client *client, u16 reg, u8 *buf, int len);
+int goodix_i2c_write(struct i2c_client *client, u16 reg, const u8 *buf, int len);
+int goodix_i2c_write_u8(struct i2c_client *client, u16 reg, u8 value);
+int goodix_send_cfg(struct goodix_ts_data *ts, const u8 *cfg, int len);
+int goodix_int_sync(struct goodix_ts_data *ts);
+int goodix_reset_no_int_sync(struct goodix_ts_data *ts);
+
+#endif
diff --git a/drivers/interconnect/imx/imx.c b/drivers/interconnect/imx/imx.c
index c770951a909c..aabd9edf2ef7 100644
--- a/drivers/interconnect/imx/imx.c
+++ b/drivers/interconnect/imx/imx.c
@@ -226,16 +226,16 @@ int imx_icc_register(struct platform_device *pdev,
 	struct device *dev = &pdev->dev;
 	struct icc_onecell_data *data;
 	struct icc_provider *provider;
-	int max_node_id;
+	int num_nodes;
 	int ret;
 
 	/* icc_onecell_data is indexed by node_id, unlike nodes param */
-	max_node_id = get_max_node_id(nodes, nodes_count);
-	data = devm_kzalloc(dev, struct_size(data, nodes, max_node_id),
+	num_nodes = get_max_node_id(nodes, nodes_count) + 1;
+	data = devm_kzalloc(dev, struct_size(data, nodes, num_nodes),
 			    GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
-	data->num_nodes = max_node_id;
+	data->num_nodes = num_nodes;
 
 	provider = devm_kzalloc(dev, sizeof(*provider), GFP_KERNEL);
 	if (!provider)
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index e23e70af718f..7154fb551ddc 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -852,7 +852,8 @@ static void build_completion_wait(struct iommu_cmd *cmd,
 	memset(cmd, 0, sizeof(*cmd));
 	cmd->data[0] = lower_32_bits(paddr) | CMD_COMPL_WAIT_STORE_MASK;
 	cmd->data[1] = upper_32_bits(paddr);
-	cmd->data[2] = data;
+	cmd->data[2] = lower_32_bits(data);
+	cmd->data[3] = upper_32_bits(data);
 	CMD_SET_TYPE(cmd, CMD_COMPL_WAIT);
 }
 
diff --git a/drivers/iommu/arm/arm-smmu/qcom_iommu.c b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
index b91874cb6cf3..a47cb654b704 100644
--- a/drivers/iommu/arm/arm-smmu/qcom_iommu.c
+++ b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
@@ -748,9 +748,12 @@ static bool qcom_iommu_has_secure_context(struct qcom_iommu_dev *qcom_iommu)
 {
 	struct device_node *child;
 
-	for_each_child_of_node(qcom_iommu->dev->of_node, child)
-		if (of_device_is_compatible(child, "qcom,msm-iommu-v1-sec"))
+	for_each_child_of_node(qcom_iommu->dev->of_node, child) {
+		if (of_device_is_compatible(child, "qcom,msm-iommu-v1-sec")) {
+			of_node_put(child);
 			return true;
+		}
+	}
 
 	return false;
 }
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index 939ffa768986..f96acc3525e8 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -630,7 +630,7 @@ static int exynos_sysmmu_probe(struct platform_device *pdev)
 
 	ret = iommu_device_register(&data->iommu, &exynos_iommu_ops, dev);
 	if (ret)
-		return ret;
+		goto err_iommu_register;
 
 	platform_set_drvdata(pdev, data);
 
@@ -657,6 +657,10 @@ static int exynos_sysmmu_probe(struct platform_device *pdev)
 	pm_runtime_enable(dev);
 
 	return 0;
+
+err_iommu_register:
+	iommu_device_sysfs_remove(&data->iommu);
+	return ret;
 }
 
 static int __maybe_unused exynos_sysmmu_suspend(struct device *dev)
diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index b7708b93f3fa..f026bd269cb0 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -385,7 +385,7 @@ static int dmar_pci_bus_notifier(struct notifier_block *nb,
 
 static struct notifier_block dmar_pci_bus_nb = {
 	.notifier_call = dmar_pci_bus_notifier,
-	.priority = INT_MIN,
+	.priority = 1,
 };
 
 static struct dmar_drhd_unit *
@@ -497,7 +497,7 @@ static int dmar_parse_one_rhsa(struct acpi_dmar_header *header, void *arg)
 		if (drhd->reg_base_addr == rhsa->base_address) {
 			int node = pxm_to_node(rhsa->proximity_domain);
 
-			if (!node_online(node))
+			if (node != NUMA_NO_NODE && !node_online(node))
 				node = NUMA_NO_NODE;
 			drhd->iommu->node = node;
 			return 0;
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index a1ffb3d6d901..2affdccb58e4 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -191,38 +191,6 @@ static phys_addr_t root_entry_uctp(struct root_entry *re)
 	return re->hi & VTD_PAGE_MASK;
 }
 
-static inline void context_clear_pasid_enable(struct context_entry *context)
-{
-	context->lo &= ~(1ULL << 11);
-}
-
-static inline bool context_pasid_enabled(struct context_entry *context)
-{
-	return !!(context->lo & (1ULL << 11));
-}
-
-static inline void context_set_copied(struct context_entry *context)
-{
-	context->hi |= (1ull << 3);
-}
-
-static inline bool context_copied(struct context_entry *context)
-{
-	return !!(context->hi & (1ULL << 3));
-}
-
-static inline bool __context_present(struct context_entry *context)
-{
-	return (context->lo & 1);
-}
-
-bool context_present(struct context_entry *context)
-{
-	return context_pasid_enabled(context) ?
-	     __context_present(context) :
-	     __context_present(context) && !context_copied(context);
-}
-
 static inline void context_set_present(struct context_entry *context)
 {
 	context->lo |= 1;
@@ -270,6 +238,26 @@ static inline void context_clear_entry(struct context_entry *context)
 	context->hi = 0;
 }
 
+static inline bool context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
+{
+	if (!iommu->copied_tables)
+		return false;
+
+	return test_bit(((long)bus << 8) | devfn, iommu->copied_tables);
+}
+
+static inline void
+set_context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
+{
+	set_bit(((long)bus << 8) | devfn, iommu->copied_tables);
+}
+
+static inline void
+clear_context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
+{
+	clear_bit(((long)bus << 8) | devfn, iommu->copied_tables);
+}
+
 /*
  * This domain is a statically identity mapping domain.
  *	1. This domain creats a static 1:1 mapping to all usable memory.
@@ -542,14 +530,36 @@ static inline int domain_pfn_supported(struct dmar_domain *domain,
 	return !(addr_width < BITS_PER_LONG && pfn >> addr_width);
 }
 
+/*
+ * Calculate the Supported Adjusted Guest Address Widths of an IOMMU.
+ * Refer to 11.4.2 of the VT-d spec for the encoding of each bit of
+ * the returned SAGAW.
+ */
+static unsigned long __iommu_calculate_sagaw(struct intel_iommu *iommu)
+{
+	unsigned long fl_sagaw, sl_sagaw;
+
+	fl_sagaw = BIT(2) | (cap_fl1gp_support(iommu->cap) ? BIT(3) : 0);
+	sl_sagaw = cap_sagaw(iommu->cap);
+
+	/* Second level only. */
+	if (!sm_supported(iommu) || !ecap_flts(iommu->ecap))
+		return sl_sagaw;
+
+	/* First level only. */
+	if (!ecap_slts(iommu->ecap))
+		return fl_sagaw;
+
+	return fl_sagaw & sl_sagaw;
+}
+
 static int __iommu_calculate_agaw(struct intel_iommu *iommu, int max_gaw)
 {
 	unsigned long sagaw;
 	int agaw;
 
-	sagaw = cap_sagaw(iommu->cap);
-	for (agaw = width_to_agaw(max_gaw);
-	     agaw >= 0; agaw--) {
+	sagaw = __iommu_calculate_sagaw(iommu);
+	for (agaw = width_to_agaw(max_gaw); agaw >= 0; agaw--) {
 		if (test_bit(agaw, &sagaw))
 			break;
 	}
@@ -770,6 +780,13 @@ struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus,
 	struct context_entry *context;
 	u64 *entry;
 
+	/*
+	 * Except that the caller requested to allocate a new entry,
+	 * returning a copied context entry makes no sense.
+	 */
+	if (!alloc && context_copied(iommu, bus, devfn))
+		return NULL;
+
 	entry = &root->lo;
 	if (sm_supported(iommu)) {
 		if (devfn >= 0x80) {
@@ -1877,6 +1894,11 @@ static void free_dmar_iommu(struct intel_iommu *iommu)
 		iommu->domain_ids = NULL;
 	}
 
+	if (iommu->copied_tables) {
+		bitmap_free(iommu->copied_tables);
+		iommu->copied_tables = NULL;
+	}
+
 	g_iommus[iommu->seq_id] = NULL;
 
 	/* free context mapping */
@@ -2085,7 +2107,7 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
 		goto out_unlock;
 
 	ret = 0;
-	if (context_present(context))
+	if (context_present(context) && !context_copied(iommu, bus, devfn))
 		goto out_unlock;
 
 	/*
@@ -2097,7 +2119,7 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
 	 * in-flight DMA will exist, and we don't need to worry anymore
 	 * hereafter.
 	 */
-	if (context_copied(context)) {
+	if (context_copied(iommu, bus, devfn)) {
 		u16 did_old = context_domain_id(context);
 
 		if (did_old < cap_ndoms(iommu->cap)) {
@@ -2108,6 +2130,8 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
 			iommu->flush.flush_iotlb(iommu, did_old, 0, 0,
 						 DMA_TLB_DSI_FLUSH);
 		}
+
+		clear_context_copied(iommu, bus, devfn);
 	}
 
 	context_clear_entry(context);
@@ -3002,32 +3026,14 @@ static int copy_context_table(struct intel_iommu *iommu,
 		/* Now copy the context entry */
 		memcpy(&ce, old_ce + idx, sizeof(ce));
 
-		if (!__context_present(&ce))
+		if (!context_present(&ce))
 			continue;
 
 		did = context_domain_id(&ce);
 		if (did >= 0 && did < cap_ndoms(iommu->cap))
 			set_bit(did, iommu->domain_ids);
 
-		/*
-		 * We need a marker for copied context entries. This
-		 * marker needs to work for the old format as well as
-		 * for extended context entries.
-		 *
-		 * Bit 67 of the context entry is used. In the old
-		 * format this bit is available to software, in the
-		 * extended format it is the PGE bit, but PGE is ignored
-		 * by HW if PASIDs are disabled (and thus still
-		 * available).
-		 *
-		 * So disable PASIDs first and then mark the entry
-		 * copied. This means that we don't copy PASID
-		 * translations from the old kernel, but this is fine as
-		 * faults there are not fatal.
-		 */
-		context_clear_pasid_enable(&ce);
-		context_set_copied(&ce);
-
+		set_context_copied(iommu, bus, devfn);
 		new_ce[idx] = ce;
 	}
 
@@ -3054,8 +3060,8 @@ static int copy_translation_tables(struct intel_iommu *iommu)
 	bool new_ext, ext;
 
 	rtaddr_reg = dmar_readq(iommu->reg + DMAR_RTADDR_REG);
-	ext        = !!(rtaddr_reg & DMA_RTADDR_RTT);
-	new_ext    = !!ecap_ecs(iommu->ecap);
+	ext        = !!(rtaddr_reg & DMA_RTADDR_SMT);
+	new_ext    = !!sm_supported(iommu);
 
 	/*
 	 * The RTT bit can only be changed when translation is disabled,
@@ -3066,6 +3072,10 @@ static int copy_translation_tables(struct intel_iommu *iommu)
 	if (new_ext != ext)
 		return -EINVAL;
 
+	iommu->copied_tables = bitmap_zalloc(BIT_ULL(16), GFP_KERNEL);
+	if (!iommu->copied_tables)
+		return -ENOMEM;
+
 	old_rt_phys = rtaddr_reg & VTD_PAGE_MASK;
 	if (!old_rt_phys)
 		return -EINVAL;
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index be066c1503d3..ba3115fd0f86 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -182,14 +182,8 @@ static bool arm_v7s_is_mtk_enabled(struct io_pgtable_cfg *cfg)
 		(cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_EXT);
 }
 
-static arm_v7s_iopte paddr_to_iopte(phys_addr_t paddr, int lvl,
-				    struct io_pgtable_cfg *cfg)
+static arm_v7s_iopte to_mtk_iopte(phys_addr_t paddr, arm_v7s_iopte pte)
 {
-	arm_v7s_iopte pte = paddr & ARM_V7S_LVL_MASK(lvl);
-
-	if (!arm_v7s_is_mtk_enabled(cfg))
-		return pte;
-
 	if (paddr & BIT_ULL(32))
 		pte |= ARM_V7S_ATTR_MTK_PA_BIT32;
 	if (paddr & BIT_ULL(33))
@@ -199,6 +193,17 @@ static arm_v7s_iopte paddr_to_iopte(phys_addr_t paddr, int lvl,
 	return pte;
 }
 
+static arm_v7s_iopte paddr_to_iopte(phys_addr_t paddr, int lvl,
+				    struct io_pgtable_cfg *cfg)
+{
+	arm_v7s_iopte pte = paddr & ARM_V7S_LVL_MASK(lvl);
+
+	if (arm_v7s_is_mtk_enabled(cfg))
+		return to_mtk_iopte(paddr, pte);
+
+	return pte;
+}
+
 static phys_addr_t iopte_to_paddr(arm_v7s_iopte pte, int lvl,
 				  struct io_pgtable_cfg *cfg)
 {
@@ -240,10 +245,17 @@ static void *__arm_v7s_alloc_table(int lvl, gfp_t gfp,
 	dma_addr_t dma;
 	size_t size = ARM_V7S_TABLE_SIZE(lvl, cfg);
 	void *table = NULL;
+	gfp_t gfp_l1;
+
+	/*
+	 * ARM_MTK_TTBR_EXT extend the translation table base support larger
+	 * memory address.
+	 */
+	gfp_l1 = cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT ?
+		 GFP_KERNEL : ARM_V7S_TABLE_GFP_DMA;
 
 	if (lvl == 1)
-		table = (void *)__get_free_pages(
-			__GFP_ZERO | ARM_V7S_TABLE_GFP_DMA, get_order(size));
+		table = (void *)__get_free_pages(gfp_l1 | __GFP_ZERO, get_order(size));
 	else if (lvl == 2)
 		table = kmem_cache_zalloc(data->l2_tables, gfp);
 
@@ -251,7 +263,8 @@ static void *__arm_v7s_alloc_table(int lvl, gfp_t gfp,
 		return NULL;
 
 	phys = virt_to_phys(table);
-	if (phys != (arm_v7s_iopte)phys) {
+	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT ?
+	    phys >= (1ULL << cfg->oas) : phys != (arm_v7s_iopte)phys) {
 		/* Doesn't fit in PTE */
 		dev_err(dev, "Page table does not fit in PTE: %pa", &phys);
 		goto out_free;
@@ -457,9 +470,14 @@ static arm_v7s_iopte arm_v7s_install_table(arm_v7s_iopte *table,
 					   arm_v7s_iopte curr,
 					   struct io_pgtable_cfg *cfg)
 {
+	phys_addr_t phys = virt_to_phys(table);
 	arm_v7s_iopte old, new;
 
-	new = virt_to_phys(table) | ARM_V7S_PTE_TYPE_TABLE;
+	new = phys | ARM_V7S_PTE_TYPE_TABLE;
+
+	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT)
+		new = to_mtk_iopte(phys, new);
+
 	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_NS)
 		new |= ARM_V7S_ATTR_NS_TABLE;
 
@@ -779,6 +797,8 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg,
 						void *cookie)
 {
 	struct arm_v7s_io_pgtable *data;
+	slab_flags_t slab_flag;
+	phys_addr_t paddr;
 
 	if (cfg->ias > (arm_v7s_is_mtk_enabled(cfg) ? 34 : ARM_V7S_ADDR_BITS))
 		return NULL;
@@ -788,7 +808,8 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg,
 
 	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS |
 			    IO_PGTABLE_QUIRK_NO_PERMS |
-			    IO_PGTABLE_QUIRK_ARM_MTK_EXT))
+			    IO_PGTABLE_QUIRK_ARM_MTK_EXT |
+			    IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT))
 		return NULL;
 
 	/* If ARM_MTK_4GB is enabled, the NO_PERMS is also expected. */
@@ -796,15 +817,27 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg,
 	    !(cfg->quirks & IO_PGTABLE_QUIRK_NO_PERMS))
 			return NULL;
 
+	if ((cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT) &&
+	    !arm_v7s_is_mtk_enabled(cfg))
+		return NULL;
+
 	data = kmalloc(sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return NULL;
 
 	spin_lock_init(&data->split_lock);
+
+	/*
+	 * ARM_MTK_TTBR_EXT extend the translation table base support larger
+	 * memory address.
+	 */
+	slab_flag = cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT ?
+		    0 : ARM_V7S_TABLE_SLAB_FLAGS;
+
 	data->l2_tables = kmem_cache_create("io-pgtable_armv7s_l2",
 					    ARM_V7S_TABLE_SIZE(2, cfg),
 					    ARM_V7S_TABLE_SIZE(2, cfg),
-					    ARM_V7S_TABLE_SLAB_FLAGS, NULL);
+					    slab_flag, NULL);
 	if (!data->l2_tables)
 		goto out_free_data;
 
@@ -850,12 +883,16 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg,
 	wmb();
 
 	/* TTBR */
-	cfg->arm_v7s_cfg.ttbr = virt_to_phys(data->pgd) | ARM_V7S_TTBR_S |
-				(cfg->coherent_walk ? (ARM_V7S_TTBR_NOS |
-				 ARM_V7S_TTBR_IRGN_ATTR(ARM_V7S_RGN_WBWA) |
-				 ARM_V7S_TTBR_ORGN_ATTR(ARM_V7S_RGN_WBWA)) :
-				(ARM_V7S_TTBR_IRGN_ATTR(ARM_V7S_RGN_NC) |
-				 ARM_V7S_TTBR_ORGN_ATTR(ARM_V7S_RGN_NC)));
+	paddr = virt_to_phys(data->pgd);
+	if (arm_v7s_is_mtk_enabled(cfg))
+		cfg->arm_v7s_cfg.ttbr = paddr | upper_32_bits(paddr);
+	else
+		cfg->arm_v7s_cfg.ttbr = paddr | ARM_V7S_TTBR_S |
+					(cfg->coherent_walk ? (ARM_V7S_TTBR_NOS |
+					 ARM_V7S_TTBR_IRGN_ATTR(ARM_V7S_RGN_WBWA) |
+					 ARM_V7S_TTBR_ORGN_ATTR(ARM_V7S_RGN_WBWA)) :
+					(ARM_V7S_TTBR_IRGN_ATTR(ARM_V7S_RGN_NC) |
+					 ARM_V7S_TTBR_ORGN_ATTR(ARM_V7S_RGN_NC)));
 	return &data->iop;
 
 out_free_data:
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index 8c5566d303e4..bc738a8937db 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -171,7 +171,7 @@ config MADERA_IRQ
 config IRQ_MIPS_CPU
 	bool
 	select GENERIC_IRQ_CHIP
-	select GENERIC_IRQ_IPI if SYS_SUPPORTS_MULTITHREADING
+	select GENERIC_IRQ_IPI if SMP && SYS_SUPPORTS_MULTITHREADING
 	select IRQ_DOMAIN
 	select GENERIC_IRQ_EFFECTIVE_AFF_MASK
 
@@ -304,7 +304,8 @@ config KEYSTONE_IRQ
 
 config MIPS_GIC
 	bool
-	select GENERIC_IRQ_IPI
+	select GENERIC_IRQ_IPI if SMP
+	select IRQ_DOMAIN_HIERARCHY
 	select MIPS_CM
 
 config INGENIC_IRQ
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 90a10f6dcf82..3269fde6f21f 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -560,7 +560,8 @@ static void gic_irq_nmi_teardown(struct irq_data *d)
 
 static void gic_eoi_irq(struct irq_data *d)
 {
-	gic_write_eoir(gic_irq(d));
+	write_gicreg(gic_irq(d), ICC_EOIR1_EL1);
+	isb();
 }
 
 static void gic_eoimode1_eoi_irq(struct irq_data *d)
@@ -657,10 +658,38 @@ static void gic_deactivate_unhandled(u32 irqnr)
 		if (irqnr < 8192)
 			gic_write_dir(irqnr);
 	} else {
-		gic_write_eoir(irqnr);
+		write_gicreg(irqnr, ICC_EOIR1_EL1);
+		isb();
 	}
 }
 
+/*
+ * Follow a read of the IAR with any HW maintenance that needs to happen prior
+ * to invoking the relevant IRQ handler. We must do two things:
+ *
+ * (1) Ensure instruction ordering between a read of IAR and subsequent
+ *     instructions in the IRQ handler using an ISB.
+ *
+ *     It is possible for the IAR to report an IRQ which was signalled *after*
+ *     the CPU took an IRQ exception as multiple interrupts can race to be
+ *     recognized by the GIC, earlier interrupts could be withdrawn, and/or
+ *     later interrupts could be prioritized by the GIC.
+ *
+ *     For devices which are tightly coupled to the CPU, such as PMUs, a
+ *     context synchronization event is necessary to ensure that system
+ *     register state is not stale, as these may have been indirectly written
+ *     *after* exception entry.
+ *
+ * (2) Deactivate the interrupt when EOI mode 1 is in use.
+ */
+static inline void gic_complete_ack(u32 irqnr)
+{
+	if (static_branch_likely(&supports_deactivate_key))
+		write_gicreg(irqnr, ICC_EOIR1_EL1);
+
+	isb();
+}
+
 static inline void gic_handle_nmi(u32 irqnr, struct pt_regs *regs)
 {
 	bool irqs_enabled = interrupts_enabled(regs);
@@ -669,8 +698,8 @@ static inline void gic_handle_nmi(u32 irqnr, struct pt_regs *regs)
 	if (irqs_enabled)
 		nmi_enter();
 
-	if (static_branch_likely(&supports_deactivate_key))
-		gic_write_eoir(irqnr);
+	gic_complete_ack(irqnr);
+
 	/*
 	 * Leave the PSR.I bit set to prevent other NMIs to be
 	 * received while handling this one.
@@ -740,10 +769,7 @@ static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs
 		gic_arch_enable_irqs();
 	}
 
-	if (static_branch_likely(&supports_deactivate_key))
-		gic_write_eoir(irqnr);
-	else
-		isb();
+	gic_complete_ack(irqnr);
 
 	if (handle_domain_irq(gic_data.domain, irqnr, regs)) {
 		WARN_ONCE(true, "Unexpected interrupt received!\n");
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index 54c7092cc61d..d815285f1efe 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -51,13 +51,15 @@ static DEFINE_PER_CPU_READ_MOSTLY(unsigned long[GIC_MAX_LONGS], pcpu_masks);
 
 static DEFINE_SPINLOCK(gic_lock);
 static struct irq_domain *gic_irq_domain;
-static struct irq_domain *gic_ipi_domain;
 static int gic_shared_intrs;
 static unsigned int gic_cpu_pin;
 static unsigned int timer_cpu_pin;
 static struct irq_chip gic_level_irq_controller, gic_edge_irq_controller;
+
+#ifdef CONFIG_GENERIC_IRQ_IPI
 static DECLARE_BITMAP(ipi_resrv, GIC_MAX_INTRS);
 static DECLARE_BITMAP(ipi_available, GIC_MAX_INTRS);
+#endif /* CONFIG_GENERIC_IRQ_IPI */
 
 static struct gic_all_vpes_chip_data {
 	u32	map;
@@ -460,9 +462,11 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int virq,
 	u32 map;
 
 	if (hwirq >= GIC_SHARED_HWIRQ_BASE) {
+#ifdef CONFIG_GENERIC_IRQ_IPI
 		/* verify that shared irqs don't conflict with an IPI irq */
 		if (test_bit(GIC_HWIRQ_TO_SHARED(hwirq), ipi_resrv))
 			return -EBUSY;
+#endif /* CONFIG_GENERIC_IRQ_IPI */
 
 		err = irq_domain_set_hwirq_and_chip(d, virq, hwirq,
 						    &gic_level_irq_controller,
@@ -551,6 +555,8 @@ static const struct irq_domain_ops gic_irq_domain_ops = {
 	.map = gic_irq_domain_map,
 };
 
+#ifdef CONFIG_GENERIC_IRQ_IPI
+
 static int gic_ipi_domain_xlate(struct irq_domain *d, struct device_node *ctrlr,
 				const u32 *intspec, unsigned int intsize,
 				irq_hw_number_t *out_hwirq,
@@ -654,6 +660,48 @@ static const struct irq_domain_ops gic_ipi_domain_ops = {
 	.match = gic_ipi_domain_match,
 };
 
+static int gic_register_ipi_domain(struct device_node *node)
+{
+	struct irq_domain *gic_ipi_domain;
+	unsigned int v[2], num_ipis;
+
+	gic_ipi_domain = irq_domain_add_hierarchy(gic_irq_domain,
+						  IRQ_DOMAIN_FLAG_IPI_PER_CPU,
+						  GIC_NUM_LOCAL_INTRS + gic_shared_intrs,
+						  node, &gic_ipi_domain_ops, NULL);
+	if (!gic_ipi_domain) {
+		pr_err("Failed to add IPI domain");
+		return -ENXIO;
+	}
+
+	irq_domain_update_bus_token(gic_ipi_domain, DOMAIN_BUS_IPI);
+
+	if (node &&
+	    !of_property_read_u32_array(node, "mti,reserved-ipi-vectors", v, 2)) {
+		bitmap_set(ipi_resrv, v[0], v[1]);
+	} else {
+		/*
+		 * Reserve 2 interrupts per possible CPU/VP for use as IPIs,
+		 * meeting the requirements of arch/mips SMP.
+		 */
+		num_ipis = 2 * num_possible_cpus();
+		bitmap_set(ipi_resrv, gic_shared_intrs - num_ipis, num_ipis);
+	}
+
+	bitmap_copy(ipi_available, ipi_resrv, GIC_MAX_INTRS);
+
+	return 0;
+}
+
+#else /* !CONFIG_GENERIC_IRQ_IPI */
+
+static inline int gic_register_ipi_domain(struct device_node *node)
+{
+	return 0;
+}
+
+#endif /* !CONFIG_GENERIC_IRQ_IPI */
+
 static int gic_cpu_startup(unsigned int cpu)
 {
 	/* Enable or disable EIC */
@@ -672,11 +720,12 @@ static int gic_cpu_startup(unsigned int cpu)
 static int __init gic_of_init(struct device_node *node,
 			      struct device_node *parent)
 {
-	unsigned int cpu_vec, i, gicconfig, v[2], num_ipis;
+	unsigned int cpu_vec, i, gicconfig;
 	unsigned long reserved;
 	phys_addr_t gic_base;
 	struct resource res;
 	size_t gic_len;
+	int ret;
 
 	/* Find the first available CPU vector. */
 	i = 0;
@@ -718,6 +767,10 @@ static int __init gic_of_init(struct device_node *node,
 	}
 
 	mips_gic_base = ioremap(gic_base, gic_len);
+	if (!mips_gic_base) {
+		pr_err("Failed to ioremap gic_base\n");
+		return -ENOMEM;
+	}
 
 	gicconfig = read_gic_config();
 	gic_shared_intrs = gicconfig & GIC_CONFIG_NUMINTERRUPTS;
@@ -765,30 +818,9 @@ static int __init gic_of_init(struct device_node *node,
 		return -ENXIO;
 	}
 
-	gic_ipi_domain = irq_domain_add_hierarchy(gic_irq_domain,
-						  IRQ_DOMAIN_FLAG_IPI_PER_CPU,
-						  GIC_NUM_LOCAL_INTRS + gic_shared_intrs,
-						  node, &gic_ipi_domain_ops, NULL);
-	if (!gic_ipi_domain) {
-		pr_err("Failed to add IPI domain");
-		return -ENXIO;
-	}
-
-	irq_domain_update_bus_token(gic_ipi_domain, DOMAIN_BUS_IPI);
-
-	if (node &&
-	    !of_property_read_u32_array(node, "mti,reserved-ipi-vectors", v, 2)) {
-		bitmap_set(ipi_resrv, v[0], v[1]);
-	} else {
-		/*
-		 * Reserve 2 interrupts per possible CPU/VP for use as IPIs,
-		 * meeting the requirements of arch/mips SMP.
-		 */
-		num_ipis = 2 * num_possible_cpus();
-		bitmap_set(ipi_resrv, gic_shared_intrs - num_ipis, num_ipis);
-	}
-
-	bitmap_copy(ipi_available, ipi_resrv, GIC_MAX_INTRS);
+	ret = gic_register_ipi_domain(node);
+	if (ret)
+		return ret;
 
 	board_bind_eic_interrupt = &gic_bind_eic_interrupt;
 
diff --git a/drivers/irqchip/irq-or1k-pic.c b/drivers/irqchip/irq-or1k-pic.c
index 03d2366118dd..d5f1fabc45d7 100644
--- a/drivers/irqchip/irq-or1k-pic.c
+++ b/drivers/irqchip/irq-or1k-pic.c
@@ -66,7 +66,6 @@ static struct or1k_pic_dev or1k_pic_level = {
 		.name = "or1k-PIC-level",
 		.irq_unmask = or1k_pic_unmask,
 		.irq_mask = or1k_pic_mask,
-		.irq_mask_ack = or1k_pic_mask_ack,
 	},
 	.handle = handle_level_irq,
 	.flags = IRQ_LEVEL | IRQ_NOPROBE,
diff --git a/drivers/irqchip/irq-tegra.c b/drivers/irqchip/irq-tegra.c
index e1f771c72fc4..ad3e2c1b3c87 100644
--- a/drivers/irqchip/irq-tegra.c
+++ b/drivers/irqchip/irq-tegra.c
@@ -148,10 +148,10 @@ static int tegra_ictlr_suspend(void)
 		lic->cop_iep[i] = readl_relaxed(ictlr + ICTLR_COP_IEP_CLASS);
 
 		/* Disable COP interrupts */
-		writel_relaxed(~0ul, ictlr + ICTLR_COP_IER_CLR);
+		writel_relaxed(GENMASK(31, 0), ictlr + ICTLR_COP_IER_CLR);
 
 		/* Disable CPU interrupts */
-		writel_relaxed(~0ul, ictlr + ICTLR_CPU_IER_CLR);
+		writel_relaxed(GENMASK(31, 0), ictlr + ICTLR_CPU_IER_CLR);
 
 		/* Enable the wakeup sources of ictlr */
 		writel_relaxed(lic->ictlr_wake_mask[i], ictlr + ICTLR_CPU_IER_SET);
@@ -172,12 +172,12 @@ static void tegra_ictlr_resume(void)
 
 		writel_relaxed(lic->cpu_iep[i],
 			       ictlr + ICTLR_CPU_IEP_CLASS);
-		writel_relaxed(~0ul, ictlr + ICTLR_CPU_IER_CLR);
+		writel_relaxed(GENMASK(31, 0), ictlr + ICTLR_CPU_IER_CLR);
 		writel_relaxed(lic->cpu_ier[i],
 			       ictlr + ICTLR_CPU_IER_SET);
 		writel_relaxed(lic->cop_iep[i],
 			       ictlr + ICTLR_COP_IEP_CLASS);
-		writel_relaxed(~0ul, ictlr + ICTLR_COP_IER_CLR);
+		writel_relaxed(GENMASK(31, 0), ictlr + ICTLR_COP_IER_CLR);
 		writel_relaxed(lic->cop_ier[i],
 			       ictlr + ICTLR_COP_IER_SET);
 	}
@@ -312,7 +312,7 @@ static int __init tegra_ictlr_init(struct device_node *node,
 		lic->base[i] = base;
 
 		/* Disable all interrupts */
-		writel_relaxed(~0UL, base + ICTLR_CPU_IER_CLR);
+		writel_relaxed(GENMASK(31, 0), base + ICTLR_CPU_IER_CLR);
 		/* All interrupts target IRQ */
 		writel_relaxed(0, base + ICTLR_CPU_IEP_CLASS);
 
diff --git a/drivers/macintosh/adb.c b/drivers/macintosh/adb.c
index 73b396189039..afb0942ccc29 100644
--- a/drivers/macintosh/adb.c
+++ b/drivers/macintosh/adb.c
@@ -647,7 +647,7 @@ do_adb_query(struct adb_request *req)
 
 	switch(req->data[1]) {
 	case ADB_QUERY_GETDEVINFO:
-		if (req->nbytes < 3)
+		if (req->nbytes < 3 || req->data[2] >= 16)
 			break;
 		mutex_lock(&adb_handler_mutex);
 		req->reply[0] = adb_handler[req->data[2]].original_address;
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index d9ef52159a22..eba277bb8a1f 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -1001,12 +1001,13 @@ static int validate_region_size(struct raid_set *rs, unsigned long region_size)
 static int validate_raid_redundancy(struct raid_set *rs)
 {
 	unsigned int i, rebuild_cnt = 0;
-	unsigned int rebuilds_per_group = 0, copies;
+	unsigned int rebuilds_per_group = 0, copies, raid_disks;
 	unsigned int group_size, last_group_start;
 
-	for (i = 0; i < rs->md.raid_disks; i++)
-		if (!test_bit(In_sync, &rs->dev[i].rdev.flags) ||
-		    !rs->dev[i].rdev.sb_page)
+	for (i = 0; i < rs->raid_disks; i++)
+		if (!test_bit(FirstUse, &rs->dev[i].rdev.flags) &&
+		    ((!test_bit(In_sync, &rs->dev[i].rdev.flags) ||
+		      !rs->dev[i].rdev.sb_page)))
 			rebuild_cnt++;
 
 	switch (rs->md.level) {
@@ -1046,8 +1047,9 @@ static int validate_raid_redundancy(struct raid_set *rs)
 		 *	    A	 A    B	   B	C
 		 *	    C	 D    D	   E	E
 		 */
+		raid_disks = min(rs->raid_disks, rs->md.raid_disks);
 		if (__is_raid10_near(rs->md.new_layout)) {
-			for (i = 0; i < rs->md.raid_disks; i++) {
+			for (i = 0; i < raid_disks; i++) {
 				if (!(i % copies))
 					rebuilds_per_group = 0;
 				if ((!rs->dev[i].rdev.sb_page ||
@@ -1070,10 +1072,10 @@ static int validate_raid_redundancy(struct raid_set *rs)
 		 * results in the need to treat the last (potentially larger)
 		 * set differently.
 		 */
-		group_size = (rs->md.raid_disks / copies);
-		last_group_start = (rs->md.raid_disks / group_size) - 1;
+		group_size = (raid_disks / copies);
+		last_group_start = (raid_disks / group_size) - 1;
 		last_group_start *= group_size;
-		for (i = 0; i < rs->md.raid_disks; i++) {
+		for (i = 0; i < raid_disks; i++) {
 			if (!(i % copies) && !(i > last_group_start))
 				rebuilds_per_group = 0;
 			if ((!rs->dev[i].rdev.sb_page ||
@@ -1588,7 +1590,7 @@ static sector_t __rdev_sectors(struct raid_set *rs)
 {
 	int i;
 
-	for (i = 0; i < rs->md.raid_disks; i++) {
+	for (i = 0; i < rs->raid_disks; i++) {
 		struct md_rdev *rdev = &rs->dev[i].rdev;
 
 		if (!test_bit(Journal, &rdev->flags) &&
@@ -3512,7 +3514,7 @@ static void raid_status(struct dm_target *ti, status_type_t type,
 {
 	struct raid_set *rs = ti->private;
 	struct mddev *mddev = &rs->md;
-	struct r5conf *conf = mddev->private;
+	struct r5conf *conf = rs_is_raid456(rs) ? mddev->private : NULL;
 	int i, max_nr_stripes = conf ? conf->max_nr_stripes : 0;
 	unsigned long recovery;
 	unsigned int raid_param_cnt = 1; /* at least 1 for chunksize */
@@ -3771,13 +3773,13 @@ static int raid_iterate_devices(struct dm_target *ti,
 	unsigned int i;
 	int r = 0;
 
-	for (i = 0; !r && i < rs->md.raid_disks; i++)
-		if (rs->dev[i].data_dev)
-			r = fn(ti,
-				 rs->dev[i].data_dev,
-				 0, /* No offset on data devs */
-				 rs->md.dev_sectors,
-				 data);
+	for (i = 0; !r && i < rs->raid_disks; i++) {
+		if (rs->dev[i].data_dev) {
+			r = fn(ti, rs->dev[i].data_dev,
+			       0, /* No offset on data devs */
+			       rs->md.dev_sectors, data);
+		}
+	}
 
 	return r;
 }
@@ -3822,7 +3824,7 @@ static void attempt_restore_of_faulty_devices(struct raid_set *rs)
 
 	memset(cleared_failed_devices, 0, sizeof(cleared_failed_devices));
 
-	for (i = 0; i < mddev->raid_disks; i++) {
+	for (i = 0; i < rs->raid_disks; i++) {
 		r = &rs->dev[i].rdev;
 		/* HM FIXME: enhance journal device recovery processing */
 		if (test_bit(Journal, &r->flags))
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index c88ed14d49e6..0ada99572b68 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -2073,10 +2073,13 @@ int dm_pool_register_metadata_threshold(struct dm_pool_metadata *pmd,
 					dm_sm_threshold_fn fn,
 					void *context)
 {
-	int r;
+	int r = -EINVAL;
 
 	pmd_write_lock_in_core(pmd);
-	r = dm_sm_register_threshold_callback(pmd->metadata_sm, threshold, fn, context);
+	if (!pmd->fail_io) {
+		r = dm_sm_register_threshold_callback(pmd->metadata_sm,
+						      threshold, fn, context);
+	}
 	pmd_write_unlock(pmd);
 
 	return r;
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 4c67b77c23c1..0a85e4cd607c 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -3401,8 +3401,10 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
 						calc_metadata_threshold(pt),
 						metadata_low_callback,
 						pool);
-	if (r)
+	if (r) {
+		ti->error = "Error registering metadata threshold";
 		goto out_flags_changed;
+	}
 
 	dm_pool_register_pre_commit_callback(pool->pmd,
 					     metadata_pre_commit_callback, pool);
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index 18320444fb0a..dfb55fe09ce1 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -22,7 +22,7 @@
 
 #define HIGH_WATERMARK			50
 #define LOW_WATERMARK			45
-#define MAX_WRITEBACK_JOBS		0
+#define MAX_WRITEBACK_JOBS		min(0x10000000 / PAGE_SIZE, totalram_pages() / 16)
 #define ENDIO_LATENCY			16
 #define WRITEBACK_LATENCY		64
 #define AUTOCOMMIT_BLOCKS_SSD		65536
@@ -1328,8 +1328,8 @@ enum wc_map_op {
 	WC_MAP_ERROR,
 };
 
-static enum wc_map_op writecache_map_remap_origin(struct dm_writecache *wc, struct bio *bio,
-						  struct wc_entry *e)
+static void writecache_map_remap_origin(struct dm_writecache *wc, struct bio *bio,
+					struct wc_entry *e)
 {
 	if (e) {
 		sector_t next_boundary =
@@ -1337,8 +1337,6 @@ static enum wc_map_op writecache_map_remap_origin(struct dm_writecache *wc, stru
 		if (next_boundary < bio->bi_iter.bi_size >> SECTOR_SHIFT)
 			dm_accept_partial_bio(bio, next_boundary);
 	}
-
-	return WC_MAP_REMAP_ORIGIN;
 }
 
 static enum wc_map_op writecache_map_read(struct dm_writecache *wc, struct bio *bio)
@@ -1365,14 +1363,16 @@ read_next_block:
 			map_op = WC_MAP_REMAP;
 		}
 	} else {
-		map_op = writecache_map_remap_origin(wc, bio, e);
+		writecache_map_remap_origin(wc, bio, e);
+		wc->stats.reads += (bio->bi_iter.bi_size - wc->block_size) >> wc->block_size_bits;
+		map_op = WC_MAP_REMAP_ORIGIN;
 	}
 
 	return map_op;
 }
 
-static enum wc_map_op writecache_bio_copy_ssd(struct dm_writecache *wc, struct bio *bio,
-					      struct wc_entry *e, bool search_used)
+static void writecache_bio_copy_ssd(struct dm_writecache *wc, struct bio *bio,
+				    struct wc_entry *e, bool search_used)
 {
 	unsigned bio_size = wc->block_size;
 	sector_t start_cache_sec = cache_sector(wc, e);
@@ -1412,14 +1412,15 @@ static enum wc_map_op writecache_bio_copy_ssd(struct dm_writecache *wc, struct b
 	bio->bi_iter.bi_sector = start_cache_sec;
 	dm_accept_partial_bio(bio, bio_size >> SECTOR_SHIFT);
 
+	wc->stats.writes += bio->bi_iter.bi_size >> wc->block_size_bits;
+	wc->stats.writes_allocate += (bio->bi_iter.bi_size - wc->block_size) >> wc->block_size_bits;
+
 	if (unlikely(wc->uncommitted_blocks >= wc->autocommit_blocks)) {
 		wc->uncommitted_blocks = 0;
 		queue_work(wc->writeback_wq, &wc->flush_work);
 	} else {
 		writecache_schedule_autocommit(wc);
 	}
-
-	return WC_MAP_REMAP;
 }
 
 static enum wc_map_op writecache_map_write(struct dm_writecache *wc, struct bio *bio)
@@ -1429,9 +1430,10 @@ static enum wc_map_op writecache_map_write(struct dm_writecache *wc, struct bio
 	do {
 		bool found_entry = false;
 		bool search_used = false;
-		wc->stats.writes++;
-		if (writecache_has_error(wc))
+		if (writecache_has_error(wc)) {
+			wc->stats.writes += bio->bi_iter.bi_size >> wc->block_size_bits;
 			return WC_MAP_ERROR;
+		}
 		e = writecache_find_entry(wc, bio->bi_iter.bi_sector, 0);
 		if (e) {
 			if (!writecache_entry_is_committed(wc, e)) {
@@ -1455,9 +1457,11 @@ static enum wc_map_op writecache_map_write(struct dm_writecache *wc, struct bio
 		if (unlikely(!e)) {
 			if (!WC_MODE_PMEM(wc) && !found_entry) {
 direct_write:
-				wc->stats.writes_around++;
 				e = writecache_find_entry(wc, bio->bi_iter.bi_sector, WFE_RETURN_FOLLOWING);
-				return writecache_map_remap_origin(wc, bio, e);
+				writecache_map_remap_origin(wc, bio, e);
+				wc->stats.writes_around += bio->bi_iter.bi_size >> wc->block_size_bits;
+				wc->stats.writes += bio->bi_iter.bi_size >> wc->block_size_bits;
+				return WC_MAP_REMAP_ORIGIN;
 			}
 			wc->stats.writes_blocked_on_freelist++;
 			writecache_wait_on_freelist(wc);
@@ -1468,10 +1472,13 @@ direct_write:
 		wc->uncommitted_blocks++;
 		wc->stats.writes_allocate++;
 bio_copy:
-		if (WC_MODE_PMEM(wc))
+		if (WC_MODE_PMEM(wc)) {
 			bio_copy_block(wc, bio, memory_data(wc, e));
-		else
-			return writecache_bio_copy_ssd(wc, bio, e, search_used);
+			wc->stats.writes++;
+		} else {
+			writecache_bio_copy_ssd(wc, bio, e, search_used);
+			return WC_MAP_REMAP;
+		}
 	} while (bio->bi_iter.bi_size);
 
 	if (unlikely(bio->bi_opf & REQ_FUA || wc->uncommitted_blocks >= wc->autocommit_blocks))
@@ -1506,7 +1513,7 @@ static enum wc_map_op writecache_map_flush(struct dm_writecache *wc, struct bio
 
 static enum wc_map_op writecache_map_discard(struct dm_writecache *wc, struct bio *bio)
 {
-	wc->stats.discards++;
+	wc->stats.discards += bio->bi_iter.bi_size >> wc->block_size_bits;
 
 	if (writecache_has_error(wc))
 		return WC_MAP_ERROR;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 36449422e7e0..41d2e1285c07 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -2911,6 +2911,11 @@ static int dm_call_pr(struct block_device *bdev, iterate_devices_callout_fn fn,
 		goto out;
 	ti = dm_table_get_target(table, 0);
 
+	if (dm_suspended_md(md)) {
+		ret = -EAGAIN;
+		goto out;
+	}
+
 	ret = -EINVAL;
 	if (!ti->type->iterate_devices)
 		goto out;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index bf1c5c0e472e..04e1e294b4b1 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5651,6 +5651,7 @@ static int md_alloc(dev_t dev, char *name)
 	 * removed (mddev_delayed_delete).
 	 */
 	flush_workqueue(md_misc_wq);
+	flush_workqueue(md_rdev_misc_wq);
 
 	mutex_lock(&disks_mutex);
 	mddev = mddev_alloc(dev);
@@ -6272,6 +6273,7 @@ void md_stop(struct mddev *mddev)
 	/* stop the array and free an attached data structures.
 	 * This is called from dm-raid
 	 */
+	__md_stop_writes(mddev);
 	__md_stop(mddev);
 	bioset_exit(&mddev->bio_set);
 	bioset_exit(&mddev->sync_set);
@@ -9467,6 +9469,7 @@ void md_reap_sync_thread(struct mddev *mddev)
 	wake_up(&resync_wait);
 	/* flag recovery needed just to double check */
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+	sysfs_notify_dirent_safe(mddev->sysfs_completed);
 	sysfs_notify_dirent_safe(mddev->sysfs_action);
 	md_new_event(mddev);
 	if (mddev->event_work.func)
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index aa2636582841..c4c1a3a7d7ab 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -2139,9 +2139,12 @@ static int raid10_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 	int err = 0;
 	int number = rdev->raid_disk;
 	struct md_rdev **rdevp;
-	struct raid10_info *p = conf->mirrors + number;
+	struct raid10_info *p;
 
 	print_conf(conf);
+	if (unlikely(number >= mddev->raid_disks))
+		return 0;
+	p = conf->mirrors + number;
 	if (rdev == p->rdev)
 		rdevp = &p->rdev;
 	else if (rdev == p->replacement)
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index e54d802ee0bb..19e497a7e747 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2864,10 +2864,10 @@ static void raid5_end_write_request(struct bio *bi)
 	if (!test_and_clear_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags))
 		clear_bit(R5_LOCKED, &sh->dev[i].flags);
 	set_bit(STRIPE_HANDLE, &sh->state);
-	raid5_release_stripe(sh);
 
 	if (sh->batch_head && sh != sh->batch_head)
 		raid5_release_stripe(sh->batch_head);
+	raid5_release_stripe(sh);
 }
 
 static void raid5_error(struct mddev *mddev, struct md_rdev *rdev)
@@ -8026,6 +8026,7 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	 */
 	if (rdev->saved_raid_disk >= 0 &&
 	    rdev->saved_raid_disk >= first &&
+	    rdev->saved_raid_disk <= last &&
 	    conf->disks[rdev->saved_raid_disk].rdev == NULL)
 		first = rdev->saved_raid_disk;
 
diff --git a/drivers/media/pci/tw686x/tw686x-core.c b/drivers/media/pci/tw686x/tw686x-core.c
index 6676e069b515..384d38754a4b 100644
--- a/drivers/media/pci/tw686x/tw686x-core.c
+++ b/drivers/media/pci/tw686x/tw686x-core.c
@@ -315,13 +315,6 @@ static int tw686x_probe(struct pci_dev *pci_dev,
 
 	spin_lock_init(&dev->lock);
 
-	err = request_irq(pci_dev->irq, tw686x_irq, IRQF_SHARED,
-			  dev->name, dev);
-	if (err < 0) {
-		dev_err(&pci_dev->dev, "unable to request interrupt\n");
-		goto iounmap;
-	}
-
 	timer_setup(&dev->dma_delay_timer, tw686x_dma_delay, 0);
 
 	/*
@@ -333,18 +326,23 @@ static int tw686x_probe(struct pci_dev *pci_dev,
 	err = tw686x_video_init(dev);
 	if (err) {
 		dev_err(&pci_dev->dev, "can't register video\n");
-		goto free_irq;
+		goto iounmap;
 	}
 
 	err = tw686x_audio_init(dev);
 	if (err)
 		dev_warn(&pci_dev->dev, "can't register audio\n");
 
+	err = request_irq(pci_dev->irq, tw686x_irq, IRQF_SHARED,
+			  dev->name, dev);
+	if (err < 0) {
+		dev_err(&pci_dev->dev, "unable to request interrupt\n");
+		goto iounmap;
+	}
+
 	pci_set_drvdata(pci_dev, dev);
 	return 0;
 
-free_irq:
-	free_irq(pci_dev->irq, dev);
 iounmap:
 	pci_iounmap(pci_dev, dev->mmio);
 free_region:
diff --git a/drivers/media/pci/tw686x/tw686x-video.c b/drivers/media/pci/tw686x/tw686x-video.c
index b227e9e78ebd..37a20fe24241 100644
--- a/drivers/media/pci/tw686x/tw686x-video.c
+++ b/drivers/media/pci/tw686x/tw686x-video.c
@@ -1282,8 +1282,10 @@ int tw686x_video_init(struct tw686x_dev *dev)
 		video_set_drvdata(vdev, vc);
 
 		err = video_register_device(vdev, VFL_TYPE_VIDEO, -1);
-		if (err < 0)
+		if (err < 0) {
+			video_device_release(vdev);
 			goto error;
+		}
 		vc->num = vdev->num;
 	}
 
diff --git a/drivers/media/platform/atmel/atmel-sama7g5-isc.c b/drivers/media/platform/atmel/atmel-sama7g5-isc.c
index 6a5d3f7ce75e..a4defc30cf41 100644
--- a/drivers/media/platform/atmel/atmel-sama7g5-isc.c
+++ b/drivers/media/platform/atmel/atmel-sama7g5-isc.c
@@ -587,11 +587,13 @@ static const struct dev_pm_ops microchip_xisc_dev_pm_ops = {
 	SET_RUNTIME_PM_OPS(xisc_runtime_suspend, xisc_runtime_resume, NULL)
 };
 
+#if IS_ENABLED(CONFIG_OF)
 static const struct of_device_id microchip_xisc_of_match[] = {
 	{ .compatible = "microchip,sama7g5-isc" },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, microchip_xisc_of_match);
+#endif
 
 static struct platform_driver microchip_xisc_driver = {
 	.probe	= microchip_xisc_probe,
diff --git a/drivers/media/platform/davinci/vpif.c b/drivers/media/platform/davinci/vpif.c
index 5658c7f148d7..8ffc01c606d0 100644
--- a/drivers/media/platform/davinci/vpif.c
+++ b/drivers/media/platform/davinci/vpif.c
@@ -41,6 +41,11 @@ MODULE_ALIAS("platform:" VPIF_DRIVER_NAME);
 #define VPIF_CH2_MAX_MODES	15
 #define VPIF_CH3_MAX_MODES	2
 
+struct vpif_data {
+	struct platform_device *capture;
+	struct platform_device *display;
+};
+
 DEFINE_SPINLOCK(vpif_lock);
 EXPORT_SYMBOL_GPL(vpif_lock);
 
@@ -423,11 +428,19 @@ int vpif_channel_getfid(u8 channel_id)
 }
 EXPORT_SYMBOL(vpif_channel_getfid);
 
+static void vpif_pdev_release(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+
+	kfree(pdev);
+}
+
 static int vpif_probe(struct platform_device *pdev)
 {
 	static struct resource	*res, *res_irq;
 	struct platform_device *pdev_capture, *pdev_display;
 	struct device_node *endpoint = NULL;
+	struct vpif_data *data;
 	int ret;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -435,6 +448,12 @@ static int vpif_probe(struct platform_device *pdev)
 	if (IS_ERR(vpif_base))
 		return PTR_ERR(vpif_base);
 
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, data);
+
 	pm_runtime_enable(&pdev->dev);
 	pm_runtime_get(&pdev->dev);
 
@@ -462,49 +481,75 @@ static int vpif_probe(struct platform_device *pdev)
 		goto err_put_rpm;
 	}
 
-	pdev_capture = devm_kzalloc(&pdev->dev, sizeof(*pdev_capture),
-				    GFP_KERNEL);
-	if (pdev_capture) {
-		pdev_capture->name = "vpif_capture";
-		pdev_capture->id = -1;
-		pdev_capture->resource = res_irq;
-		pdev_capture->num_resources = 1;
-		pdev_capture->dev.dma_mask = pdev->dev.dma_mask;
-		pdev_capture->dev.coherent_dma_mask = pdev->dev.coherent_dma_mask;
-		pdev_capture->dev.parent = &pdev->dev;
-		platform_device_register(pdev_capture);
-	} else {
-		dev_warn(&pdev->dev, "Unable to allocate memory for pdev_capture.\n");
+	pdev_capture = kzalloc(sizeof(*pdev_capture), GFP_KERNEL);
+	if (!pdev_capture) {
+		ret = -ENOMEM;
+		goto err_put_rpm;
 	}
 
-	pdev_display = devm_kzalloc(&pdev->dev, sizeof(*pdev_display),
-				    GFP_KERNEL);
-	if (pdev_display) {
-		pdev_display->name = "vpif_display";
-		pdev_display->id = -1;
-		pdev_display->resource = res_irq;
-		pdev_display->num_resources = 1;
-		pdev_display->dev.dma_mask = pdev->dev.dma_mask;
-		pdev_display->dev.coherent_dma_mask = pdev->dev.coherent_dma_mask;
-		pdev_display->dev.parent = &pdev->dev;
-		platform_device_register(pdev_display);
-	} else {
-		dev_warn(&pdev->dev, "Unable to allocate memory for pdev_display.\n");
+	pdev_capture->name = "vpif_capture";
+	pdev_capture->id = -1;
+	pdev_capture->resource = res_irq;
+	pdev_capture->num_resources = 1;
+	pdev_capture->dev.dma_mask = pdev->dev.dma_mask;
+	pdev_capture->dev.coherent_dma_mask = pdev->dev.coherent_dma_mask;
+	pdev_capture->dev.parent = &pdev->dev;
+	pdev_capture->dev.release = vpif_pdev_release;
+
+	ret = platform_device_register(pdev_capture);
+	if (ret)
+		goto err_put_pdev_capture;
+
+	pdev_display = kzalloc(sizeof(*pdev_display), GFP_KERNEL);
+	if (!pdev_display) {
+		ret = -ENOMEM;
+		goto err_put_pdev_capture;
 	}
 
+	pdev_display->name = "vpif_display";
+	pdev_display->id = -1;
+	pdev_display->resource = res_irq;
+	pdev_display->num_resources = 1;
+	pdev_display->dev.dma_mask = pdev->dev.dma_mask;
+	pdev_display->dev.coherent_dma_mask = pdev->dev.coherent_dma_mask;
+	pdev_display->dev.parent = &pdev->dev;
+	pdev_display->dev.release = vpif_pdev_release;
+
+	ret = platform_device_register(pdev_display);
+	if (ret)
+		goto err_put_pdev_display;
+
+	data->capture = pdev_capture;
+	data->display = pdev_display;
+
 	return 0;
 
+err_put_pdev_display:
+	platform_device_put(pdev_display);
+err_put_pdev_capture:
+	platform_device_put(pdev_capture);
 err_put_rpm:
 	pm_runtime_put(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
+	kfree(data);
 
 	return ret;
 }
 
 static int vpif_remove(struct platform_device *pdev)
 {
+	struct vpif_data *data = platform_get_drvdata(pdev);
+
+	if (data->capture)
+		platform_device_unregister(data->capture);
+	if (data->display)
+		platform_device_unregister(data->display);
+
 	pm_runtime_put(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
+
+	kfree(data);
+
 	return 0;
 }
 
diff --git a/drivers/media/platform/mtk-mdp/mtk_mdp_ipi.h b/drivers/media/platform/mtk-mdp/mtk_mdp_ipi.h
index 2cb8cecb3077..b810c96695c8 100644
--- a/drivers/media/platform/mtk-mdp/mtk_mdp_ipi.h
+++ b/drivers/media/platform/mtk-mdp/mtk_mdp_ipi.h
@@ -40,12 +40,14 @@ struct mdp_ipi_init {
  * @ipi_id        : IPI_MDP
  * @ap_inst       : AP mtk_mdp_vpu address
  * @vpu_inst_addr : VPU MDP instance address
+ * @padding       : Alignment padding
  */
 struct mdp_ipi_comm {
 	uint32_t msg_id;
 	uint32_t ipi_id;
 	uint64_t ap_inst;
 	uint32_t vpu_inst_addr;
+	uint32_t padding;
 };
 
 /**
diff --git a/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg.c b/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg.c
index 0da6d9341fd7..af912883dea7 100644
--- a/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg.c
+++ b/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg.c
@@ -116,7 +116,7 @@ static const struct mxc_jpeg_fmt mxc_formats[] = {
 	},
 	{
 		.name		= "YUV420", /* 1st plane = Y, 2nd plane = UV */
-		.fourcc		= V4L2_PIX_FMT_NV12,
+		.fourcc		= V4L2_PIX_FMT_NV12M,
 		.subsampling	= V4L2_JPEG_CHROMA_SUBSAMPLING_420,
 		.nc		= 3,
 		.depth		= 12, /* 6 bytes (4Y + UV) for 4 pixels */
@@ -842,6 +842,12 @@ static unsigned int mxc_jpeg_setup_cfg_stream(void *cfg_stream_vaddr,
 					      u32 fourcc,
 					      u16 w, u16 h)
 {
+	/*
+	 * There is a hardware issue that first 128 bytes of configuration data
+	 * can't be loaded correctly.
+	 * To avoid this issue, we need to write the configuration from
+	 * an offset which should be no less than 0x80 (128 bytes).
+	 */
 	unsigned int offset = 0x80;
 	u8 *cfg = (u8 *)cfg_stream_vaddr;
 	struct mxc_jpeg_sof *sof;
@@ -1286,12 +1292,24 @@ static int mxc_jpeg_queue_setup(struct vb2_queue *q,
 {
 	struct mxc_jpeg_ctx *ctx = vb2_get_drv_priv(q);
 	struct mxc_jpeg_q_data *q_data = NULL;
+	struct mxc_jpeg_q_data tmp_q;
 	int i;
 
 	q_data = mxc_jpeg_get_q_data(ctx, q->type);
 	if (!q_data)
 		return -EINVAL;
 
+	tmp_q.fmt = q_data->fmt;
+	tmp_q.w = q_data->w_adjusted;
+	tmp_q.h = q_data->h_adjusted;
+	for (i = 0; i < MXC_JPEG_MAX_PLANES; i++) {
+		tmp_q.bytesperline[i] = q_data->bytesperline[i];
+		tmp_q.sizeimage[i] = q_data->sizeimage[i];
+	}
+	mxc_jpeg_sizeimage(&tmp_q);
+	for (i = 0; i < MXC_JPEG_MAX_PLANES; i++)
+		tmp_q.sizeimage[i] = max(tmp_q.sizeimage[i], q_data->sizeimage[i]);
+
 	/* Handle CREATE_BUFS situation - *nplanes != 0 */
 	if (*nplanes) {
 		if (*nplanes != q_data->fmt->mem_planes)
@@ -1639,6 +1657,10 @@ static int mxc_jpeg_buf_prepare(struct vb2_buffer *vb)
 		vb2_set_plane_payload(vb, 0, 0);
 		vb2_set_plane_payload(vb, 1, 0);
 	}
+	if (V4L2_TYPE_IS_CAPTURE(vb->vb2_queue->type)) {
+		vb2_set_plane_payload(vb, 0, 0);
+		vb2_set_plane_payload(vb, 1, 0);
+	}
 	return 0;
 }
 
diff --git a/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg.h b/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg.h
index c965ec5de2ae..660dcaca8658 100644
--- a/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg.h
+++ b/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg.h
@@ -50,6 +50,7 @@ enum mxc_jpeg_mode {
  * @h_align:	horizontal alignment order (align to 2^h_align)
  * @v_align:	vertical alignment order (align to 2^v_align)
  * @flags:	flags describing format applicability
+ * @precision:  jpeg sample precision
  */
 struct mxc_jpeg_fmt {
 	const char				*name;
diff --git a/drivers/media/platform/omap3isp/ispstat.c b/drivers/media/platform/omap3isp/ispstat.c
index 5b9b57f4d9bf..68cf68dbcace 100644
--- a/drivers/media/platform/omap3isp/ispstat.c
+++ b/drivers/media/platform/omap3isp/ispstat.c
@@ -512,7 +512,7 @@ int omap3isp_stat_request_statistics(struct ispstat *stat,
 int omap3isp_stat_request_statistics_time32(struct ispstat *stat,
 					struct omap3isp_stat_data_time32 *data)
 {
-	struct omap3isp_stat_data data64;
+	struct omap3isp_stat_data data64 = { };
 	int ret;
 
 	ret = omap3isp_stat_request_statistics(stat, &data64);
@@ -521,7 +521,8 @@ int omap3isp_stat_request_statistics_time32(struct ispstat *stat,
 
 	data->ts.tv_sec = data64.ts.tv_sec;
 	data->ts.tv_usec = data64.ts.tv_usec;
-	memcpy(&data->buf, &data64.buf, sizeof(*data) - sizeof(data->ts));
+	data->buf = (uintptr_t)data64.buf;
+	memcpy(&data->frame, &data64.frame, sizeof(data->frame));
 
 	return 0;
 }
diff --git a/drivers/media/platform/qcom/venus/pm_helpers.c b/drivers/media/platform/qcom/venus/pm_helpers.c
index a591dd315ebc..03fc82cb3fea 100644
--- a/drivers/media/platform/qcom/venus/pm_helpers.c
+++ b/drivers/media/platform/qcom/venus/pm_helpers.c
@@ -875,7 +875,7 @@ static int vcodec_domains_get(struct venus_core *core)
 	}
 
 skip_pmdomains:
-	if (!core->has_opp_table)
+	if (!core->res->opp_pmdomain)
 		return 0;
 
 	/* Attach the power domain for setting performance state */
@@ -1007,6 +1007,10 @@ static int core_get_v4(struct venus_core *core)
 	if (ret)
 		return ret;
 
+	ret = vcodec_domains_get(core);
+	if (ret)
+		return ret;
+
 	if (core->res->opp_pmdomain) {
 		ret = devm_pm_opp_of_add_table(dev);
 		if (!ret) {
@@ -1017,10 +1021,6 @@ static int core_get_v4(struct venus_core *core)
 		}
 	}
 
-	ret = vcodec_domains_get(core);
-	if (ret)
-		return ret;
-
 	return 0;
 }
 
diff --git a/drivers/media/rc/ir_toy.c b/drivers/media/rc/ir_toy.c
index 7f394277478b..53ae19fa103a 100644
--- a/drivers/media/rc/ir_toy.c
+++ b/drivers/media/rc/ir_toy.c
@@ -310,7 +310,7 @@ static int irtoy_tx(struct rc_dev *rc, uint *txbuf, uint count)
 		buf[i] = cpu_to_be16(v);
 	}
 
-	buf[count] = cpu_to_be16(0xffff);
+	buf[count] = 0xffff;
 
 	irtoy->tx_buf = buf;
 	irtoy->tx_len = size;
diff --git a/drivers/media/rc/mceusb.c b/drivers/media/rc/mceusb.c
index 5f296f985b07..deb3db45a94c 100644
--- a/drivers/media/rc/mceusb.c
+++ b/drivers/media/rc/mceusb.c
@@ -1416,42 +1416,37 @@ static void mceusb_gen1_init(struct mceusb_dev *ir)
 {
 	int ret;
 	struct device *dev = ir->dev;
-	char *data;
-
-	data = kzalloc(USB_CTRL_MSG_SZ, GFP_KERNEL);
-	if (!data) {
-		dev_err(dev, "%s: memory allocation failed!", __func__);
-		return;
-	}
+	char data[USB_CTRL_MSG_SZ];
 
 	/*
 	 * This is a strange one. Windows issues a set address to the device
 	 * on the receive control pipe and expect a certain value pair back
 	 */
-	ret = usb_control_msg(ir->usbdev, usb_rcvctrlpipe(ir->usbdev, 0),
-			      USB_REQ_SET_ADDRESS, USB_TYPE_VENDOR, 0, 0,
-			      data, USB_CTRL_MSG_SZ, 3000);
+	ret = usb_control_msg_recv(ir->usbdev, 0, USB_REQ_SET_ADDRESS,
+				   USB_DIR_IN | USB_TYPE_VENDOR,
+				   0, 0, data, USB_CTRL_MSG_SZ, 3000,
+				   GFP_KERNEL);
 	dev_dbg(dev, "set address - ret = %d", ret);
 	dev_dbg(dev, "set address - data[0] = %d, data[1] = %d",
 						data[0], data[1]);
 
 	/* set feature: bit rate 38400 bps */
-	ret = usb_control_msg(ir->usbdev, usb_sndctrlpipe(ir->usbdev, 0),
-			      USB_REQ_SET_FEATURE, USB_TYPE_VENDOR,
-			      0xc04e, 0x0000, NULL, 0, 3000);
+	ret = usb_control_msg_send(ir->usbdev, 0,
+				   USB_REQ_SET_FEATURE, USB_TYPE_VENDOR,
+				   0xc04e, 0x0000, NULL, 0, 3000, GFP_KERNEL);
 
 	dev_dbg(dev, "set feature - ret = %d", ret);
 
 	/* bRequest 4: set char length to 8 bits */
-	ret = usb_control_msg(ir->usbdev, usb_sndctrlpipe(ir->usbdev, 0),
-			      4, USB_TYPE_VENDOR,
-			      0x0808, 0x0000, NULL, 0, 3000);
+	ret = usb_control_msg_send(ir->usbdev, 0,
+				   4, USB_TYPE_VENDOR,
+				   0x0808, 0x0000, NULL, 0, 3000, GFP_KERNEL);
 	dev_dbg(dev, "set char length - retB = %d", ret);
 
 	/* bRequest 2: set handshaking to use DTR/DSR */
-	ret = usb_control_msg(ir->usbdev, usb_sndctrlpipe(ir->usbdev, 0),
-			      2, USB_TYPE_VENDOR,
-			      0x0000, 0x0100, NULL, 0, 3000);
+	ret = usb_control_msg_send(ir->usbdev, 0,
+				   2, USB_TYPE_VENDOR,
+				   0x0000, 0x0100, NULL, 0, 3000, GFP_KERNEL);
 	dev_dbg(dev, "set handshake  - retC = %d", ret);
 
 	/* device resume */
@@ -1459,8 +1454,6 @@ static void mceusb_gen1_init(struct mceusb_dev *ir)
 
 	/* get hw/sw revision? */
 	mce_command_out(ir, GET_REVISION, sizeof(GET_REVISION));
-
-	kfree(data);
 }
 
 static void mceusb_gen2_init(struct mceusb_dev *ir)
diff --git a/drivers/media/usb/hdpvr/hdpvr-video.c b/drivers/media/usb/hdpvr/hdpvr-video.c
index 60e57e0f1927..fd7d2a9d0449 100644
--- a/drivers/media/usb/hdpvr/hdpvr-video.c
+++ b/drivers/media/usb/hdpvr/hdpvr-video.c
@@ -409,7 +409,7 @@ static ssize_t hdpvr_read(struct file *file, char __user *buffer, size_t count,
 	struct hdpvr_device *dev = video_drvdata(file);
 	struct hdpvr_buffer *buf = NULL;
 	struct urb *urb;
-	unsigned int ret = 0;
+	int ret = 0;
 	int rem, cnt;
 
 	if (*pos)
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-hdw.c b/drivers/media/usb/pvrusb2/pvrusb2-hdw.c
index fccd1798445d..d22ce328a279 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-hdw.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-hdw.c
@@ -2610,6 +2610,7 @@ struct pvr2_hdw *pvr2_hdw_create(struct usb_interface *intf,
 		del_timer_sync(&hdw->encoder_run_timer);
 		del_timer_sync(&hdw->encoder_wait_timer);
 		flush_work(&hdw->workpoll);
+		v4l2_device_unregister(&hdw->v4l2_dev);
 		usb_free_urb(hdw->ctl_read_urb);
 		usb_free_urb(hdw->ctl_write_urb);
 		kfree(hdw->ctl_read_buffer);
diff --git a/drivers/media/v4l2-core/v4l2-mem2mem.c b/drivers/media/v4l2-core/v4l2-mem2mem.c
index 3de683b5e06d..8aeed39c415f 100644
--- a/drivers/media/v4l2-core/v4l2-mem2mem.c
+++ b/drivers/media/v4l2-core/v4l2-mem2mem.c
@@ -924,7 +924,7 @@ static __poll_t v4l2_m2m_poll_for_data(struct file *file,
 	if ((!src_q->streaming || src_q->error ||
 	     list_empty(&src_q->queued_list)) &&
 	    (!dst_q->streaming || dst_q->error ||
-	     list_empty(&dst_q->queued_list)))
+	     (list_empty(&dst_q->queued_list) && !dst_q->last_buffer_dequeued)))
 		return EPOLLERR;
 
 	spin_lock_irqsave(&src_q->done_lock, flags);
diff --git a/drivers/memory/renesas-rpc-if.c b/drivers/memory/renesas-rpc-if.c
index 3a416705f61c..c77b23b68a93 100644
--- a/drivers/memory/renesas-rpc-if.c
+++ b/drivers/memory/renesas-rpc-if.c
@@ -199,7 +199,6 @@ static int rpcif_reg_read(void *context, unsigned int reg, unsigned int *val)
 
 	*val = readl(rpc->base + reg);
 	return 0;
-
 }
 
 static int rpcif_reg_write(void *context, unsigned int reg, unsigned int val)
@@ -577,6 +576,48 @@ err_out:
 }
 EXPORT_SYMBOL(rpcif_manual_xfer);
 
+static void memcpy_fromio_readw(void *to,
+				const void __iomem *from,
+				size_t count)
+{
+	const int maxw = (IS_ENABLED(CONFIG_64BIT)) ? 8 : 4;
+	u8 buf[2];
+
+	if (count && ((unsigned long)from & 1)) {
+		*(u16 *)buf = __raw_readw((void __iomem *)((unsigned long)from & ~1));
+		*(u8 *)to = buf[1];
+		from++;
+		to++;
+		count--;
+	}
+	while (count >= 2 && !IS_ALIGNED((unsigned long)from, maxw)) {
+		*(u16 *)to = __raw_readw(from);
+		from += 2;
+		to += 2;
+		count -= 2;
+	}
+	while (count >= maxw) {
+#ifdef CONFIG_64BIT
+		*(u64 *)to = __raw_readq(from);
+#else
+		*(u32 *)to = __raw_readl(from);
+#endif
+		from += maxw;
+		to += maxw;
+		count -= maxw;
+	}
+	while (count >= 2) {
+		*(u16 *)to = __raw_readw(from);
+		from += 2;
+		to += 2;
+		count -= 2;
+	}
+	if (count) {
+		*(u16 *)buf = __raw_readw(from);
+		*(u8 *)to = buf[0];
+	}
+}
+
 ssize_t rpcif_dirmap_read(struct rpcif *rpc, u64 offs, size_t len, void *buf)
 {
 	loff_t from = offs & (RPCIF_DIRMAP_SIZE - 1);
@@ -598,7 +639,10 @@ ssize_t rpcif_dirmap_read(struct rpcif *rpc, u64 offs, size_t len, void *buf)
 	regmap_write(rpc->regmap, RPCIF_DRDMCR, rpc->dummy);
 	regmap_write(rpc->regmap, RPCIF_DRDRENR, rpc->ddr);
 
-	memcpy_fromio(buf, rpc->dirmap + from, len);
+	if (rpc->bus_size == 2)
+		memcpy_fromio_readw(buf, rpc->dirmap + from, len);
+	else
+		memcpy_fromio(buf, rpc->dirmap + from, len);
 
 	pm_runtime_put(rpc->dev);
 
diff --git a/drivers/memstick/core/ms_block.c b/drivers/memstick/core/ms_block.c
index 487e4cc2951e..f854822f84d6 100644
--- a/drivers/memstick/core/ms_block.c
+++ b/drivers/memstick/core/ms_block.c
@@ -1341,17 +1341,17 @@ static int msb_ftl_initialize(struct msb_data *msb)
 	msb->zone_count = msb->block_count / MS_BLOCKS_IN_ZONE;
 	msb->logical_block_count = msb->zone_count * 496 - 2;
 
-	msb->used_blocks_bitmap = kzalloc(msb->block_count / 8, GFP_KERNEL);
-	msb->erased_blocks_bitmap = kzalloc(msb->block_count / 8, GFP_KERNEL);
+	msb->used_blocks_bitmap = bitmap_zalloc(msb->block_count, GFP_KERNEL);
+	msb->erased_blocks_bitmap = bitmap_zalloc(msb->block_count, GFP_KERNEL);
 	msb->lba_to_pba_table =
 		kmalloc_array(msb->logical_block_count, sizeof(u16),
 			      GFP_KERNEL);
 
 	if (!msb->used_blocks_bitmap || !msb->lba_to_pba_table ||
 						!msb->erased_blocks_bitmap) {
-		kfree(msb->used_blocks_bitmap);
+		bitmap_free(msb->used_blocks_bitmap);
+		bitmap_free(msb->erased_blocks_bitmap);
 		kfree(msb->lba_to_pba_table);
-		kfree(msb->erased_blocks_bitmap);
 		return -ENOMEM;
 	}
 
@@ -1962,7 +1962,8 @@ static int msb_bd_open(struct block_device *bdev, fmode_t mode)
 static void msb_data_clear(struct msb_data *msb)
 {
 	kfree(msb->boot_page);
-	kfree(msb->used_blocks_bitmap);
+	bitmap_free(msb->used_blocks_bitmap);
+	bitmap_free(msb->erased_blocks_bitmap);
 	kfree(msb->lba_to_pba_table);
 	kfree(msb->cache);
 	msb->card = NULL;
diff --git a/drivers/mfd/max77620.c b/drivers/mfd/max77620.c
index fec2096474ad..a6661e07035b 100644
--- a/drivers/mfd/max77620.c
+++ b/drivers/mfd/max77620.c
@@ -419,9 +419,11 @@ static int max77620_initialise_fps(struct max77620_chip *chip)
 		ret = max77620_config_fps(chip, fps_child);
 		if (ret < 0) {
 			of_node_put(fps_child);
+			of_node_put(fps_np);
 			return ret;
 		}
 	}
+	of_node_put(fps_np);
 
 	config = chip->enable_global_lpm ? MAX77620_ONOFFCNFG2_SLP_LPM_MSK : 0;
 	ret = regmap_update_bits(chip->rmap, MAX77620_REG_ONOFFCNFG2,
diff --git a/drivers/mfd/t7l66xb.c b/drivers/mfd/t7l66xb.c
index 5369c67e3280..663ffd4b8570 100644
--- a/drivers/mfd/t7l66xb.c
+++ b/drivers/mfd/t7l66xb.c
@@ -397,11 +397,8 @@ err_noirq:
 
 static int t7l66xb_remove(struct platform_device *dev)
 {
-	struct t7l66xb_platform_data *pdata = dev_get_platdata(&dev->dev);
 	struct t7l66xb *t7l66xb = platform_get_drvdata(dev);
-	int ret;
 
-	ret = pdata->disable(dev);
 	clk_disable_unprepare(t7l66xb->clk48m);
 	clk_put(t7l66xb->clk48m);
 	clk_disable_unprepare(t7l66xb->clk32k);
@@ -412,8 +409,7 @@ static int t7l66xb_remove(struct platform_device *dev)
 	mfd_remove_devices(&dev->dev);
 	kfree(t7l66xb);
 
-	return ret;
-
+	return 0;
 }
 
 static struct platform_driver t7l66xb_platform_driver = {
diff --git a/drivers/misc/cardreader/rtsx_pcr.c b/drivers/misc/cardreader/rtsx_pcr.c
index 5121edb0d9ef..62fdbbd55e74 100644
--- a/drivers/misc/cardreader/rtsx_pcr.c
+++ b/drivers/misc/cardreader/rtsx_pcr.c
@@ -1581,7 +1581,7 @@ static int rtsx_pci_probe(struct pci_dev *pcidev,
 	pcr->remap_addr = ioremap(base, len);
 	if (!pcr->remap_addr) {
 		ret = -ENOMEM;
-		goto free_handle;
+		goto free_idr;
 	}
 
 	pcr->rtsx_resv_buf = dma_alloc_coherent(&(pcidev->dev),
@@ -1651,6 +1651,10 @@ disable_msi:
 			pcr->rtsx_resv_buf, pcr->rtsx_resv_buf_addr);
 unmap:
 	iounmap(pcr->remap_addr);
+free_idr:
+	spin_lock(&rtsx_pci_lock);
+	idr_remove(&rtsx_pci_idr, pcr->id);
+	spin_unlock(&rtsx_pci_lock);
 free_handle:
 	kfree(handle);
 free_pcr:
diff --git a/drivers/misc/cardreader/rtsx_usb.c b/drivers/misc/cardreader/rtsx_usb.c
index 1ef9b61077c4..f150d8769f19 100644
--- a/drivers/misc/cardreader/rtsx_usb.c
+++ b/drivers/misc/cardreader/rtsx_usb.c
@@ -631,16 +631,20 @@ static int rtsx_usb_probe(struct usb_interface *intf,
 
 	ucr->pusb_dev = usb_dev;
 
-	ucr->iobuf = usb_alloc_coherent(ucr->pusb_dev, IOBUF_SIZE,
-			GFP_KERNEL, &ucr->iobuf_dma);
-	if (!ucr->iobuf)
+	ucr->cmd_buf = kmalloc(IOBUF_SIZE, GFP_KERNEL);
+	if (!ucr->cmd_buf)
 		return -ENOMEM;
 
+	ucr->rsp_buf = kmalloc(IOBUF_SIZE, GFP_KERNEL);
+	if (!ucr->rsp_buf) {
+		ret = -ENOMEM;
+		goto out_free_cmd_buf;
+	}
+
 	usb_set_intfdata(intf, ucr);
 
 	ucr->vendor_id = id->idVendor;
 	ucr->product_id = id->idProduct;
-	ucr->cmd_buf = ucr->rsp_buf = ucr->iobuf;
 
 	mutex_init(&ucr->dev_mutex);
 
@@ -668,8 +672,11 @@ static int rtsx_usb_probe(struct usb_interface *intf,
 
 out_init_fail:
 	usb_set_intfdata(ucr->pusb_intf, NULL);
-	usb_free_coherent(ucr->pusb_dev, IOBUF_SIZE, ucr->iobuf,
-			ucr->iobuf_dma);
+	kfree(ucr->rsp_buf);
+	ucr->rsp_buf = NULL;
+out_free_cmd_buf:
+	kfree(ucr->cmd_buf);
+	ucr->cmd_buf = NULL;
 	return ret;
 }
 
@@ -682,8 +689,12 @@ static void rtsx_usb_disconnect(struct usb_interface *intf)
 	mfd_remove_devices(&intf->dev);
 
 	usb_set_intfdata(ucr->pusb_intf, NULL);
-	usb_free_coherent(ucr->pusb_dev, IOBUF_SIZE, ucr->iobuf,
-			ucr->iobuf_dma);
+
+	kfree(ucr->cmd_buf);
+	ucr->cmd_buf = NULL;
+
+	kfree(ucr->rsp_buf);
+	ucr->rsp_buf = NULL;
 }
 
 #ifdef CONFIG_PM
diff --git a/drivers/misc/cxl/irq.c b/drivers/misc/cxl/irq.c
index 4cb829d5d873..2e4dcfebf19a 100644
--- a/drivers/misc/cxl/irq.c
+++ b/drivers/misc/cxl/irq.c
@@ -349,6 +349,7 @@ int afu_allocate_irqs(struct cxl_context *ctx, u32 count)
 
 out:
 	cxl_ops->release_irq_ranges(&ctx->irqs, ctx->afu->adapter);
+	bitmap_free(ctx->irq_bitmap);
 	afu_irq_name_free(ctx);
 	return -ENOMEM;
 }
diff --git a/drivers/misc/eeprom/idt_89hpesx.c b/drivers/misc/eeprom/idt_89hpesx.c
index b0cff4b152da..7f430742ce2b 100644
--- a/drivers/misc/eeprom/idt_89hpesx.c
+++ b/drivers/misc/eeprom/idt_89hpesx.c
@@ -909,14 +909,18 @@ static ssize_t idt_dbgfs_csr_write(struct file *filep, const char __user *ubuf,
 	u32 csraddr, csrval;
 	char *buf;
 
+	if (*offp)
+		return 0;
+
 	/* Copy data from User-space */
 	buf = kmalloc(count + 1, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
-	ret = simple_write_to_buffer(buf, count, offp, ubuf, count);
-	if (ret < 0)
+	if (copy_from_user(buf, ubuf, count)) {
+		ret = -EFAULT;
 		goto free_buf;
+	}
 	buf[count] = 0;
 
 	/* Find position of colon in the buffer */
diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index c7134d2cf69a..cf5705776c4f 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -1550,7 +1550,12 @@ static int fastrpc_cb_probe(struct platform_device *pdev)
 	of_property_read_u32(dev->of_node, "qcom,nsessions", &sessions);
 
 	spin_lock_irqsave(&cctx->lock, flags);
-	sess = &cctx->session[cctx->sesscount];
+	if (cctx->sesscount >= FASTRPC_MAX_SESSIONS) {
+		dev_err(&pdev->dev, "too many sessions\n");
+		spin_unlock_irqrestore(&cctx->lock, flags);
+		return -ENOSPC;
+	}
+	sess = &cctx->session[cctx->sesscount++];
 	sess->used = false;
 	sess->valid = true;
 	sess->dev = dev;
@@ -1563,13 +1568,12 @@ static int fastrpc_cb_probe(struct platform_device *pdev)
 		struct fastrpc_session_ctx *dup_sess;
 
 		for (i = 1; i < sessions; i++) {
-			if (cctx->sesscount++ >= FASTRPC_MAX_SESSIONS)
+			if (cctx->sesscount >= FASTRPC_MAX_SESSIONS)
 				break;
-			dup_sess = &cctx->session[cctx->sesscount];
+			dup_sess = &cctx->session[cctx->sesscount++];
 			memcpy(dup_sess, sess, sizeof(*dup_sess));
 		}
 	}
-	cctx->sesscount++;
 	spin_unlock_irqrestore(&cctx->lock, flags);
 	rc = dma_set_mask(dev, DMA_BIT_MASK(32));
 	if (rc) {
diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index 14da87b38e83..8132200dca67 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -3318,19 +3318,19 @@ static void gaudi_init_nic_qman(struct hl_device *hdev, u32 nic_offset,
 	u32 nic_qm_err_cfg, irq_handler_offset;
 	u32 q_off;
 
-	mtr_base_en_lo = lower_32_bits(CFG_BASE +
+	mtr_base_en_lo = lower_32_bits((CFG_BASE & U32_MAX) +
 			mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_MON_PAY_ADDRL_0);
 	mtr_base_en_hi = upper_32_bits(CFG_BASE +
 				mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_MON_PAY_ADDRL_0);
-	so_base_en_lo = lower_32_bits(CFG_BASE +
+	so_base_en_lo = lower_32_bits((CFG_BASE & U32_MAX) +
 				mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_SOB_OBJ_0);
 	so_base_en_hi = upper_32_bits(CFG_BASE +
 				mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_SOB_OBJ_0);
-	mtr_base_ws_lo = lower_32_bits(CFG_BASE +
+	mtr_base_ws_lo = lower_32_bits((CFG_BASE & U32_MAX) +
 				mmSYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_PAY_ADDRL_0);
 	mtr_base_ws_hi = upper_32_bits(CFG_BASE +
 				mmSYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_PAY_ADDRL_0);
-	so_base_ws_lo = lower_32_bits(CFG_BASE +
+	so_base_ws_lo = lower_32_bits((CFG_BASE & U32_MAX) +
 				mmSYNC_MNGR_W_S_SYNC_MNGR_OBJS_SOB_OBJ_0);
 	so_base_ws_hi = upper_32_bits(CFG_BASE +
 				mmSYNC_MNGR_W_S_SYNC_MNGR_OBJS_SOB_OBJ_0);
@@ -5744,15 +5744,17 @@ static int gaudi_parse_cb_no_ext_queue(struct hl_device *hdev,
 {
 	struct asic_fixed_properties *asic_prop = &hdev->asic_prop;
 	struct gaudi_device *gaudi = hdev->asic_specific;
-	u32 nic_mask_q_id = 1 << (HW_CAP_NIC_SHIFT +
-		((parser->hw_queue_id - GAUDI_QUEUE_ID_NIC_0_0) >> 2));
+	u32 nic_queue_offset, nic_mask_q_id;
 
 	if ((parser->hw_queue_id >= GAUDI_QUEUE_ID_NIC_0_0) &&
-			(parser->hw_queue_id <= GAUDI_QUEUE_ID_NIC_9_3) &&
-			(!(gaudi->hw_cap_initialized & nic_mask_q_id))) {
-		dev_err(hdev->dev, "h/w queue %d is disabled\n",
-				parser->hw_queue_id);
-		return -EINVAL;
+			(parser->hw_queue_id <= GAUDI_QUEUE_ID_NIC_9_3)) {
+		nic_queue_offset = parser->hw_queue_id - GAUDI_QUEUE_ID_NIC_0_0;
+		nic_mask_q_id = 1 << (HW_CAP_NIC_SHIFT + (nic_queue_offset >> 2));
+
+		if (!(gaudi->hw_cap_initialized & nic_mask_q_id)) {
+			dev_err(hdev->dev, "h/w queue %d is disabled\n", parser->hw_queue_id);
+			return -EINVAL;
+		}
 	}
 
 	/* For internal queue jobs just check if CB address is valid */
diff --git a/drivers/misc/uacce/uacce.c b/drivers/misc/uacce/uacce.c
index 488eeb2811ae..976d051071dc 100644
--- a/drivers/misc/uacce/uacce.c
+++ b/drivers/misc/uacce/uacce.c
@@ -9,43 +9,38 @@
 
 static struct class *uacce_class;
 static dev_t uacce_devt;
-static DEFINE_MUTEX(uacce_mutex);
 static DEFINE_XARRAY_ALLOC(uacce_xa);
 
-static int uacce_start_queue(struct uacce_queue *q)
+/*
+ * If the parent driver or the device disappears, the queue state is invalid and
+ * ops are not usable anymore.
+ */
+static bool uacce_queue_is_valid(struct uacce_queue *q)
 {
-	int ret = 0;
+	return q->state == UACCE_Q_INIT || q->state == UACCE_Q_STARTED;
+}
 
-	mutex_lock(&uacce_mutex);
+static int uacce_start_queue(struct uacce_queue *q)
+{
+	int ret;
 
-	if (q->state != UACCE_Q_INIT) {
-		ret = -EINVAL;
-		goto out_with_lock;
-	}
+	if (q->state != UACCE_Q_INIT)
+		return -EINVAL;
 
 	if (q->uacce->ops->start_queue) {
 		ret = q->uacce->ops->start_queue(q);
 		if (ret < 0)
-			goto out_with_lock;
+			return ret;
 	}
 
 	q->state = UACCE_Q_STARTED;
-
-out_with_lock:
-	mutex_unlock(&uacce_mutex);
-
-	return ret;
+	return 0;
 }
 
 static int uacce_put_queue(struct uacce_queue *q)
 {
 	struct uacce_device *uacce = q->uacce;
 
-	mutex_lock(&uacce_mutex);
-
-	if (q->state == UACCE_Q_ZOMBIE)
-		goto out;
-
 	if ((q->state == UACCE_Q_STARTED) && uacce->ops->stop_queue)
 		uacce->ops->stop_queue(q);
 
@@ -54,8 +49,6 @@ static int uacce_put_queue(struct uacce_queue *q)
 		uacce->ops->put_queue(q);
 
 	q->state = UACCE_Q_ZOMBIE;
-out:
-	mutex_unlock(&uacce_mutex);
 
 	return 0;
 }
@@ -65,20 +58,36 @@ static long uacce_fops_unl_ioctl(struct file *filep,
 {
 	struct uacce_queue *q = filep->private_data;
 	struct uacce_device *uacce = q->uacce;
+	long ret = -ENXIO;
+
+	/*
+	 * uacce->ops->ioctl() may take the mmap_lock when copying arg to/from
+	 * user. Avoid a circular lock dependency with uacce_fops_mmap(), which
+	 * gets called with mmap_lock held, by taking uacce->mutex instead of
+	 * q->mutex. Doing this in uacce_fops_mmap() is not possible because
+	 * uacce_fops_open() calls iommu_sva_bind_device(), which takes
+	 * mmap_lock, while holding uacce->mutex.
+	 */
+	mutex_lock(&uacce->mutex);
+	if (!uacce_queue_is_valid(q))
+		goto out_unlock;
 
 	switch (cmd) {
 	case UACCE_CMD_START_Q:
-		return uacce_start_queue(q);
-
+		ret = uacce_start_queue(q);
+		break;
 	case UACCE_CMD_PUT_Q:
-		return uacce_put_queue(q);
-
+		ret = uacce_put_queue(q);
+		break;
 	default:
-		if (!uacce->ops->ioctl)
-			return -EINVAL;
-
-		return uacce->ops->ioctl(q, cmd, arg);
+		if (uacce->ops->ioctl)
+			ret = uacce->ops->ioctl(q, cmd, arg);
+		else
+			ret = -EINVAL;
 	}
+out_unlock:
+	mutex_unlock(&uacce->mutex);
+	return ret;
 }
 
 #ifdef CONFIG_COMPAT
@@ -136,6 +145,13 @@ static int uacce_fops_open(struct inode *inode, struct file *filep)
 	if (!q)
 		return -ENOMEM;
 
+	mutex_lock(&uacce->mutex);
+
+	if (!uacce->parent) {
+		ret = -EINVAL;
+		goto out_with_mem;
+	}
+
 	ret = uacce_bind_queue(uacce, q);
 	if (ret)
 		goto out_with_mem;
@@ -152,10 +168,9 @@ static int uacce_fops_open(struct inode *inode, struct file *filep)
 	filep->private_data = q;
 	uacce->inode = inode;
 	q->state = UACCE_Q_INIT;
-
-	mutex_lock(&uacce->queues_lock);
+	mutex_init(&q->mutex);
 	list_add(&q->list, &uacce->queues);
-	mutex_unlock(&uacce->queues_lock);
+	mutex_unlock(&uacce->mutex);
 
 	return 0;
 
@@ -163,18 +178,20 @@ out_with_bond:
 	uacce_unbind_queue(q);
 out_with_mem:
 	kfree(q);
+	mutex_unlock(&uacce->mutex);
 	return ret;
 }
 
 static int uacce_fops_release(struct inode *inode, struct file *filep)
 {
 	struct uacce_queue *q = filep->private_data;
+	struct uacce_device *uacce = q->uacce;
 
-	mutex_lock(&q->uacce->queues_lock);
-	list_del(&q->list);
-	mutex_unlock(&q->uacce->queues_lock);
+	mutex_lock(&uacce->mutex);
 	uacce_put_queue(q);
 	uacce_unbind_queue(q);
+	list_del(&q->list);
+	mutex_unlock(&uacce->mutex);
 	kfree(q);
 
 	return 0;
@@ -217,10 +234,9 @@ static int uacce_fops_mmap(struct file *filep, struct vm_area_struct *vma)
 	vma->vm_private_data = q;
 	qfr->type = type;
 
-	mutex_lock(&uacce_mutex);
-
-	if (q->state != UACCE_Q_INIT && q->state != UACCE_Q_STARTED) {
-		ret = -EINVAL;
+	mutex_lock(&q->mutex);
+	if (!uacce_queue_is_valid(q)) {
+		ret = -ENXIO;
 		goto out_with_lock;
 	}
 
@@ -248,12 +264,12 @@ static int uacce_fops_mmap(struct file *filep, struct vm_area_struct *vma)
 	}
 
 	q->qfrs[type] = qfr;
-	mutex_unlock(&uacce_mutex);
+	mutex_unlock(&q->mutex);
 
 	return ret;
 
 out_with_lock:
-	mutex_unlock(&uacce_mutex);
+	mutex_unlock(&q->mutex);
 	kfree(qfr);
 	return ret;
 }
@@ -262,12 +278,20 @@ static __poll_t uacce_fops_poll(struct file *file, poll_table *wait)
 {
 	struct uacce_queue *q = file->private_data;
 	struct uacce_device *uacce = q->uacce;
+	__poll_t ret = 0;
+
+	mutex_lock(&q->mutex);
+	if (!uacce_queue_is_valid(q))
+		goto out_unlock;
 
 	poll_wait(file, &q->wait, wait);
+
 	if (uacce->ops->is_q_updated && uacce->ops->is_q_updated(q))
-		return EPOLLIN | EPOLLRDNORM;
+		ret = EPOLLIN | EPOLLRDNORM;
 
-	return 0;
+out_unlock:
+	mutex_unlock(&q->mutex);
+	return ret;
 }
 
 static const struct file_operations uacce_fops = {
@@ -450,7 +474,7 @@ struct uacce_device *uacce_alloc(struct device *parent,
 		goto err_with_uacce;
 
 	INIT_LIST_HEAD(&uacce->queues);
-	mutex_init(&uacce->queues_lock);
+	mutex_init(&uacce->mutex);
 	device_initialize(&uacce->dev);
 	uacce->dev.devt = MKDEV(MAJOR(uacce_devt), uacce->dev_id);
 	uacce->dev.class = uacce_class;
@@ -507,13 +531,23 @@ void uacce_remove(struct uacce_device *uacce)
 	if (uacce->inode)
 		unmap_mapping_range(uacce->inode->i_mapping, 0, 0, 1);
 
+	/*
+	 * uacce_fops_open() may be running concurrently, even after we remove
+	 * the cdev. Holding uacce->mutex ensures that open() does not obtain a
+	 * removed uacce device.
+	 */
+	mutex_lock(&uacce->mutex);
 	/* ensure no open queue remains */
-	mutex_lock(&uacce->queues_lock);
 	list_for_each_entry_safe(q, next_q, &uacce->queues, list) {
+		/*
+		 * Taking q->mutex ensures that fops do not use the defunct
+		 * uacce->ops after the queue is disabled.
+		 */
+		mutex_lock(&q->mutex);
 		uacce_put_queue(q);
+		mutex_unlock(&q->mutex);
 		uacce_unbind_queue(q);
 	}
-	mutex_unlock(&uacce->queues_lock);
 
 	/* disable sva now since no opened queues */
 	uacce_disable_sva(uacce);
@@ -521,6 +555,13 @@ void uacce_remove(struct uacce_device *uacce)
 	if (uacce->cdev)
 		cdev_device_del(uacce->cdev, &uacce->dev);
 	xa_erase(&uacce_xa, uacce->dev_id);
+	/*
+	 * uacce exists as long as there are open fds, but ops will be freed
+	 * now. Ensure that bugs cause NULL deref rather than use-after-free.
+	 */
+	uacce->ops = NULL;
+	uacce->parent = NULL;
+	mutex_unlock(&uacce->mutex);
 	put_device(&uacce->dev);
 }
 EXPORT_SYMBOL_GPL(uacce_remove);
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index a196116444a3..3222a9d0c245 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -175,7 +175,7 @@ static inline int mmc_blk_part_switch(struct mmc_card *card,
 				      unsigned int part_type);
 static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq,
 			       struct mmc_card *card,
-			       int disable_multi,
+			       int recovery_mode,
 			       struct mmc_queue *mq);
 static void mmc_blk_hsq_req_done(struct mmc_request *mrq);
 
@@ -1285,7 +1285,7 @@ static void mmc_blk_eval_resp_error(struct mmc_blk_request *brq)
 }
 
 static void mmc_blk_data_prep(struct mmc_queue *mq, struct mmc_queue_req *mqrq,
-			      int disable_multi, bool *do_rel_wr_p,
+			      int recovery_mode, bool *do_rel_wr_p,
 			      bool *do_data_tag_p)
 {
 	struct mmc_blk_data *md = mq->blkdata;
@@ -1351,12 +1351,12 @@ static void mmc_blk_data_prep(struct mmc_queue *mq, struct mmc_queue_req *mqrq,
 			brq->data.blocks--;
 
 		/*
-		 * After a read error, we redo the request one sector
+		 * After a read error, we redo the request one (native) sector
 		 * at a time in order to accurately determine which
 		 * sectors can be read successfully.
 		 */
-		if (disable_multi)
-			brq->data.blocks = 1;
+		if (recovery_mode)
+			brq->data.blocks = queue_physical_block_size(mq->queue) >> 9;
 
 		/*
 		 * Some controllers have HW issues while operating
@@ -1573,7 +1573,7 @@ static int mmc_blk_cqe_issue_rw_rq(struct mmc_queue *mq, struct request *req)
 
 static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq,
 			       struct mmc_card *card,
-			       int disable_multi,
+			       int recovery_mode,
 			       struct mmc_queue *mq)
 {
 	u32 readcmd, writecmd;
@@ -1582,7 +1582,7 @@ static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq,
 	struct mmc_blk_data *md = mq->blkdata;
 	bool do_rel_wr, do_data_tag;
 
-	mmc_blk_data_prep(mq, mqrq, disable_multi, &do_rel_wr, &do_data_tag);
+	mmc_blk_data_prep(mq, mqrq, recovery_mode, &do_rel_wr, &do_data_tag);
 
 	brq->mrq.cmd = &brq->cmd;
 
@@ -1673,7 +1673,7 @@ static int mmc_blk_fix_state(struct mmc_card *card, struct request *req)
 
 #define MMC_READ_SINGLE_RETRIES	2
 
-/* Single sector read during recovery */
+/* Single (native) sector read during recovery */
 static void mmc_blk_read_single(struct mmc_queue *mq, struct request *req)
 {
 	struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
@@ -1681,6 +1681,7 @@ static void mmc_blk_read_single(struct mmc_queue *mq, struct request *req)
 	struct mmc_card *card = mq->card;
 	struct mmc_host *host = card->host;
 	blk_status_t error = BLK_STS_OK;
+	size_t bytes_per_read = queue_physical_block_size(mq->queue);
 
 	do {
 		u32 status;
@@ -1715,13 +1716,13 @@ static void mmc_blk_read_single(struct mmc_queue *mq, struct request *req)
 		else
 			error = BLK_STS_OK;
 
-	} while (blk_update_request(req, error, 512));
+	} while (blk_update_request(req, error, bytes_per_read));
 
 	return;
 
 error_exit:
 	mrq->data->bytes_xfered = 0;
-	blk_update_request(req, BLK_STS_IOERR, 512);
+	blk_update_request(req, BLK_STS_IOERR, bytes_per_read);
 	/* Let it try the remaining request again */
 	if (mqrq->retries > MMC_MAX_RETRIES - 1)
 		mqrq->retries = MMC_MAX_RETRIES - 1;
@@ -1862,10 +1863,9 @@ static void mmc_blk_mq_rw_recovery(struct mmc_queue *mq, struct request *req)
 		return;
 	}
 
-	/* FIXME: Missing single sector read for large sector size */
-	if (!mmc_large_sector(card) && rq_data_dir(req) == READ &&
-	    brq->data.blocks > 1) {
-		/* Read one sector at a time */
+	if (rq_data_dir(req) == READ && brq->data.blocks >
+			queue_physical_block_size(mq->queue) >> 9) {
+		/* Read one (native) sector at a time */
 		mmc_blk_read_single(mq, req);
 		return;
 	}
diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
index 44e134fa04af..7e8d4abed602 100644
--- a/drivers/mmc/core/sd.c
+++ b/drivers/mmc/core/sd.c
@@ -942,16 +942,17 @@ int mmc_sd_setup_card(struct mmc_host *host, struct mmc_card *card,
 
 		/* Erase init depends on CSD and SSR */
 		mmc_init_erase(card);
-
-		/*
-		 * Fetch switch information from card.
-		 */
-		err = mmc_read_switch(card);
-		if (err)
-			return err;
 	}
 
 	/*
+	 * Fetch switch information from card. Note, sd3_bus_mode can change if
+	 * voltage switch outcome changes, so do this always.
+	 */
+	err = mmc_read_switch(card);
+	if (err)
+		return err;
+
+	/*
 	 * For SPI, enable CRC as appropriate.
 	 * This CRC enable is located AFTER the reading of the
 	 * card registers because some SDHC cards are not able
@@ -1473,26 +1474,15 @@ retry:
 	if (!v18_fixup_failed && !mmc_host_is_spi(host) && mmc_host_uhs(host) &&
 	    mmc_sd_card_using_v18(card) &&
 	    host->ios.signal_voltage != MMC_SIGNAL_VOLTAGE_180) {
-		/*
-		 * Re-read switch information in case it has changed since
-		 * oldcard was initialized.
-		 */
-		if (oldcard) {
-			err = mmc_read_switch(card);
-			if (err)
-				goto free_card;
-		}
-		if (mmc_sd_card_using_v18(card)) {
-			if (mmc_host_set_uhs_voltage(host) ||
-			    mmc_sd_init_uhs_card(card)) {
-				v18_fixup_failed = true;
-				mmc_power_cycle(host, ocr);
-				if (!oldcard)
-					mmc_remove_card(card);
-				goto retry;
-			}
-			goto done;
+		if (mmc_host_set_uhs_voltage(host) ||
+		    mmc_sd_init_uhs_card(card)) {
+			v18_fixup_failed = true;
+			mmc_power_cycle(host, ocr);
+			if (!oldcard)
+				mmc_remove_card(card);
+			goto retry;
 		}
+		goto cont;
 	}
 
 	/* Initialization sequence for UHS-I cards */
@@ -1527,7 +1517,7 @@ retry:
 			mmc_set_bus_width(host, MMC_BUS_WIDTH_4);
 		}
 	}
-
+cont:
 	if (!oldcard) {
 		/* Read/parse the extension registers. */
 		err = sd_read_ext_regs(card);
@@ -1559,7 +1549,7 @@ retry:
 		err = -EINVAL;
 		goto free_card;
 	}
-done:
+
 	host->card = card;
 	return 0;
 
diff --git a/drivers/mmc/host/cavium-octeon.c b/drivers/mmc/host/cavium-octeon.c
index 2c4b2df52adb..12dca91a8ef6 100644
--- a/drivers/mmc/host/cavium-octeon.c
+++ b/drivers/mmc/host/cavium-octeon.c
@@ -277,6 +277,7 @@ static int octeon_mmc_probe(struct platform_device *pdev)
 		if (ret) {
 			dev_err(&pdev->dev, "Error populating slots\n");
 			octeon_mmc_set_shared_power(host, 0);
+			of_node_put(cn);
 			goto error;
 		}
 		i++;
diff --git a/drivers/mmc/host/cavium-thunderx.c b/drivers/mmc/host/cavium-thunderx.c
index 76013bbbcff3..202b1d6da678 100644
--- a/drivers/mmc/host/cavium-thunderx.c
+++ b/drivers/mmc/host/cavium-thunderx.c
@@ -142,8 +142,10 @@ static int thunder_mmc_probe(struct pci_dev *pdev,
 				continue;
 
 			ret = cvm_mmc_of_slot_probe(&host->slot_pdev[i]->dev, host);
-			if (ret)
+			if (ret) {
+				of_node_put(child_node);
 				goto error;
+			}
 		}
 		i++;
 	}
diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c
index 58ab9d90bc8b..9b2e2548bd18 100644
--- a/drivers/mmc/host/meson-gx-mmc.c
+++ b/drivers/mmc/host/meson-gx-mmc.c
@@ -1172,8 +1172,10 @@ static int meson_mmc_probe(struct platform_device *pdev)
 	}
 
 	ret = device_reset_optional(&pdev->dev);
-	if (ret)
-		return dev_err_probe(&pdev->dev, ret, "device reset failed\n");
+	if (ret) {
+		dev_err_probe(&pdev->dev, ret, "device reset failed\n");
+		goto free_host;
+	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	host->regs = devm_ioremap_resource(&pdev->dev, res);
diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c
index f9b2897569bb..99d8881a7d6c 100644
--- a/drivers/mmc/host/mtk-sd.c
+++ b/drivers/mmc/host/mtk-sd.c
@@ -2345,6 +2345,9 @@ static void msdc_cqe_disable(struct mmc_host *mmc, bool recovery)
 	/* disable busy check */
 	sdr_clr_bits(host->base + MSDC_PATCH_BIT1, MSDC_PB1_BUSY_CHECK_SEL);
 
+	val = readl(host->base + MSDC_INT);
+	writel(val, host->base + MSDC_INT);
+
 	if (recovery) {
 		sdr_set_field(host->base + MSDC_DMA_CTRL,
 			      MSDC_DMA_CTRL_STOP, 1);
@@ -2785,11 +2788,14 @@ static int __maybe_unused msdc_suspend(struct device *dev)
 {
 	struct mmc_host *mmc = dev_get_drvdata(dev);
 	int ret;
+	u32 val;
 
 	if (mmc->caps2 & MMC_CAP2_CQE) {
 		ret = cqhci_suspend(mmc);
 		if (ret)
 			return ret;
+		val = readl(((struct msdc_host *)mmc_priv(mmc))->base + MSDC_INT);
+		writel(val, ((struct msdc_host *)mmc_priv(mmc))->base + MSDC_INT);
 	}
 
 	return pm_runtime_force_suspend(dev);
diff --git a/drivers/mmc/host/mxcmmc.c b/drivers/mmc/host/mxcmmc.c
index 2fe6fcdbb1b3..9bf95ba217fa 100644
--- a/drivers/mmc/host/mxcmmc.c
+++ b/drivers/mmc/host/mxcmmc.c
@@ -1025,7 +1025,7 @@ static int mxcmci_probe(struct platform_device *pdev)
 	mmc->max_req_size = mmc->max_blk_size * mmc->max_blk_count;
 	mmc->max_seg_size = mmc->max_req_size;
 
-	host->devtype = (enum mxcmci_type)of_device_get_match_data(&pdev->dev);
+	host->devtype = (uintptr_t)of_device_get_match_data(&pdev->dev);
 
 	/* adjust max_segs after devtype detection */
 	if (!is_mpc512x_mmc(host))
diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c
index 316393c694d7..55868b6b8658 100644
--- a/drivers/mmc/host/pxamci.c
+++ b/drivers/mmc/host/pxamci.c
@@ -648,7 +648,7 @@ static int pxamci_probe(struct platform_device *pdev)
 
 	ret = pxamci_of_init(pdev, mmc);
 	if (ret)
-		return ret;
+		goto out;
 
 	host = mmc_priv(mmc);
 	host->mmc = mmc;
@@ -672,7 +672,7 @@ static int pxamci_probe(struct platform_device *pdev)
 
 	ret = pxamci_init_ocr(host);
 	if (ret < 0)
-		return ret;
+		goto out;
 
 	mmc->caps = 0;
 	host->cmdat = 0;
diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c
index ae689bf54686..387f2a4f693a 100644
--- a/drivers/mmc/host/renesas_sdhi_core.c
+++ b/drivers/mmc/host/renesas_sdhi_core.c
@@ -51,9 +51,6 @@
 #define HOST_MODE_GEN3_32BIT	(HOST_MODE_GEN3_WMODE | HOST_MODE_GEN3_BUSWIDTH)
 #define HOST_MODE_GEN3_64BIT	0
 
-#define CTL_SDIF_MODE	0xe6
-#define SDIF_MODE_HS400		BIT(0)
-
 #define SDHI_VER_GEN2_SDR50	0x490c
 #define SDHI_VER_RZ_A1		0x820b
 /* very old datasheets said 0x490c for SDR104, too. They are wrong! */
@@ -550,23 +547,25 @@ static void renesas_sdhi_scc_reset(struct tmio_mmc_host *host, struct renesas_sd
 }
 
 /* only populated for TMIO_MMC_MIN_RCAR2 */
-static void renesas_sdhi_reset(struct tmio_mmc_host *host)
+static void renesas_sdhi_reset(struct tmio_mmc_host *host, bool preserve)
 {
 	struct renesas_sdhi *priv = host_to_priv(host);
 	int ret;
 	u16 val;
 
-	if (priv->rstc) {
-		reset_control_reset(priv->rstc);
-		/* Unknown why but without polling reset status, it will hang */
-		read_poll_timeout(reset_control_status, ret, ret == 0, 1, 100,
-				  false, priv->rstc);
-		/* At least SDHI_VER_GEN2_SDR50 needs manual release of reset */
-		sd_ctrl_write16(host, CTL_RESET_SD, 0x0001);
-		priv->needs_adjust_hs400 = false;
-		renesas_sdhi_set_clock(host, host->clk_cache);
-	} else if (priv->scc_ctl) {
-		renesas_sdhi_scc_reset(host, priv);
+	if (!preserve) {
+		if (priv->rstc) {
+			reset_control_reset(priv->rstc);
+			/* Unknown why but without polling reset status, it will hang */
+			read_poll_timeout(reset_control_status, ret, ret == 0, 1, 100,
+					  false, priv->rstc);
+			/* At least SDHI_VER_GEN2_SDR50 needs manual release of reset */
+			sd_ctrl_write16(host, CTL_RESET_SD, 0x0001);
+			priv->needs_adjust_hs400 = false;
+			renesas_sdhi_set_clock(host, host->clk_cache);
+		} else if (priv->scc_ctl) {
+			renesas_sdhi_scc_reset(host, priv);
+		}
 	}
 
 	if (sd_ctrl_read16(host, CTL_VERSION) >= SDHI_VER_GEN3_SD) {
@@ -925,6 +924,10 @@ int renesas_sdhi_probe(struct platform_device *pdev,
 	if (IS_ERR(priv->clk_cd))
 		priv->clk_cd = NULL;
 
+	priv->rstc = devm_reset_control_get_optional_exclusive(&pdev->dev, NULL);
+	if (IS_ERR(priv->rstc))
+		return PTR_ERR(priv->rstc);
+
 	priv->pinctrl = devm_pinctrl_get(&pdev->dev);
 	if (!IS_ERR(priv->pinctrl)) {
 		priv->pins_default = pinctrl_lookup_state(priv->pinctrl,
@@ -1013,10 +1016,6 @@ int renesas_sdhi_probe(struct platform_device *pdev,
 	if (ret)
 		goto efree;
 
-	priv->rstc = devm_reset_control_get_optional_exclusive(&pdev->dev, NULL);
-	if (IS_ERR(priv->rstc))
-		return PTR_ERR(priv->rstc);
-
 	ver = sd_ctrl_read16(host, CTL_VERSION);
 	/* GEN2_SDR104 is first known SDHI to use 32bit block count */
 	if (ver < SDHI_VER_GEN2_SDR104 && mmc_data->max_blk_count > U16_MAX)
diff --git a/drivers/mmc/host/sdhci-of-at91.c b/drivers/mmc/host/sdhci-of-at91.c
index d1a1c548c515..0452c312b65e 100644
--- a/drivers/mmc/host/sdhci-of-at91.c
+++ b/drivers/mmc/host/sdhci-of-at91.c
@@ -100,8 +100,13 @@ static void sdhci_at91_set_clock(struct sdhci_host *host, unsigned int clock)
 static void sdhci_at91_set_uhs_signaling(struct sdhci_host *host,
 					 unsigned int timing)
 {
-	if (timing == MMC_TIMING_MMC_DDR52)
-		sdhci_writeb(host, SDMMC_MC1R_DDR, SDMMC_MC1R);
+	u8 mc1r;
+
+	if (timing == MMC_TIMING_MMC_DDR52) {
+		mc1r = sdhci_readb(host, SDMMC_MC1R);
+		mc1r |= SDMMC_MC1R_DDR;
+		sdhci_writeb(host, mc1r, SDMMC_MC1R);
+	}
 	sdhci_set_uhs_signaling(host, timing);
 }
 
diff --git a/drivers/mmc/host/sdhci-of-dwcmshc.c b/drivers/mmc/host/sdhci-of-dwcmshc.c
index bac874ab0b33..335c88fd849c 100644
--- a/drivers/mmc/host/sdhci-of-dwcmshc.c
+++ b/drivers/mmc/host/sdhci-of-dwcmshc.c
@@ -15,6 +15,7 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
+#include <linux/reset.h>
 #include <linux/sizes.h>
 
 #include "sdhci-pltfm.h"
@@ -55,14 +56,15 @@
 #define DLL_LOCK_WO_TMOUT(x) \
 	((((x) & DWCMSHC_EMMC_DLL_LOCKED) == DWCMSHC_EMMC_DLL_LOCKED) && \
 	(((x) & DWCMSHC_EMMC_DLL_TIMEOUT) == 0))
-#define RK3568_MAX_CLKS 3
+#define RK35xx_MAX_CLKS 3
 
 #define BOUNDARY_OK(addr, len) \
 	((addr | (SZ_128M - 1)) == ((addr + len - 1) | (SZ_128M - 1)))
 
-struct rk3568_priv {
+struct rk35xx_priv {
 	/* Rockchip specified optional clocks */
-	struct clk_bulk_data rockchip_clks[RK3568_MAX_CLKS];
+	struct clk_bulk_data rockchip_clks[RK35xx_MAX_CLKS];
+	struct reset_control *reset;
 	u8 txclk_tapnum;
 };
 
@@ -176,7 +178,7 @@ static void dwcmshc_rk3568_set_clock(struct sdhci_host *host, unsigned int clock
 {
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	struct dwcmshc_priv *dwc_priv = sdhci_pltfm_priv(pltfm_host);
-	struct rk3568_priv *priv = dwc_priv->priv;
+	struct rk35xx_priv *priv = dwc_priv->priv;
 	u8 txclk_tapnum = DLL_TXCLK_TAPNUM_DEFAULT;
 	u32 extra, reg;
 	int err;
@@ -255,6 +257,21 @@ static void dwcmshc_rk3568_set_clock(struct sdhci_host *host, unsigned int clock
 	sdhci_writel(host, extra, DWCMSHC_EMMC_DLL_STRBIN);
 }
 
+static void rk35xx_sdhci_reset(struct sdhci_host *host, u8 mask)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct dwcmshc_priv *dwc_priv = sdhci_pltfm_priv(pltfm_host);
+	struct rk35xx_priv *priv = dwc_priv->priv;
+
+	if (mask & SDHCI_RESET_ALL && priv->reset) {
+		reset_control_assert(priv->reset);
+		udelay(1);
+		reset_control_deassert(priv->reset);
+	}
+
+	sdhci_reset(host, mask);
+}
+
 static const struct sdhci_ops sdhci_dwcmshc_ops = {
 	.set_clock		= sdhci_set_clock,
 	.set_bus_width		= sdhci_set_bus_width,
@@ -264,12 +281,12 @@ static const struct sdhci_ops sdhci_dwcmshc_ops = {
 	.adma_write_desc	= dwcmshc_adma_write_desc,
 };
 
-static const struct sdhci_ops sdhci_dwcmshc_rk3568_ops = {
+static const struct sdhci_ops sdhci_dwcmshc_rk35xx_ops = {
 	.set_clock		= dwcmshc_rk3568_set_clock,
 	.set_bus_width		= sdhci_set_bus_width,
 	.set_uhs_signaling	= dwcmshc_set_uhs_signaling,
 	.get_max_clock		= sdhci_pltfm_clk_get_max_clock,
-	.reset			= sdhci_reset,
+	.reset			= rk35xx_sdhci_reset,
 	.adma_write_desc	= dwcmshc_adma_write_desc,
 };
 
@@ -279,30 +296,46 @@ static const struct sdhci_pltfm_data sdhci_dwcmshc_pdata = {
 	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
 };
 
-static const struct sdhci_pltfm_data sdhci_dwcmshc_rk3568_pdata = {
-	.ops = &sdhci_dwcmshc_rk3568_ops,
+#ifdef CONFIG_ACPI
+static const struct sdhci_pltfm_data sdhci_dwcmshc_bf3_pdata = {
+	.ops = &sdhci_dwcmshc_ops,
+	.quirks = SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN,
+	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN |
+		   SDHCI_QUIRK2_ACMD23_BROKEN,
+};
+#endif
+
+static const struct sdhci_pltfm_data sdhci_dwcmshc_rk35xx_pdata = {
+	.ops = &sdhci_dwcmshc_rk35xx_ops,
 	.quirks = SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN |
 		  SDHCI_QUIRK_BROKEN_TIMEOUT_VAL,
 	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN |
 		   SDHCI_QUIRK2_CLOCK_DIV_ZERO_BROKEN,
 };
 
-static int dwcmshc_rk3568_init(struct sdhci_host *host, struct dwcmshc_priv *dwc_priv)
+static int dwcmshc_rk35xx_init(struct sdhci_host *host, struct dwcmshc_priv *dwc_priv)
 {
 	int err;
-	struct rk3568_priv *priv = dwc_priv->priv;
+	struct rk35xx_priv *priv = dwc_priv->priv;
+
+	priv->reset = devm_reset_control_array_get_optional_exclusive(mmc_dev(host->mmc));
+	if (IS_ERR(priv->reset)) {
+		err = PTR_ERR(priv->reset);
+		dev_err(mmc_dev(host->mmc), "failed to get reset control %d\n", err);
+		return err;
+	}
 
 	priv->rockchip_clks[0].id = "axi";
 	priv->rockchip_clks[1].id = "block";
 	priv->rockchip_clks[2].id = "timer";
-	err = devm_clk_bulk_get_optional(mmc_dev(host->mmc), RK3568_MAX_CLKS,
+	err = devm_clk_bulk_get_optional(mmc_dev(host->mmc), RK35xx_MAX_CLKS,
 					 priv->rockchip_clks);
 	if (err) {
 		dev_err(mmc_dev(host->mmc), "failed to get clocks %d\n", err);
 		return err;
 	}
 
-	err = clk_bulk_prepare_enable(RK3568_MAX_CLKS, priv->rockchip_clks);
+	err = clk_bulk_prepare_enable(RK35xx_MAX_CLKS, priv->rockchip_clks);
 	if (err) {
 		dev_err(mmc_dev(host->mmc), "failed to enable clocks %d\n", err);
 		return err;
@@ -324,7 +357,7 @@ static int dwcmshc_rk3568_init(struct sdhci_host *host, struct dwcmshc_priv *dwc
 static const struct of_device_id sdhci_dwcmshc_dt_ids[] = {
 	{
 		.compatible = "rockchip,rk3568-dwcmshc",
-		.data = &sdhci_dwcmshc_rk3568_pdata,
+		.data = &sdhci_dwcmshc_rk35xx_pdata,
 	},
 	{
 		.compatible = "snps,dwcmshc-sdhci",
@@ -336,7 +369,10 @@ MODULE_DEVICE_TABLE(of, sdhci_dwcmshc_dt_ids);
 
 #ifdef CONFIG_ACPI
 static const struct acpi_device_id sdhci_dwcmshc_acpi_ids[] = {
-	{ .id = "MLNXBF30" },
+	{
+		.id = "MLNXBF30",
+		.driver_data = (kernel_ulong_t)&sdhci_dwcmshc_bf3_pdata,
+	},
 	{}
 };
 #endif
@@ -347,12 +383,12 @@ static int dwcmshc_probe(struct platform_device *pdev)
 	struct sdhci_pltfm_host *pltfm_host;
 	struct sdhci_host *host;
 	struct dwcmshc_priv *priv;
-	struct rk3568_priv *rk_priv = NULL;
+	struct rk35xx_priv *rk_priv = NULL;
 	const struct sdhci_pltfm_data *pltfm_data;
 	int err;
 	u32 extra;
 
-	pltfm_data = of_device_get_match_data(&pdev->dev);
+	pltfm_data = device_get_match_data(&pdev->dev);
 	if (!pltfm_data) {
 		dev_err(&pdev->dev, "Error: No device match data found\n");
 		return -ENODEV;
@@ -402,8 +438,8 @@ static int dwcmshc_probe(struct platform_device *pdev)
 	host->mmc_host_ops.request = dwcmshc_request;
 	host->mmc_host_ops.hs400_enhanced_strobe = dwcmshc_hs400_enhanced_strobe;
 
-	if (pltfm_data == &sdhci_dwcmshc_rk3568_pdata) {
-		rk_priv = devm_kzalloc(&pdev->dev, sizeof(struct rk3568_priv), GFP_KERNEL);
+	if (pltfm_data == &sdhci_dwcmshc_rk35xx_pdata) {
+		rk_priv = devm_kzalloc(&pdev->dev, sizeof(struct rk35xx_priv), GFP_KERNEL);
 		if (!rk_priv) {
 			err = -ENOMEM;
 			goto err_clk;
@@ -411,7 +447,7 @@ static int dwcmshc_probe(struct platform_device *pdev)
 
 		priv->priv = rk_priv;
 
-		err = dwcmshc_rk3568_init(host, priv);
+		err = dwcmshc_rk35xx_init(host, priv);
 		if (err)
 			goto err_clk;
 	}
@@ -428,7 +464,7 @@ err_clk:
 	clk_disable_unprepare(pltfm_host->clk);
 	clk_disable_unprepare(priv->bus_clk);
 	if (rk_priv)
-		clk_bulk_disable_unprepare(RK3568_MAX_CLKS,
+		clk_bulk_disable_unprepare(RK35xx_MAX_CLKS,
 					   rk_priv->rockchip_clks);
 free_pltfm:
 	sdhci_pltfm_free(pdev);
@@ -440,14 +476,14 @@ static int dwcmshc_remove(struct platform_device *pdev)
 	struct sdhci_host *host = platform_get_drvdata(pdev);
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	struct dwcmshc_priv *priv = sdhci_pltfm_priv(pltfm_host);
-	struct rk3568_priv *rk_priv = priv->priv;
+	struct rk35xx_priv *rk_priv = priv->priv;
 
 	sdhci_remove_host(host, 0);
 
 	clk_disable_unprepare(pltfm_host->clk);
 	clk_disable_unprepare(priv->bus_clk);
 	if (rk_priv)
-		clk_bulk_disable_unprepare(RK3568_MAX_CLKS,
+		clk_bulk_disable_unprepare(RK35xx_MAX_CLKS,
 					   rk_priv->rockchip_clks);
 	sdhci_pltfm_free(pdev);
 
@@ -460,7 +496,7 @@ static int dwcmshc_suspend(struct device *dev)
 	struct sdhci_host *host = dev_get_drvdata(dev);
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	struct dwcmshc_priv *priv = sdhci_pltfm_priv(pltfm_host);
-	struct rk3568_priv *rk_priv = priv->priv;
+	struct rk35xx_priv *rk_priv = priv->priv;
 	int ret;
 
 	ret = sdhci_suspend_host(host);
@@ -472,7 +508,7 @@ static int dwcmshc_suspend(struct device *dev)
 		clk_disable_unprepare(priv->bus_clk);
 
 	if (rk_priv)
-		clk_bulk_disable_unprepare(RK3568_MAX_CLKS,
+		clk_bulk_disable_unprepare(RK35xx_MAX_CLKS,
 					   rk_priv->rockchip_clks);
 
 	return ret;
@@ -483,7 +519,7 @@ static int dwcmshc_resume(struct device *dev)
 	struct sdhci_host *host = dev_get_drvdata(dev);
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	struct dwcmshc_priv *priv = sdhci_pltfm_priv(pltfm_host);
-	struct rk3568_priv *rk_priv = priv->priv;
+	struct rk35xx_priv *rk_priv = priv->priv;
 	int ret;
 
 	ret = clk_prepare_enable(pltfm_host->clk);
@@ -497,7 +533,7 @@ static int dwcmshc_resume(struct device *dev)
 	}
 
 	if (rk_priv) {
-		ret = clk_bulk_prepare_enable(RK3568_MAX_CLKS,
+		ret = clk_bulk_prepare_enable(RK35xx_MAX_CLKS,
 					      rk_priv->rockchip_clks);
 		if (ret)
 			return ret;
diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c
index d68ab222582e..6b44daf4bcd4 100644
--- a/drivers/mmc/host/sdhci-of-esdhc.c
+++ b/drivers/mmc/host/sdhci-of-esdhc.c
@@ -919,6 +919,7 @@ static int esdhc_signal_voltage_switch(struct mmc_host *mmc,
 		scfg_node = of_find_matching_node(NULL, scfg_device_ids);
 		if (scfg_node)
 			scfg_base = of_iomap(scfg_node, 0);
+		of_node_put(scfg_node);
 		if (scfg_base) {
 			sdhciovselcr = SDHCIOVSELCR_TGLEN |
 				       SDHCIOVSELCR_VSELVAL;
diff --git a/drivers/mmc/host/tmio_mmc.c b/drivers/mmc/host/tmio_mmc.c
index b55a29c53d9c..53a2ad9a24b8 100644
--- a/drivers/mmc/host/tmio_mmc.c
+++ b/drivers/mmc/host/tmio_mmc.c
@@ -75,7 +75,7 @@ static void tmio_mmc_set_clock(struct tmio_mmc_host *host,
 	tmio_mmc_clk_start(host);
 }
 
-static void tmio_mmc_reset(struct tmio_mmc_host *host)
+static void tmio_mmc_reset(struct tmio_mmc_host *host, bool preserve)
 {
 	sd_ctrl_write16(host, CTL_RESET_SDIO, 0x0000);
 	usleep_range(10000, 11000);
diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h
index f936aad945ce..da63193dd45b 100644
--- a/drivers/mmc/host/tmio_mmc.h
+++ b/drivers/mmc/host/tmio_mmc.h
@@ -42,6 +42,7 @@
 #define CTL_DMA_ENABLE 0xd8
 #define CTL_RESET_SD 0xe0
 #define CTL_VERSION 0xe2
+#define CTL_SDIF_MODE 0xe6 /* only known on R-Car 2+ */
 
 /* Definitions for values the CTL_STOP_INTERNAL_ACTION register can take */
 #define TMIO_STOP_STP		BIT(0)
@@ -98,6 +99,9 @@
 /* Definitions for values the CTL_DMA_ENABLE register can take */
 #define DMA_ENABLE_DMASDRW	BIT(1)
 
+/* Definitions for values the CTL_SDIF_MODE register can take */
+#define SDIF_MODE_HS400		BIT(0) /* only known on R-Car 2+ */
+
 /* Define some IRQ masks */
 /* This is the mask used at reset by the chip */
 #define TMIO_MASK_ALL           0x837f031d
@@ -181,7 +185,7 @@ struct tmio_mmc_host {
 	int (*multi_io_quirk)(struct mmc_card *card,
 			      unsigned int direction, int blk_size);
 	int (*write16_hook)(struct tmio_mmc_host *host, int addr);
-	void (*reset)(struct tmio_mmc_host *host);
+	void (*reset)(struct tmio_mmc_host *host, bool preserve);
 	bool (*check_retune)(struct tmio_mmc_host *host, struct mmc_request *mrq);
 	void (*fixup_request)(struct tmio_mmc_host *host, struct mmc_request *mrq);
 	unsigned int (*get_timeout_cycles)(struct tmio_mmc_host *host);
diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c
index a5850d83908b..437048bb8027 100644
--- a/drivers/mmc/host/tmio_mmc_core.c
+++ b/drivers/mmc/host/tmio_mmc_core.c
@@ -179,8 +179,17 @@ static void tmio_mmc_set_bus_width(struct tmio_mmc_host *host,
 	sd_ctrl_write16(host, CTL_SD_MEM_CARD_OPT, reg);
 }
 
-static void tmio_mmc_reset(struct tmio_mmc_host *host)
+static void tmio_mmc_reset(struct tmio_mmc_host *host, bool preserve)
 {
+	u16 card_opt, clk_ctrl, sdif_mode;
+
+	if (preserve) {
+		card_opt = sd_ctrl_read16(host, CTL_SD_MEM_CARD_OPT);
+		clk_ctrl = sd_ctrl_read16(host, CTL_SD_CARD_CLK_CTL);
+		if (host->pdata->flags & TMIO_MMC_MIN_RCAR2)
+			sdif_mode = sd_ctrl_read16(host, CTL_SDIF_MODE);
+	}
+
 	/* FIXME - should we set stop clock reg here */
 	sd_ctrl_write16(host, CTL_RESET_SD, 0x0000);
 	usleep_range(10000, 11000);
@@ -190,7 +199,7 @@ static void tmio_mmc_reset(struct tmio_mmc_host *host)
 	tmio_mmc_abort_dma(host);
 
 	if (host->reset)
-		host->reset(host);
+		host->reset(host, preserve);
 
 	sd_ctrl_write32_as_16_and_16(host, CTL_IRQ_MASK, host->sdcard_irq_mask_all);
 	host->sdcard_irq_mask = host->sdcard_irq_mask_all;
@@ -206,6 +215,13 @@ static void tmio_mmc_reset(struct tmio_mmc_host *host)
 		sd_ctrl_write16(host, CTL_TRANSACTION_CTL, 0x0001);
 	}
 
+	if (preserve) {
+		sd_ctrl_write16(host, CTL_SD_MEM_CARD_OPT, card_opt);
+		sd_ctrl_write16(host, CTL_SD_CARD_CLK_CTL, clk_ctrl);
+		if (host->pdata->flags & TMIO_MMC_MIN_RCAR2)
+			sd_ctrl_write16(host, CTL_SDIF_MODE, sdif_mode);
+	}
+
 	if (host->mmc->card)
 		mmc_retune_needed(host->mmc);
 }
@@ -248,7 +264,7 @@ static void tmio_mmc_reset_work(struct work_struct *work)
 
 	spin_unlock_irqrestore(&host->lock, flags);
 
-	tmio_mmc_reset(host);
+	tmio_mmc_reset(host, true);
 
 	/* Ready for new calls */
 	host->mrq = NULL;
@@ -961,7 +977,7 @@ static void tmio_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 		tmio_mmc_power_off(host);
 		/* For R-Car Gen2+, we need to reset SDHI specific SCC */
 		if (host->pdata->flags & TMIO_MMC_MIN_RCAR2)
-			tmio_mmc_reset(host);
+			tmio_mmc_reset(host, false);
 
 		host->set_clock(host, 0);
 		break;
@@ -1189,7 +1205,7 @@ int tmio_mmc_host_probe(struct tmio_mmc_host *_host)
 		_host->sdcard_irq_mask_all = TMIO_MASK_ALL;
 
 	_host->set_clock(_host, 0);
-	tmio_mmc_reset(_host);
+	tmio_mmc_reset(_host, false);
 
 	spin_lock_init(&_host->lock);
 	mutex_init(&_host->ios_lock);
@@ -1285,7 +1301,7 @@ int tmio_mmc_host_runtime_resume(struct device *dev)
 	struct tmio_mmc_host *host = dev_get_drvdata(dev);
 
 	tmio_mmc_clk_enable(host);
-	tmio_mmc_reset(host);
+	tmio_mmc_reset(host, false);
 
 	if (host->clk_cache)
 		host->set_clock(host, host->clk_cache);
diff --git a/drivers/mtd/devices/mtd_dataflash.c b/drivers/mtd/devices/mtd_dataflash.c
index 2b317ed6c103..9c714c982c6e 100644
--- a/drivers/mtd/devices/mtd_dataflash.c
+++ b/drivers/mtd/devices/mtd_dataflash.c
@@ -112,6 +112,13 @@ static const struct of_device_id dataflash_dt_ids[] = {
 MODULE_DEVICE_TABLE(of, dataflash_dt_ids);
 #endif
 
+static const struct spi_device_id dataflash_spi_ids[] = {
+	{ .name = "at45", },
+	{ .name = "dataflash", },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(spi, dataflash_spi_ids);
+
 /* ......................................................................... */
 
 /*
@@ -938,6 +945,7 @@ static struct spi_driver dataflash_driver = {
 
 	.probe		= dataflash_probe,
 	.remove		= dataflash_remove,
+	.id_table	= dataflash_spi_ids,
 
 	/* FIXME:  investigate suspend and resume... */
 };
diff --git a/drivers/mtd/devices/st_spi_fsm.c b/drivers/mtd/devices/st_spi_fsm.c
index 983999c020d6..48bda2dd1bb5 100644
--- a/drivers/mtd/devices/st_spi_fsm.c
+++ b/drivers/mtd/devices/st_spi_fsm.c
@@ -2115,10 +2115,12 @@ static int stfsm_probe(struct platform_device *pdev)
 		(long long)fsm->mtd.size, (long long)(fsm->mtd.size >> 20),
 		fsm->mtd.erasesize, (fsm->mtd.erasesize >> 10));
 
-	return mtd_device_register(&fsm->mtd, NULL, 0);
-
+	ret = mtd_device_register(&fsm->mtd, NULL, 0);
+	if (ret) {
 err_clk_unprepare:
-	clk_disable_unprepare(fsm->clk);
+		clk_disable_unprepare(fsm->clk);
+	}
+
 	return ret;
 }
 
diff --git a/drivers/mtd/maps/physmap-versatile.c b/drivers/mtd/maps/physmap-versatile.c
index ad7cd9cfaee0..a1b8b7b25f88 100644
--- a/drivers/mtd/maps/physmap-versatile.c
+++ b/drivers/mtd/maps/physmap-versatile.c
@@ -93,6 +93,7 @@ static int ap_flash_init(struct platform_device *pdev)
 		return -ENODEV;
 	}
 	ebi_base = of_iomap(ebi, 0);
+	of_node_put(ebi);
 	if (!ebi_base)
 		return -ENODEV;
 
@@ -207,6 +208,7 @@ int of_flash_probe_versatile(struct platform_device *pdev,
 
 		versatile_flashprot = (enum versatile_flashprot)devid->data;
 		rmap = syscon_node_to_regmap(sysnp);
+		of_node_put(sysnp);
 		if (IS_ERR(rmap))
 			return PTR_ERR(rmap);
 
diff --git a/drivers/mtd/nand/raw/arasan-nand-controller.c b/drivers/mtd/nand/raw/arasan-nand-controller.c
index 53bd10738418..296fb16c8dc3 100644
--- a/drivers/mtd/nand/raw/arasan-nand-controller.c
+++ b/drivers/mtd/nand/raw/arasan-nand-controller.c
@@ -347,17 +347,17 @@ static int anfc_select_target(struct nand_chip *chip, int target)
 
 	/* Update clock frequency */
 	if (nfc->cur_clk != anand->clk) {
-		clk_disable_unprepare(nfc->controller_clk);
-		ret = clk_set_rate(nfc->controller_clk, anand->clk);
+		clk_disable_unprepare(nfc->bus_clk);
+		ret = clk_set_rate(nfc->bus_clk, anand->clk);
 		if (ret) {
 			dev_err(nfc->dev, "Failed to change clock rate\n");
 			return ret;
 		}
 
-		ret = clk_prepare_enable(nfc->controller_clk);
+		ret = clk_prepare_enable(nfc->bus_clk);
 		if (ret) {
 			dev_err(nfc->dev,
-				"Failed to re-enable the controller clock\n");
+				"Failed to re-enable the bus clock\n");
 			return ret;
 		}
 
@@ -1043,7 +1043,13 @@ static int anfc_setup_interface(struct nand_chip *chip, int target,
 				 DQS_BUFF_SEL_OUT(dqs_mode);
 	}
 
-	anand->clk = ANFC_XLNX_SDR_DFLT_CORE_CLK;
+	if (nand_interface_is_sdr(conf)) {
+		anand->clk = ANFC_XLNX_SDR_DFLT_CORE_CLK;
+	} else {
+		/* ONFI timings are defined in picoseconds */
+		anand->clk = div_u64((u64)NSEC_PER_SEC * 1000,
+				     conf->timings.nvddr.tCK_min);
+	}
 
 	/*
 	 * Due to a hardware bug in the ZynqMP SoC, SDR timing modes 0-1 work
diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
index f01200e94241..909ef222ab46 100644
--- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
+++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
@@ -849,8 +849,8 @@ err_out:
  *         RDN_DELAY = -----------------------     {3}
  *                           RP
  */
-static void gpmi_nfc_compute_timings(struct gpmi_nand_data *this,
-				     const struct nand_sdr_timings *sdr)
+static int gpmi_nfc_compute_timings(struct gpmi_nand_data *this,
+				    const struct nand_sdr_timings *sdr)
 {
 	struct gpmi_nfc_hardware_timing *hw = &this->hw;
 	struct resources *r = &this->resources;
@@ -862,24 +862,34 @@ static void gpmi_nfc_compute_timings(struct gpmi_nand_data *this,
 	int sample_delay_ps, sample_delay_factor;
 	unsigned int busy_timeout_cycles;
 	u8 wrn_dly_sel;
+	unsigned long clk_rate, min_rate;
 	u64 busy_timeout_ps;
 
 	if (sdr->tRC_min >= 30000) {
 		/* ONFI non-EDO modes [0-3] */
 		hw->clk_rate = 22000000;
+		min_rate = 0;
 		wrn_dly_sel = BV_GPMI_CTRL1_WRN_DLY_SEL_4_TO_8NS;
 	} else if (sdr->tRC_min >= 25000) {
 		/* ONFI EDO mode 4 */
 		hw->clk_rate = 80000000;
+		min_rate = 22000000;
 		wrn_dly_sel = BV_GPMI_CTRL1_WRN_DLY_SEL_NO_DELAY;
 	} else {
 		/* ONFI EDO mode 5 */
 		hw->clk_rate = 100000000;
+		min_rate = 80000000;
 		wrn_dly_sel = BV_GPMI_CTRL1_WRN_DLY_SEL_NO_DELAY;
 	}
 
-	hw->clk_rate = clk_round_rate(r->clock[0], hw->clk_rate);
+	clk_rate = clk_round_rate(r->clock[0], hw->clk_rate);
+	if (clk_rate <= min_rate) {
+		dev_err(this->dev, "clock setting: expected %ld, got %ld\n",
+			hw->clk_rate, clk_rate);
+		return -ENOTSUPP;
+	}
 
+	hw->clk_rate = clk_rate;
 	/* SDR core timings are given in picoseconds */
 	period_ps = div_u64((u64)NSEC_PER_SEC * 1000, hw->clk_rate);
 
@@ -892,7 +902,7 @@ static void gpmi_nfc_compute_timings(struct gpmi_nand_data *this,
 	hw->timing0 = BF_GPMI_TIMING0_ADDRESS_SETUP(addr_setup_cycles) |
 		      BF_GPMI_TIMING0_DATA_HOLD(data_hold_cycles) |
 		      BF_GPMI_TIMING0_DATA_SETUP(data_setup_cycles);
-	hw->timing1 = BF_GPMI_TIMING1_BUSY_TIMEOUT(DIV_ROUND_UP(busy_timeout_cycles, 4096));
+	hw->timing1 = BF_GPMI_TIMING1_BUSY_TIMEOUT(busy_timeout_cycles * 4096);
 
 	/*
 	 * Derive NFC ideal delay from {3}:
@@ -921,6 +931,7 @@ static void gpmi_nfc_compute_timings(struct gpmi_nand_data *this,
 		hw->ctrl1n |= BF_GPMI_CTRL1_RDN_DELAY(sample_delay_factor) |
 			      BM_GPMI_CTRL1_DLL_ENABLE |
 			      (use_half_period ? BM_GPMI_CTRL1_HALF_PERIOD : 0);
+	return 0;
 }
 
 static int gpmi_nfc_apply_timings(struct gpmi_nand_data *this)
@@ -979,6 +990,7 @@ static int gpmi_setup_interface(struct nand_chip *chip, int chipnr,
 {
 	struct gpmi_nand_data *this = nand_get_controller_data(chip);
 	const struct nand_sdr_timings *sdr;
+	int ret;
 
 	/* Retrieve required NAND timings */
 	sdr = nand_get_sdr_timings(conf);
@@ -994,7 +1006,9 @@ static int gpmi_setup_interface(struct nand_chip *chip, int chipnr,
 		return 0;
 
 	/* Do the actual derivation of the controller timings */
-	gpmi_nfc_compute_timings(this, sdr);
+	ret = gpmi_nfc_compute_timings(this, sdr);
+	if (ret)
+		return ret;
 
 	this->hw.must_apply_timings = true;
 
diff --git a/drivers/mtd/nand/raw/meson_nand.c b/drivers/mtd/nand/raw/meson_nand.c
index ac3be92872d0..032180183339 100644
--- a/drivers/mtd/nand/raw/meson_nand.c
+++ b/drivers/mtd/nand/raw/meson_nand.c
@@ -1307,7 +1307,6 @@ static int meson_nfc_nand_chip_cleanup(struct meson_nfc *nfc)
 		if (ret)
 			return ret;
 
-		meson_nfc_free_buffer(&meson_chip->nand);
 		nand_cleanup(&meson_chip->nand);
 		list_del(&meson_chip->node);
 	}
diff --git a/drivers/mtd/parsers/ofpart_bcm4908.c b/drivers/mtd/parsers/ofpart_bcm4908.c
index 0eddef4c198e..bb072a0940e4 100644
--- a/drivers/mtd/parsers/ofpart_bcm4908.c
+++ b/drivers/mtd/parsers/ofpart_bcm4908.c
@@ -35,12 +35,15 @@ static long long bcm4908_partitions_fw_offset(void)
 		err = kstrtoul(s + len + 1, 0, &offset);
 		if (err) {
 			pr_err("failed to parse %s\n", s + len + 1);
+			of_node_put(root);
 			return err;
 		}
 
+		of_node_put(root);
 		return offset << 10;
 	}
 
+	of_node_put(root);
 	return -ENOENT;
 }
 
diff --git a/drivers/mtd/parsers/redboot.c b/drivers/mtd/parsers/redboot.c
index feb44a573d44..a16b42a88581 100644
--- a/drivers/mtd/parsers/redboot.c
+++ b/drivers/mtd/parsers/redboot.c
@@ -58,6 +58,7 @@ static void parse_redboot_of(struct mtd_info *master)
 		return;
 
 	ret = of_property_read_u32(npart, "fis-index-block", &dirblock);
+	of_node_put(npart);
 	if (ret)
 		return;
 
diff --git a/drivers/mtd/sm_ftl.c b/drivers/mtd/sm_ftl.c
index 0cff2cda1b5a..7f955fade838 100644
--- a/drivers/mtd/sm_ftl.c
+++ b/drivers/mtd/sm_ftl.c
@@ -1111,9 +1111,9 @@ static void sm_release(struct mtd_blktrans_dev *dev)
 {
 	struct sm_ftl *ftl = dev->priv;
 
-	mutex_lock(&ftl->mutex);
 	del_timer_sync(&ftl->timer);
 	cancel_work_sync(&ftl->flush_work);
+	mutex_lock(&ftl->mutex);
 	sm_cache_flush(ftl);
 	mutex_unlock(&ftl->mutex);
 }
diff --git a/drivers/mtd/spi-nor/core.c b/drivers/mtd/spi-nor/core.c
index 90f39aabc1ff..eb5d7b3d1860 100644
--- a/drivers/mtd/spi-nor/core.c
+++ b/drivers/mtd/spi-nor/core.c
@@ -177,7 +177,7 @@ static int spi_nor_controller_ops_write_reg(struct spi_nor *nor, u8 opcode,
 
 static int spi_nor_controller_ops_erase(struct spi_nor *nor, loff_t offs)
 {
-	if (spi_nor_protocol_is_dtr(nor->write_proto))
+	if (spi_nor_protocol_is_dtr(nor->reg_proto))
 		return -EOPNOTSUPP;
 
 	return nor->controller_ops->erase(nor, offs);
@@ -1195,7 +1195,7 @@ static int spi_nor_erase_chip(struct spi_nor *nor)
 				   SPI_MEM_OP_NO_DUMMY,
 				   SPI_MEM_OP_NO_DATA);
 
-		spi_nor_spimem_setup_op(nor, &op, nor->write_proto);
+		spi_nor_spimem_setup_op(nor, &op, nor->reg_proto);
 
 		ret = spi_mem_exec_op(nor->spimem, &op);
 	} else {
@@ -1340,7 +1340,7 @@ int spi_nor_erase_sector(struct spi_nor *nor, u32 addr)
 				   SPI_MEM_OP_NO_DUMMY,
 				   SPI_MEM_OP_NO_DATA);
 
-		spi_nor_spimem_setup_op(nor, &op, nor->write_proto);
+		spi_nor_spimem_setup_op(nor, &op, nor->reg_proto);
 
 		return spi_mem_exec_op(nor->spimem, &op);
 	} else if (nor->controller_ops->erase) {
@@ -3148,7 +3148,6 @@ int spi_nor_scan(struct spi_nor *nor, const char *name,
 	mtd->writesize = nor->params->writesize;
 	mtd->flags = MTD_CAP_NORFLASH;
 	mtd->size = nor->params->size;
-	mtd->_erase = spi_nor_erase;
 	mtd->_read = spi_nor_read;
 	mtd->_suspend = spi_nor_suspend;
 	mtd->_resume = spi_nor_resume;
@@ -3178,6 +3177,8 @@ int spi_nor_scan(struct spi_nor *nor, const char *name,
 
 	if (info->flags & SPI_NOR_NO_ERASE)
 		mtd->flags |= MTD_NO_ERASE;
+	else
+		mtd->_erase = spi_nor_erase;
 
 	mtd->dev.parent = dev;
 	nor->page_size = nor->params->page_size;
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index a86b1f71762e..1f0120cbe9e8 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -2007,30 +2007,24 @@ void bond_3ad_initiate_agg_selection(struct bonding *bond, int timeout)
  */
 void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution)
 {
-	/* check that the bond is not initialized yet */
-	if (!MAC_ADDRESS_EQUAL(&(BOND_AD_INFO(bond).system.sys_mac_addr),
-				bond->dev->dev_addr)) {
-
-		BOND_AD_INFO(bond).aggregator_identifier = 0;
-
-		BOND_AD_INFO(bond).system.sys_priority =
-			bond->params.ad_actor_sys_prio;
-		if (is_zero_ether_addr(bond->params.ad_actor_system))
-			BOND_AD_INFO(bond).system.sys_mac_addr =
-			    *((struct mac_addr *)bond->dev->dev_addr);
-		else
-			BOND_AD_INFO(bond).system.sys_mac_addr =
-			    *((struct mac_addr *)bond->params.ad_actor_system);
+	BOND_AD_INFO(bond).aggregator_identifier = 0;
+	BOND_AD_INFO(bond).system.sys_priority =
+		bond->params.ad_actor_sys_prio;
+	if (is_zero_ether_addr(bond->params.ad_actor_system))
+		BOND_AD_INFO(bond).system.sys_mac_addr =
+		    *((struct mac_addr *)bond->dev->dev_addr);
+	else
+		BOND_AD_INFO(bond).system.sys_mac_addr =
+		    *((struct mac_addr *)bond->params.ad_actor_system);
 
-		/* initialize how many times this module is called in one
-		 * second (should be about every 100ms)
-		 */
-		ad_ticks_per_sec = tick_resolution;
+	/* initialize how many times this module is called in one
+	 * second (should be about every 100ms)
+	 */
+	ad_ticks_per_sec = tick_resolution;
 
-		bond_3ad_initiate_agg_selection(bond,
-						AD_AGGREGATOR_SELECTION_TIMER *
-						ad_ticks_per_sec);
-	}
+	bond_3ad_initiate_agg_selection(bond,
+					AD_AGGREGATOR_SELECTION_TIMER *
+					ad_ticks_per_sec);
 }
 
 /**
@@ -2228,7 +2222,8 @@ void bond_3ad_unbind_slave(struct slave *slave)
 				temp_aggregator->num_of_ports--;
 				if (__agg_active_ports(temp_aggregator) == 0) {
 					select_new_active_agg = temp_aggregator->is_active;
-					ad_clear_agg(temp_aggregator);
+					if (temp_aggregator->num_of_ports == 0)
+						ad_clear_agg(temp_aggregator);
 					if (select_new_active_agg) {
 						slave_info(bond->dev, slave->dev, "Removing an active aggregator\n");
 						/* select new active aggregator */
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index bca36be884b8..a6a70b872ac4 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -1281,12 +1281,12 @@ int bond_alb_initialize(struct bonding *bond, int rlb_enabled)
 		return res;
 
 	if (rlb_enabled) {
-		bond->alb_info.rlb_enabled = 1;
 		res = rlb_initialize(bond);
 		if (res) {
 			tlb_deinitialize(bond);
 			return res;
 		}
+		bond->alb_info.rlb_enabled = 1;
 	} else {
 		bond->alb_info.rlb_enabled = 0;
 	}
diff --git a/drivers/net/caif/caif_virtio.c b/drivers/net/caif/caif_virtio.c
index 91230894692d..da87de02b2fc 100644
--- a/drivers/net/caif/caif_virtio.c
+++ b/drivers/net/caif/caif_virtio.c
@@ -721,13 +721,21 @@ static int cfv_probe(struct virtio_device *vdev)
 	/* Carrier is off until netdevice is opened */
 	netif_carrier_off(netdev);
 
+	/* serialize netdev register + virtio_device_ready() with ndo_open() */
+	rtnl_lock();
+
 	/* register Netdev */
-	err = register_netdev(netdev);
+	err = register_netdevice(netdev);
 	if (err) {
+		rtnl_unlock();
 		dev_err(&vdev->dev, "Unable to register netdev (%d)\n", err);
 		goto err;
 	}
 
+	virtio_device_ready(vdev);
+
+	rtnl_unlock();
+
 	debugfs_init(cfv);
 
 	return 0;
diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c
index 80425636049d..29e2beae3357 100644
--- a/drivers/net/can/dev/netlink.c
+++ b/drivers/net/can/dev/netlink.c
@@ -76,7 +76,8 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[],
 		 * directly via do_set_bitrate(). Bail out if neither
 		 * is given.
 		 */
-		if (!priv->bittiming_const && !priv->do_set_bittiming)
+		if (!priv->bittiming_const && !priv->do_set_bittiming &&
+		    !priv->bitrate_const)
 			return -EOPNOTSUPP;
 
 		memcpy(&bt, nla_data(data[IFLA_CAN_BITTIMING]), sizeof(bt));
@@ -169,7 +170,8 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[],
 		 * directly via do_set_bitrate(). Bail out if neither
 		 * is given.
 		 */
-		if (!priv->data_bittiming_const && !priv->do_set_data_bittiming)
+		if (!priv->data_bittiming_const && !priv->do_set_data_bittiming &&
+		    !priv->data_bitrate_const)
 			return -EOPNOTSUPP;
 
 		memcpy(&dbt, nla_data(data[IFLA_CAN_DATA_BITTIMING]),
diff --git a/drivers/net/can/grcan.c b/drivers/net/can/grcan.c
index daee3652ac8b..e098f594a749 100644
--- a/drivers/net/can/grcan.c
+++ b/drivers/net/can/grcan.c
@@ -1659,7 +1659,6 @@ static int grcan_probe(struct platform_device *ofdev)
 	 */
 	sysid_parent = of_find_node_by_path("/ambapp0");
 	if (sysid_parent) {
-		of_node_get(sysid_parent);
 		err = of_property_read_u32(sysid_parent, "systemid", &sysid);
 		if (!err && ((sysid & GRLIB_VERSION_MASK) >=
 			     GRCAN_TXBUG_SAFE_GRLIB_VERSION))
diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index bff33a619acd..c4596fbe6d2f 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -532,7 +532,7 @@ static int m_can_read_fifo(struct net_device *dev, u32 rxfs)
 	stats->rx_packets++;
 	stats->rx_bytes += cf->len;
 
-	timestamp = FIELD_GET(RX_BUF_RXTS_MASK, fifo_header.dlc);
+	timestamp = FIELD_GET(RX_BUF_RXTS_MASK, fifo_header.dlc) << 16;
 
 	m_can_receive_skb(cdev, skb, timestamp);
 
@@ -1043,7 +1043,7 @@ static int m_can_echo_tx_event(struct net_device *dev)
 		}
 
 		msg_mark = FIELD_GET(TX_EVENT_MM_MASK, txe);
-		timestamp = FIELD_GET(TX_EVENT_TXTS_MASK, txe);
+		timestamp = FIELD_GET(TX_EVENT_TXTS_MASK, txe) << 16;
 
 		/* ack txe element */
 		m_can_write(cdev, M_CAN_TXEFA, FIELD_PREP(TXEFA_EFAI_MASK,
@@ -1367,7 +1367,9 @@ static void m_can_chip_config(struct net_device *dev)
 	/* enable internal timestamp generation, with a prescalar of 16. The
 	 * prescalar is applied to the nominal bit timing
 	 */
-	m_can_write(cdev, M_CAN_TSCC, FIELD_PREP(TSCC_TCP_MASK, 0xf));
+	m_can_write(cdev, M_CAN_TSCC,
+		    FIELD_PREP(TSCC_TCP_MASK, 0xf) |
+		    FIELD_PREP(TSCC_TSS_MASK, TSCC_TSS_INTERNAL));
 
 	m_can_config_endisable(cdev, false);
 
diff --git a/drivers/net/can/pch_can.c b/drivers/net/can/pch_can.c
index 964c8a09226a..cd8d536c6fb2 100644
--- a/drivers/net/can/pch_can.c
+++ b/drivers/net/can/pch_can.c
@@ -489,6 +489,7 @@ static void pch_can_error(struct net_device *ndev, u32 status)
 	if (!skb)
 		return;
 
+	errc = ioread32(&priv->regs->errc);
 	if (status & PCH_BUS_OFF) {
 		pch_can_set_tx_all(priv, 0);
 		pch_can_set_rx_all(priv, 0);
@@ -496,9 +497,11 @@ static void pch_can_error(struct net_device *ndev, u32 status)
 		cf->can_id |= CAN_ERR_BUSOFF;
 		priv->can.can_stats.bus_off++;
 		can_bus_off(ndev);
+	} else {
+		cf->data[6] = errc & PCH_TEC;
+		cf->data[7] = (errc & PCH_REC) >> 8;
 	}
 
-	errc = ioread32(&priv->regs->errc);
 	/* Warning interrupt. */
 	if (status & PCH_EWARN) {
 		state = CAN_STATE_ERROR_WARNING;
@@ -556,9 +559,6 @@ static void pch_can_error(struct net_device *ndev, u32 status)
 		break;
 	}
 
-	cf->data[6] = errc & PCH_TEC;
-	cf->data[7] = (errc & PCH_REC) >> 8;
-
 	priv->can.state = state;
 	netif_receive_skb(skb);
 
diff --git a/drivers/net/can/rcar/rcar_can.c b/drivers/net/can/rcar/rcar_can.c
index 8999ec9455ec..945b319de841 100644
--- a/drivers/net/can/rcar/rcar_can.c
+++ b/drivers/net/can/rcar/rcar_can.c
@@ -235,11 +235,8 @@ static void rcar_can_error(struct net_device *ndev)
 	if (eifr & (RCAR_CAN_EIFR_EWIF | RCAR_CAN_EIFR_EPIF)) {
 		txerr = readb(&priv->regs->tecr);
 		rxerr = readb(&priv->regs->recr);
-		if (skb) {
+		if (skb)
 			cf->can_id |= CAN_ERR_CRTL;
-			cf->data[6] = txerr;
-			cf->data[7] = rxerr;
-		}
 	}
 	if (eifr & RCAR_CAN_EIFR_BEIF) {
 		int rx_errors = 0, tx_errors = 0;
@@ -339,6 +336,9 @@ static void rcar_can_error(struct net_device *ndev)
 		can_bus_off(ndev);
 		if (skb)
 			cf->can_id |= CAN_ERR_BUSOFF;
+	} else if (skb) {
+		cf->data[6] = txerr;
+		cf->data[7] = rxerr;
 	}
 	if (eifr & RCAR_CAN_EIFR_ORIF) {
 		netdev_dbg(priv->ndev, "Receive overrun error interrupt\n");
diff --git a/drivers/net/can/sja1000/sja1000.c b/drivers/net/can/sja1000/sja1000.c
index 3fad54646746..aae2677e24f9 100644
--- a/drivers/net/can/sja1000/sja1000.c
+++ b/drivers/net/can/sja1000/sja1000.c
@@ -404,9 +404,6 @@ static int sja1000_err(struct net_device *dev, uint8_t isrc, uint8_t status)
 	txerr = priv->read_reg(priv, SJA1000_TXERR);
 	rxerr = priv->read_reg(priv, SJA1000_RXERR);
 
-	cf->data[6] = txerr;
-	cf->data[7] = rxerr;
-
 	if (isrc & IRQ_DOI) {
 		/* data overrun interrupt */
 		netdev_dbg(dev, "data overrun interrupt\n");
@@ -428,6 +425,10 @@ static int sja1000_err(struct net_device *dev, uint8_t isrc, uint8_t status)
 		else
 			state = CAN_STATE_ERROR_ACTIVE;
 	}
+	if (state != CAN_STATE_BUS_OFF) {
+		cf->data[6] = txerr;
+		cf->data[7] = rxerr;
+	}
 	if (isrc & IRQ_BEI) {
 		/* bus error interrupt */
 		priv->can.can_stats.bus_error++;
diff --git a/drivers/net/can/spi/hi311x.c b/drivers/net/can/spi/hi311x.c
index 89d9c986a229..b08b98e6ad1c 100644
--- a/drivers/net/can/spi/hi311x.c
+++ b/drivers/net/can/spi/hi311x.c
@@ -670,8 +670,6 @@ static irqreturn_t hi3110_can_ist(int irq, void *dev_id)
 
 			txerr = hi3110_read(spi, HI3110_READ_TEC);
 			rxerr = hi3110_read(spi, HI3110_READ_REC);
-			cf->data[6] = txerr;
-			cf->data[7] = rxerr;
 			tx_state = txerr >= rxerr ? new_state : 0;
 			rx_state = txerr <= rxerr ? new_state : 0;
 			can_change_state(net, cf, tx_state, rx_state);
@@ -684,6 +682,9 @@ static irqreturn_t hi3110_can_ist(int irq, void *dev_id)
 					hi3110_hw_sleep(spi);
 					break;
 				}
+			} else {
+				cf->data[6] = txerr;
+				cf->data[7] = rxerr;
 			}
 		}
 
diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c
index 0579ab74f728..baab3adc34bc 100644
--- a/drivers/net/can/spi/mcp251x.c
+++ b/drivers/net/can/spi/mcp251x.c
@@ -1074,9 +1074,6 @@ static irqreturn_t mcp251x_can_ist(int irq, void *dev_id)
 
 		mcp251x_read_2regs(spi, CANINTF, &intf, &eflag);
 
-		/* mask out flags we don't care about */
-		intf &= CANINTF_RX | CANINTF_TX | CANINTF_ERR;
-
 		/* receive buffer 0 */
 		if (intf & CANINTF_RX0IF) {
 			mcp251x_hw_rx(spi, 0);
@@ -1086,6 +1083,18 @@ static irqreturn_t mcp251x_can_ist(int irq, void *dev_id)
 			if (mcp251x_is_2510(spi))
 				mcp251x_write_bits(spi, CANINTF,
 						   CANINTF_RX0IF, 0x00);
+
+			/* check if buffer 1 is already known to be full, no need to re-read */
+			if (!(intf & CANINTF_RX1IF)) {
+				u8 intf1, eflag1;
+
+				/* intf needs to be read again to avoid a race condition */
+				mcp251x_read_2regs(spi, CANINTF, &intf1, &eflag1);
+
+				/* combine flags from both operations for error handling */
+				intf |= intf1;
+				eflag |= eflag1;
+			}
 		}
 
 		/* receive buffer 1 */
@@ -1096,6 +1105,9 @@ static irqreturn_t mcp251x_can_ist(int irq, void *dev_id)
 				clear_intf |= CANINTF_RX1IF;
 		}
 
+		/* mask out flags we don't care about */
+		intf &= CANINTF_RX | CANINTF_TX | CANINTF_ERR;
+
 		/* any error or tx interrupt we need to clear? */
 		if (intf & (CANINTF_ERR | CANINTF_TX))
 			clear_intf |= intf & (CANINTF_ERR | CANINTF_TX);
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c
index 297491516a26..bb559663a3fa 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c
@@ -325,19 +325,21 @@ mcp251xfd_regmap_crc_read(void *context,
 		 * register. It increments once per SYS clock tick,
 		 * which is 20 or 40 MHz.
 		 *
-		 * Observation shows that if the lowest byte (which is
-		 * transferred first on the SPI bus) of that register
-		 * is 0x00 or 0x80 the calculated CRC doesn't always
-		 * match the transferred one.
+		 * Observation on the mcp2518fd shows that if the
+		 * lowest byte (which is transferred first on the SPI
+		 * bus) of that register is 0x00 or 0x80 the
+		 * calculated CRC doesn't always match the transferred
+		 * one. On the mcp2517fd this problem is not limited
+		 * to the first byte being 0x00 or 0x80.
 		 *
 		 * If the highest bit in the lowest byte is flipped
 		 * the transferred CRC matches the calculated one. We
-		 * assume for now the CRC calculation in the chip
-		 * works on wrong data and the transferred data is
-		 * correct.
+		 * assume for now the CRC operates on the correct
+		 * data.
 		 */
 		if (reg == MCP251XFD_REG_TBC &&
-		    (buf_rx->data[0] == 0x0 || buf_rx->data[0] == 0x80)) {
+		    ((buf_rx->data[0] & 0xf8) == 0x0 ||
+		     (buf_rx->data[0] & 0xf8) == 0x80)) {
 			/* Flip highest bit in lowest byte of le32 */
 			buf_rx->data[0] ^= 0x80;
 
@@ -347,10 +349,8 @@ mcp251xfd_regmap_crc_read(void *context,
 								  val_len);
 			if (!err) {
 				/* If CRC is now correct, assume
-				 * transferred data was OK, flip bit
-				 * back to original value.
+				 * flipped data is OK.
 				 */
-				buf_rx->data[0] ^= 0x80;
 				goto out;
 			}
 		}
diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c
index 54aa7c25c4de..ad8f50807aca 100644
--- a/drivers/net/can/sun4i_can.c
+++ b/drivers/net/can/sun4i_can.c
@@ -525,11 +525,6 @@ static int sun4i_can_err(struct net_device *dev, u8 isrc, u8 status)
 	rxerr = (errc >> 16) & 0xFF;
 	txerr = errc & 0xFF;
 
-	if (skb) {
-		cf->data[6] = txerr;
-		cf->data[7] = rxerr;
-	}
-
 	if (isrc & SUN4I_INT_DATA_OR) {
 		/* data overrun interrupt */
 		netdev_dbg(dev, "data overrun interrupt\n");
@@ -560,6 +555,10 @@ static int sun4i_can_err(struct net_device *dev, u8 isrc, u8 status)
 		else
 			state = CAN_STATE_ERROR_ACTIVE;
 	}
+	if (skb && state != CAN_STATE_BUS_OFF) {
+		cf->data[6] = txerr;
+		cf->data[7] = rxerr;
+	}
 	if (isrc & SUN4I_INT_BUS_ERR) {
 		/* bus error interrupt */
 		netdev_dbg(dev, "bus error interrupt\n");
diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c
index c9552846fe25..a1b7c1a451c0 100644
--- a/drivers/net/can/usb/ems_usb.c
+++ b/drivers/net/can/usb/ems_usb.c
@@ -194,7 +194,7 @@ struct __packed ems_cpc_msg {
 	__le32 ts_sec;	/* timestamp in seconds */
 	__le32 ts_nsec;	/* timestamp in nano seconds */
 
-	union {
+	union __packed {
 		u8 generic[64];
 		struct cpc_can_msg can_msg;
 		struct cpc_can_params can_params;
diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index d68d698f2606..e26b3d6f5b48 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -185,6 +185,8 @@ struct gs_can {
 
 	struct usb_anchor tx_submitted;
 	atomic_t active_tx_urbs;
+	void *rxbuf[GS_MAX_RX_URBS];
+	dma_addr_t rxbuf_dma[GS_MAX_RX_URBS];
 };
 
 /* usb interface struct */
@@ -594,6 +596,7 @@ static int gs_can_open(struct net_device *netdev)
 		for (i = 0; i < GS_MAX_RX_URBS; i++) {
 			struct urb *urb;
 			u8 *buf;
+			dma_addr_t buf_dma;
 
 			/* alloc rx urb */
 			urb = usb_alloc_urb(0, GFP_KERNEL);
@@ -604,7 +607,7 @@ static int gs_can_open(struct net_device *netdev)
 			buf = usb_alloc_coherent(dev->udev,
 						 sizeof(struct gs_host_frame),
 						 GFP_KERNEL,
-						 &urb->transfer_dma);
+						 &buf_dma);
 			if (!buf) {
 				netdev_err(netdev,
 					   "No memory left for USB buffer\n");
@@ -612,6 +615,8 @@ static int gs_can_open(struct net_device *netdev)
 				return -ENOMEM;
 			}
 
+			urb->transfer_dma = buf_dma;
+
 			/* fill, anchor, and submit rx urb */
 			usb_fill_bulk_urb(urb,
 					  dev->udev,
@@ -635,10 +640,17 @@ static int gs_can_open(struct net_device *netdev)
 					   rc);
 
 				usb_unanchor_urb(urb);
+				usb_free_coherent(dev->udev,
+						  sizeof(struct gs_host_frame),
+						  buf,
+						  buf_dma);
 				usb_free_urb(urb);
 				break;
 			}
 
+			dev->rxbuf[i] = buf;
+			dev->rxbuf_dma[i] = buf_dma;
+
 			/* Drop reference,
 			 * USB core will take care of freeing it
 			 */
@@ -703,13 +715,20 @@ static int gs_can_close(struct net_device *netdev)
 	int rc;
 	struct gs_can *dev = netdev_priv(netdev);
 	struct gs_usb *parent = dev->parent;
+	unsigned int i;
 
 	netif_stop_queue(netdev);
 
 	/* Stop polling */
 	parent->active_channels--;
-	if (!parent->active_channels)
+	if (!parent->active_channels) {
 		usb_kill_anchored_urbs(&parent->rx_submitted);
+		for (i = 0; i < GS_MAX_RX_URBS; i++)
+			usb_free_coherent(dev->udev,
+					  sizeof(struct gs_host_frame),
+					  dev->rxbuf[i],
+					  dev->rxbuf_dma[i]);
+	}
 
 	/* Stop sending URBs */
 	usb_kill_anchored_urbs(&dev->tx_submitted);
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h
index 390b6bde883c..61e67986b625 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h
@@ -35,9 +35,10 @@
 #define KVASER_USB_RX_BUFFER_SIZE		3072
 #define KVASER_USB_MAX_NET_DEVICES		5
 
-/* USB devices features */
-#define KVASER_USB_HAS_SILENT_MODE		BIT(0)
-#define KVASER_USB_HAS_TXRX_ERRORS		BIT(1)
+/* Kvaser USB device quirks */
+#define KVASER_USB_QUIRK_HAS_SILENT_MODE	BIT(0)
+#define KVASER_USB_QUIRK_HAS_TXRX_ERRORS	BIT(1)
+#define KVASER_USB_QUIRK_IGNORE_CLK_FREQ	BIT(2)
 
 /* Device capabilities */
 #define KVASER_USB_CAP_BERR_CAP			0x01
@@ -65,12 +66,7 @@ struct kvaser_usb_dev_card_data_hydra {
 struct kvaser_usb_dev_card_data {
 	u32 ctrlmode_supported;
 	u32 capabilities;
-	union {
-		struct {
-			enum kvaser_usb_leaf_family family;
-		} leaf;
-		struct kvaser_usb_dev_card_data_hydra hydra;
-	};
+	struct kvaser_usb_dev_card_data_hydra hydra;
 };
 
 /* Context for an outstanding, not yet ACKed, transmission */
@@ -84,7 +80,7 @@ struct kvaser_usb {
 	struct usb_device *udev;
 	struct usb_interface *intf;
 	struct kvaser_usb_net_priv *nets[KVASER_USB_MAX_NET_DEVICES];
-	const struct kvaser_usb_dev_ops *ops;
+	const struct kvaser_usb_driver_info *driver_info;
 	const struct kvaser_usb_dev_cfg *cfg;
 
 	struct usb_endpoint_descriptor *bulk_in, *bulk_out;
@@ -166,6 +162,12 @@ struct kvaser_usb_dev_ops {
 				  int *cmd_len, u16 transid);
 };
 
+struct kvaser_usb_driver_info {
+	u32 quirks;
+	enum kvaser_usb_leaf_family family;
+	const struct kvaser_usb_dev_ops *ops;
+};
+
 struct kvaser_usb_dev_cfg {
 	const struct can_clock clock;
 	const unsigned int timestamp_freq;
@@ -185,4 +187,7 @@ int kvaser_usb_send_cmd_async(struct kvaser_usb_net_priv *priv, void *cmd,
 			      int len);
 
 int kvaser_usb_can_rx_over_error(struct net_device *netdev);
+
+extern const struct can_bittiming_const kvaser_usb_flexc_bittiming_const;
+
 #endif /* KVASER_USB_H */
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
index 0cc0fc866a2a..e570f5a76bbf 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
@@ -61,8 +61,6 @@
 #define USB_USBCAN_R_V2_PRODUCT_ID		294
 #define USB_LEAF_LIGHT_R_V2_PRODUCT_ID		295
 #define USB_LEAF_LIGHT_HS_V2_OEM2_PRODUCT_ID	296
-#define USB_LEAF_PRODUCT_ID_END \
-	USB_LEAF_LIGHT_HS_V2_OEM2_PRODUCT_ID
 
 /* Kvaser USBCan-II devices product ids */
 #define USB_USBCAN_REVB_PRODUCT_ID		2
@@ -89,116 +87,153 @@
 #define USB_USBCAN_PRO_4HS_PRODUCT_ID		276
 #define USB_HYBRID_CANLIN_PRODUCT_ID		277
 #define USB_HYBRID_PRO_CANLIN_PRODUCT_ID	278
-#define USB_HYDRA_PRODUCT_ID_END \
-	USB_HYBRID_PRO_CANLIN_PRODUCT_ID
 
-static inline bool kvaser_is_leaf(const struct usb_device_id *id)
-{
-	return (id->idProduct >= USB_LEAF_DEVEL_PRODUCT_ID &&
-		id->idProduct <= USB_CAN_R_PRODUCT_ID) ||
-		(id->idProduct >= USB_LEAF_LITE_V2_PRODUCT_ID &&
-		 id->idProduct <= USB_LEAF_PRODUCT_ID_END);
-}
+static const struct kvaser_usb_driver_info kvaser_usb_driver_info_hydra = {
+	.quirks = 0,
+	.ops = &kvaser_usb_hydra_dev_ops,
+};
 
-static inline bool kvaser_is_usbcan(const struct usb_device_id *id)
-{
-	return id->idProduct >= USB_USBCAN_REVB_PRODUCT_ID &&
-	       id->idProduct <= USB_MEMORATOR_PRODUCT_ID;
-}
+static const struct kvaser_usb_driver_info kvaser_usb_driver_info_usbcan = {
+	.quirks = KVASER_USB_QUIRK_HAS_TXRX_ERRORS |
+		  KVASER_USB_QUIRK_HAS_SILENT_MODE,
+	.family = KVASER_USBCAN,
+	.ops = &kvaser_usb_leaf_dev_ops,
+};
 
-static inline bool kvaser_is_hydra(const struct usb_device_id *id)
-{
-	return id->idProduct >= USB_BLACKBIRD_V2_PRODUCT_ID &&
-	       id->idProduct <= USB_HYDRA_PRODUCT_ID_END;
-}
+static const struct kvaser_usb_driver_info kvaser_usb_driver_info_leaf = {
+	.quirks = KVASER_USB_QUIRK_IGNORE_CLK_FREQ,
+	.family = KVASER_LEAF,
+	.ops = &kvaser_usb_leaf_dev_ops,
+};
+
+static const struct kvaser_usb_driver_info kvaser_usb_driver_info_leaf_err = {
+	.quirks = KVASER_USB_QUIRK_HAS_TXRX_ERRORS |
+		  KVASER_USB_QUIRK_IGNORE_CLK_FREQ,
+	.family = KVASER_LEAF,
+	.ops = &kvaser_usb_leaf_dev_ops,
+};
+
+static const struct kvaser_usb_driver_info kvaser_usb_driver_info_leaf_err_listen = {
+	.quirks = KVASER_USB_QUIRK_HAS_TXRX_ERRORS |
+		  KVASER_USB_QUIRK_HAS_SILENT_MODE |
+		  KVASER_USB_QUIRK_IGNORE_CLK_FREQ,
+	.family = KVASER_LEAF,
+	.ops = &kvaser_usb_leaf_dev_ops,
+};
+
+static const struct kvaser_usb_driver_info kvaser_usb_driver_info_leafimx = {
+	.quirks = 0,
+	.ops = &kvaser_usb_leaf_dev_ops,
+};
 
 static const struct usb_device_id kvaser_usb_table[] = {
-	/* Leaf USB product IDs */
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_DEVEL_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_PRODUCT_ID) },
+	/* Leaf M32C USB product IDs */
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_DEVEL_PRODUCT_ID),
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_leaf },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_PRODUCT_ID),
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_leaf },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_PRODUCT_ID),
-		.driver_info = KVASER_USB_HAS_TXRX_ERRORS |
-			       KVASER_USB_HAS_SILENT_MODE },
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_leaf_err_listen },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_SPRO_PRODUCT_ID),
-		.driver_info = KVASER_USB_HAS_TXRX_ERRORS |
-			       KVASER_USB_HAS_SILENT_MODE },
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_leaf_err_listen },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_LS_PRODUCT_ID),
-		.driver_info = KVASER_USB_HAS_TXRX_ERRORS |
-			       KVASER_USB_HAS_SILENT_MODE },
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_leaf_err_listen },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_SWC_PRODUCT_ID),
-		.driver_info = KVASER_USB_HAS_TXRX_ERRORS |
-			       KVASER_USB_HAS_SILENT_MODE },
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_leaf_err_listen },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_LIN_PRODUCT_ID),
-		.driver_info = KVASER_USB_HAS_TXRX_ERRORS |
-			       KVASER_USB_HAS_SILENT_MODE },
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_leaf_err_listen },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_SPRO_LS_PRODUCT_ID),
-		.driver_info = KVASER_USB_HAS_TXRX_ERRORS |
-			       KVASER_USB_HAS_SILENT_MODE },
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_leaf_err_listen },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_SPRO_SWC_PRODUCT_ID),
-		.driver_info = KVASER_USB_HAS_TXRX_ERRORS |
-			       KVASER_USB_HAS_SILENT_MODE },
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_leaf_err_listen },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO2_DEVEL_PRODUCT_ID),
-		.driver_info = KVASER_USB_HAS_TXRX_ERRORS |
-			       KVASER_USB_HAS_SILENT_MODE },
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_leaf_err_listen },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO2_HSHS_PRODUCT_ID),
-		.driver_info = KVASER_USB_HAS_TXRX_ERRORS |
-			       KVASER_USB_HAS_SILENT_MODE },
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_leaf_err_listen },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_UPRO_HSHS_PRODUCT_ID),
-		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_GI_PRODUCT_ID) },
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_leaf_err },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_GI_PRODUCT_ID),
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_leaf },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_OBDII_PRODUCT_ID),
-		.driver_info = KVASER_USB_HAS_TXRX_ERRORS |
-			       KVASER_USB_HAS_SILENT_MODE },
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_leaf_err_listen },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO2_HSLS_PRODUCT_ID),
-		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_leaf_err },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_CH_PRODUCT_ID),
-		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_leaf_err },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_BLACKBIRD_SPRO_PRODUCT_ID),
-		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_leaf_err },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_OEM_MERCURY_PRODUCT_ID),
-		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_leaf_err },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_OEM_LEAF_PRODUCT_ID),
-		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_leaf_err },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_CAN_R_PRODUCT_ID),
-		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_V2_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MINI_PCIE_HS_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LIGHT_HS_V2_OEM_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_LIGHT_2HS_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MINI_PCIE_2HS_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_R_V2_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LIGHT_R_V2_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LIGHT_HS_V2_OEM2_PRODUCT_ID) },
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_leaf_err },
+
+	/* Leaf i.MX28 USB product IDs */
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_V2_PRODUCT_ID),
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_leafimx },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MINI_PCIE_HS_PRODUCT_ID),
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_leafimx },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LIGHT_HS_V2_OEM_PRODUCT_ID),
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_leafimx },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_LIGHT_2HS_PRODUCT_ID),
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_leafimx },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MINI_PCIE_2HS_PRODUCT_ID),
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_leafimx },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_R_V2_PRODUCT_ID),
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_leafimx },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LIGHT_R_V2_PRODUCT_ID),
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_leafimx },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LIGHT_HS_V2_OEM2_PRODUCT_ID),
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_leafimx },
 
 	/* USBCANII USB product IDs */
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN2_PRODUCT_ID),
-		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_usbcan },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_REVB_PRODUCT_ID),
-		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_usbcan },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMORATOR_PRODUCT_ID),
-		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_usbcan },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_VCI2_PRODUCT_ID),
-		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_usbcan },
 
 	/* Minihydra USB product IDs */
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_BLACKBIRD_V2_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO_PRO_5HS_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_PRO_5HS_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_LIGHT_4HS_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_HS_V2_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_PRO_2HS_V2_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO_2HS_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO_PRO_2HS_V2_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_HYBRID_2CANLIN_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_ATI_USBCAN_PRO_2HS_V2_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_ATI_MEMO_PRO_2HS_V2_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_HYBRID_PRO_2CANLIN_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_U100_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_U100P_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_U100S_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_PRO_4HS_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_HYBRID_CANLIN_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_HYBRID_PRO_CANLIN_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_BLACKBIRD_V2_PRODUCT_ID),
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_hydra },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO_PRO_5HS_PRODUCT_ID),
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_hydra },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_PRO_5HS_PRODUCT_ID),
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_hydra },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_LIGHT_4HS_PRODUCT_ID),
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_hydra },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_HS_V2_PRODUCT_ID),
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_hydra },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_PRO_2HS_V2_PRODUCT_ID),
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_hydra },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO_2HS_PRODUCT_ID),
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_hydra },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO_PRO_2HS_V2_PRODUCT_ID),
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_hydra },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_HYBRID_2CANLIN_PRODUCT_ID),
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_hydra },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_ATI_USBCAN_PRO_2HS_V2_PRODUCT_ID),
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_hydra },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_ATI_MEMO_PRO_2HS_V2_PRODUCT_ID),
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_hydra },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_HYBRID_PRO_2CANLIN_PRODUCT_ID),
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_hydra },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_U100_PRODUCT_ID),
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_hydra },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_U100P_PRODUCT_ID),
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_hydra },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_U100S_PRODUCT_ID),
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_hydra },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_PRO_4HS_PRODUCT_ID),
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_hydra },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_HYBRID_CANLIN_PRODUCT_ID),
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_hydra },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_HYBRID_PRO_CANLIN_PRODUCT_ID),
+		.driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_hydra },
 	{ }
 };
 MODULE_DEVICE_TABLE(usb, kvaser_usb_table);
@@ -289,6 +324,7 @@ int kvaser_usb_can_rx_over_error(struct net_device *netdev)
 static void kvaser_usb_read_bulk_callback(struct urb *urb)
 {
 	struct kvaser_usb *dev = urb->context;
+	const struct kvaser_usb_dev_ops *ops = dev->driver_info->ops;
 	int err;
 	unsigned int i;
 
@@ -305,8 +341,8 @@ static void kvaser_usb_read_bulk_callback(struct urb *urb)
 		goto resubmit_urb;
 	}
 
-	dev->ops->dev_read_bulk_callback(dev, urb->transfer_buffer,
-					 urb->actual_length);
+	ops->dev_read_bulk_callback(dev, urb->transfer_buffer,
+				    urb->actual_length);
 
 resubmit_urb:
 	usb_fill_bulk_urb(urb, dev->udev,
@@ -400,6 +436,7 @@ static int kvaser_usb_open(struct net_device *netdev)
 {
 	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
 	struct kvaser_usb *dev = priv->dev;
+	const struct kvaser_usb_dev_ops *ops = dev->driver_info->ops;
 	int err;
 
 	err = open_candev(netdev);
@@ -410,11 +447,11 @@ static int kvaser_usb_open(struct net_device *netdev)
 	if (err)
 		goto error;
 
-	err = dev->ops->dev_set_opt_mode(priv);
+	err = ops->dev_set_opt_mode(priv);
 	if (err)
 		goto error;
 
-	err = dev->ops->dev_start_chip(priv);
+	err = ops->dev_start_chip(priv);
 	if (err) {
 		netdev_warn(netdev, "Cannot start device, error %d\n", err);
 		goto error;
@@ -471,22 +508,23 @@ static int kvaser_usb_close(struct net_device *netdev)
 {
 	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
 	struct kvaser_usb *dev = priv->dev;
+	const struct kvaser_usb_dev_ops *ops = dev->driver_info->ops;
 	int err;
 
 	netif_stop_queue(netdev);
 
-	err = dev->ops->dev_flush_queue(priv);
+	err = ops->dev_flush_queue(priv);
 	if (err)
 		netdev_warn(netdev, "Cannot flush queue, error %d\n", err);
 
-	if (dev->ops->dev_reset_chip) {
-		err = dev->ops->dev_reset_chip(dev, priv->channel);
+	if (ops->dev_reset_chip) {
+		err = ops->dev_reset_chip(dev, priv->channel);
 		if (err)
 			netdev_warn(netdev, "Cannot reset card, error %d\n",
 				    err);
 	}
 
-	err = dev->ops->dev_stop_chip(priv);
+	err = ops->dev_stop_chip(priv);
 	if (err)
 		netdev_warn(netdev, "Cannot stop device, error %d\n", err);
 
@@ -525,6 +563,7 @@ static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb,
 {
 	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
 	struct kvaser_usb *dev = priv->dev;
+	const struct kvaser_usb_dev_ops *ops = dev->driver_info->ops;
 	struct net_device_stats *stats = &netdev->stats;
 	struct kvaser_usb_tx_urb_context *context = NULL;
 	struct urb *urb;
@@ -567,8 +606,8 @@ static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb,
 		goto freeurb;
 	}
 
-	buf = dev->ops->dev_frame_to_cmd(priv, skb, &context->dlc, &cmd_len,
-					 context->echo_index);
+	buf = ops->dev_frame_to_cmd(priv, skb, &context->dlc, &cmd_len,
+				    context->echo_index);
 	if (!buf) {
 		stats->tx_dropped++;
 		dev_kfree_skb(skb);
@@ -652,15 +691,16 @@ static void kvaser_usb_remove_interfaces(struct kvaser_usb *dev)
 	}
 }
 
-static int kvaser_usb_init_one(struct kvaser_usb *dev,
-			       const struct usb_device_id *id, int channel)
+static int kvaser_usb_init_one(struct kvaser_usb *dev, int channel)
 {
 	struct net_device *netdev;
 	struct kvaser_usb_net_priv *priv;
+	const struct kvaser_usb_driver_info *driver_info = dev->driver_info;
+	const struct kvaser_usb_dev_ops *ops = driver_info->ops;
 	int err;
 
-	if (dev->ops->dev_reset_chip) {
-		err = dev->ops->dev_reset_chip(dev, channel);
+	if (ops->dev_reset_chip) {
+		err = ops->dev_reset_chip(dev, channel);
 		if (err)
 			return err;
 	}
@@ -689,20 +729,19 @@ static int kvaser_usb_init_one(struct kvaser_usb *dev,
 	priv->can.state = CAN_STATE_STOPPED;
 	priv->can.clock.freq = dev->cfg->clock.freq;
 	priv->can.bittiming_const = dev->cfg->bittiming_const;
-	priv->can.do_set_bittiming = dev->ops->dev_set_bittiming;
-	priv->can.do_set_mode = dev->ops->dev_set_mode;
-	if ((id->driver_info & KVASER_USB_HAS_TXRX_ERRORS) ||
+	priv->can.do_set_bittiming = ops->dev_set_bittiming;
+	priv->can.do_set_mode = ops->dev_set_mode;
+	if ((driver_info->quirks & KVASER_USB_QUIRK_HAS_TXRX_ERRORS) ||
 	    (priv->dev->card_data.capabilities & KVASER_USB_CAP_BERR_CAP))
-		priv->can.do_get_berr_counter = dev->ops->dev_get_berr_counter;
-	if (id->driver_info & KVASER_USB_HAS_SILENT_MODE)
+		priv->can.do_get_berr_counter = ops->dev_get_berr_counter;
+	if (driver_info->quirks & KVASER_USB_QUIRK_HAS_SILENT_MODE)
 		priv->can.ctrlmode_supported |= CAN_CTRLMODE_LISTENONLY;
 
 	priv->can.ctrlmode_supported |= dev->card_data.ctrlmode_supported;
 
 	if (priv->can.ctrlmode_supported & CAN_CTRLMODE_FD) {
 		priv->can.data_bittiming_const = dev->cfg->data_bittiming_const;
-		priv->can.do_set_data_bittiming =
-					dev->ops->dev_set_data_bittiming;
+		priv->can.do_set_data_bittiming = ops->dev_set_data_bittiming;
 	}
 
 	netdev->flags |= IFF_ECHO;
@@ -733,29 +772,22 @@ static int kvaser_usb_probe(struct usb_interface *intf,
 	struct kvaser_usb *dev;
 	int err;
 	int i;
+	const struct kvaser_usb_driver_info *driver_info;
+	const struct kvaser_usb_dev_ops *ops;
+
+	driver_info = (const struct kvaser_usb_driver_info *)id->driver_info;
+	if (!driver_info)
+		return -ENODEV;
 
 	dev = devm_kzalloc(&intf->dev, sizeof(*dev), GFP_KERNEL);
 	if (!dev)
 		return -ENOMEM;
 
-	if (kvaser_is_leaf(id)) {
-		dev->card_data.leaf.family = KVASER_LEAF;
-		dev->ops = &kvaser_usb_leaf_dev_ops;
-	} else if (kvaser_is_usbcan(id)) {
-		dev->card_data.leaf.family = KVASER_USBCAN;
-		dev->ops = &kvaser_usb_leaf_dev_ops;
-	} else if (kvaser_is_hydra(id)) {
-		dev->ops = &kvaser_usb_hydra_dev_ops;
-	} else {
-		dev_err(&intf->dev,
-			"Product ID (%d) is not a supported Kvaser USB device\n",
-			id->idProduct);
-		return -ENODEV;
-	}
-
 	dev->intf = intf;
+	dev->driver_info = driver_info;
+	ops = driver_info->ops;
 
-	err = dev->ops->dev_setup_endpoints(dev);
+	err = ops->dev_setup_endpoints(dev);
 	if (err) {
 		dev_err(&intf->dev, "Cannot get usb endpoint(s)");
 		return err;
@@ -769,22 +801,22 @@ static int kvaser_usb_probe(struct usb_interface *intf,
 
 	dev->card_data.ctrlmode_supported = 0;
 	dev->card_data.capabilities = 0;
-	err = dev->ops->dev_init_card(dev);
+	err = ops->dev_init_card(dev);
 	if (err) {
 		dev_err(&intf->dev,
 			"Failed to initialize card, error %d\n", err);
 		return err;
 	}
 
-	err = dev->ops->dev_get_software_info(dev);
+	err = ops->dev_get_software_info(dev);
 	if (err) {
 		dev_err(&intf->dev,
 			"Cannot get software info, error %d\n", err);
 		return err;
 	}
 
-	if (dev->ops->dev_get_software_details) {
-		err = dev->ops->dev_get_software_details(dev);
+	if (ops->dev_get_software_details) {
+		err = ops->dev_get_software_details(dev);
 		if (err) {
 			dev_err(&intf->dev,
 				"Cannot get software details, error %d\n", err);
@@ -802,14 +834,14 @@ static int kvaser_usb_probe(struct usb_interface *intf,
 
 	dev_dbg(&intf->dev, "Max outstanding tx = %d URBs\n", dev->max_tx_urbs);
 
-	err = dev->ops->dev_get_card_info(dev);
+	err = ops->dev_get_card_info(dev);
 	if (err) {
 		dev_err(&intf->dev, "Cannot get card info, error %d\n", err);
 		return err;
 	}
 
-	if (dev->ops->dev_get_capabilities) {
-		err = dev->ops->dev_get_capabilities(dev);
+	if (ops->dev_get_capabilities) {
+		err = ops->dev_get_capabilities(dev);
 		if (err) {
 			dev_err(&intf->dev,
 				"Cannot get capabilities, error %d\n", err);
@@ -819,7 +851,7 @@ static int kvaser_usb_probe(struct usb_interface *intf,
 	}
 
 	for (i = 0; i < dev->nchannels; i++) {
-		err = kvaser_usb_init_one(dev, id, i);
+		err = kvaser_usb_init_one(dev, i);
 		if (err) {
 			kvaser_usb_remove_interfaces(dev);
 			return err;
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
index dcee8dc828ec..93d7ee6d17b6 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
@@ -373,7 +373,7 @@ static const struct can_bittiming_const kvaser_usb_hydra_kcan_bittiming_c = {
 	.brp_inc = 1,
 };
 
-static const struct can_bittiming_const kvaser_usb_hydra_flexc_bittiming_c = {
+const struct can_bittiming_const kvaser_usb_flexc_bittiming_const = {
 	.name = "kvaser_usb_flex",
 	.tseg1_min = 4,
 	.tseg1_max = 16,
@@ -916,8 +916,10 @@ static void kvaser_usb_hydra_update_state(struct kvaser_usb_net_priv *priv,
 	    new_state < CAN_STATE_BUS_OFF)
 		priv->can.can_stats.restarts++;
 
-	cf->data[6] = bec->txerr;
-	cf->data[7] = bec->rxerr;
+	if (new_state != CAN_STATE_BUS_OFF) {
+		cf->data[6] = bec->txerr;
+		cf->data[7] = bec->rxerr;
+	}
 
 	stats = &netdev->stats;
 	stats->rx_packets++;
@@ -1071,8 +1073,10 @@ kvaser_usb_hydra_error_frame(struct kvaser_usb_net_priv *priv,
 	shhwtstamps->hwtstamp = hwtstamp;
 
 	cf->can_id |= CAN_ERR_BUSERROR;
-	cf->data[6] = bec.txerr;
-	cf->data[7] = bec.rxerr;
+	if (new_state != CAN_STATE_BUS_OFF) {
+		cf->data[6] = bec.txerr;
+		cf->data[7] = bec.rxerr;
+	}
 
 	stats->rx_packets++;
 	stats->rx_bytes += cf->len;
@@ -2052,7 +2056,7 @@ static const struct kvaser_usb_dev_cfg kvaser_usb_hydra_dev_cfg_flexc = {
 		.freq = 24000000,
 	},
 	.timestamp_freq = 1,
-	.bittiming_const = &kvaser_usb_hydra_flexc_bittiming_c,
+	.bittiming_const = &kvaser_usb_flexc_bittiming_const,
 };
 
 static const struct kvaser_usb_dev_cfg kvaser_usb_hydra_dev_cfg_rt = {
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
index f7af1bf5ab46..05d54c4f929f 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
@@ -100,16 +100,6 @@
 #define USBCAN_ERROR_STATE_RX_ERROR	BIT(1)
 #define USBCAN_ERROR_STATE_BUSERROR	BIT(2)
 
-/* bittiming parameters */
-#define KVASER_USB_TSEG1_MIN		1
-#define KVASER_USB_TSEG1_MAX		16
-#define KVASER_USB_TSEG2_MIN		1
-#define KVASER_USB_TSEG2_MAX		8
-#define KVASER_USB_SJW_MAX		4
-#define KVASER_USB_BRP_MIN		1
-#define KVASER_USB_BRP_MAX		64
-#define KVASER_USB_BRP_INC		1
-
 /* ctrl modes */
 #define KVASER_CTRL_MODE_NORMAL		1
 #define KVASER_CTRL_MODE_SILENT		2
@@ -342,48 +332,68 @@ struct kvaser_usb_err_summary {
 	};
 };
 
-static const struct can_bittiming_const kvaser_usb_leaf_bittiming_const = {
-	.name = "kvaser_usb",
-	.tseg1_min = KVASER_USB_TSEG1_MIN,
-	.tseg1_max = KVASER_USB_TSEG1_MAX,
-	.tseg2_min = KVASER_USB_TSEG2_MIN,
-	.tseg2_max = KVASER_USB_TSEG2_MAX,
-	.sjw_max = KVASER_USB_SJW_MAX,
-	.brp_min = KVASER_USB_BRP_MIN,
-	.brp_max = KVASER_USB_BRP_MAX,
-	.brp_inc = KVASER_USB_BRP_INC,
+static const struct can_bittiming_const kvaser_usb_leaf_m16c_bittiming_const = {
+	.name = "kvaser_usb_ucii",
+	.tseg1_min = 4,
+	.tseg1_max = 16,
+	.tseg2_min = 2,
+	.tseg2_max = 8,
+	.sjw_max = 4,
+	.brp_min = 1,
+	.brp_max = 16,
+	.brp_inc = 1,
+};
+
+static const struct can_bittiming_const kvaser_usb_leaf_m32c_bittiming_const = {
+	.name = "kvaser_usb_leaf",
+	.tseg1_min = 3,
+	.tseg1_max = 16,
+	.tseg2_min = 2,
+	.tseg2_max = 8,
+	.sjw_max = 4,
+	.brp_min = 2,
+	.brp_max = 128,
+	.brp_inc = 2,
 };
 
-static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg_8mhz = {
+static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_usbcan_dev_cfg = {
 	.clock = {
 		.freq = 8000000,
 	},
 	.timestamp_freq = 1,
-	.bittiming_const = &kvaser_usb_leaf_bittiming_const,
+	.bittiming_const = &kvaser_usb_leaf_m16c_bittiming_const,
+};
+
+static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_m32c_dev_cfg = {
+	.clock = {
+		.freq = 16000000,
+	},
+	.timestamp_freq = 1,
+	.bittiming_const = &kvaser_usb_leaf_m32c_bittiming_const,
 };
 
-static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg_16mhz = {
+static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_imx_dev_cfg_16mhz = {
 	.clock = {
 		.freq = 16000000,
 	},
 	.timestamp_freq = 1,
-	.bittiming_const = &kvaser_usb_leaf_bittiming_const,
+	.bittiming_const = &kvaser_usb_flexc_bittiming_const,
 };
 
-static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg_24mhz = {
+static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_imx_dev_cfg_24mhz = {
 	.clock = {
 		.freq = 24000000,
 	},
 	.timestamp_freq = 1,
-	.bittiming_const = &kvaser_usb_leaf_bittiming_const,
+	.bittiming_const = &kvaser_usb_flexc_bittiming_const,
 };
 
-static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg_32mhz = {
+static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_imx_dev_cfg_32mhz = {
 	.clock = {
 		.freq = 32000000,
 	},
 	.timestamp_freq = 1,
-	.bittiming_const = &kvaser_usb_leaf_bittiming_const,
+	.bittiming_const = &kvaser_usb_flexc_bittiming_const,
 };
 
 static void *
@@ -405,7 +415,7 @@ kvaser_usb_leaf_frame_to_cmd(const struct kvaser_usb_net_priv *priv,
 				      sizeof(struct kvaser_cmd_tx_can);
 		cmd->u.tx_can.channel = priv->channel;
 
-		switch (dev->card_data.leaf.family) {
+		switch (dev->driver_info->family) {
 		case KVASER_LEAF:
 			cmd_tx_can_flags = &cmd->u.tx_can.leaf.flags;
 			break;
@@ -525,16 +535,23 @@ static void kvaser_usb_leaf_get_software_info_leaf(struct kvaser_usb *dev,
 	dev->fw_version = le32_to_cpu(softinfo->fw_version);
 	dev->max_tx_urbs = le16_to_cpu(softinfo->max_outstanding_tx);
 
-	switch (sw_options & KVASER_USB_LEAF_SWOPTION_FREQ_MASK) {
-	case KVASER_USB_LEAF_SWOPTION_FREQ_16_MHZ_CLK:
-		dev->cfg = &kvaser_usb_leaf_dev_cfg_16mhz;
-		break;
-	case KVASER_USB_LEAF_SWOPTION_FREQ_24_MHZ_CLK:
-		dev->cfg = &kvaser_usb_leaf_dev_cfg_24mhz;
-		break;
-	case KVASER_USB_LEAF_SWOPTION_FREQ_32_MHZ_CLK:
-		dev->cfg = &kvaser_usb_leaf_dev_cfg_32mhz;
-		break;
+	if (dev->driver_info->quirks & KVASER_USB_QUIRK_IGNORE_CLK_FREQ) {
+		/* Firmware expects bittiming parameters calculated for 16MHz
+		 * clock, regardless of the actual clock
+		 */
+		dev->cfg = &kvaser_usb_leaf_m32c_dev_cfg;
+	} else {
+		switch (sw_options & KVASER_USB_LEAF_SWOPTION_FREQ_MASK) {
+		case KVASER_USB_LEAF_SWOPTION_FREQ_16_MHZ_CLK:
+			dev->cfg = &kvaser_usb_leaf_imx_dev_cfg_16mhz;
+			break;
+		case KVASER_USB_LEAF_SWOPTION_FREQ_24_MHZ_CLK:
+			dev->cfg = &kvaser_usb_leaf_imx_dev_cfg_24mhz;
+			break;
+		case KVASER_USB_LEAF_SWOPTION_FREQ_32_MHZ_CLK:
+			dev->cfg = &kvaser_usb_leaf_imx_dev_cfg_32mhz;
+			break;
+		}
 	}
 }
 
@@ -551,7 +568,7 @@ static int kvaser_usb_leaf_get_software_info_inner(struct kvaser_usb *dev)
 	if (err)
 		return err;
 
-	switch (dev->card_data.leaf.family) {
+	switch (dev->driver_info->family) {
 	case KVASER_LEAF:
 		kvaser_usb_leaf_get_software_info_leaf(dev, &cmd.u.leaf.softinfo);
 		break;
@@ -559,7 +576,7 @@ static int kvaser_usb_leaf_get_software_info_inner(struct kvaser_usb *dev)
 		dev->fw_version = le32_to_cpu(cmd.u.usbcan.softinfo.fw_version);
 		dev->max_tx_urbs =
 			le16_to_cpu(cmd.u.usbcan.softinfo.max_outstanding_tx);
-		dev->cfg = &kvaser_usb_leaf_dev_cfg_8mhz;
+		dev->cfg = &kvaser_usb_leaf_usbcan_dev_cfg;
 		break;
 	}
 
@@ -598,7 +615,7 @@ static int kvaser_usb_leaf_get_card_info(struct kvaser_usb *dev)
 
 	dev->nchannels = cmd.u.cardinfo.nchannels;
 	if (dev->nchannels > KVASER_USB_MAX_NET_DEVICES ||
-	    (dev->card_data.leaf.family == KVASER_USBCAN &&
+	    (dev->driver_info->family == KVASER_USBCAN &&
 	     dev->nchannels > MAX_USBCAN_NET_DEVICES))
 		return -EINVAL;
 
@@ -734,7 +751,7 @@ kvaser_usb_leaf_rx_error_update_can_state(struct kvaser_usb_net_priv *priv,
 	    new_state < CAN_STATE_BUS_OFF)
 		priv->can.can_stats.restarts++;
 
-	switch (dev->card_data.leaf.family) {
+	switch (dev->driver_info->family) {
 	case KVASER_LEAF:
 		if (es->leaf.error_factor) {
 			priv->can.can_stats.bus_error++;
@@ -813,7 +830,7 @@ static void kvaser_usb_leaf_rx_error(const struct kvaser_usb *dev,
 		}
 	}
 
-	switch (dev->card_data.leaf.family) {
+	switch (dev->driver_info->family) {
 	case KVASER_LEAF:
 		if (es->leaf.error_factor) {
 			cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_PROT;
@@ -840,8 +857,10 @@ static void kvaser_usb_leaf_rx_error(const struct kvaser_usb *dev,
 		break;
 	}
 
-	cf->data[6] = es->txerr;
-	cf->data[7] = es->rxerr;
+	if (new_state != CAN_STATE_BUS_OFF) {
+		cf->data[6] = es->txerr;
+		cf->data[7] = es->rxerr;
+	}
 
 	stats->rx_packets++;
 	stats->rx_bytes += cf->len;
@@ -1005,7 +1024,7 @@ static void kvaser_usb_leaf_rx_can_msg(const struct kvaser_usb *dev,
 	stats = &priv->netdev->stats;
 
 	if ((cmd->u.rx_can_header.flag & MSG_FLAG_ERROR_FRAME) &&
-	    (dev->card_data.leaf.family == KVASER_LEAF &&
+	    (dev->driver_info->family == KVASER_LEAF &&
 	     cmd->id == CMD_LEAF_LOG_MESSAGE)) {
 		kvaser_usb_leaf_leaf_rx_error(dev, cmd);
 		return;
@@ -1021,7 +1040,7 @@ static void kvaser_usb_leaf_rx_can_msg(const struct kvaser_usb *dev,
 		return;
 	}
 
-	switch (dev->card_data.leaf.family) {
+	switch (dev->driver_info->family) {
 	case KVASER_LEAF:
 		rx_data = cmd->u.leaf.rx_can.data;
 		break;
@@ -1036,7 +1055,7 @@ static void kvaser_usb_leaf_rx_can_msg(const struct kvaser_usb *dev,
 		return;
 	}
 
-	if (dev->card_data.leaf.family == KVASER_LEAF && cmd->id ==
+	if (dev->driver_info->family == KVASER_LEAF && cmd->id ==
 	    CMD_LEAF_LOG_MESSAGE) {
 		cf->can_id = le32_to_cpu(cmd->u.leaf.log_message.id);
 		if (cf->can_id & KVASER_EXTENDED_FRAME)
@@ -1133,14 +1152,14 @@ static void kvaser_usb_leaf_handle_command(const struct kvaser_usb *dev,
 		break;
 
 	case CMD_LEAF_LOG_MESSAGE:
-		if (dev->card_data.leaf.family != KVASER_LEAF)
+		if (dev->driver_info->family != KVASER_LEAF)
 			goto warn;
 		kvaser_usb_leaf_rx_can_msg(dev, cmd);
 		break;
 
 	case CMD_CHIP_STATE_EVENT:
 	case CMD_CAN_ERROR_EVENT:
-		if (dev->card_data.leaf.family == KVASER_LEAF)
+		if (dev->driver_info->family == KVASER_LEAF)
 			kvaser_usb_leaf_leaf_rx_error(dev, cmd);
 		else
 			kvaser_usb_leaf_usbcan_rx_error(dev, cmd);
@@ -1152,12 +1171,12 @@ static void kvaser_usb_leaf_handle_command(const struct kvaser_usb *dev,
 
 	/* Ignored commands */
 	case CMD_USBCAN_CLOCK_OVERFLOW_EVENT:
-		if (dev->card_data.leaf.family != KVASER_USBCAN)
+		if (dev->driver_info->family != KVASER_USBCAN)
 			goto warn;
 		break;
 
 	case CMD_FLUSH_QUEUE_REPLY:
-		if (dev->card_data.leaf.family != KVASER_LEAF)
+		if (dev->driver_info->family != KVASER_LEAF)
 			goto warn;
 		break;
 
diff --git a/drivers/net/can/usb/usb_8dev.c b/drivers/net/can/usb/usb_8dev.c
index d4c8f934a1ce..a5dee2ee2465 100644
--- a/drivers/net/can/usb/usb_8dev.c
+++ b/drivers/net/can/usb/usb_8dev.c
@@ -442,9 +442,10 @@ static void usb_8dev_rx_err_msg(struct usb_8dev_priv *priv,
 
 	if (rx_errors)
 		stats->rx_errors++;
-
-	cf->data[6] = txerr;
-	cf->data[7] = rxerr;
+	if (priv->can.state != CAN_STATE_BUS_OFF) {
+		cf->data[6] = txerr;
+		cf->data[7] = rxerr;
+	}
 
 	priv->bec.txerr = txerr;
 	priv->bec.rxerr = rxerr;
diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index 262b783d1df8..a2e751f0ae0b 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -259,7 +259,7 @@ static const struct can_bittiming_const xcan_bittiming_const_canfd2 = {
 	.tseg2_min = 1,
 	.tseg2_max = 128,
 	.sjw_max = 128,
-	.brp_min = 2,
+	.brp_min = 1,
 	.brp_max = 256,
 	.brp_inc = 1,
 };
@@ -272,7 +272,7 @@ static const struct can_bittiming_const xcan_data_bittiming_const_canfd2 = {
 	.tseg2_min = 1,
 	.tseg2_max = 16,
 	.sjw_max = 16,
-	.brp_min = 2,
+	.brp_min = 1,
 	.brp_max = 256,
 	.brp_inc = 1,
 };
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index b3a43a3d90e4..d76b2377d66e 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -865,6 +865,11 @@ static void bcm_sf2_sw_mac_link_up(struct dsa_switch *ds, int port,
 		if (duplex == DUPLEX_FULL)
 			reg |= DUPLX_MODE;
 
+		if (tx_pause)
+			reg |= TXFLOW_CNTL;
+		if (rx_pause)
+			reg |= RXFLOW_CNTL;
+
 		core_writel(priv, reg, offset);
 	}
 
diff --git a/drivers/net/dsa/hirschmann/hellcreek_ptp.c b/drivers/net/dsa/hirschmann/hellcreek_ptp.c
index 2572c6087bb5..b28baab6d56a 100644
--- a/drivers/net/dsa/hirschmann/hellcreek_ptp.c
+++ b/drivers/net/dsa/hirschmann/hellcreek_ptp.c
@@ -300,6 +300,7 @@ static int hellcreek_led_setup(struct hellcreek *hellcreek)
 	const char *label, *state;
 	int ret = -EINVAL;
 
+	of_node_get(hellcreek->dev->of_node);
 	leds = of_find_node_by_name(hellcreek->dev->of_node, "leds");
 	if (!leds) {
 		dev_err(hellcreek->dev, "No LEDs specified in device tree!\n");
diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c
index 387d1c89ed7e..9b6bd359d160 100644
--- a/drivers/net/dsa/microchip/ksz9477.c
+++ b/drivers/net/dsa/microchip/ksz9477.c
@@ -721,6 +721,9 @@ static int ksz9477_port_fdb_dump(struct dsa_switch *ds, int port,
 			goto exit;
 		}
 
+		if (!(ksz_data & ALU_VALID))
+			continue;
+
 		/* read ALU table */
 		ksz9477_read_table(dev, alu_table);
 
diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index 466d5d28334b..ed39b5c74c0e 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -444,18 +444,21 @@ int ksz_switch_register(struct ksz_device *dev,
 		ports = of_get_child_by_name(dev->dev->of_node, "ethernet-ports");
 		if (!ports)
 			ports = of_get_child_by_name(dev->dev->of_node, "ports");
-		if (ports)
+		if (ports) {
 			for_each_available_child_of_node(ports, port) {
 				if (of_property_read_u32(port, "reg",
 							 &port_num))
 					continue;
 				if (!(dev->port_mask & BIT(port_num))) {
 					of_node_put(port);
+					of_node_put(ports);
 					return -EINVAL;
 				}
 				of_get_phy_mode(port,
 						&dev->ports[port_num].interface);
 			}
+			of_node_put(ports);
+		}
 		dev->synclko_125 = of_property_read_bool(dev->dev->of_node,
 							 "microchip,synclko-125");
 	}
diff --git a/drivers/net/dsa/mv88e6060.c b/drivers/net/dsa/mv88e6060.c
index a4c6eb9a52d0..83dca9179aa0 100644
--- a/drivers/net/dsa/mv88e6060.c
+++ b/drivers/net/dsa/mv88e6060.c
@@ -118,6 +118,9 @@ static int mv88e6060_setup_port(struct mv88e6060_priv *priv, int p)
 	int addr = REG_PORT(p);
 	int ret;
 
+	if (dsa_is_unused_port(priv->ds, p))
+		return 0;
+
 	/* Do not force flow control, disable Ingress and Egress
 	 * Header tagging, disable VLAN tunneling, and set the port
 	 * state to Forwarding.  Additionally, if this is the CPU
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index b1a2421d31e3..e118de2f89b4 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -588,7 +588,8 @@ static const struct ocelot_stat_layout vsc9959_stats_layout[] = {
 	{ .offset = 0x87,	.name = "tx_frames_below_65_octets", },
 	{ .offset = 0x88,	.name = "tx_frames_65_to_127_octets", },
 	{ .offset = 0x89,	.name = "tx_frames_128_255_octets", },
-	{ .offset = 0x8B,	.name = "tx_frames_256_511_octets", },
+	{ .offset = 0x8A,	.name = "tx_frames_256_511_octets", },
+	{ .offset = 0x8B,	.name = "tx_frames_512_1023_octets", },
 	{ .offset = 0x8C,	.name = "tx_frames_1024_1526_octets", },
 	{ .offset = 0x8D,	.name = "tx_frames_over_1526_octets", },
 	{ .offset = 0x8E,	.name = "tx_yellow_prio_0", },
diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c
index 1b3737258751..26293dce16bc 100644
--- a/drivers/net/dsa/qca8k.c
+++ b/drivers/net/dsa/qca8k.c
@@ -1928,7 +1928,7 @@ static int
 qca8k_port_change_mtu(struct dsa_switch *ds, int port, int new_mtu)
 {
 	struct qca8k_priv *priv = ds->priv;
-	int i, mtu = 0;
+	int ret, i, mtu = 0;
 
 	priv->port_mtu[port] = new_mtu;
 
@@ -1936,8 +1936,27 @@ qca8k_port_change_mtu(struct dsa_switch *ds, int port, int new_mtu)
 		if (priv->port_mtu[i] > mtu)
 			mtu = priv->port_mtu[i];
 
+	/* To change the MAX_FRAME_SIZE the cpu ports must be off or
+	 * the switch panics.
+	 * Turn off both cpu ports before applying the new value to prevent
+	 * this.
+	 */
+	if (priv->port_sts[0].enabled)
+		qca8k_port_set_status(priv, 0, 0);
+
+	if (priv->port_sts[6].enabled)
+		qca8k_port_set_status(priv, 6, 0);
+
 	/* Include L2 header / FCS length */
-	return qca8k_write(priv, QCA8K_MAX_FRAME_SIZE, mtu + ETH_HLEN + ETH_FCS_LEN);
+	ret = qca8k_write(priv, QCA8K_MAX_FRAME_SIZE, mtu + ETH_HLEN + ETH_FCS_LEN);
+
+	if (priv->port_sts[0].enabled)
+		qca8k_port_set_status(priv, 0, 1);
+
+	if (priv->port_sts[6].enabled)
+		qca8k_port_set_status(priv, 6, 1);
+
+	return ret;
 }
 
 static int
diff --git a/drivers/net/dsa/sja1105/sja1105_devlink.c b/drivers/net/dsa/sja1105/sja1105_devlink.c
index 0569ff066634..10c6fea1227f 100644
--- a/drivers/net/dsa/sja1105/sja1105_devlink.c
+++ b/drivers/net/dsa/sja1105/sja1105_devlink.c
@@ -93,7 +93,7 @@ static int sja1105_setup_devlink_regions(struct dsa_switch *ds)
 
 		region = dsa_devlink_region_create(ds, ops, 1, size);
 		if (IS_ERR(region)) {
-			while (i-- >= 0)
+			while (--i >= 0)
 				dsa_devlink_region_destroy(priv->regions[i]);
 			return PTR_ERR(region);
 		}
diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index b7fb1d92ccd3..0c89314006c9 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -3400,12 +3400,28 @@ static const struct of_device_id sja1105_dt_ids[] = {
 };
 MODULE_DEVICE_TABLE(of, sja1105_dt_ids);
 
+static const struct spi_device_id sja1105_spi_ids[] = {
+	{ "sja1105e" },
+	{ "sja1105t" },
+	{ "sja1105p" },
+	{ "sja1105q" },
+	{ "sja1105r" },
+	{ "sja1105s" },
+	{ "sja1110a" },
+	{ "sja1110b" },
+	{ "sja1110c" },
+	{ "sja1110d" },
+	{ },
+};
+MODULE_DEVICE_TABLE(spi, sja1105_spi_ids);
+
 static struct spi_driver sja1105_driver = {
 	.driver = {
 		.name  = "sja1105",
 		.owner = THIS_MODULE,
 		.of_match_table = of_match_ptr(sja1105_dt_ids),
 	},
+	.id_table = sja1105_spi_ids,
 	.probe  = sja1105_probe,
 	.remove = sja1105_remove,
 	.shutdown = sja1105_shutdown,
diff --git a/drivers/net/dsa/vitesse-vsc73xx-spi.c b/drivers/net/dsa/vitesse-vsc73xx-spi.c
index 645398901e05..922ae22fad66 100644
--- a/drivers/net/dsa/vitesse-vsc73xx-spi.c
+++ b/drivers/net/dsa/vitesse-vsc73xx-spi.c
@@ -207,10 +207,20 @@ static const struct of_device_id vsc73xx_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, vsc73xx_of_match);
 
+static const struct spi_device_id vsc73xx_spi_ids[] = {
+	{ "vsc7385" },
+	{ "vsc7388" },
+	{ "vsc7395" },
+	{ "vsc7398" },
+	{ },
+};
+MODULE_DEVICE_TABLE(spi, vsc73xx_spi_ids);
+
 static struct spi_driver vsc73xx_spi_driver = {
 	.probe = vsc73xx_spi_probe,
 	.remove = vsc73xx_spi_remove,
 	.shutdown = vsc73xx_spi_shutdown,
+	.id_table = vsc73xx_spi_ids,
 	.driver = {
 		.name = "vsc73xx-spi",
 		.of_match_table = vsc73xx_of_match,
diff --git a/drivers/net/dsa/xrs700x/xrs700x.c b/drivers/net/dsa/xrs700x/xrs700x.c
index f657d6f7a50b..db69b0204812 100644
--- a/drivers/net/dsa/xrs700x/xrs700x.c
+++ b/drivers/net/dsa/xrs700x/xrs700x.c
@@ -108,6 +108,7 @@ static void xrs700x_read_port_counters(struct xrs700x *priv, int port)
 {
 	struct xrs700x_port *p = &priv->ports[port];
 	struct rtnl_link_stats64 stats;
+	unsigned long flags;
 	int i;
 
 	memset(&stats, 0, sizeof(stats));
@@ -137,9 +138,9 @@ static void xrs700x_read_port_counters(struct xrs700x *priv, int port)
 	 */
 	stats.rx_packets += stats.multicast;
 
-	u64_stats_update_begin(&p->syncp);
+	flags = u64_stats_update_begin_irqsave(&p->syncp);
 	p->stats64 = stats;
-	u64_stats_update_end(&p->syncp);
+	u64_stats_update_end_irqrestore(&p->syncp, flags);
 
 	mutex_unlock(&p->mib_mutex);
 }
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index fbb1e05d5878..ea2e7cd8946d 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -265,12 +265,10 @@ static void aq_nic_service_timer_cb(struct timer_list *t)
 static void aq_nic_polling_timer_cb(struct timer_list *t)
 {
 	struct aq_nic_s *self = from_timer(self, t, polling_timer);
-	struct aq_vec_s *aq_vec = NULL;
 	unsigned int i = 0U;
 
-	for (i = 0U, aq_vec = self->aq_vec[0];
-		self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i])
-		aq_vec_isr(i, (void *)aq_vec);
+	for (i = 0U; self->aq_vecs > i; ++i)
+		aq_vec_isr(i, (void *)self->aq_vec[i]);
 
 	mod_timer(&self->polling_timer, jiffies +
 		  AQ_CFG_POLLING_TIMER_INTERVAL);
@@ -872,7 +870,6 @@ int aq_nic_get_regs_count(struct aq_nic_s *self)
 
 u64 *aq_nic_get_stats(struct aq_nic_s *self, u64 *data)
 {
-	struct aq_vec_s *aq_vec = NULL;
 	struct aq_stats_s *stats;
 	unsigned int count = 0U;
 	unsigned int i = 0U;
@@ -922,11 +919,11 @@ u64 *aq_nic_get_stats(struct aq_nic_s *self, u64 *data)
 	data += i;
 
 	for (tc = 0U; tc < self->aq_nic_cfg.tcs; tc++) {
-		for (i = 0U, aq_vec = self->aq_vec[0];
-		     aq_vec && self->aq_vecs > i;
-		     ++i, aq_vec = self->aq_vec[i]) {
+		for (i = 0U; self->aq_vecs > i; ++i) {
+			if (!self->aq_vec[i])
+				break;
 			data += count;
-			count = aq_vec_get_sw_stats(aq_vec, tc, data);
+			count = aq_vec_get_sw_stats(self->aq_vec[i], tc, data);
 		}
 	}
 
@@ -1240,7 +1237,6 @@ int aq_nic_set_loopback(struct aq_nic_s *self)
 
 int aq_nic_stop(struct aq_nic_s *self)
 {
-	struct aq_vec_s *aq_vec = NULL;
 	unsigned int i = 0U;
 
 	netif_tx_disable(self->ndev);
@@ -1258,9 +1254,8 @@ int aq_nic_stop(struct aq_nic_s *self)
 
 	aq_ptp_irq_free(self);
 
-	for (i = 0U, aq_vec = self->aq_vec[0];
-		self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i])
-		aq_vec_stop(aq_vec);
+	for (i = 0U; self->aq_vecs > i; ++i)
+		aq_vec_stop(self->aq_vec[i]);
 
 	aq_ptp_ring_stop(self);
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
index 831833911a52..8647125d60ae 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
@@ -379,7 +379,7 @@ static void aq_pci_shutdown(struct pci_dev *pdev)
 	}
 }
 
-static int aq_suspend_common(struct device *dev, bool deep)
+static int aq_suspend_common(struct device *dev)
 {
 	struct aq_nic_s *nic = pci_get_drvdata(to_pci_dev(dev));
 
@@ -392,17 +392,15 @@ static int aq_suspend_common(struct device *dev, bool deep)
 	if (netif_running(nic->ndev))
 		aq_nic_stop(nic);
 
-	if (deep) {
-		aq_nic_deinit(nic, !nic->aq_hw->aq_nic_cfg->wol);
-		aq_nic_set_power(nic);
-	}
+	aq_nic_deinit(nic, !nic->aq_hw->aq_nic_cfg->wol);
+	aq_nic_set_power(nic);
 
 	rtnl_unlock();
 
 	return 0;
 }
 
-static int atl_resume_common(struct device *dev, bool deep)
+static int atl_resume_common(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct aq_nic_s *nic;
@@ -415,11 +413,6 @@ static int atl_resume_common(struct device *dev, bool deep)
 	pci_set_power_state(pdev, PCI_D0);
 	pci_restore_state(pdev);
 
-	if (deep) {
-		/* Reinitialize Nic/Vecs objects */
-		aq_nic_deinit(nic, !nic->aq_hw->aq_nic_cfg->wol);
-	}
-
 	if (netif_running(nic->ndev)) {
 		ret = aq_nic_init(nic);
 		if (ret)
@@ -444,22 +437,22 @@ err_exit:
 
 static int aq_pm_freeze(struct device *dev)
 {
-	return aq_suspend_common(dev, true);
+	return aq_suspend_common(dev);
 }
 
 static int aq_pm_suspend_poweroff(struct device *dev)
 {
-	return aq_suspend_common(dev, true);
+	return aq_suspend_common(dev);
 }
 
 static int aq_pm_thaw(struct device *dev)
 {
-	return atl_resume_common(dev, true);
+	return atl_resume_common(dev);
 }
 
 static int aq_pm_resume_restore(struct device *dev)
 {
-	return atl_resume_common(dev, true);
+	return atl_resume_common(dev);
 }
 
 static const struct dev_pm_ops aq_pm_ops = {
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index fe4d99abd548..6e8bc6726031 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -189,8 +189,8 @@ static netdev_tx_t bgmac_dma_tx_add(struct bgmac *bgmac,
 	}
 
 	slot->skb = skb;
-	ring->end += nr_frags + 1;
 	netdev_sent_queue(net_dev, skb->len);
+	ring->end += nr_frags + 1;
 
 	wmb();
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index cb5314945589..6962abe2358b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -9806,7 +9806,8 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
 
 	if (flags & FUNC_DRV_IF_CHANGE_RESP_FLAGS_RESC_CHANGE)
 		resc_reinit = true;
-	if (flags & FUNC_DRV_IF_CHANGE_RESP_FLAGS_HOT_FW_RESET_DONE)
+	if (flags & FUNC_DRV_IF_CHANGE_RESP_FLAGS_HOT_FW_RESET_DONE ||
+	    test_bit(BNXT_STATE_FW_RESET_DET, &bp->state))
 		fw_reset = true;
 	else if (bp->fw_health && !bp->fw_health->status_reliable)
 		bnxt_try_map_fw_health_reg(bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
index 62a931de5b1a..a78cc65a38f2 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
@@ -61,14 +61,23 @@ static int bnxt_refclk_read(struct bnxt *bp, struct ptp_system_timestamp *sts,
 			    u64 *ns)
 {
 	struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
+	u32 high_before, high_now, low;
 
 	if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
 		return -EIO;
 
+	high_before = readl(bp->bar0 + ptp->refclk_mapped_regs[1]);
 	ptp_read_system_prets(sts);
-	*ns = readl(bp->bar0 + ptp->refclk_mapped_regs[0]);
+	low = readl(bp->bar0 + ptp->refclk_mapped_regs[0]);
 	ptp_read_system_postts(sts);
-	*ns |= (u64)readl(bp->bar0 + ptp->refclk_mapped_regs[1]) << 32;
+	high_now = readl(bp->bar0 + ptp->refclk_mapped_regs[1]);
+	if (high_now != high_before) {
+		ptp_read_system_prets(sts);
+		low = readl(bp->bar0 + ptp->refclk_mapped_regs[0]);
+		ptp_read_system_postts(sts);
+	}
+	*ns = ((u64)high_now << 32) | low;
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index 70d8ca3039dc..78763f5027d1 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -623,7 +623,7 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs, bool reset)
 		hw_resc->max_stat_ctxs -= le16_to_cpu(req->min_stat_ctx) * n;
 		hw_resc->max_vnics -= le16_to_cpu(req->min_vnics) * n;
 		if (bp->flags & BNXT_FLAG_CHIP_P5)
-			hw_resc->max_irqs -= vf_msix * n;
+			hw_resc->max_nqs -= vf_msix;
 
 		rc = pf->active_vfs;
 	}
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 89d16c587bb7..dbd2ede53f94 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -361,6 +361,9 @@ int bcmgenet_mii_probe(struct net_device *dev)
 	if (priv->internal_phy && !GENET_IS_V5(priv))
 		dev->phydev->irq = PHY_MAC_INTERRUPT;
 
+	/* Indicate that the MAC is responsible for PHY PM */
+	dev->phydev->mac_managed_pm = true;
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 5e0e0e70d801..8aab07419263 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -18078,16 +18078,20 @@ static void tg3_shutdown(struct pci_dev *pdev)
 	struct net_device *dev = pci_get_drvdata(pdev);
 	struct tg3 *tp = netdev_priv(dev);
 
+	tg3_reset_task_cancel(tp);
+
 	rtnl_lock();
+
 	netif_device_detach(dev);
 
 	if (netif_running(dev))
 		dev_close(dev);
 
-	if (system_state == SYSTEM_POWER_OFF)
-		tg3_power_down(tp);
+	tg3_power_down(tp);
 
 	rtnl_unlock();
+
+	pci_disable_device(pdev);
 }
 
 /**
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c
index 4af5561cbfc5..ddfe9208529a 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c
@@ -1236,8 +1236,8 @@ static struct sock *chtls_recv_sock(struct sock *lsk,
 	csk->sndbuf = newsk->sk_sndbuf;
 	csk->smac_idx = ((struct port_info *)netdev_priv(ndev))->smt_idx;
 	RCV_WSCALE(tp) = select_rcv_wscale(tcp_full_space(newsk),
-					   sock_net(newsk)->
-						ipv4.sysctl_tcp_window_scaling,
+					   READ_ONCE(sock_net(newsk)->
+						     ipv4.sysctl_tcp_window_scaling),
 					   tp->window_clamp);
 	neigh_release(n);
 	inet_inherit_port(&tcp_hashinfo, lsk, newsk);
@@ -1384,7 +1384,7 @@ static void chtls_pass_accept_request(struct sock *sk,
 #endif
 	}
 	if (req->tcpopt.wsf <= 14 &&
-	    sock_net(sk)->ipv4.sysctl_tcp_window_scaling) {
+	    READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_window_scaling)) {
 		inet_rsk(oreq)->wscale_ok = 1;
 		inet_rsk(oreq)->snd_wscale = req->tcpopt.wsf;
 	}
@@ -1392,7 +1392,7 @@ static void chtls_pass_accept_request(struct sock *sk,
 	th_ecn = tcph->ece && tcph->cwr;
 	if (th_ecn) {
 		ect = !INET_ECN_is_not_ect(ip_dsfield);
-		ecn_ok = sock_net(sk)->ipv4.sysctl_tcp_ecn;
+		ecn_ok = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn);
 		if ((!ect && ecn_ok) || tcp_ca_needs_ecn(sk))
 			inet_rsk(oreq)->ecn_ok = 1;
 	}
diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index 012ca11a38cc..8361faf03e42 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -1920,7 +1920,7 @@ static void gmac_get_stats64(struct net_device *netdev,
 
 	/* Racing with RX NAPI */
 	do {
-		start = u64_stats_fetch_begin(&port->rx_stats_syncp);
+		start = u64_stats_fetch_begin_irq(&port->rx_stats_syncp);
 
 		stats->rx_packets = port->stats.rx_packets;
 		stats->rx_bytes = port->stats.rx_bytes;
@@ -1932,11 +1932,11 @@ static void gmac_get_stats64(struct net_device *netdev,
 		stats->rx_crc_errors = port->stats.rx_crc_errors;
 		stats->rx_frame_errors = port->stats.rx_frame_errors;
 
-	} while (u64_stats_fetch_retry(&port->rx_stats_syncp, start));
+	} while (u64_stats_fetch_retry_irq(&port->rx_stats_syncp, start));
 
 	/* Racing with MIB and TX completion interrupts */
 	do {
-		start = u64_stats_fetch_begin(&port->ir_stats_syncp);
+		start = u64_stats_fetch_begin_irq(&port->ir_stats_syncp);
 
 		stats->tx_errors = port->stats.tx_errors;
 		stats->tx_packets = port->stats.tx_packets;
@@ -1946,15 +1946,15 @@ static void gmac_get_stats64(struct net_device *netdev,
 		stats->rx_missed_errors = port->stats.rx_missed_errors;
 		stats->rx_fifo_errors = port->stats.rx_fifo_errors;
 
-	} while (u64_stats_fetch_retry(&port->ir_stats_syncp, start));
+	} while (u64_stats_fetch_retry_irq(&port->ir_stats_syncp, start));
 
 	/* Racing with hard_start_xmit */
 	do {
-		start = u64_stats_fetch_begin(&port->tx_stats_syncp);
+		start = u64_stats_fetch_begin_irq(&port->tx_stats_syncp);
 
 		stats->tx_dropped = port->stats.tx_dropped;
 
-	} while (u64_stats_fetch_retry(&port->tx_stats_syncp, start));
+	} while (u64_stats_fetch_retry_irq(&port->tx_stats_syncp, start));
 
 	stats->rx_dropped += stats->rx_missed_errors;
 }
@@ -2032,18 +2032,18 @@ static void gmac_get_ethtool_stats(struct net_device *netdev,
 	/* Racing with MIB interrupt */
 	do {
 		p = values;
-		start = u64_stats_fetch_begin(&port->ir_stats_syncp);
+		start = u64_stats_fetch_begin_irq(&port->ir_stats_syncp);
 
 		for (i = 0; i < RX_STATS_NUM; i++)
 			*p++ = port->hw_stats[i];
 
-	} while (u64_stats_fetch_retry(&port->ir_stats_syncp, start));
+	} while (u64_stats_fetch_retry_irq(&port->ir_stats_syncp, start));
 	values = p;
 
 	/* Racing with RX NAPI */
 	do {
 		p = values;
-		start = u64_stats_fetch_begin(&port->rx_stats_syncp);
+		start = u64_stats_fetch_begin_irq(&port->rx_stats_syncp);
 
 		for (i = 0; i < RX_STATUS_NUM; i++)
 			*p++ = port->rx_stats[i];
@@ -2051,13 +2051,13 @@ static void gmac_get_ethtool_stats(struct net_device *netdev,
 			*p++ = port->rx_csum_stats[i];
 		*p++ = port->rx_napi_exits;
 
-	} while (u64_stats_fetch_retry(&port->rx_stats_syncp, start));
+	} while (u64_stats_fetch_retry_irq(&port->rx_stats_syncp, start));
 	values = p;
 
 	/* Racing with TX start_xmit */
 	do {
 		p = values;
-		start = u64_stats_fetch_begin(&port->tx_stats_syncp);
+		start = u64_stats_fetch_begin_irq(&port->tx_stats_syncp);
 
 		for (i = 0; i < TX_MAX_FRAGS; i++) {
 			*values++ = port->tx_frag_stats[i];
@@ -2066,7 +2066,7 @@ static void gmac_get_ethtool_stats(struct net_device *netdev,
 		*values++ = port->tx_frags_linearized;
 		*values++ = port->tx_hw_csummed;
 
-	} while (u64_stats_fetch_retry(&port->tx_stats_syncp, start));
+	} while (u64_stats_fetch_retry_irq(&port->tx_stats_syncp, start));
 }
 
 static int gmac_get_ksettings(struct net_device *netdev,
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 649c5c429bd7..1288b5e3d220 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -2287,7 +2287,7 @@ err:
 
 /* Uses sync mcc */
 int be_cmd_read_port_transceiver_data(struct be_adapter *adapter,
-				      u8 page_num, u8 *data)
+				      u8 page_num, u32 off, u32 len, u8 *data)
 {
 	struct be_dma_mem cmd;
 	struct be_mcc_wrb *wrb;
@@ -2321,10 +2321,10 @@ int be_cmd_read_port_transceiver_data(struct be_adapter *adapter,
 	req->port = cpu_to_le32(adapter->hba_port_num);
 	req->page_num = cpu_to_le32(page_num);
 	status = be_mcc_notify_wait(adapter);
-	if (!status) {
+	if (!status && len > 0) {
 		struct be_cmd_resp_port_type *resp = cmd.va;
 
-		memcpy(data, resp->page_data, PAGE_DATA_LEN);
+		memcpy(data, resp->page_data + off, len);
 	}
 err:
 	mutex_unlock(&adapter->mcc_lock);
@@ -2415,7 +2415,7 @@ int be_cmd_query_cable_type(struct be_adapter *adapter)
 	int status;
 
 	status = be_cmd_read_port_transceiver_data(adapter, TR_PAGE_A0,
-						   page_data);
+						   0, PAGE_DATA_LEN, page_data);
 	if (!status) {
 		switch (adapter->phy.interface_type) {
 		case PHY_TYPE_QSFP:
@@ -2440,7 +2440,7 @@ int be_cmd_query_sfp_info(struct be_adapter *adapter)
 	int status;
 
 	status = be_cmd_read_port_transceiver_data(adapter, TR_PAGE_A0,
-						   page_data);
+						   0, PAGE_DATA_LEN, page_data);
 	if (!status) {
 		strlcpy(adapter->phy.vendor_name, page_data +
 			SFP_VENDOR_NAME_OFFSET, SFP_VENDOR_NAME_LEN - 1);
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h
index c30d6d6f0f3a..9e17d6a7ab8c 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.h
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.h
@@ -2427,7 +2427,7 @@ int be_cmd_set_beacon_state(struct be_adapter *adapter, u8 port_num, u8 beacon,
 int be_cmd_get_beacon_state(struct be_adapter *adapter, u8 port_num,
 			    u32 *state);
 int be_cmd_read_port_transceiver_data(struct be_adapter *adapter,
-				      u8 page_num, u8 *data);
+				      u8 page_num, u32 off, u32 len, u8 *data);
 int be_cmd_query_cable_type(struct be_adapter *adapter);
 int be_cmd_query_sfp_info(struct be_adapter *adapter);
 int lancer_cmd_read_object(struct be_adapter *adapter, struct be_dma_mem *cmd,
diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c
index f9955308b93d..010a0024f3ce 100644
--- a/drivers/net/ethernet/emulex/benet/be_ethtool.c
+++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c
@@ -1342,7 +1342,7 @@ static int be_get_module_info(struct net_device *netdev,
 		return -EOPNOTSUPP;
 
 	status = be_cmd_read_port_transceiver_data(adapter, TR_PAGE_A0,
-						   page_data);
+						   0, PAGE_DATA_LEN, page_data);
 	if (!status) {
 		if (!page_data[SFP_PLUS_SFF_8472_COMP]) {
 			modinfo->type = ETH_MODULE_SFF_8079;
@@ -1360,25 +1360,32 @@ static int be_get_module_eeprom(struct net_device *netdev,
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 	int status;
+	u32 begin, end;
 
 	if (!check_privilege(adapter, MAX_PRIVILEGES))
 		return -EOPNOTSUPP;
 
-	status = be_cmd_read_port_transceiver_data(adapter, TR_PAGE_A0,
-						   data);
-	if (status)
-		goto err;
+	begin = eeprom->offset;
+	end = eeprom->offset + eeprom->len;
+
+	if (begin < PAGE_DATA_LEN) {
+		status = be_cmd_read_port_transceiver_data(adapter, TR_PAGE_A0, begin,
+							   min_t(u32, end, PAGE_DATA_LEN) - begin,
+							   data);
+		if (status)
+			goto err;
+
+		data += PAGE_DATA_LEN - begin;
+		begin = PAGE_DATA_LEN;
+	}
 
-	if (eeprom->offset + eeprom->len > PAGE_DATA_LEN) {
-		status = be_cmd_read_port_transceiver_data(adapter,
-							   TR_PAGE_A2,
-							   data +
-							   PAGE_DATA_LEN);
+	if (end > PAGE_DATA_LEN) {
+		status = be_cmd_read_port_transceiver_data(adapter, TR_PAGE_A2,
+							   begin - PAGE_DATA_LEN,
+							   end - begin, data);
 		if (status)
 			goto err;
 	}
-	if (eeprom->offset)
-		memcpy(data, data + eeprom->offset, eeprom->len);
 err:
 	return be_cmd_status(status);
 }
diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c
index 0b833572205f..4a2dadb91f02 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.c
+++ b/drivers/net/ethernet/faraday/ftgmac100.c
@@ -1746,6 +1746,19 @@ cleanup_clk:
 	return rc;
 }
 
+static bool ftgmac100_has_child_node(struct device_node *np, const char *name)
+{
+	struct device_node *child_np = of_get_child_by_name(np, name);
+	bool ret = false;
+
+	if (child_np) {
+		ret = true;
+		of_node_put(child_np);
+	}
+
+	return ret;
+}
+
 static int ftgmac100_probe(struct platform_device *pdev)
 {
 	struct resource *res;
@@ -1865,7 +1878,7 @@ static int ftgmac100_probe(struct platform_device *pdev)
 
 		/* Display what we found */
 		phy_attached_info(phy);
-	} else if (np && !of_get_child_by_name(np, "mdio")) {
+	} else if (np && !ftgmac100_has_child_node(np, "mdio")) {
 		/* Support legacy ASPEED devicetree descriptions that decribe a
 		 * MAC with an embedded MDIO controller but have no "mdio"
 		 * child node. Automatically scan the MDIO bus for available
diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index d71eac7e1924..c5ae67300590 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -136,11 +136,7 @@ static int fec_ptp_enable_pps(struct fec_enet_private *fep, uint enable)
 		 * NSEC_PER_SEC - ts.tv_nsec. Add the remaining nanoseconds
 		 * to current timer would be next second.
 		 */
-		tempval = readl(fep->hwp + FEC_ATIME_CTRL);
-		tempval |= FEC_T_CTRL_CAPTURE;
-		writel(tempval, fep->hwp + FEC_ATIME_CTRL);
-
-		tempval = readl(fep->hwp + FEC_ATIME);
+		tempval = fep->cc.read(&fep->cc);
 		/* Convert the ptp local counter to 1588 timestamp */
 		ns = timecounter_cyc2time(&fep->tc, tempval);
 		ts = ns_to_timespec64(ns);
diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c
index 716e6240305d..878329ddcf8d 100644
--- a/drivers/net/ethernet/google/gve/gve_ethtool.c
+++ b/drivers/net/ethernet/google/gve/gve_ethtool.c
@@ -174,14 +174,14 @@ gve_get_ethtool_stats(struct net_device *netdev,
 				struct gve_rx_ring *rx = &priv->rx[ring];
 
 				start =
-				  u64_stats_fetch_begin(&priv->rx[ring].statss);
+				  u64_stats_fetch_begin_irq(&priv->rx[ring].statss);
 				tmp_rx_pkts = rx->rpackets;
 				tmp_rx_bytes = rx->rbytes;
 				tmp_rx_skb_alloc_fail = rx->rx_skb_alloc_fail;
 				tmp_rx_buf_alloc_fail = rx->rx_buf_alloc_fail;
 				tmp_rx_desc_err_dropped_pkt =
 					rx->rx_desc_err_dropped_pkt;
-			} while (u64_stats_fetch_retry(&priv->rx[ring].statss,
+			} while (u64_stats_fetch_retry_irq(&priv->rx[ring].statss,
 						       start));
 			rx_pkts += tmp_rx_pkts;
 			rx_bytes += tmp_rx_bytes;
@@ -195,10 +195,10 @@ gve_get_ethtool_stats(struct net_device *netdev,
 		if (priv->tx) {
 			do {
 				start =
-				  u64_stats_fetch_begin(&priv->tx[ring].statss);
+				  u64_stats_fetch_begin_irq(&priv->tx[ring].statss);
 				tmp_tx_pkts = priv->tx[ring].pkt_done;
 				tmp_tx_bytes = priv->tx[ring].bytes_done;
-			} while (u64_stats_fetch_retry(&priv->tx[ring].statss,
+			} while (u64_stats_fetch_retry_irq(&priv->tx[ring].statss,
 						       start));
 			tx_pkts += tmp_tx_pkts;
 			tx_bytes += tmp_tx_bytes;
@@ -256,13 +256,13 @@ gve_get_ethtool_stats(struct net_device *netdev,
 			data[i++] = rx->cnt;
 			do {
 				start =
-				  u64_stats_fetch_begin(&priv->rx[ring].statss);
+				  u64_stats_fetch_begin_irq(&priv->rx[ring].statss);
 				tmp_rx_bytes = rx->rbytes;
 				tmp_rx_skb_alloc_fail = rx->rx_skb_alloc_fail;
 				tmp_rx_buf_alloc_fail = rx->rx_buf_alloc_fail;
 				tmp_rx_desc_err_dropped_pkt =
 					rx->rx_desc_err_dropped_pkt;
-			} while (u64_stats_fetch_retry(&priv->rx[ring].statss,
+			} while (u64_stats_fetch_retry_irq(&priv->rx[ring].statss,
 						       start));
 			data[i++] = tmp_rx_bytes;
 			/* rx dropped packets */
@@ -323,9 +323,9 @@ gve_get_ethtool_stats(struct net_device *netdev,
 			}
 			do {
 				start =
-				  u64_stats_fetch_begin(&priv->tx[ring].statss);
+				  u64_stats_fetch_begin_irq(&priv->tx[ring].statss);
 				tmp_tx_bytes = tx->bytes_done;
-			} while (u64_stats_fetch_retry(&priv->tx[ring].statss,
+			} while (u64_stats_fetch_retry_irq(&priv->tx[ring].statss,
 						       start));
 			data[i++] = tmp_tx_bytes;
 			data[i++] = tx->wake_queue;
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index 68552848d388..49850cf7cfaf 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -51,10 +51,10 @@ static void gve_get_stats(struct net_device *dev, struct rtnl_link_stats64 *s)
 		for (ring = 0; ring < priv->rx_cfg.num_queues; ring++) {
 			do {
 				start =
-				  u64_stats_fetch_begin(&priv->rx[ring].statss);
+				  u64_stats_fetch_begin_irq(&priv->rx[ring].statss);
 				packets = priv->rx[ring].rpackets;
 				bytes = priv->rx[ring].rbytes;
-			} while (u64_stats_fetch_retry(&priv->rx[ring].statss,
+			} while (u64_stats_fetch_retry_irq(&priv->rx[ring].statss,
 						       start));
 			s->rx_packets += packets;
 			s->rx_bytes += bytes;
@@ -64,10 +64,10 @@ static void gve_get_stats(struct net_device *dev, struct rtnl_link_stats64 *s)
 		for (ring = 0; ring < priv->tx_cfg.num_queues; ring++) {
 			do {
 				start =
-				  u64_stats_fetch_begin(&priv->tx[ring].statss);
+				  u64_stats_fetch_begin_irq(&priv->tx[ring].statss);
 				packets = priv->tx[ring].pkt_done;
 				bytes = priv->tx[ring].bytes_done;
-			} while (u64_stats_fetch_retry(&priv->tx[ring].statss,
+			} while (u64_stats_fetch_retry_irq(&priv->tx[ring].statss,
 						       start));
 			s->tx_packets += packets;
 			s->tx_bytes += bytes;
@@ -1260,9 +1260,9 @@ void gve_handle_report_stats(struct gve_priv *priv)
 			}
 
 			do {
-				start = u64_stats_fetch_begin(&priv->tx[idx].statss);
+				start = u64_stats_fetch_begin_irq(&priv->tx[idx].statss);
 				tx_bytes = priv->tx[idx].bytes_done;
-			} while (u64_stats_fetch_retry(&priv->tx[idx].statss, start));
+			} while (u64_stats_fetch_retry_irq(&priv->tx[idx].statss, start));
 			stats[stats_idx++] = (struct stats) {
 				.stat_name = cpu_to_be32(TX_WAKE_CNT),
 				.value = cpu_to_be64(priv->tx[idx].wake_queue),
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_dev.h
index fb3e89141a0d..a4fbf44f944c 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_dev.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_dev.h
@@ -95,9 +95,6 @@ struct hinic_dev {
 	u16				sq_depth;
 	u16				rq_depth;
 
-	struct hinic_txq_stats          tx_stats;
-	struct hinic_rxq_stats          rx_stats;
-
 	u8				rss_tmpl_idx;
 	u8				rss_hash_engine;
 	u16				num_rss;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c
index f8aa80ec201b..8c6ec7c25809 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_main.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c
@@ -62,8 +62,6 @@ MODULE_PARM_DESC(rx_weight, "Number Rx packets for NAPI budget (default=64)");
 
 #define HINIC_LRO_RX_TIMER_DEFAULT	16
 
-#define VLAN_BITMAP_SIZE(nic_dev)       (ALIGN(VLAN_N_VID, 8) / 8)
-
 #define work_to_rx_mode_work(work)      \
 		container_of(work, struct hinic_rx_mode_work, work)
 
@@ -82,56 +80,44 @@ static int set_features(struct hinic_dev *nic_dev,
 			netdev_features_t pre_features,
 			netdev_features_t features, bool force_change);
 
-static void update_rx_stats(struct hinic_dev *nic_dev, struct hinic_rxq *rxq)
+static void gather_rx_stats(struct hinic_rxq_stats *nic_rx_stats, struct hinic_rxq *rxq)
 {
-	struct hinic_rxq_stats *nic_rx_stats = &nic_dev->rx_stats;
 	struct hinic_rxq_stats rx_stats;
 
-	u64_stats_init(&rx_stats.syncp);
-
 	hinic_rxq_get_stats(rxq, &rx_stats);
 
-	u64_stats_update_begin(&nic_rx_stats->syncp);
 	nic_rx_stats->bytes += rx_stats.bytes;
 	nic_rx_stats->pkts  += rx_stats.pkts;
 	nic_rx_stats->errors += rx_stats.errors;
 	nic_rx_stats->csum_errors += rx_stats.csum_errors;
 	nic_rx_stats->other_errors += rx_stats.other_errors;
-	u64_stats_update_end(&nic_rx_stats->syncp);
-
-	hinic_rxq_clean_stats(rxq);
 }
 
-static void update_tx_stats(struct hinic_dev *nic_dev, struct hinic_txq *txq)
+static void gather_tx_stats(struct hinic_txq_stats *nic_tx_stats, struct hinic_txq *txq)
 {
-	struct hinic_txq_stats *nic_tx_stats = &nic_dev->tx_stats;
 	struct hinic_txq_stats tx_stats;
 
-	u64_stats_init(&tx_stats.syncp);
-
 	hinic_txq_get_stats(txq, &tx_stats);
 
-	u64_stats_update_begin(&nic_tx_stats->syncp);
 	nic_tx_stats->bytes += tx_stats.bytes;
 	nic_tx_stats->pkts += tx_stats.pkts;
 	nic_tx_stats->tx_busy += tx_stats.tx_busy;
 	nic_tx_stats->tx_wake += tx_stats.tx_wake;
 	nic_tx_stats->tx_dropped += tx_stats.tx_dropped;
 	nic_tx_stats->big_frags_pkts += tx_stats.big_frags_pkts;
-	u64_stats_update_end(&nic_tx_stats->syncp);
-
-	hinic_txq_clean_stats(txq);
 }
 
-static void update_nic_stats(struct hinic_dev *nic_dev)
+static void gather_nic_stats(struct hinic_dev *nic_dev,
+			     struct hinic_rxq_stats *nic_rx_stats,
+			     struct hinic_txq_stats *nic_tx_stats)
 {
 	int i, num_qps = hinic_hwdev_num_qps(nic_dev->hwdev);
 
 	for (i = 0; i < num_qps; i++)
-		update_rx_stats(nic_dev, &nic_dev->rxqs[i]);
+		gather_rx_stats(nic_rx_stats, &nic_dev->rxqs[i]);
 
 	for (i = 0; i < num_qps; i++)
-		update_tx_stats(nic_dev, &nic_dev->txqs[i]);
+		gather_tx_stats(nic_tx_stats, &nic_dev->txqs[i]);
 }
 
 /**
@@ -560,8 +546,6 @@ int hinic_close(struct net_device *netdev)
 	netif_carrier_off(netdev);
 	netif_tx_disable(netdev);
 
-	update_nic_stats(nic_dev);
-
 	up(&nic_dev->mgmt_lock);
 
 	if (!HINIC_IS_VF(nic_dev->hwdev->hwif))
@@ -855,26 +839,19 @@ static void hinic_get_stats64(struct net_device *netdev,
 			      struct rtnl_link_stats64 *stats)
 {
 	struct hinic_dev *nic_dev = netdev_priv(netdev);
-	struct hinic_rxq_stats *nic_rx_stats;
-	struct hinic_txq_stats *nic_tx_stats;
-
-	nic_rx_stats = &nic_dev->rx_stats;
-	nic_tx_stats = &nic_dev->tx_stats;
-
-	down(&nic_dev->mgmt_lock);
+	struct hinic_rxq_stats nic_rx_stats = {};
+	struct hinic_txq_stats nic_tx_stats = {};
 
 	if (nic_dev->flags & HINIC_INTF_UP)
-		update_nic_stats(nic_dev);
-
-	up(&nic_dev->mgmt_lock);
+		gather_nic_stats(nic_dev, &nic_rx_stats, &nic_tx_stats);
 
-	stats->rx_bytes   = nic_rx_stats->bytes;
-	stats->rx_packets = nic_rx_stats->pkts;
-	stats->rx_errors  = nic_rx_stats->errors;
+	stats->rx_bytes   = nic_rx_stats.bytes;
+	stats->rx_packets = nic_rx_stats.pkts;
+	stats->rx_errors  = nic_rx_stats.errors;
 
-	stats->tx_bytes   = nic_tx_stats->bytes;
-	stats->tx_packets = nic_tx_stats->pkts;
-	stats->tx_errors  = nic_tx_stats->tx_dropped;
+	stats->tx_bytes   = nic_tx_stats.bytes;
+	stats->tx_packets = nic_tx_stats.pkts;
+	stats->tx_errors  = nic_tx_stats.tx_dropped;
 }
 
 static int hinic_set_features(struct net_device *netdev,
@@ -1173,8 +1150,6 @@ static void hinic_free_intr_coalesce(struct hinic_dev *nic_dev)
 static int nic_dev_init(struct pci_dev *pdev)
 {
 	struct hinic_rx_mode_work *rx_mode_work;
-	struct hinic_txq_stats *tx_stats;
-	struct hinic_rxq_stats *rx_stats;
 	struct hinic_dev *nic_dev;
 	struct net_device *netdev;
 	struct hinic_hwdev *hwdev;
@@ -1235,15 +1210,8 @@ static int nic_dev_init(struct pci_dev *pdev)
 
 	sema_init(&nic_dev->mgmt_lock, 1);
 
-	tx_stats = &nic_dev->tx_stats;
-	rx_stats = &nic_dev->rx_stats;
-
-	u64_stats_init(&tx_stats->syncp);
-	u64_stats_init(&rx_stats->syncp);
-
-	nic_dev->vlan_bitmap = devm_kzalloc(&pdev->dev,
-					    VLAN_BITMAP_SIZE(nic_dev),
-					    GFP_KERNEL);
+	nic_dev->vlan_bitmap = devm_bitmap_zalloc(&pdev->dev, VLAN_N_VID,
+						  GFP_KERNEL);
 	if (!nic_dev->vlan_bitmap) {
 		err = -ENOMEM;
 		goto err_vlan_bitmap;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
index fed3b6bc0d76..d11ec69a2e17 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
@@ -73,17 +73,15 @@ void hinic_rxq_get_stats(struct hinic_rxq *rxq, struct hinic_rxq_stats *stats)
 	struct hinic_rxq_stats *rxq_stats = &rxq->rxq_stats;
 	unsigned int start;
 
-	u64_stats_update_begin(&stats->syncp);
 	do {
-		start = u64_stats_fetch_begin(&rxq_stats->syncp);
+		start = u64_stats_fetch_begin_irq(&rxq_stats->syncp);
 		stats->pkts = rxq_stats->pkts;
 		stats->bytes = rxq_stats->bytes;
 		stats->errors = rxq_stats->csum_errors +
 				rxq_stats->other_errors;
 		stats->csum_errors = rxq_stats->csum_errors;
 		stats->other_errors = rxq_stats->other_errors;
-	} while (u64_stats_fetch_retry(&rxq_stats->syncp, start));
-	u64_stats_update_end(&stats->syncp);
+	} while (u64_stats_fetch_retry_irq(&rxq_stats->syncp, start));
 }
 
 /**
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
index a984a7a6dd2e..8d3ec6c729cc 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
@@ -97,17 +97,15 @@ void hinic_txq_get_stats(struct hinic_txq *txq, struct hinic_txq_stats *stats)
 	struct hinic_txq_stats *txq_stats = &txq->txq_stats;
 	unsigned int start;
 
-	u64_stats_update_begin(&stats->syncp);
 	do {
-		start = u64_stats_fetch_begin(&txq_stats->syncp);
+		start = u64_stats_fetch_begin_irq(&txq_stats->syncp);
 		stats->pkts    = txq_stats->pkts;
 		stats->bytes   = txq_stats->bytes;
 		stats->tx_busy = txq_stats->tx_busy;
 		stats->tx_wake = txq_stats->tx_wake;
 		stats->tx_dropped = txq_stats->tx_dropped;
 		stats->big_frags_pkts = txq_stats->big_frags_pkts;
-	} while (u64_stats_fetch_retry(&txq_stats->syncp, start));
-	u64_stats_update_end(&stats->syncp);
+	} while (u64_stats_fetch_retry_irq(&txq_stats->syncp, start));
 }
 
 /**
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index b262aa84b6a2..4a070724a8fb 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -2064,6 +2064,19 @@ static const char *reset_reason_to_string(enum ibmvnic_reset_reason reason)
 }
 
 /*
+ * Initialize the init_done completion and return code values. We
+ * can get a transport event just after registering the CRQ and the
+ * tasklet will use this to communicate the transport event. To ensure
+ * we don't miss the notification/error, initialize these _before_
+ * regisering the CRQ.
+ */
+static inline void reinit_init_done(struct ibmvnic_adapter *adapter)
+{
+	reinit_completion(&adapter->init_done);
+	adapter->init_done_rc = 0;
+}
+
+/*
  * do_reset returns zero if we are able to keep processing reset events, or
  * non-zero if we hit a fatal error and must halt.
  */
@@ -2169,6 +2182,8 @@ static int do_reset(struct ibmvnic_adapter *adapter,
 		 */
 		adapter->state = VNIC_PROBED;
 
+		reinit_init_done(adapter);
+
 		if (adapter->reset_reason == VNIC_RESET_CHANGE_PARAM) {
 			rc = init_crq_queue(adapter);
 		} else if (adapter->reset_reason == VNIC_RESET_MOBILITY) {
@@ -2314,7 +2329,8 @@ static int do_hard_reset(struct ibmvnic_adapter *adapter,
 	 */
 	adapter->state = VNIC_PROBED;
 
-	reinit_completion(&adapter->init_done);
+	reinit_init_done(adapter);
+
 	rc = init_crq_queue(adapter);
 	if (rc) {
 		netdev_err(adapter->netdev,
@@ -2455,23 +2471,82 @@ out:
 static void __ibmvnic_reset(struct work_struct *work)
 {
 	struct ibmvnic_adapter *adapter;
-	bool saved_state = false;
+	unsigned int timeout = 5000;
 	struct ibmvnic_rwi *tmprwi;
+	bool saved_state = false;
 	struct ibmvnic_rwi *rwi;
 	unsigned long flags;
-	u32 reset_state;
+	struct device *dev;
+	bool need_reset;
 	int num_fails = 0;
+	u32 reset_state;
 	int rc = 0;
 
 	adapter = container_of(work, struct ibmvnic_adapter, ibmvnic_reset);
+		dev = &adapter->vdev->dev;
 
-	if (test_and_set_bit_lock(0, &adapter->resetting)) {
+	/* Wait for ibmvnic_probe() to complete. If probe is taking too long
+	 * or if another reset is in progress, defer work for now. If probe
+	 * eventually fails it will flush and terminate our work.
+	 *
+	 * Three possibilities here:
+	 * 1. Adpater being removed  - just return
+	 * 2. Timed out on probe or another reset in progress - delay the work
+	 * 3. Completed probe - perform any resets in queue
+	 */
+	if (adapter->state == VNIC_PROBING &&
+	    !wait_for_completion_timeout(&adapter->probe_done, timeout)) {
+		dev_err(dev, "Reset thread timed out on probe");
 		queue_delayed_work(system_long_wq,
 				   &adapter->ibmvnic_delayed_reset,
 				   IBMVNIC_RESET_DELAY);
 		return;
 	}
 
+	/* adapter is done with probe (i.e state is never VNIC_PROBING now) */
+	if (adapter->state == VNIC_REMOVING)
+		return;
+
+	/* ->rwi_list is stable now (no one else is removing entries) */
+
+	/* ibmvnic_probe() may have purged the reset queue after we were
+	 * scheduled to process a reset so there maybe no resets to process.
+	 * Before setting the ->resetting bit though, we have to make sure
+	 * that there is infact a reset to process. Otherwise we may race
+	 * with ibmvnic_open() and end up leaving the vnic down:
+	 *
+	 *	__ibmvnic_reset()	    ibmvnic_open()
+	 *	-----------------	    --------------
+	 *
+	 *  set ->resetting bit
+	 *  				find ->resetting bit is set
+	 *  				set ->state to IBMVNIC_OPEN (i.e
+	 *  				assume reset will open device)
+	 *  				return
+	 *  find reset queue empty
+	 *  return
+	 *
+	 *  	Neither performed vnic login/open and vnic stays down
+	 *
+	 * If we hold the lock and conditionally set the bit, either we
+	 * or ibmvnic_open() will complete the open.
+	 */
+	need_reset = false;
+	spin_lock(&adapter->rwi_lock);
+	if (!list_empty(&adapter->rwi_list)) {
+		if (test_and_set_bit_lock(0, &adapter->resetting)) {
+			queue_delayed_work(system_long_wq,
+					   &adapter->ibmvnic_delayed_reset,
+					   IBMVNIC_RESET_DELAY);
+		} else {
+			need_reset = true;
+		}
+	}
+	spin_unlock(&adapter->rwi_lock);
+
+	if (!need_reset)
+		return;
+
 	rwi = get_next_rwi(adapter);
 	while (rwi) {
 		spin_lock_irqsave(&adapter->state_lock, flags);
@@ -2623,13 +2698,6 @@ static int ibmvnic_reset(struct ibmvnic_adapter *adapter,
 		goto err;
 	}
 
-	if (adapter->state == VNIC_PROBING) {
-		netdev_warn(netdev, "Adapter reset during probe\n");
-		adapter->init_done_rc = -EAGAIN;
-		ret = EAGAIN;
-		goto err;
-	}
-
 	list_for_each_entry(tmp, &adapter->rwi_list, list) {
 		if (tmp->reset_reason == reason) {
 			netdev_dbg(netdev, "Skipping matching reset, reason=%s\n",
@@ -5485,10 +5553,6 @@ static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter, bool reset)
 
 	adapter->from_passive_init = false;
 
-	if (reset)
-		reinit_completion(&adapter->init_done);
-
-	adapter->init_done_rc = 0;
 	rc = ibmvnic_send_crq_init(adapter);
 	if (rc) {
 		dev_err(dev, "Send crq init failed with error %d\n", rc);
@@ -5502,12 +5566,14 @@ static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter, bool reset)
 
 	if (adapter->init_done_rc) {
 		release_crq_queue(adapter);
+		dev_err(dev, "CRQ-init failed, %d\n", adapter->init_done_rc);
 		return adapter->init_done_rc;
 	}
 
 	if (adapter->from_passive_init) {
 		adapter->state = VNIC_OPEN;
 		adapter->from_passive_init = false;
+		dev_err(dev, "CRQ-init failed, passive-init\n");
 		return -1;
 	}
 
@@ -5519,6 +5585,15 @@ static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter, bool reset)
 			release_sub_crqs(adapter, 0);
 			rc = init_sub_crqs(adapter);
 		} else {
+			/* no need to reinitialize completely, but we do
+			 * need to clean up transmits that were in flight
+			 * when we processed the reset.  Failure to do so
+			 * will confound the upper layer, usually TCP, by
+			 * creating the illusion of transmits that are
+			 * awaiting completion.
+			 */
+			clean_tx_pools(adapter);
+
 			rc = reset_sub_crq_queues(adapter);
 		}
 	} else {
@@ -5547,6 +5622,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	struct ibmvnic_adapter *adapter;
 	struct net_device *netdev;
 	unsigned char *mac_addr_p;
+	unsigned long flags;
 	bool init_success;
 	int rc;
 
@@ -5588,6 +5664,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	spin_lock_init(&adapter->rwi_lock);
 	spin_lock_init(&adapter->state_lock);
 	mutex_init(&adapter->fw_lock);
+	init_completion(&adapter->probe_done);
 	init_completion(&adapter->init_done);
 	init_completion(&adapter->fw_done);
 	init_completion(&adapter->reset_done);
@@ -5596,6 +5673,33 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 
 	init_success = false;
 	do {
+		reinit_init_done(adapter);
+
+		/* clear any failovers we got in the previous pass
+		 * since we are reinitializing the CRQ
+		 */
+		adapter->failover_pending = false;
+
+		/* If we had already initialized CRQ, we may have one or
+		 * more resets queued already. Discard those and release
+		 * the CRQ before initializing the CRQ again.
+		 */
+		release_crq_queue(adapter);
+
+		/* Since we are still in PROBING state, __ibmvnic_reset()
+		 * will not access the ->rwi_list and since we released CRQ,
+		 * we won't get _new_ transport events. But there maybe an
+		 * ongoing ibmvnic_reset() call. So serialize access to
+		 * rwi_list. If we win the race, ibvmnic_reset() could add
+		 * a reset after we purged but thats ok - we just may end
+		 * up with an extra reset (i.e similar to having two or more
+		 * resets in the queue at once).
+		 * CHECK.
+		 */
+		spin_lock_irqsave(&adapter->rwi_lock, flags);
+		flush_reset_queue(adapter);
+		spin_unlock_irqrestore(&adapter->rwi_lock, flags);
+
 		rc = init_crq_queue(adapter);
 		if (rc) {
 			dev_err(&dev->dev, "Couldn't initialize crq. rc=%d\n",
@@ -5647,6 +5751,8 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	}
 	dev_info(&dev->dev, "ibmvnic registered\n");
 
+	complete(&adapter->probe_done);
+
 	return 0;
 
 ibmvnic_register_fail:
@@ -5661,6 +5767,17 @@ ibmvnic_stats_fail:
 ibmvnic_init_fail:
 	release_sub_crqs(adapter, 1);
 	release_crq_queue(adapter);
+
+	/* cleanup worker thread after releasing CRQ so we don't get
+	 * transport events (i.e new work items for the worker thread).
+	 */
+	adapter->state = VNIC_REMOVING;
+	complete(&adapter->probe_done);
+	flush_work(&adapter->ibmvnic_reset);
+	flush_delayed_work(&adapter->ibmvnic_delayed_reset);
+
+	flush_reset_queue(adapter);
+
 	mutex_destroy(&adapter->fw_lock);
 	free_netdev(netdev);
 
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index 1a9ed9202654..b01c439965ff 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -927,6 +927,7 @@ struct ibmvnic_adapter {
 
 	struct ibmvnic_tx_pool *tx_pool;
 	struct ibmvnic_tx_pool *tso_pool;
+	struct completion probe_done;
 	struct completion init_done;
 	int init_done_rc;
 
diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h
index 13382df2f2ef..bcf680e83811 100644
--- a/drivers/net/ethernet/intel/e1000e/hw.h
+++ b/drivers/net/ethernet/intel/e1000e/hw.h
@@ -630,7 +630,6 @@ struct e1000_phy_info {
 	bool disable_polarity_correction;
 	bool is_mdix;
 	bool polarity_correction;
-	bool reset_disable;
 	bool speed_downgraded;
 	bool autoneg_wait_to_complete;
 };
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index e6c8e6d5234f..9466f65a6da7 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -2050,10 +2050,6 @@ static s32 e1000_check_reset_block_ich8lan(struct e1000_hw *hw)
 	bool blocked = false;
 	int i = 0;
 
-	/* Check the PHY (LCD) reset flag */
-	if (hw->phy.reset_disable)
-		return true;
-
 	while ((blocked = !(er32(FWSM) & E1000_ICH_FWSM_RSPCIPHY)) &&
 	       (i++ < 30))
 		usleep_range(10000, 11000);
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.h b/drivers/net/ethernet/intel/e1000e/ich8lan.h
index 638a3ddd7ada..2504b11c3169 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.h
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.h
@@ -271,7 +271,6 @@
 #define I217_CGFREG_ENABLE_MTA_RESET	0x0002
 #define I217_MEMPWR			PHY_REG(772, 26)
 #define I217_MEMPWR_DISABLE_SMB_RELEASE	0x0010
-#define I217_MEMPWR_MOEM		0x1000
 
 /* Receive Address Initial CRC Calculation */
 #define E1000_PCH_RAICC(_n)	(0x05F50 + ((_n) * 4))
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index ce48e630fe55..407bbb4cc236 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -6499,6 +6499,10 @@ static void e1000e_s0ix_exit_flow(struct e1000_adapter *adapter)
 
 	if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID &&
 	    hw->mac.type >= e1000_pch_adp) {
+		/* Keep the GPT clock enabled for CSME */
+		mac_data = er32(FEXTNVM);
+		mac_data |= BIT(3);
+		ew32(FEXTNVM, mac_data);
 		/* Request ME unconfigure the device from S0ix */
 		mac_data = er32(H2ME);
 		mac_data &= ~E1000_H2ME_START_DPG;
@@ -6992,21 +6996,8 @@ static __maybe_unused int e1000e_pm_suspend(struct device *dev)
 	struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev));
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct pci_dev *pdev = to_pci_dev(dev);
-	struct e1000_hw *hw = &adapter->hw;
-	u16 phy_data;
 	int rc;
 
-	if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID &&
-	    hw->mac.type >= e1000_pch_adp) {
-		/* Mask OEM Bits / Gig Disable / Restart AN (772_26[12] = 1) */
-		e1e_rphy(hw, I217_MEMPWR, &phy_data);
-		phy_data |= I217_MEMPWR_MOEM;
-		e1e_wphy(hw, I217_MEMPWR, phy_data);
-
-		/* Disable LCD reset */
-		hw->phy.reset_disable = true;
-	}
-
 	e1000e_flush_lpic(pdev);
 
 	e1000e_pm_freeze(dev);
@@ -7028,8 +7019,6 @@ static __maybe_unused int e1000e_pm_resume(struct device *dev)
 	struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev));
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct pci_dev *pdev = to_pci_dev(dev);
-	struct e1000_hw *hw = &adapter->hw;
-	u16 phy_data;
 	int rc;
 
 	/* Introduce S0ix implementation */
@@ -7040,17 +7029,6 @@ static __maybe_unused int e1000e_pm_resume(struct device *dev)
 	if (rc)
 		return rc;
 
-	if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID &&
-	    hw->mac.type >= e1000_pch_adp) {
-		/* Unmask OEM Bits / Gig Disable / Restart AN 772_26[12] = 0 */
-		e1e_rphy(hw, I217_MEMPWR, &phy_data);
-		phy_data &= ~I217_MEMPWR_MOEM;
-		e1e_wphy(hw, I217_MEMPWR, phy_data);
-
-		/* Enable LCD reset */
-		hw->phy.reset_disable = false;
-	}
-
 	return e1000e_pm_thaw(dev);
 }
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 56a3a6d1dbe4..0f19c237cb58 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -37,6 +37,7 @@
 #include <net/tc_act/tc_mirred.h>
 #include <net/udp_tunnel.h>
 #include <net/xdp_sock.h>
+#include <linux/bitfield.h>
 #include "i40e_type.h"
 #include "i40e_prototype.h"
 #include <linux/net/intel/i40e_client.h>
@@ -1087,6 +1088,21 @@ static inline void i40e_write_fd_input_set(struct i40e_pf *pf,
 			  (u32)(val & 0xFFFFFFFFULL));
 }
 
+/**
+ * i40e_get_pf_count - get PCI PF count.
+ * @hw: pointer to a hw.
+ *
+ * Reports the function number of the highest PCI physical
+ * function plus 1 as it is loaded from the NVM.
+ *
+ * Return: PCI PF count.
+ **/
+static inline u32 i40e_get_pf_count(struct i40e_hw *hw)
+{
+	return FIELD_GET(I40E_GLGEN_PCIFCNCNT_PCIPFCNT_MASK,
+			 rd32(hw, I40E_GLGEN_PCIFCNCNT));
+}
+
 /* needed by i40e_ethtool.c */
 int i40e_up(struct i40e_vsi *vsi);
 void i40e_down(struct i40e_vsi *vsi);
@@ -1270,4 +1286,18 @@ int i40e_add_del_cloud_filter(struct i40e_vsi *vsi,
 int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi,
 				      struct i40e_cloud_filter *filter,
 				      bool add);
+
+/**
+ * i40e_is_tc_mqprio_enabled - check if TC MQPRIO is enabled on PF
+ * @pf: pointer to a pf.
+ *
+ * Check and return value of flag I40E_FLAG_TC_MQPRIO.
+ *
+ * Return: I40E_FLAG_TC_MQPRIO set state.
+ **/
+static inline u32 i40e_is_tc_mqprio_enabled(struct i40e_pf *pf)
+{
+	return pf->flags & I40E_FLAG_TC_MQPRIO;
+}
+
 #endif /* _I40E_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c
index ea2bb0140a6e..10d7a982a5b9 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_client.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_client.c
@@ -177,6 +177,10 @@ void i40e_notify_client_of_netdev_close(struct i40e_vsi *vsi, bool reset)
 			"Cannot locate client instance close routine\n");
 		return;
 	}
+	if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) {
+		dev_dbg(&pf->pdev->dev, "Client is not open, abort close\n");
+		return;
+	}
 	cdev->client->ops->close(&cdev->lan_info, cdev->client, reset);
 	clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state);
 	i40e_client_release_qvlist(&cdev->lan_info);
@@ -429,7 +433,6 @@ void i40e_client_subtask(struct i40e_pf *pf)
 				/* Remove failed client instance */
 				clear_bit(__I40E_CLIENT_INSTANCE_OPENED,
 					  &cdev->state);
-				i40e_client_del_instance(pf);
 				return;
 			}
 		}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 0e13ce9b4d00..8e770c5e181e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -4385,7 +4385,7 @@ static int i40e_check_fdir_input_set(struct i40e_vsi *vsi,
 				    (struct in6_addr *)&ipv6_full_mask))
 			new_mask |= I40E_L3_V6_DST_MASK;
 		else if (ipv6_addr_any((struct in6_addr *)
-				       &usr_ip6_spec->ip6src))
+				       &usr_ip6_spec->ip6dst))
 			new_mask &= ~I40E_L3_V6_DST_MASK;
 		else
 			return -EOPNOTSUPP;
@@ -4921,7 +4921,7 @@ static int i40e_set_channels(struct net_device *dev,
 	/* We do not support setting channels via ethtool when TCs are
 	 * configured through mqprio
 	 */
-	if (pf->flags & I40E_FLAG_TC_MQPRIO)
+	if (i40e_is_tc_mqprio_enabled(pf))
 		return -EINVAL;
 
 	/* verify they are not requesting separate vectors */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 9bc05d671ad5..ce6eea7a6002 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -383,7 +383,9 @@ static void i40e_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 		set_bit(__I40E_GLOBAL_RESET_REQUESTED, pf->state);
 		break;
 	default:
-		netdev_err(netdev, "tx_timeout recovery unsuccessful\n");
+		netdev_err(netdev, "tx_timeout recovery unsuccessful, device is in non-recoverable state.\n");
+		set_bit(__I40E_DOWN_REQUESTED, pf->state);
+		set_bit(__I40E_VSI_DOWN_REQUESTED, vsi->state);
 		break;
 	}
 
@@ -550,6 +552,47 @@ void i40e_pf_reset_stats(struct i40e_pf *pf)
 }
 
 /**
+ * i40e_compute_pci_to_hw_id - compute index form PCI function.
+ * @vsi: ptr to the VSI to read from.
+ * @hw: ptr to the hardware info.
+ **/
+static u32 i40e_compute_pci_to_hw_id(struct i40e_vsi *vsi, struct i40e_hw *hw)
+{
+	int pf_count = i40e_get_pf_count(hw);
+
+	if (vsi->type == I40E_VSI_SRIOV)
+		return (hw->port * BIT(7)) / pf_count + vsi->vf_id;
+
+	return hw->port + BIT(7);
+}
+
+/**
+ * i40e_stat_update64 - read and update a 64 bit stat from the chip.
+ * @hw: ptr to the hardware info.
+ * @hireg: the high 32 bit reg to read.
+ * @loreg: the low 32 bit reg to read.
+ * @offset_loaded: has the initial offset been loaded yet.
+ * @offset: ptr to current offset value.
+ * @stat: ptr to the stat.
+ *
+ * Since the device stats are not reset at PFReset, they will not
+ * be zeroed when the driver starts.  We'll save the first values read
+ * and use them as offsets to be subtracted from the raw values in order
+ * to report stats that count from zero.
+ **/
+static void i40e_stat_update64(struct i40e_hw *hw, u32 hireg, u32 loreg,
+			       bool offset_loaded, u64 *offset, u64 *stat)
+{
+	u64 new_data;
+
+	new_data = rd64(hw, loreg);
+
+	if (!offset_loaded || new_data < *offset)
+		*offset = new_data;
+	*stat = new_data - *offset;
+}
+
+/**
  * i40e_stat_update48 - read and update a 48 bit stat from the chip
  * @hw: ptr to the hardware info
  * @hireg: the high 32 bit reg to read
@@ -621,6 +664,34 @@ static void i40e_stat_update_and_clear32(struct i40e_hw *hw, u32 reg, u64 *stat)
 }
 
 /**
+ * i40e_stats_update_rx_discards - update rx_discards.
+ * @vsi: ptr to the VSI to be updated.
+ * @hw: ptr to the hardware info.
+ * @stat_idx: VSI's stat_counter_idx.
+ * @offset_loaded: ptr to the VSI's stat_offsets_loaded.
+ * @stat_offset: ptr to stat_offset to store first read of specific register.
+ * @stat: ptr to VSI's stat to be updated.
+ **/
+static void
+i40e_stats_update_rx_discards(struct i40e_vsi *vsi, struct i40e_hw *hw,
+			      int stat_idx, bool offset_loaded,
+			      struct i40e_eth_stats *stat_offset,
+			      struct i40e_eth_stats *stat)
+{
+	u64 rx_rdpc, rx_rxerr;
+
+	i40e_stat_update32(hw, I40E_GLV_RDPC(stat_idx), offset_loaded,
+			   &stat_offset->rx_discards, &rx_rdpc);
+	i40e_stat_update64(hw,
+			   I40E_GL_RXERR1H(i40e_compute_pci_to_hw_id(vsi, hw)),
+			   I40E_GL_RXERR1L(i40e_compute_pci_to_hw_id(vsi, hw)),
+			   offset_loaded, &stat_offset->rx_discards_other,
+			   &rx_rxerr);
+
+	stat->rx_discards = rx_rdpc + rx_rxerr;
+}
+
+/**
  * i40e_update_eth_stats - Update VSI-specific ethernet statistics counters.
  * @vsi: the VSI to be updated
  **/
@@ -679,6 +750,10 @@ void i40e_update_eth_stats(struct i40e_vsi *vsi)
 			   I40E_GLV_BPTCL(stat_idx),
 			   vsi->stat_offsets_loaded,
 			   &oes->tx_broadcast, &es->tx_broadcast);
+
+	i40e_stats_update_rx_discards(vsi, hw, stat_idx,
+				      vsi->stat_offsets_loaded, oes, es);
+
 	vsi->stat_offsets_loaded = true;
 }
 
@@ -1835,11 +1910,15 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
 		 * non-zero req_queue_pairs says that user requested a new
 		 * queue count via ethtool's set_channels, so use this
 		 * value for queues distribution across traffic classes
+		 * We need at least one queue pair for the interface
+		 * to be usable as we see in else statement.
 		 */
 		if (vsi->req_queue_pairs > 0)
 			vsi->num_queue_pairs = vsi->req_queue_pairs;
 		else if (pf->flags & I40E_FLAG_MSIX_ENABLED)
 			vsi->num_queue_pairs = pf->num_lan_msix;
+		else
+			vsi->num_queue_pairs = 1;
 	}
 
 	/* Number of queues per enabled TC */
@@ -5241,7 +5320,7 @@ static u8 i40e_pf_get_num_tc(struct i40e_pf *pf)
 	u8 num_tc = 0;
 	struct i40e_dcbx_config *dcbcfg = &hw->local_dcbx_config;
 
-	if (pf->flags & I40E_FLAG_TC_MQPRIO)
+	if (i40e_is_tc_mqprio_enabled(pf))
 		return pf->vsi[pf->lan_vsi]->mqprio_qopt.qopt.num_tc;
 
 	/* If neither MQPRIO nor DCB is enabled, then always use single TC */
@@ -5273,7 +5352,7 @@ static u8 i40e_pf_get_num_tc(struct i40e_pf *pf)
  **/
 static u8 i40e_pf_get_tc_map(struct i40e_pf *pf)
 {
-	if (pf->flags & I40E_FLAG_TC_MQPRIO)
+	if (i40e_is_tc_mqprio_enabled(pf))
 		return i40e_mqprio_get_enabled_tc(pf);
 
 	/* If neither MQPRIO nor DCB is enabled for this PF then just return
@@ -5370,7 +5449,7 @@ static int i40e_vsi_configure_bw_alloc(struct i40e_vsi *vsi, u8 enabled_tc,
 	int i;
 
 	/* There is no need to reset BW when mqprio mode is on.  */
-	if (pf->flags & I40E_FLAG_TC_MQPRIO)
+	if (i40e_is_tc_mqprio_enabled(pf))
 		return 0;
 	if (!vsi->mqprio_qopt.qopt.hw && !(pf->flags & I40E_FLAG_DCB_ENABLED)) {
 		ret = i40e_set_bw_limit(vsi, vsi->seid, 0);
@@ -5442,7 +5521,7 @@ static void i40e_vsi_config_netdev_tc(struct i40e_vsi *vsi, u8 enabled_tc)
 					vsi->tc_config.tc_info[i].qoffset);
 	}
 
-	if (pf->flags & I40E_FLAG_TC_MQPRIO)
+	if (i40e_is_tc_mqprio_enabled(pf))
 		return;
 
 	/* Assign UP2TC map for the VSI */
@@ -5603,7 +5682,7 @@ static int i40e_vsi_config_tc(struct i40e_vsi *vsi, u8 enabled_tc)
 	ctxt.vf_num = 0;
 	ctxt.uplink_seid = vsi->uplink_seid;
 	ctxt.info = vsi->info;
-	if (vsi->back->flags & I40E_FLAG_TC_MQPRIO) {
+	if (i40e_is_tc_mqprio_enabled(pf)) {
 		ret = i40e_vsi_setup_queue_map_mqprio(vsi, &ctxt, enabled_tc);
 		if (ret)
 			goto out;
@@ -6327,7 +6406,7 @@ int i40e_create_queue_channel(struct i40e_vsi *vsi,
 		pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
 
 		if (vsi->type == I40E_VSI_MAIN) {
-			if (pf->flags & I40E_FLAG_TC_MQPRIO)
+			if (i40e_is_tc_mqprio_enabled(pf))
 				i40e_do_reset(pf, I40E_PF_RESET_FLAG, true);
 			else
 				i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG);
@@ -6438,6 +6517,9 @@ static int i40e_configure_queue_channels(struct i40e_vsi *vsi)
 			vsi->tc_seid_map[i] = ch->seid;
 		}
 	}
+
+	/* reset to reconfigure TX queue contexts */
+	i40e_do_reset(vsi->back, I40E_PF_RESET_FLAG, true);
 	return ret;
 
 err_free:
@@ -7721,7 +7803,7 @@ static void *i40e_fwd_add(struct net_device *netdev, struct net_device *vdev)
 		netdev_info(netdev, "Macvlans are not supported when DCB is enabled\n");
 		return ERR_PTR(-EINVAL);
 	}
-	if ((pf->flags & I40E_FLAG_TC_MQPRIO)) {
+	if (i40e_is_tc_mqprio_enabled(pf)) {
 		netdev_info(netdev, "Macvlans are not supported when HW TC offload is on\n");
 		return ERR_PTR(-EINVAL);
 	}
@@ -7974,7 +8056,7 @@ config_tc:
 	/* Quiesce VSI queues */
 	i40e_quiesce_vsi(vsi);
 
-	if (!hw && !(pf->flags & I40E_FLAG_TC_MQPRIO))
+	if (!hw && !i40e_is_tc_mqprio_enabled(pf))
 		i40e_remove_queue_channels(vsi);
 
 	/* Configure VSI for enabled TCs */
@@ -7998,7 +8080,7 @@ config_tc:
 		 "Setup channel (id:%u) utilizing num_queues %d\n",
 		 vsi->seid, vsi->tc_config.tc_info[0].qcount);
 
-	if (pf->flags & I40E_FLAG_TC_MQPRIO) {
+	if (i40e_is_tc_mqprio_enabled(pf)) {
 		if (vsi->mqprio_qopt.max_rate[0]) {
 			u64 max_tx_rate = vsi->mqprio_qopt.max_rate[0];
 
@@ -10558,7 +10640,7 @@ static int i40e_reset(struct i40e_pf *pf)
  **/
 static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 {
-	int old_recovery_mode_bit = test_bit(__I40E_RECOVERY_MODE, pf->state);
+	const bool is_recovery_mode_reported = i40e_check_recovery_mode(pf);
 	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
 	struct i40e_hw *hw = &pf->hw;
 	i40e_status ret;
@@ -10566,13 +10648,11 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 	int v;
 
 	if (test_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state) &&
-	    i40e_check_recovery_mode(pf)) {
+	    is_recovery_mode_reported)
 		i40e_set_ethtool_ops(pf->vsi[pf->lan_vsi]->netdev);
-	}
 
 	if (test_bit(__I40E_DOWN, pf->state) &&
-	    !test_bit(__I40E_RECOVERY_MODE, pf->state) &&
-	    !old_recovery_mode_bit)
+	    !test_bit(__I40E_RECOVERY_MODE, pf->state))
 		goto clear_recovery;
 	dev_dbg(&pf->pdev->dev, "Rebuilding internal switch\n");
 
@@ -10599,13 +10679,12 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 	 * accordingly with regard to resources initialization
 	 * and deinitialization
 	 */
-	if (test_bit(__I40E_RECOVERY_MODE, pf->state) ||
-	    old_recovery_mode_bit) {
+	if (test_bit(__I40E_RECOVERY_MODE, pf->state)) {
 		if (i40e_get_capabilities(pf,
 					  i40e_aqc_opc_list_func_capabilities))
 			goto end_unlock;
 
-		if (test_bit(__I40E_RECOVERY_MODE, pf->state)) {
+		if (is_recovery_mode_reported) {
 			/* we're staying in recovery mode so we'll reinitialize
 			 * misc vector here
 			 */
@@ -10655,7 +10734,7 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 	 * unless I40E_FLAG_TC_MQPRIO was enabled or DCB
 	 * is not supported with new link speed
 	 */
-	if (pf->flags & I40E_FLAG_TC_MQPRIO) {
+	if (i40e_is_tc_mqprio_enabled(pf)) {
 		i40e_aq_set_dcb_parameters(hw, false, NULL);
 	} else {
 		if (I40E_IS_X710TL_DEVICE(hw->device_id) &&
diff --git a/drivers/net/ethernet/intel/i40e/i40e_register.h b/drivers/net/ethernet/intel/i40e/i40e_register.h
index 1908eed4fa5e..7339003aa17c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_register.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_register.h
@@ -211,6 +211,11 @@
 #define I40E_GLGEN_MSRWD_MDIWRDATA_SHIFT 0
 #define I40E_GLGEN_MSRWD_MDIRDDATA_SHIFT 16
 #define I40E_GLGEN_MSRWD_MDIRDDATA_MASK I40E_MASK(0xFFFF, I40E_GLGEN_MSRWD_MDIRDDATA_SHIFT)
+#define I40E_GLGEN_PCIFCNCNT                0x001C0AB4 /* Reset: PCIR */
+#define I40E_GLGEN_PCIFCNCNT_PCIPFCNT_SHIFT 0
+#define I40E_GLGEN_PCIFCNCNT_PCIPFCNT_MASK  I40E_MASK(0x1F, I40E_GLGEN_PCIFCNCNT_PCIPFCNT_SHIFT)
+#define I40E_GLGEN_PCIFCNCNT_PCIVFCNT_SHIFT 16
+#define I40E_GLGEN_PCIFCNCNT_PCIVFCNT_MASK  I40E_MASK(0xFF, I40E_GLGEN_PCIFCNCNT_PCIVFCNT_SHIFT)
 #define I40E_GLGEN_RSTAT 0x000B8188 /* Reset: POR */
 #define I40E_GLGEN_RSTAT_DEVSTATE_SHIFT 0
 #define I40E_GLGEN_RSTAT_DEVSTATE_MASK I40E_MASK(0x3, I40E_GLGEN_RSTAT_DEVSTATE_SHIFT)
@@ -643,6 +648,14 @@
 #define I40E_VFQF_HKEY1_MAX_INDEX 12
 #define I40E_VFQF_HLUT1(_i, _VF) (0x00220000 + ((_i) * 1024 + (_VF) * 4)) /* _i=0...15, _VF=0...127 */ /* Reset: CORER */
 #define I40E_VFQF_HLUT1_MAX_INDEX 15
+#define I40E_GL_RXERR1H(_i)             (0x00318004 + ((_i) * 8)) /* _i=0...143 */ /* Reset: CORER */
+#define I40E_GL_RXERR1H_MAX_INDEX       143
+#define I40E_GL_RXERR1H_RXERR1H_SHIFT   0
+#define I40E_GL_RXERR1H_RXERR1H_MASK    I40E_MASK(0xFFFFFFFF, I40E_GL_RXERR1H_RXERR1H_SHIFT)
+#define I40E_GL_RXERR1L(_i)             (0x00318000 + ((_i) * 8)) /* _i=0...143 */ /* Reset: CORER */
+#define I40E_GL_RXERR1L_MAX_INDEX       143
+#define I40E_GL_RXERR1L_RXERR1L_SHIFT   0
+#define I40E_GL_RXERR1L_RXERR1L_MASK    I40E_MASK(0xFFFFFFFF, I40E_GL_RXERR1L_RXERR1L_SHIFT)
 #define I40E_GLPRT_BPRCH(_i) (0x003005E4 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
 #define I40E_GLPRT_BPRCL(_i) (0x003005E0 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
 #define I40E_GLPRT_BPTCH(_i) (0x00300A04 + ((_i) * 8)) /* _i=0...3 */ /* Reset: CORER */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index d3a4a33977ee..326fd25d055f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -3651,7 +3651,8 @@ u16 i40e_lan_select_queue(struct net_device *netdev,
 	u8 prio;
 
 	/* is DCB enabled at all? */
-	if (vsi->tc_config.numtc == 1)
+	if (vsi->tc_config.numtc == 1 ||
+	    i40e_is_tc_mqprio_enabled(vsi->back))
 		return netdev_pick_tx(netdev, skb, sb_dev);
 
 	prio = skb->priority;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index 36a4ca1ffb1a..7b3f30beb757 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -1172,6 +1172,7 @@ struct i40e_eth_stats {
 	u64 tx_broadcast;		/* bptc */
 	u64 tx_discards;		/* tdpc */
 	u64 tx_errors;			/* tepc */
+	u64 rx_discards_other;          /* rxerr1 */
 };
 
 /* Statistics collected per VEB per TC */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 6c1e668f4ebf..d78ac5e7f658 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -2147,6 +2147,10 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg)
 		/* VFs only use TC 0 */
 		vfres->vsi_res[0].qset_handle
 					  = le16_to_cpu(vsi->info.qs_handle[0]);
+		if (!(vf->driver_caps & VIRTCHNL_VF_OFFLOAD_USO) && !vf->pf_set_mac) {
+			i40e_del_mac_filter(vsi, vf->default_lan_addr.addr);
+			eth_zero_addr(vf->default_lan_addr.addr);
+		}
 		ether_addr_copy(vfres->vsi_res[0].default_mac_addr,
 				vf->default_lan_addr.addr);
 	}
diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index 9a122aea6979..99d2b090a1e6 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -89,6 +89,7 @@ struct iavf_vsi {
 #define IAVF_HKEY_ARRAY_SIZE ((IAVF_VFQF_HKEY_MAX_INDEX + 1) * 4)
 #define IAVF_HLUT_ARRAY_SIZE ((IAVF_VFQF_HLUT_MAX_INDEX + 1) * 4)
 #define IAVF_MBPS_DIVISOR	125000 /* divisor to convert to Mbps */
+#define IAVF_MBPS_QUANTA	50
 
 #define IAVF_VIRTCHNL_VF_RESOURCE_SIZE (sizeof(struct virtchnl_vf_resource) + \
 					(IAVF_MAX_VF_VSI * \
@@ -377,6 +378,11 @@ struct iavf_adapter {
 	/* lock to protect access to the cloud filter list */
 	spinlock_t cloud_filter_list_lock;
 	u16 num_cloud_filters;
+	/* snapshot of "num_active_queues" before setup_tc for qdisc add
+	 * is invoked. This information is useful during qdisc del flow,
+	 * to restore correct number of queues
+	 */
+	int orig_num_active_queues;
 
 #define IAVF_MAX_FDIR_FILTERS 128	/* max allowed Flow Director filters */
 	u16 fdir_active_fltr;
diff --git a/drivers/net/ethernet/intel/iavf/iavf_adminq.c b/drivers/net/ethernet/intel/iavf/iavf_adminq.c
index 9fa3fa99b4c2..897b349cdaf1 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_adminq.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_adminq.c
@@ -324,6 +324,7 @@ static enum iavf_status iavf_config_arq_regs(struct iavf_hw *hw)
 static enum iavf_status iavf_init_asq(struct iavf_hw *hw)
 {
 	enum iavf_status ret_code = 0;
+	int i;
 
 	if (hw->aq.asq.count > 0) {
 		/* queue already initialized */
@@ -354,12 +355,17 @@ static enum iavf_status iavf_init_asq(struct iavf_hw *hw)
 	/* initialize base registers */
 	ret_code = iavf_config_asq_regs(hw);
 	if (ret_code)
-		goto init_adminq_free_rings;
+		goto init_free_asq_bufs;
 
 	/* success! */
 	hw->aq.asq.count = hw->aq.num_asq_entries;
 	goto init_adminq_exit;
 
+init_free_asq_bufs:
+	for (i = 0; i < hw->aq.num_asq_entries; i++)
+		iavf_free_dma_mem(hw, &hw->aq.asq.r.asq_bi[i]);
+	iavf_free_virt_mem(hw, &hw->aq.asq.dma_head);
+
 init_adminq_free_rings:
 	iavf_free_adminq_asq(hw);
 
@@ -383,6 +389,7 @@ init_adminq_exit:
 static enum iavf_status iavf_init_arq(struct iavf_hw *hw)
 {
 	enum iavf_status ret_code = 0;
+	int i;
 
 	if (hw->aq.arq.count > 0) {
 		/* queue already initialized */
@@ -413,12 +420,16 @@ static enum iavf_status iavf_init_arq(struct iavf_hw *hw)
 	/* initialize base registers */
 	ret_code = iavf_config_arq_regs(hw);
 	if (ret_code)
-		goto init_adminq_free_rings;
+		goto init_free_arq_bufs;
 
 	/* success! */
 	hw->aq.arq.count = hw->aq.num_arq_entries;
 	goto init_adminq_exit;
 
+init_free_arq_bufs:
+	for (i = 0; i < hw->aq.num_arq_entries; i++)
+		iavf_free_dma_mem(hw, &hw->aq.arq.r.arq_bi[i]);
+	iavf_free_virt_mem(hw, &hw->aq.arq.dma_head);
 init_adminq_free_rings:
 	iavf_free_adminq_arq(hw);
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index ca74824d40b8..00b2ef01f4ea 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -2222,6 +2222,11 @@ static void iavf_reset_task(struct work_struct *work)
 	int i = 0, err;
 	bool running;
 
+	/* Detach interface to avoid subsequent NDO callbacks */
+	rtnl_lock();
+	netif_device_detach(netdev);
+	rtnl_unlock();
+
 	/* When device is being removed it doesn't make sense to run the reset
 	 * task, just return in such a case.
 	 */
@@ -2229,7 +2234,7 @@ static void iavf_reset_task(struct work_struct *work)
 		if (adapter->state != __IAVF_REMOVE)
 			queue_work(iavf_wq, &adapter->reset_task);
 
-		return;
+		goto reset_finish;
 	}
 
 	while (!mutex_trylock(&adapter->client_lock))
@@ -2299,7 +2304,6 @@ continue_reset:
 
 	if (running) {
 		netif_carrier_off(netdev);
-		netif_tx_stop_all_queues(netdev);
 		adapter->link_up = false;
 		iavf_napi_disable_all(adapter);
 	}
@@ -2412,14 +2416,21 @@ continue_reset:
 	mutex_unlock(&adapter->client_lock);
 	mutex_unlock(&adapter->crit_lock);
 
-	return;
+	goto reset_finish;
 reset_err:
+	if (running) {
+		set_bit(__IAVF_VSI_DOWN, adapter->vsi.state);
+		iavf_free_traffic_irqs(adapter);
+	}
+	iavf_disable_vf(adapter);
+
 	mutex_unlock(&adapter->client_lock);
 	mutex_unlock(&adapter->crit_lock);
-	if (running)
-		iavf_change_state(adapter, __IAVF_RUNNING);
 	dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n");
-	iavf_close(netdev);
+reset_finish:
+	rtnl_lock();
+	netif_device_attach(netdev);
+	rtnl_unlock();
 }
 
 /**
@@ -2732,6 +2743,7 @@ static int iavf_validate_ch_config(struct iavf_adapter *adapter,
 				   struct tc_mqprio_qopt_offload *mqprio_qopt)
 {
 	u64 total_max_rate = 0;
+	u32 tx_rate_rem = 0;
 	int i, num_qps = 0;
 	u64 tx_rate = 0;
 	int ret = 0;
@@ -2746,12 +2758,32 @@ static int iavf_validate_ch_config(struct iavf_adapter *adapter,
 			return -EINVAL;
 		if (mqprio_qopt->min_rate[i]) {
 			dev_err(&adapter->pdev->dev,
-				"Invalid min tx rate (greater than 0) specified\n");
+				"Invalid min tx rate (greater than 0) specified for TC%d\n",
+				i);
 			return -EINVAL;
 		}
-		/*convert to Mbps */
+
+		/* convert to Mbps */
 		tx_rate = div_u64(mqprio_qopt->max_rate[i],
 				  IAVF_MBPS_DIVISOR);
+
+		if (mqprio_qopt->max_rate[i] &&
+		    tx_rate < IAVF_MBPS_QUANTA) {
+			dev_err(&adapter->pdev->dev,
+				"Invalid max tx rate for TC%d, minimum %dMbps\n",
+				i, IAVF_MBPS_QUANTA);
+			return -EINVAL;
+		}
+
+		(void)div_u64_rem(tx_rate, IAVF_MBPS_QUANTA, &tx_rate_rem);
+
+		if (tx_rate_rem != 0) {
+			dev_err(&adapter->pdev->dev,
+				"Invalid max tx rate for TC%d, not divisible by %d\n",
+				i, IAVF_MBPS_QUANTA);
+			return -EINVAL;
+		}
+
 		total_max_rate += tx_rate;
 		num_qps += mqprio_qopt->qopt.count[i];
 	}
@@ -2818,6 +2850,7 @@ static int __iavf_setup_tc(struct net_device *netdev, void *type_data)
 			netif_tx_disable(netdev);
 			iavf_del_all_cloud_filters(adapter);
 			adapter->aq_required = IAVF_FLAG_AQ_DISABLE_CHANNELS;
+			total_qps = adapter->orig_num_active_queues;
 			goto exit;
 		} else {
 			return -EINVAL;
@@ -2861,7 +2894,21 @@ static int __iavf_setup_tc(struct net_device *netdev, void *type_data)
 				adapter->ch_config.ch_info[i].offset = 0;
 			}
 		}
+
+		/* Take snapshot of original config such as "num_active_queues"
+		 * It is used later when delete ADQ flow is exercised, so that
+		 * once delete ADQ flow completes, VF shall go back to its
+		 * original queue configuration
+		 */
+
+		adapter->orig_num_active_queues = adapter->num_active_queues;
+
+		/* Store queue info based on TC so that VF gets configured
+		 * with correct number of queues when VF completes ADQ config
+		 * flow
+		 */
 		adapter->ch_config.total_qps = total_qps;
+
 		netif_tx_stop_all_queues(netdev);
 		netif_tx_disable(netdev);
 		adapter->aq_required |= IAVF_FLAG_AQ_ENABLE_CHANNELS;
@@ -2878,6 +2925,12 @@ static int __iavf_setup_tc(struct net_device *netdev, void *type_data)
 		}
 	}
 exit:
+	if (test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section))
+		return 0;
+
+	netif_set_real_num_rx_queues(netdev, total_qps);
+	netif_set_real_num_tx_queues(netdev, total_qps);
+
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
index 3525eab8e9f9..5448ed0e0357 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
@@ -1250,11 +1250,10 @@ static struct iavf_rx_buffer *iavf_get_rx_buffer(struct iavf_ring *rx_ring,
 {
 	struct iavf_rx_buffer *rx_buffer;
 
-	if (!size)
-		return NULL;
-
 	rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean];
 	prefetchw(rx_buffer->page);
+	if (!size)
+		return rx_buffer;
 
 	/* we are reusing so sync this buffer for CPU use */
 	dma_sync_single_range_for_cpu(rx_ring->dev,
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 982db894754f..9b9c2b885486 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -651,7 +651,8 @@ static int ice_lbtest_receive_frames(struct ice_ring *rx_ring)
 		rx_desc = ICE_RX_DESC(rx_ring, i);
 
 		if (!(rx_desc->wb.status_error0 &
-		    cpu_to_le16(ICE_TX_DESC_CMD_EOP | ICE_TX_DESC_CMD_RS)))
+		    (cpu_to_le16(BIT(ICE_RX_FLEX_DESC_STATUS0_DD_S)) |
+		     cpu_to_le16(BIT(ICE_RX_FLEX_DESC_STATUS0_EOF_S)))))
 			continue;
 
 		rx_buf = &rx_ring->rx_buf[i];
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 188abf36a5b2..63ae4674d200 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -3549,7 +3549,7 @@ static int ice_init_pf(struct ice_pf *pf)
 
 	pf->avail_rxqs = bitmap_zalloc(pf->max_pf_rxqs, GFP_KERNEL);
 	if (!pf->avail_rxqs) {
-		devm_kfree(ice_pf_to_dev(pf), pf->avail_txqs);
+		bitmap_free(pf->avail_txqs);
 		pf->avail_txqs = NULL;
 		return -ENOMEM;
 	}
@@ -5481,10 +5481,12 @@ int ice_vsi_cfg(struct ice_vsi *vsi)
 	if (vsi->netdev) {
 		ice_set_rx_mode(vsi->netdev);
 
-		err = ice_vsi_vlan_setup(vsi);
+		if (vsi->type != ICE_VSI_LB) {
+			err = ice_vsi_vlan_setup(vsi);
 
-		if (err)
-			return err;
+			if (err)
+				return err;
+		}
 	}
 	ice_vsi_cfg_dcb_rings(vsi);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 3b6c1420aa7b..deb828e761fa 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -2614,7 +2614,7 @@ ice_set_vlan_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask,
 		else
 			status = ice_set_vsi_promisc(hw, vsi_handle,
 						     promisc_mask, vlan_id);
-		if (status)
+		if (status && status != -EEXIST)
 			break;
 	}
 
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 5581747947e5..60d8ef0c8859 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -321,6 +321,19 @@ int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid)
 	bool if_running, pool_present = !!pool;
 	int ret = 0, pool_failure = 0;
 
+	if (qid >= vsi->num_rxq || qid >= vsi->num_txq) {
+		netdev_err(vsi->netdev, "Please use queue id in scope of combined queues count\n");
+		pool_failure = -EINVAL;
+		goto failure;
+	}
+
+	if (!is_power_of_2(vsi->rx_rings[qid]->count) ||
+	    !is_power_of_2(vsi->tx_rings[qid]->count)) {
+		netdev_err(vsi->netdev, "Please align ring sizes to power of 2\n");
+		pool_failure = -EINVAL;
+		goto failure;
+	}
+
 	if_running = netif_running(vsi->netdev) && ice_is_xdp_ena_vsi(vsi);
 
 	if (if_running) {
@@ -343,6 +356,7 @@ xsk_pool_if_up:
 			netdev_err(vsi->netdev, "ice_qp_ena error = %d\n", ret);
 	}
 
+failure:
 	if (pool_failure) {
 		netdev_err(vsi->netdev, "Could not %sable buffer pool, error = %d\n",
 			   pool_present ? "en" : "dis", pool_failure);
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 2d3daf022651..015b78144114 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -664,6 +664,8 @@ struct igb_adapter {
 	struct igb_mac_addr *mac_table;
 	struct vf_mac_filter vf_macs;
 	struct vf_mac_filter *vf_mac_list;
+	/* lock for VF resources */
+	spinlock_t vfs_lock;
 };
 
 /* flags controlling PTP/1588 function */
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index db11a1c278f6..f19e64830739 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -3637,6 +3637,7 @@ static int igb_disable_sriov(struct pci_dev *pdev)
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
+	unsigned long flags;
 
 	/* reclaim resources allocated to VFs */
 	if (adapter->vf_data) {
@@ -3649,12 +3650,13 @@ static int igb_disable_sriov(struct pci_dev *pdev)
 			pci_disable_sriov(pdev);
 			msleep(500);
 		}
-
+		spin_lock_irqsave(&adapter->vfs_lock, flags);
 		kfree(adapter->vf_mac_list);
 		adapter->vf_mac_list = NULL;
 		kfree(adapter->vf_data);
 		adapter->vf_data = NULL;
 		adapter->vfs_allocated_count = 0;
+		spin_unlock_irqrestore(&adapter->vfs_lock, flags);
 		wr32(E1000_IOVCTL, E1000_IOVCTL_REUSE_VFQ);
 		wrfl();
 		msleep(100);
@@ -3814,7 +3816,9 @@ static void igb_remove(struct pci_dev *pdev)
 	igb_release_hw_control(adapter);
 
 #ifdef CONFIG_PCI_IOV
+	rtnl_lock();
 	igb_disable_sriov(pdev);
+	rtnl_unlock();
 #endif
 
 	unregister_netdev(netdev);
@@ -3974,6 +3978,9 @@ static int igb_sw_init(struct igb_adapter *adapter)
 
 	spin_lock_init(&adapter->nfc_lock);
 	spin_lock_init(&adapter->stats64_lock);
+
+	/* init spinlock to avoid concurrency of VF resources */
+	spin_lock_init(&adapter->vfs_lock);
 #ifdef CONFIG_PCI_IOV
 	switch (hw->mac.type) {
 	case e1000_82576:
@@ -7846,8 +7853,10 @@ unlock:
 static void igb_msg_task(struct igb_adapter *adapter)
 {
 	struct e1000_hw *hw = &adapter->hw;
+	unsigned long flags;
 	u32 vf;
 
+	spin_lock_irqsave(&adapter->vfs_lock, flags);
 	for (vf = 0; vf < adapter->vfs_allocated_count; vf++) {
 		/* process any reset requests */
 		if (!igb_check_for_rst(hw, vf))
@@ -7861,6 +7870,7 @@ static void igb_msg_task(struct igb_adapter *adapter)
 		if (!igb_check_for_ack(hw, vf))
 			igb_rcv_ack_from_vf(adapter, vf);
 	}
+	spin_unlock_irqrestore(&adapter->vfs_lock, flags);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index f99819fc559d..2a84f57ea68b 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -6159,6 +6159,9 @@ u32 igc_rd32(struct igc_hw *hw, u32 reg)
 	u8 __iomem *hw_addr = READ_ONCE(hw->hw_addr);
 	u32 value = 0;
 
+	if (IGC_REMOVED(hw_addr))
+		return ~value;
+
 	value = readl(&hw_addr[reg]);
 
 	/* reads should not return all F's */
diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
index e197a33d93a0..026c3b65fc37 100644
--- a/drivers/net/ethernet/intel/igc/igc_regs.h
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -306,7 +306,8 @@ u32 igc_rd32(struct igc_hw *hw, u32 reg);
 #define wr32(reg, val) \
 do { \
 	u8 __iomem *hw_addr = READ_ONCE((hw)->hw_addr); \
-	writel((val), &hw_addr[(reg)]); \
+	if (!IGC_REMOVED(hw_addr)) \
+		writel((val), &hw_addr[(reg)]); \
 } while (0)
 
 #define rd32(reg) (igc_rd32(hw, reg))
@@ -318,4 +319,6 @@ do { \
 
 #define array_rd32(reg, offset) (igc_rd32(hw, (reg) + ((offset) << 2)))
 
+#define IGC_REMOVED(h) unlikely(!(h))
+
 #endif
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index a604552fa634..c375a5d54b40 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -770,6 +770,7 @@ struct ixgbe_adapter {
 #ifdef CONFIG_IXGBE_IPSEC
 	struct ixgbe_ipsec *ipsec;
 #endif /* CONFIG_IXGBE_IPSEC */
+	spinlock_t vfs_lock;
 };
 
 static inline u8 ixgbe_max_rss_indices(struct ixgbe_adapter *adapter)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 750b02bb2fdc..8cb20af51ecd 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -6397,6 +6397,9 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter,
 	/* n-tuple support exists, always init our spinlock */
 	spin_lock_init(&adapter->fdir_perfect_lock);
 
+	/* init spinlock to avoid concurrency of VF resources */
+	spin_lock_init(&adapter->vfs_lock);
+
 #ifdef CONFIG_IXGBE_DCB
 	ixgbe_init_dcb(adapter);
 #endif
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
index 23ddfd79fc8b..29be1d6eca43 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
@@ -1212,7 +1212,6 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter)
 	struct cyclecounter cc;
 	unsigned long flags;
 	u32 incval = 0;
-	u32 tsauxc = 0;
 	u32 fuse0 = 0;
 
 	/* For some of the boards below this mask is technically incorrect.
@@ -1247,18 +1246,6 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_x550em_a:
 	case ixgbe_mac_X550:
 		cc.read = ixgbe_ptp_read_X550;
-
-		/* enable SYSTIME counter */
-		IXGBE_WRITE_REG(hw, IXGBE_SYSTIMR, 0);
-		IXGBE_WRITE_REG(hw, IXGBE_SYSTIML, 0);
-		IXGBE_WRITE_REG(hw, IXGBE_SYSTIMH, 0);
-		tsauxc = IXGBE_READ_REG(hw, IXGBE_TSAUXC);
-		IXGBE_WRITE_REG(hw, IXGBE_TSAUXC,
-				tsauxc & ~IXGBE_TSAUXC_DISABLE_SYSTIME);
-		IXGBE_WRITE_REG(hw, IXGBE_TSIM, IXGBE_TSIM_TXTS);
-		IXGBE_WRITE_REG(hw, IXGBE_EIMS, IXGBE_EIMS_TIMESYNC);
-
-		IXGBE_WRITE_FLUSH(hw);
 		break;
 	case ixgbe_mac_X540:
 		cc.read = ixgbe_ptp_read_82599;
@@ -1291,6 +1278,50 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter)
 }
 
 /**
+ * ixgbe_ptp_init_systime - Initialize SYSTIME registers
+ * @adapter: the ixgbe private board structure
+ *
+ * Initialize and start the SYSTIME registers.
+ */
+static void ixgbe_ptp_init_systime(struct ixgbe_adapter *adapter)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 tsauxc;
+
+	switch (hw->mac.type) {
+	case ixgbe_mac_X550EM_x:
+	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_X550:
+		tsauxc = IXGBE_READ_REG(hw, IXGBE_TSAUXC);
+
+		/* Reset SYSTIME registers to 0 */
+		IXGBE_WRITE_REG(hw, IXGBE_SYSTIMR, 0);
+		IXGBE_WRITE_REG(hw, IXGBE_SYSTIML, 0);
+		IXGBE_WRITE_REG(hw, IXGBE_SYSTIMH, 0);
+
+		/* Reset interrupt settings */
+		IXGBE_WRITE_REG(hw, IXGBE_TSIM, IXGBE_TSIM_TXTS);
+		IXGBE_WRITE_REG(hw, IXGBE_EIMS, IXGBE_EIMS_TIMESYNC);
+
+		/* Activate the SYSTIME counter */
+		IXGBE_WRITE_REG(hw, IXGBE_TSAUXC,
+				tsauxc & ~IXGBE_TSAUXC_DISABLE_SYSTIME);
+		break;
+	case ixgbe_mac_X540:
+	case ixgbe_mac_82599EB:
+		/* Reset SYSTIME registers to 0 */
+		IXGBE_WRITE_REG(hw, IXGBE_SYSTIML, 0);
+		IXGBE_WRITE_REG(hw, IXGBE_SYSTIMH, 0);
+		break;
+	default:
+		/* Other devices aren't supported */
+		return;
+	};
+
+	IXGBE_WRITE_FLUSH(hw);
+}
+
+/**
  * ixgbe_ptp_reset
  * @adapter: the ixgbe private board structure
  *
@@ -1316,6 +1347,8 @@ void ixgbe_ptp_reset(struct ixgbe_adapter *adapter)
 
 	ixgbe_ptp_start_cyclecounter(adapter);
 
+	ixgbe_ptp_init_systime(adapter);
+
 	spin_lock_irqsave(&adapter->tmreg_lock, flags);
 	timecounter_init(&adapter->hw_tc, &adapter->hw_cc,
 			 ktime_to_ns(ktime_get_real()));
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
index aaebdae8b5ff..0078ae592616 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
@@ -204,10 +204,13 @@ void ixgbe_enable_sriov(struct ixgbe_adapter *adapter, unsigned int max_vfs)
 int ixgbe_disable_sriov(struct ixgbe_adapter *adapter)
 {
 	unsigned int num_vfs = adapter->num_vfs, vf;
+	unsigned long flags;
 	int rss;
 
+	spin_lock_irqsave(&adapter->vfs_lock, flags);
 	/* set num VFs to 0 to prevent access to vfinfo */
 	adapter->num_vfs = 0;
+	spin_unlock_irqrestore(&adapter->vfs_lock, flags);
 
 	/* put the reference to all of the vf devices */
 	for (vf = 0; vf < num_vfs; ++vf) {
@@ -1305,8 +1308,10 @@ static void ixgbe_rcv_ack_from_vf(struct ixgbe_adapter *adapter, u32 vf)
 void ixgbe_msg_task(struct ixgbe_adapter *adapter)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
+	unsigned long flags;
 	u32 vf;
 
+	spin_lock_irqsave(&adapter->vfs_lock, flags);
 	for (vf = 0; vf < adapter->num_vfs; vf++) {
 		/* process any reset requests */
 		if (!ixgbe_check_for_rst(hw, vf))
@@ -1320,6 +1325,7 @@ void ixgbe_msg_task(struct ixgbe_adapter *adapter)
 		if (!ixgbe_check_for_ack(hw, vf))
 			ixgbe_rcv_ack_from_vf(adapter, vf);
 	}
+	spin_unlock_irqrestore(&adapter->vfs_lock, flags);
 }
 
 void ixgbe_disable_tx_rx(struct ixgbe_adapter *adapter)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index 11ef46e72ddd..bd33b90aaa67 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -2504,6 +2504,12 @@ static void __rvu_flr_handler(struct rvu *rvu, u16 pcifunc)
 	rvu_blklf_teardown(rvu, pcifunc, BLKADDR_NPA);
 	rvu_reset_lmt_map_tbl(rvu, pcifunc);
 	rvu_detach_rsrcs(rvu, NULL, pcifunc);
+	/* In scenarios where PF/VF drivers detach NIXLF without freeing MCAM
+	 * entries, check and free the MCAM entries explicitly to avoid leak.
+	 * Since LF is detached use LF number as -1.
+	 */
+	rvu_npc_free_mcam_entries(rvu, pcifunc, -1);
+
 	mutex_unlock(&rvu->flr_lock);
 }
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index c4a46b295d40..d1249da7a18f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -1096,6 +1096,9 @@ static void npc_enadis_default_entries(struct rvu *rvu, u16 pcifunc,
 
 void rvu_npc_disable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf)
 {
+	if (nixlf < 0)
+		return;
+
 	npc_enadis_default_entries(rvu, pcifunc, nixlf, false);
 
 	/* Delete multicast and promisc MCAM entries */
@@ -1107,6 +1110,9 @@ void rvu_npc_disable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf)
 
 void rvu_npc_enable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf)
 {
+	if (nixlf < 0)
+		return;
+
 	/* Enables only broadcast match entry. Promisc/Allmulti are enabled
 	 * in set_rx_mode mbox handler.
 	 */
@@ -1650,7 +1656,7 @@ static void npc_load_kpu_profile(struct rvu *rvu)
 	 * Firmware database method.
 	 * Default KPU profile.
 	 */
-	if (!request_firmware(&fw, kpu_profile, rvu->dev)) {
+	if (!request_firmware_direct(&fw, kpu_profile, rvu->dev)) {
 		dev_info(rvu->dev, "Loading KPU profile from firmware: %s\n",
 			 kpu_profile);
 		rvu->kpu_fwdata = kzalloc(fw->size, GFP_KERNEL);
@@ -1915,6 +1921,7 @@ static void rvu_npc_hw_init(struct rvu *rvu, int blkaddr)
 
 static void rvu_npc_setup_interfaces(struct rvu *rvu, int blkaddr)
 {
+	struct npc_mcam_kex *mkex = rvu->kpu.mkex;
 	struct npc_mcam *mcam = &rvu->hw->mcam;
 	struct rvu_hwinfo *hw = rvu->hw;
 	u64 nibble_ena, rx_kex, tx_kex;
@@ -1927,15 +1934,15 @@ static void rvu_npc_setup_interfaces(struct rvu *rvu, int blkaddr)
 	mcam->counters.max--;
 	mcam->rx_miss_act_cntr = mcam->counters.max;
 
-	rx_kex = npc_mkex_default.keyx_cfg[NIX_INTF_RX];
-	tx_kex = npc_mkex_default.keyx_cfg[NIX_INTF_TX];
+	rx_kex = mkex->keyx_cfg[NIX_INTF_RX];
+	tx_kex = mkex->keyx_cfg[NIX_INTF_TX];
 	nibble_ena = FIELD_GET(NPC_PARSE_NIBBLE, rx_kex);
 
 	nibble_ena = rvu_npc_get_tx_nibble_cfg(rvu, nibble_ena);
 	if (nibble_ena) {
 		tx_kex &= ~NPC_PARSE_NIBBLE;
 		tx_kex |= FIELD_PREP(NPC_PARSE_NIBBLE, nibble_ena);
-		npc_mkex_default.keyx_cfg[NIX_INTF_TX] = tx_kex;
+		mkex->keyx_cfg[NIX_INTF_TX] = tx_kex;
 	}
 
 	/* Configure RX interfaces */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
index ca404d51d9f5..750aaa167687 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
@@ -445,7 +445,8 @@ do {									       \
 	NPC_SCAN_HDR(NPC_VLAN_TAG1, NPC_LID_LB, NPC_LT_LB_CTAG, 2, 2);
 	NPC_SCAN_HDR(NPC_VLAN_TAG2, NPC_LID_LB, NPC_LT_LB_STAG_QINQ, 2, 2);
 	NPC_SCAN_HDR(NPC_DMAC, NPC_LID_LA, la_ltype, la_start, 6);
-	NPC_SCAN_HDR(NPC_SMAC, NPC_LID_LA, la_ltype, la_start, 6);
+	/* SMAC follows the DMAC(which is 6 bytes) */
+	NPC_SCAN_HDR(NPC_SMAC, NPC_LID_LA, la_ltype, la_start + 6, 6);
 	/* PF_FUNC is 2 bytes at 0th byte of NPC_LT_LA_IH_NIX_ETHER */
 	NPC_SCAN_HDR(NPC_PF_FUNC, NPC_LID_LA, NPC_LT_LA_IH_NIX_ETHER, 0, 2);
 }
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 78df173e6df2..7cf24dd5c878 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -631,6 +631,12 @@ int otx2_txschq_config(struct otx2_nic *pfvf, int lvl)
 		req->num_regs++;
 		req->reg[1] = NIX_AF_TL3X_SCHEDULE(schq);
 		req->regval[1] = dwrr_val;
+		if (lvl == hw->txschq_link_cfg_lvl) {
+			req->num_regs++;
+			req->reg[2] = NIX_AF_TL3_TL2X_LINKX_CFG(schq, hw->tx_link);
+			/* Enable this queue and backpressure */
+			req->regval[2] = BIT_ULL(13) | BIT_ULL(12);
+		}
 	} else if (lvl == NIX_TXSCH_LVL_TL2) {
 		parent =  hw->txschq_list[NIX_TXSCH_LVL_TL1][0];
 		req->reg[0] = NIX_AF_TL2X_PARENT(schq);
@@ -640,11 +646,12 @@ int otx2_txschq_config(struct otx2_nic *pfvf, int lvl)
 		req->reg[1] = NIX_AF_TL2X_SCHEDULE(schq);
 		req->regval[1] = TXSCH_TL1_DFLT_RR_PRIO << 24 | dwrr_val;
 
-		req->num_regs++;
-		req->reg[2] = NIX_AF_TL3_TL2X_LINKX_CFG(schq, hw->tx_link);
-		/* Enable this queue and backpressure */
-		req->regval[2] = BIT_ULL(13) | BIT_ULL(12);
-
+		if (lvl == hw->txschq_link_cfg_lvl) {
+			req->num_regs++;
+			req->reg[2] = NIX_AF_TL3_TL2X_LINKX_CFG(schq, hw->tx_link);
+			/* Enable this queue and backpressure */
+			req->regval[2] = BIT_ULL(13) | BIT_ULL(12);
+		}
 	} else if (lvl == NIX_TXSCH_LVL_TL1) {
 		/* Default config for TL1.
 		 * For VF this is always ignored.
@@ -1563,6 +1570,8 @@ void mbox_handler_nix_txsch_alloc(struct otx2_nic *pf,
 		for (schq = 0; schq < rsp->schq[lvl]; schq++)
 			pf->hw.txschq_list[lvl][schq] =
 				rsp->schq_list[lvl][schq];
+
+	pf->hw.txschq_link_cfg_lvl = rsp->link_cfg_lvl;
 }
 EXPORT_SYMBOL(mbox_handler_nix_txsch_alloc);
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index 637450de189c..4ecd0ef05f3b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -182,6 +182,7 @@ struct otx2_hw {
 	u16			sqb_size;
 
 	/* NIX */
+	u8			txschq_link_cfg_lvl;
 	u16		txschq_list[NIX_TXSCH_LVL_CNT][MAX_TXSCHQ_PER_FUNC];
 	u16			matchall_ipolicer;
 	u32			dwrr_mtu;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
index 8c90be81677d..59fbb5b78f2c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
@@ -28,6 +28,9 @@
 #define MAX_RATE_EXPONENT		0x0FULL
 #define MAX_RATE_MANTISSA		0xFFULL
 
+#define CN10K_MAX_BURST_MANTISSA	0x7FFFULL
+#define CN10K_MAX_BURST_SIZE		8453888ULL
+
 /* Bitfields in NIX_TLX_PIR register */
 #define TLX_RATE_MANTISSA		GENMASK_ULL(8, 1)
 #define TLX_RATE_EXPONENT		GENMASK_ULL(12, 9)
@@ -35,6 +38,9 @@
 #define TLX_BURST_MANTISSA		GENMASK_ULL(36, 29)
 #define TLX_BURST_EXPONENT		GENMASK_ULL(40, 37)
 
+#define CN10K_TLX_BURST_MANTISSA	GENMASK_ULL(43, 29)
+#define CN10K_TLX_BURST_EXPONENT	GENMASK_ULL(47, 44)
+
 struct otx2_tc_flow_stats {
 	u64 bytes;
 	u64 pkts;
@@ -77,33 +83,42 @@ int otx2_tc_alloc_ent_bitmap(struct otx2_nic *nic)
 }
 EXPORT_SYMBOL(otx2_tc_alloc_ent_bitmap);
 
-static void otx2_get_egress_burst_cfg(u32 burst, u32 *burst_exp,
-				      u32 *burst_mantissa)
+static void otx2_get_egress_burst_cfg(struct otx2_nic *nic, u32 burst,
+				      u32 *burst_exp, u32 *burst_mantissa)
 {
+	int max_burst, max_mantissa;
 	unsigned int tmp;
 
+	if (is_dev_otx2(nic->pdev)) {
+		max_burst = MAX_BURST_SIZE;
+		max_mantissa = MAX_BURST_MANTISSA;
+	} else {
+		max_burst = CN10K_MAX_BURST_SIZE;
+		max_mantissa = CN10K_MAX_BURST_MANTISSA;
+	}
+
 	/* Burst is calculated as
 	 * ((256 + BURST_MANTISSA) << (1 + BURST_EXPONENT)) / 256
 	 * Max supported burst size is 130,816 bytes.
 	 */
-	burst = min_t(u32, burst, MAX_BURST_SIZE);
+	burst = min_t(u32, burst, max_burst);
 	if (burst) {
 		*burst_exp = ilog2(burst) ? ilog2(burst) - 1 : 0;
 		tmp = burst - rounddown_pow_of_two(burst);
-		if (burst < MAX_BURST_MANTISSA)
+		if (burst < max_mantissa)
 			*burst_mantissa = tmp * 2;
 		else
 			*burst_mantissa = tmp / (1ULL << (*burst_exp - 7));
 	} else {
 		*burst_exp = MAX_BURST_EXPONENT;
-		*burst_mantissa = MAX_BURST_MANTISSA;
+		*burst_mantissa = max_mantissa;
 	}
 }
 
-static void otx2_get_egress_rate_cfg(u32 maxrate, u32 *exp,
+static void otx2_get_egress_rate_cfg(u64 maxrate, u32 *exp,
 				     u32 *mantissa, u32 *div_exp)
 {
-	unsigned int tmp;
+	u64 tmp;
 
 	/* Rate calculation by hardware
 	 *
@@ -132,21 +147,44 @@ static void otx2_get_egress_rate_cfg(u32 maxrate, u32 *exp,
 	}
 }
 
-static int otx2_set_matchall_egress_rate(struct otx2_nic *nic, u32 burst, u32 maxrate)
+static u64 otx2_get_txschq_rate_regval(struct otx2_nic *nic,
+				       u64 maxrate, u32 burst)
 {
-	struct otx2_hw *hw = &nic->hw;
-	struct nix_txschq_config *req;
 	u32 burst_exp, burst_mantissa;
 	u32 exp, mantissa, div_exp;
+	u64 regval = 0;
+
+	/* Get exponent and mantissa values from the desired rate */
+	otx2_get_egress_burst_cfg(nic, burst, &burst_exp, &burst_mantissa);
+	otx2_get_egress_rate_cfg(maxrate, &exp, &mantissa, &div_exp);
+
+	if (is_dev_otx2(nic->pdev)) {
+		regval = FIELD_PREP(TLX_BURST_EXPONENT, (u64)burst_exp) |
+				FIELD_PREP(TLX_BURST_MANTISSA, (u64)burst_mantissa) |
+				FIELD_PREP(TLX_RATE_DIVIDER_EXPONENT, div_exp) |
+				FIELD_PREP(TLX_RATE_EXPONENT, exp) |
+				FIELD_PREP(TLX_RATE_MANTISSA, mantissa) | BIT_ULL(0);
+	} else {
+		regval = FIELD_PREP(CN10K_TLX_BURST_EXPONENT, (u64)burst_exp) |
+				FIELD_PREP(CN10K_TLX_BURST_MANTISSA, (u64)burst_mantissa) |
+				FIELD_PREP(TLX_RATE_DIVIDER_EXPONENT, div_exp) |
+				FIELD_PREP(TLX_RATE_EXPONENT, exp) |
+				FIELD_PREP(TLX_RATE_MANTISSA, mantissa) | BIT_ULL(0);
+	}
+
+	return regval;
+}
+
+static int otx2_set_matchall_egress_rate(struct otx2_nic *nic,
+					 u32 burst, u64 maxrate)
+{
+	struct otx2_hw *hw = &nic->hw;
+	struct nix_txschq_config *req;
 	int txschq, err;
 
 	/* All SQs share the same TL4, so pick the first scheduler */
 	txschq = hw->txschq_list[NIX_TXSCH_LVL_TL4][0];
 
-	/* Get exponent and mantissa values from the desired rate */
-	otx2_get_egress_burst_cfg(burst, &burst_exp, &burst_mantissa);
-	otx2_get_egress_rate_cfg(maxrate, &exp, &mantissa, &div_exp);
-
 	mutex_lock(&nic->mbox.lock);
 	req = otx2_mbox_alloc_msg_nix_txschq_cfg(&nic->mbox);
 	if (!req) {
@@ -157,11 +195,7 @@ static int otx2_set_matchall_egress_rate(struct otx2_nic *nic, u32 burst, u32 ma
 	req->lvl = NIX_TXSCH_LVL_TL4;
 	req->num_regs = 1;
 	req->reg[0] = NIX_AF_TL4X_PIR(txschq);
-	req->regval[0] = FIELD_PREP(TLX_BURST_EXPONENT, burst_exp) |
-			 FIELD_PREP(TLX_BURST_MANTISSA, burst_mantissa) |
-			 FIELD_PREP(TLX_RATE_DIVIDER_EXPONENT, div_exp) |
-			 FIELD_PREP(TLX_RATE_EXPONENT, exp) |
-			 FIELD_PREP(TLX_RATE_MANTISSA, mantissa) | BIT_ULL(0);
+	req->regval[0] = otx2_get_txschq_rate_regval(nic, maxrate, burst);
 
 	err = otx2_sync_mbox_msg(&nic->mbox);
 	mutex_unlock(&nic->mbox.lock);
@@ -230,7 +264,7 @@ static int otx2_tc_egress_matchall_install(struct otx2_nic *nic,
 	struct netlink_ext_ack *extack = cls->common.extack;
 	struct flow_action *actions = &cls->rule->action;
 	struct flow_action_entry *entry;
-	u32 rate;
+	u64 rate;
 	int err;
 
 	err = otx2_tc_validate_flow(nic, actions, extack);
@@ -256,7 +290,7 @@ static int otx2_tc_egress_matchall_install(struct otx2_nic *nic,
 		}
 		/* Convert bytes per second to Mbps */
 		rate = entry->police.rate_bytes_ps * 8;
-		rate = max_t(u32, rate / 1000000, 1);
+		rate = max_t(u64, rate / 1000000, 1);
 		err = otx2_set_matchall_egress_rate(nic, entry->police.burst, rate);
 		if (err)
 			return err;
@@ -614,21 +648,27 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node,
 
 		flow_spec->dport = match.key->dst;
 		flow_mask->dport = match.mask->dst;
-		if (ip_proto == IPPROTO_UDP)
-			req->features |= BIT_ULL(NPC_DPORT_UDP);
-		else if (ip_proto == IPPROTO_TCP)
-			req->features |= BIT_ULL(NPC_DPORT_TCP);
-		else if (ip_proto == IPPROTO_SCTP)
-			req->features |= BIT_ULL(NPC_DPORT_SCTP);
+
+		if (flow_mask->dport) {
+			if (ip_proto == IPPROTO_UDP)
+				req->features |= BIT_ULL(NPC_DPORT_UDP);
+			else if (ip_proto == IPPROTO_TCP)
+				req->features |= BIT_ULL(NPC_DPORT_TCP);
+			else if (ip_proto == IPPROTO_SCTP)
+				req->features |= BIT_ULL(NPC_DPORT_SCTP);
+		}
 
 		flow_spec->sport = match.key->src;
 		flow_mask->sport = match.mask->src;
-		if (ip_proto == IPPROTO_UDP)
-			req->features |= BIT_ULL(NPC_SPORT_UDP);
-		else if (ip_proto == IPPROTO_TCP)
-			req->features |= BIT_ULL(NPC_SPORT_TCP);
-		else if (ip_proto == IPPROTO_SCTP)
-			req->features |= BIT_ULL(NPC_SPORT_SCTP);
+
+		if (flow_mask->sport) {
+			if (ip_proto == IPPROTO_UDP)
+				req->features |= BIT_ULL(NPC_SPORT_UDP);
+			else if (ip_proto == IPPROTO_TCP)
+				req->features |= BIT_ULL(NPC_SPORT_TCP);
+			else if (ip_proto == IPPROTO_SCTP)
+				req->features |= BIT_ULL(NPC_SPORT_SCTP);
+		}
 	}
 
 	return otx2_tc_parse_actions(nic, &rule->action, req, f, node);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 7204bc86e474..c22a38e5337b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -103,7 +103,7 @@ struct page_pool;
 #define MLX5E_REQUIRED_WQE_MTTS		(MLX5_ALIGN_MTTS(MLX5_MPWRQ_PAGES_PER_WQE + 1))
 #define MLX5E_REQUIRED_MTTS(wqes)	(wqes * MLX5E_REQUIRED_WQE_MTTS)
 #define MLX5E_MAX_RQ_NUM_MTTS	\
-	((1 << 16) * 2) /* So that MLX5_MTT_OCTW(num_mtts) fits into u16 */
+	(ALIGN_DOWN(U16_MAX, 4) * 2) /* So that MLX5_MTT_OCTW(num_mtts) fits into u16 */
 #define MLX5E_ORDER2_MAX_PACKET_MTU (order_base_2(10 * 1024))
 #define MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE_MPW	\
 		(ilog2(MLX5E_MAX_RQ_NUM_MTTS / MLX5E_REQUIRED_WQE_MTTS))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index cf03297c8471..d90c6dc41c9f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -497,7 +497,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 	int err;
 
 	attr.ttl = tun_key->ttl;
-	attr.fl.fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tun_key->tos), tun_key->label);
+	attr.fl.fl6.flowlabel = ip6_make_flowinfo(tun_key->tos, tun_key->label);
 	attr.fl.fl6.daddr = tun_key->u.ipv6.dst;
 	attr.fl.fl6.saddr = tun_key->u.ipv6.src;
 
@@ -611,7 +611,7 @@ int mlx5e_tc_tun_update_header_ipv6(struct mlx5e_priv *priv,
 
 	attr.ttl = tun_key->ttl;
 
-	attr.fl.fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tun_key->tos), tun_key->label);
+	attr.fl.fl6.flowlabel = ip6_make_flowinfo(tun_key->tos, tun_key->label);
 	attr.fl.fl6.daddr = tun_key->u.ipv6.dst;
 	attr.fl.fl6.saddr = tun_key->u.ipv6.src;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c
index d93aadbf10da..90ea78239d40 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c
@@ -16,7 +16,7 @@ static int mlx5e_ktls_add(struct net_device *netdev, struct sock *sk,
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int err;
 
-	if (WARN_ON(!mlx5e_ktls_type_check(mdev, crypto_info)))
+	if (!mlx5e_ktls_type_check(mdev, crypto_info))
 		return -EOPNOTSUPP;
 
 	if (direction == TLS_OFFLOAD_CTX_DIR_TX)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
index 15711814d2d2..d92b97c56f4c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
@@ -231,8 +231,7 @@ mlx5e_set_ktls_rx_priv_ctx(struct tls_context *tls_ctx,
 	struct mlx5e_ktls_offload_context_rx **ctx =
 		__tls_driver_ctx(tls_ctx, TLS_OFFLOAD_CTX_DIR_RX);
 
-	BUILD_BUG_ON(sizeof(struct mlx5e_ktls_offload_context_rx *) >
-		     TLS_OFFLOAD_CONTEXT_SIZE_RX);
+	BUILD_BUG_ON(sizeof(priv_rx) > TLS_DRIVER_STATE_SIZE_RX);
 
 	*ctx = priv_rx;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index 9ad3459fb63a..dadb71081ed0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -68,8 +68,7 @@ mlx5e_set_ktls_tx_priv_ctx(struct tls_context *tls_ctx,
 	struct mlx5e_ktls_offload_context_tx **ctx =
 		__tls_driver_ctx(tls_ctx, TLS_OFFLOAD_CTX_DIR_TX);
 
-	BUILD_BUG_ON(sizeof(struct mlx5e_ktls_offload_context_tx *) >
-		     TLS_OFFLOAD_CONTEXT_SIZE_TX);
+	BUILD_BUG_ON(sizeof(priv_tx) > TLS_DRIVER_STATE_SIZE_TX);
 
 	*ctx = priv_tx;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index e00648094fc2..c1c4f380803a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3325,7 +3325,9 @@ static int set_feature_hw_tc(struct net_device *netdev, bool enable)
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
 #if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
-	if (!enable && mlx5e_tc_num_filters(priv, MLX5_TC_FLAG(NIC_OFFLOAD))) {
+	int tc_flag = mlx5e_is_uplink_rep(priv) ? MLX5_TC_FLAG(ESW_OFFLOAD) :
+						  MLX5_TC_FLAG(NIC_OFFLOAD);
+	if (!enable && mlx5e_tc_num_filters(priv, tc_flag)) {
 		netdev_err(netdev,
 			   "Active offloaded tc filters, can't turn hw_tc_offload off\n");
 		return -EINVAL;
@@ -4350,14 +4352,6 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16
 	/* RQ */
 	mlx5e_build_rq_params(mdev, params);
 
-	/* HW LRO */
-	if (MLX5_CAP_ETH(mdev, lro_cap) &&
-	    params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
-		/* No XSK params: checking the availability of striding RQ in general. */
-		if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL))
-			params->packet_merge.type = slow_pci_heuristic(mdev) ?
-				MLX5E_PACKET_MERGE_NONE : MLX5E_PACKET_MERGE_LRO;
-	}
 	params->packet_merge.timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT);
 
 	/* CQ moderation params */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 161b60e1139b..3d614bf5cff9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -618,6 +618,8 @@ static void mlx5e_build_rep_params(struct net_device *netdev)
 
 	params->mqprio.num_tc       = 1;
 	params->tunneled_offload_en = false;
+	if (rep->vport != MLX5_VPORT_UPLINK)
+		params->vlan_strip_disable = true;
 
 	/* Set an initial non-zero value, so that mlx5e_select_queue won't
 	 * divide by zero if called before first activating channels.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index e1dd17019030..5a5c6eda29d2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -614,7 +614,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(vnic_env)
 	u32 in[MLX5_ST_SZ_DW(query_vnic_env_in)] = {};
 	struct mlx5_core_dev *mdev = priv->mdev;
 
-	if (!MLX5_CAP_GEN(priv->mdev, nic_receive_steering_discard))
+	if (!mlx5e_stats_grp_vnic_env_num_stats(priv))
 		return;
 
 	MLX5_SET(query_vnic_env_in, in, opcode, MLX5_CMD_OP_QUERY_VNIC_ENV);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 015eaef9667e..489348060286 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -3291,37 +3291,68 @@ out_ok:
 	return true;
 }
 
-static bool actions_match_supported(struct mlx5e_priv *priv,
-				    struct flow_action *flow_action,
-				    struct mlx5e_tc_flow_parse_attr *parse_attr,
-				    struct mlx5e_tc_flow *flow,
-				    struct netlink_ext_ack *extack)
+static bool
+actions_match_supported_fdb(struct mlx5e_priv *priv,
+			    struct mlx5e_tc_flow_parse_attr *parse_attr,
+			    struct mlx5e_tc_flow *flow,
+			    struct netlink_ext_ack *extack)
 {
-	bool ct_flow = false, ct_clear = false;
-	u32 actions;
+	bool ct_flow, ct_clear;
 
-	ct_clear = flow->attr->ct_attr.ct_action &
-		TCA_CT_ACT_CLEAR;
+	ct_clear = flow->attr->ct_attr.ct_action & TCA_CT_ACT_CLEAR;
 	ct_flow = flow_flag_test(flow, CT) && !ct_clear;
-	actions = flow->attr->action;
 
-	if (mlx5e_is_eswitch_flow(flow)) {
-		if (flow->attr->esw_attr->split_count && ct_flow &&
-		    !MLX5_CAP_GEN(flow->attr->esw_attr->in_mdev, reg_c_preserve)) {
-			/* All registers used by ct are cleared when using
-			 * split rules.
-			 */
-			NL_SET_ERR_MSG_MOD(extack,
-					   "Can't offload mirroring with action ct");
-			return false;
-		}
+	if (flow->attr->esw_attr->split_count && ct_flow &&
+	    !MLX5_CAP_GEN(flow->attr->esw_attr->in_mdev, reg_c_preserve)) {
+		/* All registers used by ct are cleared when using
+		 * split rules.
+		 */
+		NL_SET_ERR_MSG_MOD(extack, "Can't offload mirroring with action ct");
+		return false;
+	}
+
+	return true;
+}
+
+static bool
+actions_match_supported(struct mlx5e_priv *priv,
+			struct flow_action *flow_action,
+			struct mlx5e_tc_flow_parse_attr *parse_attr,
+			struct mlx5e_tc_flow *flow,
+			struct netlink_ext_ack *extack)
+{
+	u32 actions = flow->attr->action;
+	bool ct_flow, ct_clear;
+
+	ct_clear = flow->attr->ct_attr.ct_action & TCA_CT_ACT_CLEAR;
+	ct_flow = flow_flag_test(flow, CT) && !ct_clear;
+
+	if (!(actions &
+	      (MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_DROP))) {
+		NL_SET_ERR_MSG_MOD(extack, "Rule must have at least one forward/drop action");
+		return false;
+	}
+
+	if (!(~actions &
+	      (MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_DROP))) {
+		NL_SET_ERR_MSG_MOD(extack, "Rule cannot support forward+drop action");
+		return false;
 	}
 
-	if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
-		return modify_header_match_supported(priv, &parse_attr->spec,
-						     flow_action, actions,
-						     ct_flow, ct_clear,
-						     extack);
+	if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR &&
+	    actions & MLX5_FLOW_CONTEXT_ACTION_DROP) {
+		NL_SET_ERR_MSG_MOD(extack, "Drop with modify header action is not supported");
+		return false;
+	}
+
+	if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR &&
+	    !modify_header_match_supported(priv, &parse_attr->spec, flow_action,
+					   actions, ct_flow, ct_clear, extack))
+		return false;
+
+	if (mlx5e_is_eswitch_flow(flow) &&
+	    !actions_match_supported_fdb(priv, parse_attr, flow, extack))
+		return false;
 
 	return true;
 }
@@ -4207,13 +4238,6 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 		attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 	}
 
-	if (!(attr->action &
-	      (MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_DROP))) {
-		NL_SET_ERR_MSG_MOD(extack,
-				   "Rule must have at least one forward/drop action");
-		return -EOPNOTSUPP;
-	}
-
 	if (esw_attr->split_count > 0 && !mlx5_esw_has_fwd_fdb(priv->mdev)) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "current firmware doesn't support split rule for port mirroring");
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 7fd33b356cc8..1544d4c2c636 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -429,6 +429,26 @@ static void mlx5e_tx_check_stop(struct mlx5e_txqsq *sq)
 	}
 }
 
+static void mlx5e_tx_flush(struct mlx5e_txqsq *sq)
+{
+	struct mlx5e_tx_wqe_info *wi;
+	struct mlx5e_tx_wqe *wqe;
+	u16 pi;
+
+	/* Must not be called when a MPWQE session is active but empty. */
+	mlx5e_tx_mpwqe_ensure_complete(sq);
+
+	pi = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->pc);
+	wi = &sq->db.wqe_info[pi];
+
+	*wi = (struct mlx5e_tx_wqe_info) {
+		.num_wqebbs = 1,
+	};
+
+	wqe = mlx5e_post_nop(&sq->wq, sq->sqn, &sq->pc);
+	mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &wqe->ctrl);
+}
+
 static inline void
 mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		     const struct mlx5e_tx_attr *attr,
@@ -521,6 +541,7 @@ mlx5e_sq_xmit_wqe(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 err_drop:
 	stats->dropped++;
 	dev_kfree_skb_any(skb);
+	mlx5e_tx_flush(sq);
 }
 
 static bool mlx5e_tx_skb_supports_mpwqe(struct sk_buff *skb, struct mlx5e_tx_attr *attr)
@@ -622,6 +643,13 @@ mlx5e_sq_xmit_mpwqe(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	struct mlx5_wqe_ctrl_seg *cseg;
 	struct mlx5e_xmit_data txd;
 
+	txd.data = skb->data;
+	txd.len = skb->len;
+
+	txd.dma_addr = dma_map_single(sq->pdev, txd.data, txd.len, DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(sq->pdev, txd.dma_addr)))
+		goto err_unmap;
+
 	if (!mlx5e_tx_mpwqe_session_is_active(sq)) {
 		mlx5e_tx_mpwqe_session_start(sq, eseg);
 	} else if (!mlx5e_tx_mpwqe_same_eseg(sq, eseg)) {
@@ -631,18 +659,9 @@ mlx5e_sq_xmit_mpwqe(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 
 	sq->stats->xmit_more += xmit_more;
 
-	txd.data = skb->data;
-	txd.len = skb->len;
-
-	txd.dma_addr = dma_map_single(sq->pdev, txd.data, txd.len, DMA_TO_DEVICE);
-	if (unlikely(dma_mapping_error(sq->pdev, txd.dma_addr)))
-		goto err_unmap;
 	mlx5e_dma_push(sq, txd.dma_addr, txd.len, MLX5E_DMA_MAP_SINGLE);
-
 	mlx5e_skb_fifo_push(&sq->db.skb_fifo, skb);
-
 	mlx5e_tx_mpwqe_add_dseg(sq, &txd);
-
 	mlx5e_tx_skb_update_hwts_flags(skb);
 
 	if (unlikely(mlx5e_tx_mpwqe_is_full(&sq->mpwqe))) {
@@ -664,6 +683,7 @@ err_unmap:
 	mlx5e_dma_unmap_wqe_err(sq, 1);
 	sq->stats->dropped++;
 	dev_kfree_skb_any(skb);
+	mlx5e_tx_flush(sq);
 }
 
 void mlx5e_tx_mpwqe_ensure_complete(struct mlx5e_txqsq *sq)
@@ -1033,5 +1053,6 @@ void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 err_drop:
 	stats->dropped++;
 	dev_kfree_skb_any(skb);
+	mlx5e_tx_flush(sq);
 }
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
index 0c4c743ca31e..3a2575dc5355 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
@@ -11,6 +11,7 @@
 #include "mlx5_core.h"
 #include "eswitch.h"
 #include "fs_core.h"
+#include "fs_ft_pool.h"
 #include "esw/qos.h"
 
 enum {
@@ -95,8 +96,7 @@ static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw)
 	if (!flow_group_in)
 		return -ENOMEM;
 
-	table_size = BIT(MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size));
-	ft_attr.max_fte = table_size;
+	ft_attr.max_fte = POOL_NEXT_SIZE;
 	ft_attr.prio = LEGACY_FDB_PRIO;
 	fdb = mlx5_create_flow_table(root_ns, &ft_attr);
 	if (IS_ERR(fdb)) {
@@ -105,6 +105,7 @@ static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw)
 		goto out;
 	}
 	esw->fdb_table.legacy.fdb = fdb;
+	table_size = fdb->max_fte;
 
 	/* Addresses group : Full match unicast/multicast addresses */
 	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 4ed740994279..740065e21181 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -516,7 +516,7 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
 
 	/* Check log_max_qp from HCA caps to set in current profile */
 	if (prof->log_max_qp == LOG_MAX_SUPPORTED_QPS) {
-		prof->log_max_qp = min_t(u8, 17, MLX5_CAP_GEN_MAX(dev, log_max_qp));
+		prof->log_max_qp = min_t(u8, 18, MLX5_CAP_GEN_MAX(dev, log_max_qp));
 	} else if (MLX5_CAP_GEN_MAX(dev, log_max_qp) < prof->log_max_qp) {
 		mlx5_core_warn(dev, "log_max_qp value in current profile is %d, changing it to HCA capability limit (%d)\n",
 			       prof->log_max_qp,
@@ -1427,7 +1427,9 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 	memcpy(&dev->profile, &profile[profile_idx], sizeof(dev->profile));
 	INIT_LIST_HEAD(&priv->ctx_list);
 	spin_lock_init(&priv->ctx_lock);
+	lockdep_register_key(&dev->lock_key);
 	mutex_init(&dev->intf_state_mutex);
+	lockdep_set_class(&dev->intf_state_mutex, &dev->lock_key);
 
 	mutex_init(&priv->bfregs.reg_head.lock);
 	mutex_init(&priv->bfregs.wc_head.lock);
@@ -1474,6 +1476,7 @@ err_health_init:
 	mutex_destroy(&priv->bfregs.wc_head.lock);
 	mutex_destroy(&priv->bfregs.reg_head.lock);
 	mutex_destroy(&dev->intf_state_mutex);
+	lockdep_unregister_key(&dev->lock_key);
 	return err;
 }
 
@@ -1491,6 +1494,7 @@ void mlx5_mdev_uninit(struct mlx5_core_dev *dev)
 	mutex_destroy(&priv->bfregs.wc_head.lock);
 	mutex_destroy(&priv->bfregs.reg_head.lock);
 	mutex_destroy(&dev->intf_state_mutex);
+	lockdep_unregister_key(&dev->lock_key);
 }
 
 static int probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h
index e3509e69ed1c..3e8725b7f0b7 100644
--- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h
+++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h
@@ -80,6 +80,7 @@ struct mlxbf_gige {
 	struct net_device *netdev;
 	struct platform_device *pdev;
 	void __iomem *mdio_io;
+	void __iomem *clk_io;
 	struct mii_bus *mdiobus;
 	void __iomem *gpio_io;
 	struct irq_domain *irqdomain;
@@ -149,7 +150,8 @@ enum mlxbf_gige_res {
 	MLXBF_GIGE_RES_MDIO9,
 	MLXBF_GIGE_RES_GPIO0,
 	MLXBF_GIGE_RES_LLU,
-	MLXBF_GIGE_RES_PLU
+	MLXBF_GIGE_RES_PLU,
+	MLXBF_GIGE_RES_CLK
 };
 
 /* Version of register data returned by mlxbf_gige_get_regs() */
diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c
index 7905179a9575..f979ba7e5eff 100644
--- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c
+++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c
@@ -22,10 +22,23 @@
 #include <linux/property.h>
 
 #include "mlxbf_gige.h"
+#include "mlxbf_gige_regs.h"
 
 #define MLXBF_GIGE_MDIO_GW_OFFSET	0x0
 #define MLXBF_GIGE_MDIO_CFG_OFFSET	0x4
 
+#define MLXBF_GIGE_MDIO_FREQ_REFERENCE 156250000ULL
+#define MLXBF_GIGE_MDIO_COREPLL_CONST  16384ULL
+#define MLXBF_GIGE_MDC_CLK_NS          400
+#define MLXBF_GIGE_MDIO_PLL_I1CLK_REG1 0x4
+#define MLXBF_GIGE_MDIO_PLL_I1CLK_REG2 0x8
+#define MLXBF_GIGE_MDIO_CORE_F_SHIFT   0
+#define MLXBF_GIGE_MDIO_CORE_F_MASK    GENMASK(25, 0)
+#define MLXBF_GIGE_MDIO_CORE_R_SHIFT   26
+#define MLXBF_GIGE_MDIO_CORE_R_MASK    GENMASK(31, 26)
+#define MLXBF_GIGE_MDIO_CORE_OD_SHIFT  0
+#define MLXBF_GIGE_MDIO_CORE_OD_MASK   GENMASK(3, 0)
+
 /* Support clause 22 */
 #define MLXBF_GIGE_MDIO_CL22_ST1	0x1
 #define MLXBF_GIGE_MDIO_CL22_WRITE	0x1
@@ -50,27 +63,76 @@
 #define MLXBF_GIGE_MDIO_CFG_MDIO_IN_SAMP_MASK		GENMASK(23, 16)
 #define MLXBF_GIGE_MDIO_CFG_MDIO_OUT_SAMP_MASK		GENMASK(31, 24)
 
+#define MLXBF_GIGE_MDIO_CFG_VAL (FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDIO_MODE_MASK, 1) | \
+				 FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDIO3_3_MASK, 1) | \
+				 FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDIO_FULL_DRIVE_MASK, 1) | \
+				 FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDIO_IN_SAMP_MASK, 6) | \
+				 FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDIO_OUT_SAMP_MASK, 13))
+
+#define MLXBF_GIGE_BF2_COREPLL_ADDR 0x02800c30
+#define MLXBF_GIGE_BF2_COREPLL_SIZE 0x0000000c
+
+static struct resource corepll_params[] = {
+	[MLXBF_GIGE_VERSION_BF2] = {
+		.start = MLXBF_GIGE_BF2_COREPLL_ADDR,
+		.end = MLXBF_GIGE_BF2_COREPLL_ADDR + MLXBF_GIGE_BF2_COREPLL_SIZE - 1,
+		.name = "COREPLL_RES"
+	},
+};
+
+/* Returns core clock i1clk in Hz */
+static u64 calculate_i1clk(struct mlxbf_gige *priv)
+{
+	u8 core_od, core_r;
+	u64 freq_output;
+	u32 reg1, reg2;
+	u32 core_f;
+
+	reg1 = readl(priv->clk_io + MLXBF_GIGE_MDIO_PLL_I1CLK_REG1);
+	reg2 = readl(priv->clk_io + MLXBF_GIGE_MDIO_PLL_I1CLK_REG2);
+
+	core_f = (reg1 & MLXBF_GIGE_MDIO_CORE_F_MASK) >>
+		MLXBF_GIGE_MDIO_CORE_F_SHIFT;
+	core_r = (reg1 & MLXBF_GIGE_MDIO_CORE_R_MASK) >>
+		MLXBF_GIGE_MDIO_CORE_R_SHIFT;
+	core_od = (reg2 & MLXBF_GIGE_MDIO_CORE_OD_MASK) >>
+		MLXBF_GIGE_MDIO_CORE_OD_SHIFT;
+
+	/* Compute PLL output frequency as follow:
+	 *
+	 *                                     CORE_F / 16384
+	 * freq_output = freq_reference * ----------------------------
+	 *                              (CORE_R + 1) * (CORE_OD + 1)
+	 */
+	freq_output = div_u64((MLXBF_GIGE_MDIO_FREQ_REFERENCE * core_f),
+			      MLXBF_GIGE_MDIO_COREPLL_CONST);
+	freq_output = div_u64(freq_output, (core_r + 1) * (core_od + 1));
+
+	return freq_output;
+}
+
 /* Formula for encoding the MDIO period. The encoded value is
  * passed to the MDIO config register.
  *
- * mdc_clk = 2*(val + 1)*i1clk
+ * mdc_clk = 2*(val + 1)*(core clock in sec)
  *
- * 400 ns = 2*(val + 1)*(((1/430)*1000) ns)
+ * i1clk is in Hz:
+ * 400 ns = 2*(val + 1)*(1/i1clk)
  *
- * val = (((400 * 430 / 1000) / 2) - 1)
+ * val = (((400/10^9) / (1/i1clk) / 2) - 1)
+ * val = (400/2 * i1clk)/10^9 - 1
  */
-#define MLXBF_GIGE_I1CLK_MHZ		430
-#define MLXBF_GIGE_MDC_CLK_NS		400
+static u8 mdio_period_map(struct mlxbf_gige *priv)
+{
+	u8 mdio_period;
+	u64 i1clk;
 
-#define MLXBF_GIGE_MDIO_PERIOD	(((MLXBF_GIGE_MDC_CLK_NS * MLXBF_GIGE_I1CLK_MHZ / 1000) / 2) - 1)
+	i1clk = calculate_i1clk(priv);
 
-#define MLXBF_GIGE_MDIO_CFG_VAL (FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDIO_MODE_MASK, 1) | \
-				 FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDIO3_3_MASK, 1) | \
-				 FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDIO_FULL_DRIVE_MASK, 1) | \
-				 FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDC_PERIOD_MASK, \
-					    MLXBF_GIGE_MDIO_PERIOD) | \
-				 FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDIO_IN_SAMP_MASK, 6) | \
-				 FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDIO_OUT_SAMP_MASK, 13))
+	mdio_period = div_u64((MLXBF_GIGE_MDC_CLK_NS >> 1) * i1clk, 1000000000) - 1;
+
+	return mdio_period;
+}
 
 static u32 mlxbf_gige_mdio_create_cmd(u16 data, int phy_add,
 				      int phy_reg, u32 opcode)
@@ -123,9 +185,9 @@ static int mlxbf_gige_mdio_write(struct mii_bus *bus, int phy_add,
 				 int phy_reg, u16 val)
 {
 	struct mlxbf_gige *priv = bus->priv;
+	u32 temp;
 	u32 cmd;
 	int ret;
-	u32 temp;
 
 	if (phy_reg & MII_ADDR_C45)
 		return -EOPNOTSUPP;
@@ -142,18 +204,44 @@ static int mlxbf_gige_mdio_write(struct mii_bus *bus, int phy_add,
 	return ret;
 }
 
+static void mlxbf_gige_mdio_cfg(struct mlxbf_gige *priv)
+{
+	u8 mdio_period;
+	u32 val;
+
+	mdio_period = mdio_period_map(priv);
+
+	val = MLXBF_GIGE_MDIO_CFG_VAL;
+	val |= FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDC_PERIOD_MASK, mdio_period);
+	writel(val, priv->mdio_io + MLXBF_GIGE_MDIO_CFG_OFFSET);
+}
+
 int mlxbf_gige_mdio_probe(struct platform_device *pdev, struct mlxbf_gige *priv)
 {
 	struct device *dev = &pdev->dev;
+	struct resource *res;
 	int ret;
 
 	priv->mdio_io = devm_platform_ioremap_resource(pdev, MLXBF_GIGE_RES_MDIO9);
 	if (IS_ERR(priv->mdio_io))
 		return PTR_ERR(priv->mdio_io);
 
-	/* Configure mdio parameters */
-	writel(MLXBF_GIGE_MDIO_CFG_VAL,
-	       priv->mdio_io + MLXBF_GIGE_MDIO_CFG_OFFSET);
+	/* clk resource shared with other drivers so cannot use
+	 * devm_platform_ioremap_resource
+	 */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, MLXBF_GIGE_RES_CLK);
+	if (!res) {
+		/* For backward compatibility with older ACPI tables, also keep
+		 * CLK resource internal to the driver.
+		 */
+		res = &corepll_params[MLXBF_GIGE_VERSION_BF2];
+	}
+
+	priv->clk_io = devm_ioremap(dev, res->start, resource_size(res));
+	if (IS_ERR(priv->clk_io))
+		return PTR_ERR(priv->clk_io);
+
+	mlxbf_gige_mdio_cfg(priv);
 
 	priv->mdiobus = devm_mdiobus_alloc(dev);
 	if (!priv->mdiobus) {
diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h
index 5fb33c9294bf..7be3a793984d 100644
--- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h
+++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h
@@ -8,6 +8,8 @@
 #ifndef __MLXBF_GIGE_REGS_H__
 #define __MLXBF_GIGE_REGS_H__
 
+#define MLXBF_GIGE_VERSION                            0x0000
+#define MLXBF_GIGE_VERSION_BF2                        0x0
 #define MLXBF_GIGE_STATUS                             0x0010
 #define MLXBF_GIGE_STATUS_READY                       BIT(0)
 #define MLXBF_GIGE_INT_STATUS                         0x0028
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index edfdd44de579..35908a8c640a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1730,9 +1730,9 @@ static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port)
 
 	cancel_delayed_work_sync(&mlxsw_sp_port->periodic_hw_stats.update_dw);
 	cancel_delayed_work_sync(&mlxsw_sp_port->ptp.shaper_dw);
-	mlxsw_sp_port_ptp_clear(mlxsw_sp_port);
 	mlxsw_core_port_clear(mlxsw_sp->core, local_port, mlxsw_sp);
 	unregister_netdev(mlxsw_sp_port->dev); /* This calls ndo_stop */
+	mlxsw_sp_port_ptp_clear(mlxsw_sp_port);
 	mlxsw_sp_port_vlan_classification_set(mlxsw_sp_port, true, true);
 	mlxsw_sp->ports[local_port] = NULL;
 	mlxsw_sp_port_vlan_flush(mlxsw_sp_port, true);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 19bb3ca0515e..55de90d5ae59 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -4293,6 +4293,8 @@ static int mlxsw_sp_nexthop4_init(struct mlxsw_sp *mlxsw_sp,
 	return 0;
 
 err_nexthop_neigh_init:
+	list_del(&nh->router_list_node);
+	mlxsw_sp_nexthop_counter_free(mlxsw_sp, nh);
 	mlxsw_sp_nexthop_remove(mlxsw_sp, nh);
 	return err;
 }
@@ -5194,7 +5196,7 @@ static bool mlxsw_sp_fi_is_gateway(const struct mlxsw_sp *mlxsw_sp,
 {
 	const struct fib_nh *nh = fib_info_nh(fi, 0);
 
-	return nh->fib_nh_scope == RT_SCOPE_LINK ||
+	return nh->fib_nh_gw_family ||
 	       mlxsw_sp_nexthop4_ipip_type(mlxsw_sp, nh, NULL);
 }
 
@@ -6578,6 +6580,7 @@ static int mlxsw_sp_nexthop6_init(struct mlxsw_sp *mlxsw_sp,
 				  const struct fib6_info *rt)
 {
 	struct net_device *dev = rt->fib6_nh->fib_nh_dev;
+	int err;
 
 	nh->nhgi = nh_grp->nhgi;
 	nh->nh_weight = rt->fib6_nh->fib_nh_weight;
@@ -6593,7 +6596,16 @@ static int mlxsw_sp_nexthop6_init(struct mlxsw_sp *mlxsw_sp,
 		return 0;
 	nh->ifindex = dev->ifindex;
 
-	return mlxsw_sp_nexthop_type_init(mlxsw_sp, nh, dev);
+	err = mlxsw_sp_nexthop_type_init(mlxsw_sp, nh, dev);
+	if (err)
+		goto err_nexthop_type_init;
+
+	return 0;
+
+err_nexthop_type_init:
+	list_del(&nh->router_list_node);
+	mlxsw_sp_nexthop_counter_free(mlxsw_sp, nh);
+	return err;
 }
 
 static void mlxsw_sp_nexthop6_fini(struct mlxsw_sp *mlxsw_sp,
@@ -9576,7 +9588,7 @@ static void mlxsw_sp_mp4_hash_init(struct mlxsw_sp *mlxsw_sp,
 	unsigned long *fields = config->fields;
 	u32 hash_fields;
 
-	switch (net->ipv4.sysctl_fib_multipath_hash_policy) {
+	switch (READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_policy)) {
 	case 0:
 		mlxsw_sp_mp4_hash_outer_addr(config);
 		break;
@@ -9594,7 +9606,7 @@ static void mlxsw_sp_mp4_hash_init(struct mlxsw_sp *mlxsw_sp,
 		mlxsw_sp_mp_hash_inner_l3(config);
 		break;
 	case 3:
-		hash_fields = net->ipv4.sysctl_fib_multipath_hash_fields;
+		hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields);
 		/* Outer */
 		MLXSW_SP_MP_HASH_HEADER_SET(headers, IPV4_EN_NOT_TCP_NOT_UDP);
 		MLXSW_SP_MP_HASH_HEADER_SET(headers, IPV4_EN_TCP_UDP);
@@ -9775,13 +9787,14 @@ static int mlxsw_sp_dscp_init(struct mlxsw_sp *mlxsw_sp)
 static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
 {
 	struct net *net = mlxsw_sp_net(mlxsw_sp);
-	bool usp = net->ipv4.sysctl_ip_fwd_update_priority;
 	char rgcr_pl[MLXSW_REG_RGCR_LEN];
 	u64 max_rifs;
+	bool usp;
 
 	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_RIFS))
 		return -EIO;
 	max_rifs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS);
+	usp = READ_ONCE(net->ipv4.sysctl_ip_fwd_update_priority);
 
 	mlxsw_reg_rgcr_pack(rgcr_pl, true, true);
 	mlxsw_reg_rgcr_max_router_interfaces_set(rgcr_pl, max_rifs);
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c
index 148d431fcde4..c460168131c2 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c
@@ -107,6 +107,8 @@ static void sparx5_xtr_grp(struct sparx5 *sparx5, u8 grp, bool byte_swap)
 			/* This assumes STATUS_WORD_POS == 1, Status
 			 * just after last data
 			 */
+			if (!byte_swap)
+				val = ntohl((__force __be32)val);
 			byte_cnt -= (4 - XTR_VALID_BYTES(val));
 			eof_flag = true;
 			break;
diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c
index 49def6934cad..fa4c596e6ec6 100644
--- a/drivers/net/ethernet/moxa/moxart_ether.c
+++ b/drivers/net/ethernet/moxa/moxart_ether.c
@@ -74,11 +74,6 @@ static int moxart_set_mac_address(struct net_device *ndev, void *addr)
 static void moxart_mac_free_memory(struct net_device *ndev)
 {
 	struct moxart_mac_priv_t *priv = netdev_priv(ndev);
-	int i;
-
-	for (i = 0; i < RX_DESC_NUM; i++)
-		dma_unmap_single(&ndev->dev, priv->rx_mapping[i],
-				 priv->rx_buf_size, DMA_FROM_DEVICE);
 
 	if (priv->tx_desc_base)
 		dma_free_coherent(&priv->pdev->dev,
@@ -147,11 +142,11 @@ static void moxart_mac_setup_desc_ring(struct net_device *ndev)
 		       desc + RX_REG_OFFSET_DESC1);
 
 		priv->rx_buf[i] = priv->rx_buf_base + priv->rx_buf_size * i;
-		priv->rx_mapping[i] = dma_map_single(&ndev->dev,
+		priv->rx_mapping[i] = dma_map_single(&priv->pdev->dev,
 						     priv->rx_buf[i],
 						     priv->rx_buf_size,
 						     DMA_FROM_DEVICE);
-		if (dma_mapping_error(&ndev->dev, priv->rx_mapping[i]))
+		if (dma_mapping_error(&priv->pdev->dev, priv->rx_mapping[i]))
 			netdev_err(ndev, "DMA mapping error\n");
 
 		moxart_desc_write(priv->rx_mapping[i],
@@ -193,6 +188,7 @@ static int moxart_mac_open(struct net_device *ndev)
 static int moxart_mac_stop(struct net_device *ndev)
 {
 	struct moxart_mac_priv_t *priv = netdev_priv(ndev);
+	int i;
 
 	napi_disable(&priv->napi);
 
@@ -204,6 +200,11 @@ static int moxart_mac_stop(struct net_device *ndev)
 	/* disable all functions */
 	writel(0, priv->base + REG_MAC_CTRL);
 
+	/* unmap areas mapped in moxart_mac_setup_desc_ring() */
+	for (i = 0; i < RX_DESC_NUM; i++)
+		dma_unmap_single(&priv->pdev->dev, priv->rx_mapping[i],
+				 priv->rx_buf_size, DMA_FROM_DEVICE);
+
 	return 0;
 }
 
@@ -240,7 +241,7 @@ static int moxart_rx_poll(struct napi_struct *napi, int budget)
 		if (len > RX_BUF_SIZE)
 			len = RX_BUF_SIZE;
 
-		dma_sync_single_for_cpu(&ndev->dev,
+		dma_sync_single_for_cpu(&priv->pdev->dev,
 					priv->rx_mapping[rx_head],
 					priv->rx_buf_size, DMA_FROM_DEVICE);
 		skb = netdev_alloc_skb_ip_align(ndev, len);
@@ -294,7 +295,7 @@ static void moxart_tx_finished(struct net_device *ndev)
 	unsigned int tx_tail = priv->tx_tail;
 
 	while (tx_tail != tx_head) {
-		dma_unmap_single(&ndev->dev, priv->tx_mapping[tx_tail],
+		dma_unmap_single(&priv->pdev->dev, priv->tx_mapping[tx_tail],
 				 priv->tx_len[tx_tail], DMA_TO_DEVICE);
 
 		ndev->stats.tx_packets++;
@@ -358,9 +359,9 @@ static netdev_tx_t moxart_mac_start_xmit(struct sk_buff *skb,
 
 	len = skb->len > TX_BUF_SIZE ? TX_BUF_SIZE : skb->len;
 
-	priv->tx_mapping[tx_head] = dma_map_single(&ndev->dev, skb->data,
+	priv->tx_mapping[tx_head] = dma_map_single(&priv->pdev->dev, skb->data,
 						   len, DMA_TO_DEVICE);
-	if (dma_mapping_error(&ndev->dev, priv->tx_mapping[tx_head])) {
+	if (dma_mapping_error(&priv->pdev->dev, priv->tx_mapping[tx_head])) {
 		netdev_err(ndev, "DMA mapping error\n");
 		goto out_unlock;
 	}
@@ -379,7 +380,7 @@ static netdev_tx_t moxart_mac_start_xmit(struct sk_buff *skb,
 		len = ETH_ZLEN;
 	}
 
-	dma_sync_single_for_device(&ndev->dev, priv->tx_mapping[tx_head],
+	dma_sync_single_for_device(&priv->pdev->dev, priv->tx_mapping[tx_head],
 				   priv->tx_buf_size, DMA_TO_DEVICE);
 
 	txdes1 = TX_DESC1_LTS | TX_DESC1_FTS | (len & TX_DESC1_BUF_SIZE_MASK);
@@ -493,7 +494,7 @@ static int moxart_mac_probe(struct platform_device *pdev)
 	priv->tx_buf_size = TX_BUF_SIZE;
 	priv->rx_buf_size = RX_BUF_SIZE;
 
-	priv->tx_desc_base = dma_alloc_coherent(&pdev->dev, TX_REG_DESC_SIZE *
+	priv->tx_desc_base = dma_alloc_coherent(p_dev, TX_REG_DESC_SIZE *
 						TX_DESC_NUM, &priv->tx_base,
 						GFP_DMA | GFP_KERNEL);
 	if (!priv->tx_desc_base) {
@@ -501,7 +502,7 @@ static int moxart_mac_probe(struct platform_device *pdev)
 		goto init_fail;
 	}
 
-	priv->rx_desc_base = dma_alloc_coherent(&pdev->dev, RX_REG_DESC_SIZE *
+	priv->rx_desc_base = dma_alloc_coherent(p_dev, RX_REG_DESC_SIZE *
 						RX_DESC_NUM, &priv->rx_base,
 						GFP_DMA | GFP_KERNEL);
 	if (!priv->rx_desc_base) {
diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index 2a432de11858..df5a6a0bf1d5 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -472,7 +472,7 @@ nfp_fl_set_tun(struct nfp_app *app, struct nfp_fl_set_tun *set_tun,
 			set_tun->ttl = ip4_dst_hoplimit(&rt->dst);
 			ip_rt_put(rt);
 		} else {
-			set_tun->ttl = net->ipv4.sysctl_ip_default_ttl;
+			set_tun->ttl = READ_ONCE(net->ipv4.sysctl_ip_default_ttl);
 		}
 	}
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 850bfdf83d0a..69ac205bbdbd 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -3482,21 +3482,21 @@ static void nfp_net_stat64(struct net_device *netdev,
 		unsigned int start;
 
 		do {
-			start = u64_stats_fetch_begin(&r_vec->rx_sync);
+			start = u64_stats_fetch_begin_irq(&r_vec->rx_sync);
 			data[0] = r_vec->rx_pkts;
 			data[1] = r_vec->rx_bytes;
 			data[2] = r_vec->rx_drops;
-		} while (u64_stats_fetch_retry(&r_vec->rx_sync, start));
+		} while (u64_stats_fetch_retry_irq(&r_vec->rx_sync, start));
 		stats->rx_packets += data[0];
 		stats->rx_bytes += data[1];
 		stats->rx_dropped += data[2];
 
 		do {
-			start = u64_stats_fetch_begin(&r_vec->tx_sync);
+			start = u64_stats_fetch_begin_irq(&r_vec->tx_sync);
 			data[0] = r_vec->tx_pkts;
 			data[1] = r_vec->tx_bytes;
 			data[2] = r_vec->tx_errors;
-		} while (u64_stats_fetch_retry(&r_vec->tx_sync, start));
+		} while (u64_stats_fetch_retry_irq(&r_vec->tx_sync, start));
 		stats->tx_packets += data[0];
 		stats->tx_bytes += data[1];
 		stats->tx_errors += data[2];
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
index 8b614b0201e7..62546d197bfd 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
@@ -483,7 +483,7 @@ static u64 *nfp_vnic_get_sw_stats(struct net_device *netdev, u64 *data)
 		unsigned int start;
 
 		do {
-			start = u64_stats_fetch_begin(&nn->r_vecs[i].rx_sync);
+			start = u64_stats_fetch_begin_irq(&nn->r_vecs[i].rx_sync);
 			data[0] = nn->r_vecs[i].rx_pkts;
 			tmp[0] = nn->r_vecs[i].hw_csum_rx_ok;
 			tmp[1] = nn->r_vecs[i].hw_csum_rx_inner_ok;
@@ -491,10 +491,10 @@ static u64 *nfp_vnic_get_sw_stats(struct net_device *netdev, u64 *data)
 			tmp[3] = nn->r_vecs[i].hw_csum_rx_error;
 			tmp[4] = nn->r_vecs[i].rx_replace_buf_alloc_fail;
 			tmp[5] = nn->r_vecs[i].hw_tls_rx;
-		} while (u64_stats_fetch_retry(&nn->r_vecs[i].rx_sync, start));
+		} while (u64_stats_fetch_retry_irq(&nn->r_vecs[i].rx_sync, start));
 
 		do {
-			start = u64_stats_fetch_begin(&nn->r_vecs[i].tx_sync);
+			start = u64_stats_fetch_begin_irq(&nn->r_vecs[i].tx_sync);
 			data[1] = nn->r_vecs[i].tx_pkts;
 			data[2] = nn->r_vecs[i].tx_busy;
 			tmp[6] = nn->r_vecs[i].hw_csum_tx;
@@ -504,7 +504,7 @@ static u64 *nfp_vnic_get_sw_stats(struct net_device *netdev, u64 *data)
 			tmp[10] = nn->r_vecs[i].hw_tls_tx;
 			tmp[11] = nn->r_vecs[i].tls_tx_fallback;
 			tmp[12] = nn->r_vecs[i].tls_tx_no_fallback;
-		} while (u64_stats_fetch_retry(&nn->r_vecs[i].tx_sync, start));
+		} while (u64_stats_fetch_retry_irq(&nn->r_vecs[i].tx_sync, start));
 
 		data += NN_RVEC_PER_Q_STATS;
 
@@ -1219,6 +1219,8 @@ nfp_port_get_module_info(struct net_device *netdev,
 	u8 data;
 
 	port = nfp_port_from_netdev(netdev);
+	/* update port state to get latest interface */
+	set_bit(NFP_PORT_CHANGED, &port->flags);
 	eth_port = nfp_port_get_eth_port(port);
 	if (!eth_port)
 		return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 6ac507ddf09a..c713a3ee6571 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -1565,7 +1565,7 @@ static int ionic_set_nic_features(struct ionic_lif *lif,
 	if ((old_hw_features ^ lif->hw_features) & IONIC_ETH_HW_RX_HASH)
 		ionic_lif_rss_config(lif, lif->rss_types, NULL, NULL);
 
-	if ((vlan_flags & features) &&
+	if ((vlan_flags & le64_to_cpu(ctx.cmd.lif_setattr.features)) &&
 	    !(vlan_flags & le64_to_cpu(ctx.comp.lif_setattr.features)))
 		dev_info_once(lif->ionic->dev, "NIC is not supporting vlan offload, likely in SmartNIC mode\n");
 
@@ -1692,8 +1692,67 @@ static int ionic_set_features(struct net_device *netdev,
 	return err;
 }
 
+static int ionic_set_attr_mac(struct ionic_lif *lif, u8 *mac)
+{
+	struct ionic_admin_ctx ctx = {
+		.work = COMPLETION_INITIALIZER_ONSTACK(ctx.work),
+		.cmd.lif_setattr = {
+			.opcode = IONIC_CMD_LIF_SETATTR,
+			.index = cpu_to_le16(lif->index),
+			.attr = IONIC_LIF_ATTR_MAC,
+		},
+	};
+
+	ether_addr_copy(ctx.cmd.lif_setattr.mac, mac);
+	return ionic_adminq_post_wait(lif, &ctx);
+}
+
+static int ionic_get_attr_mac(struct ionic_lif *lif, u8 *mac_addr)
+{
+	struct ionic_admin_ctx ctx = {
+		.work = COMPLETION_INITIALIZER_ONSTACK(ctx.work),
+		.cmd.lif_getattr = {
+			.opcode = IONIC_CMD_LIF_GETATTR,
+			.index = cpu_to_le16(lif->index),
+			.attr = IONIC_LIF_ATTR_MAC,
+		},
+	};
+	int err;
+
+	err = ionic_adminq_post_wait(lif, &ctx);
+	if (err)
+		return err;
+
+	ether_addr_copy(mac_addr, ctx.comp.lif_getattr.mac);
+	return 0;
+}
+
+static int ionic_program_mac(struct ionic_lif *lif, u8 *mac)
+{
+	u8  get_mac[ETH_ALEN];
+	int err;
+
+	err = ionic_set_attr_mac(lif, mac);
+	if (err)
+		return err;
+
+	err = ionic_get_attr_mac(lif, get_mac);
+	if (err)
+		return err;
+
+	/* To deal with older firmware that silently ignores the set attr mac:
+	 * doesn't actually change the mac and doesn't return an error, so we
+	 * do the get attr to verify whether or not the set actually happened
+	 */
+	if (!ether_addr_equal(get_mac, mac))
+		return 1;
+
+	return 0;
+}
+
 static int ionic_set_mac_address(struct net_device *netdev, void *sa)
 {
+	struct ionic_lif *lif = netdev_priv(netdev);
 	struct sockaddr *addr = sa;
 	u8 *mac;
 	int err;
@@ -1702,6 +1761,14 @@ static int ionic_set_mac_address(struct net_device *netdev, void *sa)
 	if (ether_addr_equal(netdev->dev_addr, mac))
 		return 0;
 
+	err = ionic_program_mac(lif, mac);
+	if (err < 0)
+		return err;
+
+	if (err > 0)
+		netdev_dbg(netdev, "%s: SET and GET ATTR Mac are not equal-due to old FW running\n",
+			   __func__);
+
 	err = eth_prepare_mac_addr_change(netdev, addr);
 	if (err)
 		return err;
@@ -2974,11 +3041,10 @@ static void ionic_lif_handle_fw_down(struct ionic_lif *lif)
 
 	netif_device_detach(lif->netdev);
 
+	mutex_lock(&lif->queue_lock);
 	if (test_bit(IONIC_LIF_F_UP, lif->state)) {
 		dev_info(ionic->dev, "Surprise FW stop, stopping queues\n");
-		mutex_lock(&lif->queue_lock);
 		ionic_stop_queues(lif);
-		mutex_unlock(&lif->queue_lock);
 	}
 
 	if (netif_running(lif->netdev)) {
@@ -2989,6 +3055,8 @@ static void ionic_lif_handle_fw_down(struct ionic_lif *lif)
 	ionic_reset(ionic);
 	ionic_qcqs_free(lif);
 
+	mutex_unlock(&lif->queue_lock);
+
 	dev_info(ionic->dev, "FW Down: LIFs stopped\n");
 }
 
@@ -3012,9 +3080,15 @@ static void ionic_lif_handle_fw_up(struct ionic_lif *lif)
 	err = ionic_port_init(ionic);
 	if (err)
 		goto err_out;
+
+	mutex_lock(&lif->queue_lock);
+
+	if (test_and_clear_bit(IONIC_LIF_F_BROKEN, lif->state))
+		dev_info(ionic->dev, "FW Up: clearing broken state\n");
+
 	err = ionic_qcqs_alloc(lif);
 	if (err)
-		goto err_out;
+		goto err_unlock;
 
 	err = ionic_lif_init(lif);
 	if (err)
@@ -3035,6 +3109,8 @@ static void ionic_lif_handle_fw_up(struct ionic_lif *lif)
 			goto err_txrx_free;
 	}
 
+	mutex_unlock(&lif->queue_lock);
+
 	clear_bit(IONIC_LIF_F_FW_RESET, lif->state);
 	ionic_link_status_check_request(lif, CAN_SLEEP);
 	netif_device_attach(lif->netdev);
@@ -3051,6 +3127,8 @@ err_lifs_deinit:
 	ionic_lif_deinit(lif);
 err_qcqs_free:
 	ionic_qcqs_free(lif);
+err_unlock:
+	mutex_unlock(&lif->queue_lock);
 err_out:
 	dev_err(ionic->dev, "FW Up: LIFs restart failed - err %d\n", err);
 }
@@ -3215,6 +3293,7 @@ static int ionic_station_set(struct ionic_lif *lif)
 			.attr = IONIC_LIF_ATTR_MAC,
 		},
 	};
+	u8 mac_address[ETH_ALEN];
 	struct sockaddr addr;
 	int err;
 
@@ -3223,8 +3302,23 @@ static int ionic_station_set(struct ionic_lif *lif)
 		return err;
 	netdev_dbg(lif->netdev, "found initial MAC addr %pM\n",
 		   ctx.comp.lif_getattr.mac);
-	if (is_zero_ether_addr(ctx.comp.lif_getattr.mac))
-		return 0;
+	ether_addr_copy(mac_address, ctx.comp.lif_getattr.mac);
+
+	if (is_zero_ether_addr(mac_address)) {
+		eth_hw_addr_random(netdev);
+		netdev_dbg(netdev, "Random Mac generated: %pM\n", netdev->dev_addr);
+		ether_addr_copy(mac_address, netdev->dev_addr);
+
+		err = ionic_program_mac(lif, mac_address);
+		if (err < 0)
+			return err;
+
+		if (err > 0) {
+			netdev_dbg(netdev, "%s:SET/GET ATTR Mac are not same-due to old FW running\n",
+				   __func__);
+			return 0;
+		}
+	}
 
 	if (!is_zero_ether_addr(netdev->dev_addr)) {
 		/* If the netdev mac is non-zero and doesn't match the default
@@ -3232,12 +3326,11 @@ static int ionic_station_set(struct ionic_lif *lif)
 		 * likely here again after a fw-upgrade reset.  We need to be
 		 * sure the netdev mac is in our filter list.
 		 */
-		if (!ether_addr_equal(ctx.comp.lif_getattr.mac,
-				      netdev->dev_addr))
+		if (!ether_addr_equal(mac_address, netdev->dev_addr))
 			ionic_lif_addr_add(lif, netdev->dev_addr);
 	} else {
 		/* Update the netdev mac with the device's mac */
-		memcpy(addr.sa_data, ctx.comp.lif_getattr.mac, netdev->addr_len);
+		ether_addr_copy(addr.sa_data, mac_address);
 		addr.sa_family = AF_INET;
 		err = eth_prepare_mac_addr_change(netdev, &addr);
 		if (err) {
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c
index 480f85bc17f9..9ede66842118 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_main.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c
@@ -395,8 +395,8 @@ try_again:
 				ionic_opcode_to_str(opcode), opcode,
 				ionic_error_to_str(err), err);
 
-			msleep(1000);
 			iowrite32(0, &idev->dev_cmd_regs->done);
+			msleep(1000);
 			iowrite32(1, &idev->dev_cmd_regs->doorbell);
 			goto try_again;
 		}
@@ -409,6 +409,8 @@ try_again:
 		return ionic_error_to_errno(err);
 	}
 
+	ionic_dev_cmd_clean(ionic);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c
index dfaf10edfabf..ba8c7a31cce1 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c
@@ -2763,25 +2763,6 @@ static int qed_configure_filter_mcast(struct qed_dev *cdev,
 	return qed_filter_mcast_cmd(cdev, &mcast, QED_SPQ_MODE_CB, NULL);
 }
 
-static int qed_configure_filter(struct qed_dev *cdev,
-				struct qed_filter_params *params)
-{
-	enum qed_filter_rx_mode_type accept_flags;
-
-	switch (params->type) {
-	case QED_FILTER_TYPE_UCAST:
-		return qed_configure_filter_ucast(cdev, &params->filter.ucast);
-	case QED_FILTER_TYPE_MCAST:
-		return qed_configure_filter_mcast(cdev, &params->filter.mcast);
-	case QED_FILTER_TYPE_RX_MODE:
-		accept_flags = params->filter.accept_flags;
-		return qed_configure_filter_rx_mode(cdev, accept_flags);
-	default:
-		DP_NOTICE(cdev, "Unknown filter type %d\n", (int)params->type);
-		return -EINVAL;
-	}
-}
-
 static int qed_configure_arfs_searcher(struct qed_dev *cdev,
 				       enum qed_filter_config_mode mode)
 {
@@ -2904,7 +2885,9 @@ static const struct qed_eth_ops qed_eth_ops_pass = {
 	.q_rx_stop = &qed_stop_rxq,
 	.q_tx_start = &qed_start_txq,
 	.q_tx_stop = &qed_stop_txq,
-	.filter_config = &qed_configure_filter,
+	.filter_config_rx_mode = &qed_configure_filter_rx_mode,
+	.filter_config_ucast = &qed_configure_filter_ucast,
+	.filter_config_mcast = &qed_configure_filter_mcast,
 	.fastpath_stop = &qed_fastpath_stop,
 	.eth_cqe_completion = &qed_fp_cqe_completion,
 	.get_vport_stats = &qed_get_vport_stats,
diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c
index a2e4dfb5cb44..f99b085b56a5 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_filter.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c
@@ -619,30 +619,28 @@ static int qede_set_ucast_rx_mac(struct qede_dev *edev,
 				 enum qed_filter_xcast_params_type opcode,
 				 unsigned char mac[ETH_ALEN])
 {
-	struct qed_filter_params filter_cmd;
+	struct qed_filter_ucast_params ucast;
 
-	memset(&filter_cmd, 0, sizeof(filter_cmd));
-	filter_cmd.type = QED_FILTER_TYPE_UCAST;
-	filter_cmd.filter.ucast.type = opcode;
-	filter_cmd.filter.ucast.mac_valid = 1;
-	ether_addr_copy(filter_cmd.filter.ucast.mac, mac);
+	memset(&ucast, 0, sizeof(ucast));
+	ucast.type = opcode;
+	ucast.mac_valid = 1;
+	ether_addr_copy(ucast.mac, mac);
 
-	return edev->ops->filter_config(edev->cdev, &filter_cmd);
+	return edev->ops->filter_config_ucast(edev->cdev, &ucast);
 }
 
 static int qede_set_ucast_rx_vlan(struct qede_dev *edev,
 				  enum qed_filter_xcast_params_type opcode,
 				  u16 vid)
 {
-	struct qed_filter_params filter_cmd;
+	struct qed_filter_ucast_params ucast;
 
-	memset(&filter_cmd, 0, sizeof(filter_cmd));
-	filter_cmd.type = QED_FILTER_TYPE_UCAST;
-	filter_cmd.filter.ucast.type = opcode;
-	filter_cmd.filter.ucast.vlan_valid = 1;
-	filter_cmd.filter.ucast.vlan = vid;
+	memset(&ucast, 0, sizeof(ucast));
+	ucast.type = opcode;
+	ucast.vlan_valid = 1;
+	ucast.vlan = vid;
 
-	return edev->ops->filter_config(edev->cdev, &filter_cmd);
+	return edev->ops->filter_config_ucast(edev->cdev, &ucast);
 }
 
 static int qede_config_accept_any_vlan(struct qede_dev *edev, bool action)
@@ -1057,18 +1055,17 @@ static int qede_set_mcast_rx_mac(struct qede_dev *edev,
 				 enum qed_filter_xcast_params_type opcode,
 				 unsigned char *mac, int num_macs)
 {
-	struct qed_filter_params filter_cmd;
+	struct qed_filter_mcast_params mcast;
 	int i;
 
-	memset(&filter_cmd, 0, sizeof(filter_cmd));
-	filter_cmd.type = QED_FILTER_TYPE_MCAST;
-	filter_cmd.filter.mcast.type = opcode;
-	filter_cmd.filter.mcast.num = num_macs;
+	memset(&mcast, 0, sizeof(mcast));
+	mcast.type = opcode;
+	mcast.num = num_macs;
 
 	for (i = 0; i < num_macs; i++, mac += ETH_ALEN)
-		ether_addr_copy(filter_cmd.filter.mcast.mac[i], mac);
+		ether_addr_copy(mcast.mac[i], mac);
 
-	return edev->ops->filter_config(edev->cdev, &filter_cmd);
+	return edev->ops->filter_config_mcast(edev->cdev, &mcast);
 }
 
 int qede_set_mac_addr(struct net_device *ndev, void *p)
@@ -1194,7 +1191,6 @@ void qede_config_rx_mode(struct net_device *ndev)
 {
 	enum qed_filter_rx_mode_type accept_flags;
 	struct qede_dev *edev = netdev_priv(ndev);
-	struct qed_filter_params rx_mode;
 	unsigned char *uc_macs, *temp;
 	struct netdev_hw_addr *ha;
 	int rc, uc_count;
@@ -1220,10 +1216,6 @@ void qede_config_rx_mode(struct net_device *ndev)
 
 	netif_addr_unlock_bh(ndev);
 
-	/* Configure the struct for the Rx mode */
-	memset(&rx_mode, 0, sizeof(struct qed_filter_params));
-	rx_mode.type = QED_FILTER_TYPE_RX_MODE;
-
 	/* Remove all previous unicast secondary macs and multicast macs
 	 * (configure / leave the primary mac)
 	 */
@@ -1271,8 +1263,7 @@ void qede_config_rx_mode(struct net_device *ndev)
 		qede_config_accept_any_vlan(edev, false);
 	}
 
-	rx_mode.filter.accept_flags = accept_flags;
-	edev->ops->filter_config(edev->cdev, &rx_mode);
+	edev->ops->filter_config_rx_mode(edev->cdev, accept_flags);
 out:
 	kfree(uc_macs);
 }
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 2918947dd57c..2af4c76bcf02 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -4177,7 +4177,6 @@ static void rtl8169_tso_csum_v1(struct sk_buff *skb, u32 *opts)
 static bool rtl8169_tso_csum_v2(struct rtl8169_private *tp,
 				struct sk_buff *skb, u32 *opts)
 {
-	u32 transport_offset = (u32)skb_transport_offset(skb);
 	struct skb_shared_info *shinfo = skb_shinfo(skb);
 	u32 mss = shinfo->gso_size;
 
@@ -4194,7 +4193,7 @@ static bool rtl8169_tso_csum_v2(struct rtl8169_private *tp,
 			WARN_ON_ONCE(1);
 		}
 
-		opts[0] |= transport_offset << GTTCPHO_SHIFT;
+		opts[0] |= skb_transport_offset(skb) << GTTCPHO_SHIFT;
 		opts[1] |= mss << TD1_MSS_SHIFT;
 	} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		u8 ip_protocol;
@@ -4222,7 +4221,7 @@ static bool rtl8169_tso_csum_v2(struct rtl8169_private *tp,
 		else
 			WARN_ON_ONCE(1);
 
-		opts[1] |= transport_offset << TCPHO_SHIFT;
+		opts[1] |= skb_transport_offset(skb) << TCPHO_SHIFT;
 	} else {
 		unsigned int padto = rtl_quirk_packet_padto(tp, skb);
 
@@ -4389,14 +4388,13 @@ static netdev_features_t rtl8169_features_check(struct sk_buff *skb,
 						struct net_device *dev,
 						netdev_features_t features)
 {
-	int transport_offset = skb_transport_offset(skb);
 	struct rtl8169_private *tp = netdev_priv(dev);
 
 	if (skb_is_gso(skb)) {
 		if (tp->mac_version == RTL_GIGA_MAC_VER_34)
 			features = rtl8168evl_fix_tso(skb, features);
 
-		if (transport_offset > GTTCPHO_MAX &&
+		if (skb_transport_offset(skb) > GTTCPHO_MAX &&
 		    rtl_chip_supports_csum_v2(tp))
 			features &= ~NETIF_F_ALL_TSO;
 	} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
@@ -4407,7 +4405,7 @@ static netdev_features_t rtl8169_features_check(struct sk_buff *skb,
 		if (rtl_quirk_packet_padto(tp, skb))
 			features &= ~NETIF_F_CSUM_MASK;
 
-		if (transport_offset > TCPHO_MAX &&
+		if (skb_transport_offset(skb) > TCPHO_MAX &&
 		    rtl_chip_supports_csum_v2(tp))
 			features &= ~NETIF_F_CSUM_MASK;
 	}
diff --git a/drivers/net/ethernet/rocker/rocker_ofdpa.c b/drivers/net/ethernet/rocker/rocker_ofdpa.c
index bc70c6abd6a5..58cf7cc54f40 100644
--- a/drivers/net/ethernet/rocker/rocker_ofdpa.c
+++ b/drivers/net/ethernet/rocker/rocker_ofdpa.c
@@ -1273,7 +1273,7 @@ static int ofdpa_port_ipv4_neigh(struct ofdpa_port *ofdpa_port,
 	bool removing;
 	int err = 0;
 
-	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	entry = kzalloc(sizeof(*entry), GFP_ATOMIC);
 	if (!entry)
 		return -ENOMEM;
 
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index c1cd1c97f09d..056c24ec1249 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -1932,7 +1932,10 @@ static int efx_ef10_try_update_nic_stats_vf(struct efx_nic *efx)
 
 	efx_update_sw_stats(efx, stats);
 out:
+	/* releasing a DMA coherent buffer with BH disabled can panic */
+	spin_unlock_bh(&efx->stats_lock);
 	efx_nic_free_buffer(efx, &stats_buf);
+	spin_lock_bh(&efx->stats_lock);
 	return rc;
 }
 
diff --git a/drivers/net/ethernet/sfc/ef10_sriov.c b/drivers/net/ethernet/sfc/ef10_sriov.c
index 752d6406f07e..f488461a23d1 100644
--- a/drivers/net/ethernet/sfc/ef10_sriov.c
+++ b/drivers/net/ethernet/sfc/ef10_sriov.c
@@ -408,8 +408,9 @@ fail1:
 static int efx_ef10_pci_sriov_disable(struct efx_nic *efx, bool force)
 {
 	struct pci_dev *dev = efx->pci_dev;
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
 	unsigned int vfs_assigned = pci_vfs_assigned(dev);
-	int rc = 0;
+	int i, rc = 0;
 
 	if (vfs_assigned && !force) {
 		netif_info(efx, drv, efx->net_dev, "VFs are assigned to guests; "
@@ -417,10 +418,13 @@ static int efx_ef10_pci_sriov_disable(struct efx_nic *efx, bool force)
 		return -EBUSY;
 	}
 
-	if (!vfs_assigned)
+	if (!vfs_assigned) {
+		for (i = 0; i < efx->vf_count; i++)
+			nic_data->vf[i].pci_dev = NULL;
 		pci_disable_sriov(dev);
-	else
+	} else {
 		rc = -EBUSY;
+	}
 
 	efx_ef10_sriov_free_vf_vswitching(efx);
 	efx->vf_count = 0;
diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c
index 725b0f38813a..a2b4e3befa59 100644
--- a/drivers/net/ethernet/sfc/ptp.c
+++ b/drivers/net/ethernet/sfc/ptp.c
@@ -1100,7 +1100,29 @@ static void efx_ptp_xmit_skb_queue(struct efx_nic *efx, struct sk_buff *skb)
 
 	tx_queue = efx_channel_get_tx_queue(ptp_data->channel, type);
 	if (tx_queue && tx_queue->timestamping) {
+		/* This code invokes normal driver TX code which is always
+		 * protected from softirqs when called from generic TX code,
+		 * which in turn disables preemption. Look at __dev_queue_xmit
+		 * which uses rcu_read_lock_bh disabling preemption for RCU
+		 * plus disabling softirqs. We do not need RCU reader
+		 * protection here.
+		 *
+		 * Although it is theoretically safe for current PTP TX/RX code
+		 * running without disabling softirqs, there are three good
+		 * reasond for doing so:
+		 *
+		 *      1) The code invoked is mainly implemented for non-PTP
+		 *         packets and it is always executed with softirqs
+		 *         disabled.
+		 *      2) This being a single PTP packet, better to not
+		 *         interrupt its processing by softirqs which can lead
+		 *         to high latencies.
+		 *      3) netdev_xmit_more checks preemption is disabled and
+		 *         triggers a BUG_ON if not.
+		 */
+		local_bh_disable();
 		efx_enqueue_skb(tx_queue, skb);
+		local_bh_enable();
 	} else {
 		WARN_ONCE(1, "PTP channel has no timestamped tx queue\n");
 		dev_kfree_skb_any(skb);
diff --git a/drivers/net/ethernet/smsc/epic100.c b/drivers/net/ethernet/smsc/epic100.c
index 44daf79a8f97..f3b1af9a59e8 100644
--- a/drivers/net/ethernet/smsc/epic100.c
+++ b/drivers/net/ethernet/smsc/epic100.c
@@ -1513,14 +1513,14 @@ static void epic_remove_one(struct pci_dev *pdev)
 	struct net_device *dev = pci_get_drvdata(pdev);
 	struct epic_private *ep = netdev_priv(dev);
 
+	unregister_netdev(dev);
 	dma_free_coherent(&pdev->dev, TX_TOTAL_SIZE, ep->tx_ring,
 			  ep->tx_ring_dma);
 	dma_free_coherent(&pdev->dev, RX_TOTAL_SIZE, ep->rx_ring,
 			  ep->rx_ring_dma);
-	unregister_netdev(dev);
 	pci_iounmap(pdev, ep->ioaddr);
-	pci_release_regions(pdev);
 	free_netdev(dev);
+	pci_release_regions(pdev);
 	pci_disable_device(pdev);
 	/* pci_power_off(pdev, -1); */
 }
diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c
index 592e191adbf7..63b99dd8ca51 100644
--- a/drivers/net/ethernet/smsc/smsc911x.c
+++ b/drivers/net/ethernet/smsc/smsc911x.c
@@ -1037,6 +1037,8 @@ static int smsc911x_mii_probe(struct net_device *dev)
 		return ret;
 	}
 
+	/* Indicate that the MAC is responsible for managing PHY PM */
+	phydev->mac_managed_pm = true;
 	phy_attached_info(phydev);
 
 	phy_set_max_speed(phydev, SPEED_100);
@@ -2584,6 +2586,8 @@ static int smsc911x_suspend(struct device *dev)
 	if (netif_running(ndev)) {
 		netif_stop_queue(ndev);
 		netif_device_detach(ndev);
+		if (!device_may_wakeup(dev))
+			phy_stop(ndev->phydev);
 	}
 
 	/* enable wake on LAN, energy detection and the external PME
@@ -2625,6 +2629,8 @@ static int smsc911x_resume(struct device *dev)
 	if (netif_running(ndev)) {
 		netif_device_attach(ndev);
 		netif_start_queue(ndev);
+		if (!device_may_wakeup(dev))
+			phy_start(ndev->phydev);
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
index bc91fd867dcd..358fc26f8d1f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
@@ -361,6 +361,7 @@ bypass_clk_reset_gpio:
 	data->fix_mac_speed = tegra_eqos_fix_speed;
 	data->init = tegra_eqos_init;
 	data->bsp_priv = eqos;
+	data->sph_disable = 1;
 
 	err = tegra_eqos_init(pdev, eqos);
 	if (err < 0)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c
index 9a6d819b84ae..378b4dd826bb 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c
@@ -273,7 +273,8 @@ static int ingenic_mac_probe(struct platform_device *pdev)
 			mac->tx_delay = tx_delay_ps * 1000;
 		} else {
 			dev_err(&pdev->dev, "Invalid TX clock delay: %dps\n", tx_delay_ps);
-			return -EINVAL;
+			ret = -EINVAL;
+			goto err_remove_config_dt;
 		}
 	}
 
@@ -283,7 +284,8 @@ static int ingenic_mac_probe(struct platform_device *pdev)
 			mac->rx_delay = rx_delay_ps * 1000;
 		} else {
 			dev_err(&pdev->dev, "Invalid RX clock delay: %dps\n", rx_delay_ps);
-			return -EINVAL;
+			ret = -EINVAL;
+			goto err_remove_config_dt;
 		}
 	}
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index 502fbbc082fb..b32f1f5d841f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -1098,6 +1098,7 @@ static void intel_eth_pci_remove(struct pci_dev *pdev)
 
 	stmmac_dvr_remove(&pdev->dev);
 
+	clk_disable_unprepare(priv->plat->stmmac_clk);
 	clk_unregister_fixed_rate(priv->plat->stmmac_clk);
 
 	pcim_iounmap_regions(pdev, BIT(0));
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index b21745368983..412abfabd28b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -219,6 +219,9 @@ static void dwmac4_map_mtl_dma(struct mac_device_info *hw, u32 queue, u32 chan)
 	if (queue == 0 || queue == 4) {
 		value &= ~MTL_RXQ_DMA_Q04MDMACH_MASK;
 		value |= MTL_RXQ_DMA_Q04MDMACH(chan);
+	} else if (queue > 4) {
+		value &= ~MTL_RXQ_DMA_QXMDMACH_MASK(queue - 4);
+		value |= MTL_RXQ_DMA_QXMDMACH(chan, queue - 4);
 	} else {
 		value &= ~MTL_RXQ_DMA_QXMDMACH_MASK(queue);
 		value |= MTL_RXQ_DMA_QXMDMACH(chan, queue);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
index d1c31200bb91..01d0a14f6752 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
@@ -258,14 +258,18 @@ EXPORT_SYMBOL_GPL(stmmac_set_mac_addr);
 /* Enable disable MAC RX/TX */
 void stmmac_set_mac(void __iomem *ioaddr, bool enable)
 {
-	u32 value = readl(ioaddr + MAC_CTRL_REG);
+	u32 old_val, value;
+
+	old_val = readl(ioaddr + MAC_CTRL_REG);
+	value = old_val;
 
 	if (enable)
 		value |= MAC_ENABLE_RX | MAC_ENABLE_TX;
 	else
 		value &= ~(MAC_ENABLE_TX | MAC_ENABLE_RX);
 
-	writel(value, ioaddr + MAC_CTRL_REG);
+	if (value != old_val)
+		writel(value, ioaddr + MAC_CTRL_REG);
 }
 
 void stmmac_get_mac_addr(void __iomem *ioaddr, unsigned char *addr,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 8f563b446d5c..dc31501fec8f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -800,14 +800,6 @@ static int stmmac_ethtool_op_set_eee(struct net_device *dev,
 		netdev_warn(priv->dev,
 			    "Setting EEE tx-lpi is not supported\n");
 
-	if (priv->hw->xpcs) {
-		ret = xpcs_config_eee(priv->hw->xpcs,
-				      priv->plat->mult_fact_100ns,
-				      edata->eee_enabled);
-		if (ret)
-			return ret;
-	}
-
 	if (!edata->eee_enabled)
 		stmmac_disable_eee_mode(priv);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index eed1094f547f..031a0e551882 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -846,19 +846,10 @@ int stmmac_init_tstamp_counter(struct stmmac_priv *priv, u32 systime_flags)
 	struct timespec64 now;
 	u32 sec_inc = 0;
 	u64 temp = 0;
-	int ret;
 
 	if (!(priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp))
 		return -EOPNOTSUPP;
 
-	ret = clk_prepare_enable(priv->plat->clk_ptp_ref);
-	if (ret < 0) {
-		netdev_warn(priv->dev,
-			    "failed to enable PTP reference clock: %pe\n",
-			    ERR_PTR(ret));
-		return ret;
-	}
-
 	stmmac_config_hw_tstamping(priv, priv->ptpaddr, systime_flags);
 	priv->systime_flags = systime_flags;
 
@@ -1094,10 +1085,10 @@ static void stmmac_mac_link_up(struct phylink_config *config,
 			       bool tx_pause, bool rx_pause)
 {
 	struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev));
-	u32 ctrl;
+	u32 old_ctrl, ctrl;
 
-	ctrl = readl(priv->ioaddr + MAC_CTRL_REG);
-	ctrl &= ~priv->hw->link.speed_mask;
+	old_ctrl = readl(priv->ioaddr + MAC_CTRL_REG);
+	ctrl = old_ctrl & ~priv->hw->link.speed_mask;
 
 	if (interface == PHY_INTERFACE_MODE_USXGMII) {
 		switch (speed) {
@@ -1172,7 +1163,8 @@ static void stmmac_mac_link_up(struct phylink_config *config,
 	if (tx_pause && rx_pause)
 		stmmac_mac_flow_ctrl(priv, duplex);
 
-	writel(ctrl, priv->ioaddr + MAC_CTRL_REG);
+	if (ctrl != old_ctrl)
+		writel(ctrl, priv->ioaddr + MAC_CTRL_REG);
 
 	stmmac_mac_set(priv, priv->ioaddr, true);
 	if (phy && priv->dma_cap.eee) {
@@ -3330,6 +3322,14 @@ static int stmmac_hw_setup(struct net_device *dev, bool ptp_register)
 
 	stmmac_mmc_setup(priv);
 
+	if (ptp_register) {
+		ret = clk_prepare_enable(priv->plat->clk_ptp_ref);
+		if (ret < 0)
+			netdev_warn(priv->dev,
+				    "failed to enable PTP reference clock: %pe\n",
+				    ERR_PTR(ret));
+	}
+
 	ret = stmmac_init_ptp(priv);
 	if (ret == -EOPNOTSUPP)
 		netdev_warn(priv->dev, "PTP not supported by HW\n");
@@ -7280,8 +7280,6 @@ int stmmac_dvr_remove(struct device *dev)
 	netdev_info(priv->dev, "%s: removing driver", __func__);
 
 	pm_runtime_get_sync(dev);
-	pm_runtime_disable(dev);
-	pm_runtime_put_noidle(dev);
 
 	stmmac_stop_all_dma(priv);
 	stmmac_mac_set(priv, priv->ioaddr, false);
@@ -7308,6 +7306,9 @@ int stmmac_dvr_remove(struct device *dev)
 	mutex_destroy(&priv->lock);
 	bitmap_free(priv->af_xdp_zc_qps);
 
+	pm_runtime_disable(dev);
+	pm_runtime_put_noidle(dev);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(stmmac_dvr_remove);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 78e1fed1a319..a2d6eb4de2aa 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -813,7 +813,13 @@ static int __maybe_unused stmmac_pltfr_noirq_resume(struct device *dev)
 		if (ret)
 			return ret;
 
-		stmmac_init_tstamp_counter(priv, priv->systime_flags);
+		ret = clk_prepare_enable(priv->plat->clk_ptp_ref);
+		if (ret < 0) {
+			netdev_warn(priv->dev,
+				    "failed to enable PTP reference clock: %pe\n",
+				    ERR_PTR(ret));
+			return ret;
+		}
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c
index 287ae4c538aa..6472425539e1 100644
--- a/drivers/net/ethernet/sun/cassini.c
+++ b/drivers/net/ethernet/sun/cassini.c
@@ -1325,7 +1325,7 @@ static void cas_init_rx_dma(struct cas *cp)
 	writel(val, cp->regs + REG_RX_PAGE_SIZE);
 
 	/* enable the header parser if desired */
-	if (CAS_HP_FIRMWARE == cas_prog_null)
+	if (&CAS_HP_FIRMWARE[0] == &cas_prog_null[0])
 		return;
 
 	val = CAS_BASE(HP_CFG_NUM_CPU, CAS_NCPUS > 63 ? 0 : CAS_NCPUS);
@@ -3794,7 +3794,7 @@ static void cas_reset(struct cas *cp, int blkflag)
 
 	/* program header parser */
 	if ((cp->cas_flags & CAS_FLAG_TARGET_ABORT) ||
-	    (CAS_HP_ALT_FIRMWARE == cas_prog_null)) {
+	    (&CAS_HP_ALT_FIRMWARE[0] == &cas_prog_null[0])) {
 		cas_load_firmware(cp, CAS_HP_FIRMWARE);
 	} else {
 		cas_load_firmware(cp, CAS_HP_ALT_FIRMWARE);
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index ea9d073e87fa..901571c2626a 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -2467,7 +2467,6 @@ static int am65_cpsw_nuss_register_devlink(struct am65_cpsw_common *common)
 				port->port_id, ret);
 			goto dl_port_unreg;
 		}
-		devlink_port_type_eth_set(dl_port, port->ndev);
 	}
 
 	return ret;
@@ -2514,6 +2513,7 @@ static void am65_cpsw_unregister_devlink(struct am65_cpsw_common *common)
 static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common)
 {
 	struct device *dev = common->dev;
+	struct devlink_port *dl_port;
 	struct am65_cpsw_port *port;
 	int ret = 0, i;
 
@@ -2530,6 +2530,10 @@ static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common)
 		return ret;
 	}
 
+	ret = am65_cpsw_nuss_register_devlink(common);
+	if (ret)
+		return ret;
+
 	for (i = 0; i < common->port_num; i++) {
 		port = &common->ports[i];
 
@@ -2542,25 +2546,24 @@ static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common)
 				i, ret);
 			goto err_cleanup_ndev;
 		}
+
+		dl_port = &port->devlink_port;
+		devlink_port_type_eth_set(dl_port, port->ndev);
 	}
 
 	ret = am65_cpsw_register_notifiers(common);
 	if (ret)
 		goto err_cleanup_ndev;
 
-	ret = am65_cpsw_nuss_register_devlink(common);
-	if (ret)
-		goto clean_unregister_notifiers;
-
 	/* can't auto unregister ndev using devm_add_action() due to
 	 * devres release sequence in DD core for DMA
 	 */
 
 	return 0;
-clean_unregister_notifiers:
-	am65_cpsw_unregister_notifiers(common);
+
 err_cleanup_ndev:
 	am65_cpsw_nuss_cleanup_ndev(common);
+	am65_cpsw_unregister_devlink(common);
 
 	return ret;
 }
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 1ab94b5f9bbf..605332f36d9d 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -774,7 +774,8 @@ static struct rtable *geneve_get_v4_rt(struct sk_buff *skb,
 				       struct geneve_sock *gs4,
 				       struct flowi4 *fl4,
 				       const struct ip_tunnel_info *info,
-				       __be16 dport, __be16 sport)
+				       __be16 dport, __be16 sport,
+				       __u8 *full_tos)
 {
 	bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
 	struct geneve_dev *geneve = netdev_priv(dev);
@@ -799,6 +800,8 @@ static struct rtable *geneve_get_v4_rt(struct sk_buff *skb,
 		use_cache = false;
 	}
 	fl4->flowi4_tos = RT_TOS(tos);
+	if (full_tos)
+		*full_tos = tos;
 
 	dst_cache = (struct dst_cache *)&info->dst_cache;
 	if (use_cache) {
@@ -852,8 +855,7 @@ static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb,
 		use_cache = false;
 	}
 
-	fl6->flowlabel = ip6_make_flowinfo(RT_TOS(prio),
-					   info->key.label);
+	fl6->flowlabel = ip6_make_flowinfo(prio, info->key.label);
 	dst_cache = (struct dst_cache *)&info->dst_cache;
 	if (use_cache) {
 		dst = dst_cache_get_ip6(dst_cache, &fl6->saddr);
@@ -887,6 +889,7 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	const struct ip_tunnel_key *key = &info->key;
 	struct rtable *rt;
 	struct flowi4 fl4;
+	__u8 full_tos;
 	__u8 tos, ttl;
 	__be16 df = 0;
 	__be16 sport;
@@ -897,7 +900,7 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 
 	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
 	rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info,
-			      geneve->cfg.info.key.tp_dst, sport);
+			      geneve->cfg.info.key.tp_dst, sport, &full_tos);
 	if (IS_ERR(rt))
 		return PTR_ERR(rt);
 
@@ -941,7 +944,7 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 
 		df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0;
 	} else {
-		tos = ip_tunnel_ecn_encap(fl4.flowi4_tos, ip_hdr(skb), skb);
+		tos = ip_tunnel_ecn_encap(full_tos, ip_hdr(skb), skb);
 		if (geneve->cfg.ttl_inherit)
 			ttl = ip_tunnel_get_ttl(ip_hdr(skb), skb);
 		else
@@ -1123,7 +1126,7 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 					  1, USHRT_MAX, true);
 
 		rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info,
-				      geneve->cfg.info.key.tp_dst, sport);
+				      geneve->cfg.info.key.tp_dst, sport, NULL);
 		if (IS_ERR(rt))
 			return PTR_ERR(rt);
 
diff --git a/drivers/net/ieee802154/adf7242.c b/drivers/net/ieee802154/adf7242.c
index 7db9cbd0f5de..07adbeec1978 100644
--- a/drivers/net/ieee802154/adf7242.c
+++ b/drivers/net/ieee802154/adf7242.c
@@ -1310,10 +1310,11 @@ static int adf7242_remove(struct spi_device *spi)
 
 	debugfs_remove_recursive(lp->debugfs_root);
 
+	ieee802154_unregister_hw(lp->hw);
+
 	cancel_delayed_work_sync(&lp->work);
 	destroy_workqueue(lp->wqueue);
 
-	ieee802154_unregister_hw(lp->hw);
 	mutex_destroy(&lp->bmux);
 	ieee802154_free_hw(lp->hw);
 
diff --git a/drivers/net/ieee802154/cc2520.c b/drivers/net/ieee802154/cc2520.c
index 89c046b204e0..4517517215f2 100644
--- a/drivers/net/ieee802154/cc2520.c
+++ b/drivers/net/ieee802154/cc2520.c
@@ -504,6 +504,7 @@ cc2520_tx(struct ieee802154_hw *hw, struct sk_buff *skb)
 		goto err_tx;
 
 	if (status & CC2520_STATUS_TX_UNDERFLOW) {
+		rc = -EINVAL;
 		dev_err(&priv->spi->dev, "cc2520 tx underflow exception\n");
 		goto err_tx;
 	}
diff --git a/drivers/net/ipa/ipa_mem.c b/drivers/net/ipa/ipa_mem.c
index 4337b0920d3d..cad0798985a1 100644
--- a/drivers/net/ipa/ipa_mem.c
+++ b/drivers/net/ipa/ipa_mem.c
@@ -570,7 +570,7 @@ static int ipa_smem_init(struct ipa *ipa, u32 item, size_t size)
 	}
 
 	/* Align the address down and the size up to a page boundary */
-	addr = qcom_smem_virt_to_phys(virt) & PAGE_MASK;
+	addr = qcom_smem_virt_to_phys(virt);
 	phys = addr & PAGE_MASK;
 	size = PAGE_ALIGN(size + addr - phys);
 	iova = phys;	/* We just want a direct mapping */
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index c0b21a5580d5..3f43c253adac 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -787,7 +787,7 @@ static int ipvlan_device_event(struct notifier_block *unused,
 
 	case NETDEV_CHANGEADDR:
 		list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
-			ether_addr_copy(ipvlan->dev->dev_addr, dev->dev_addr);
+			eth_hw_addr_set(ipvlan->dev, dev->dev_addr);
 			call_netdevice_notifiers(NETDEV_CHANGEADDR, ipvlan->dev);
 		}
 		break;
diff --git a/drivers/net/ipvlan/ipvtap.c b/drivers/net/ipvlan/ipvtap.c
index 1cedb634f4f7..f01078b2581c 100644
--- a/drivers/net/ipvlan/ipvtap.c
+++ b/drivers/net/ipvlan/ipvtap.c
@@ -194,7 +194,7 @@ static struct notifier_block ipvtap_notifier_block __read_mostly = {
 	.notifier_call	= ipvtap_device_event,
 };
 
-static int ipvtap_init(void)
+static int __init ipvtap_init(void)
 {
 	int err;
 
@@ -228,7 +228,7 @@ out1:
 }
 module_init(ipvtap_init);
 
-static void ipvtap_exit(void)
+static void __exit ipvtap_exit(void)
 {
 	rtnl_link_unregister(&ipvtap_link_ops);
 	unregister_netdevice_notifier(&ipvtap_notifier_block);
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index e53b40359fd1..71700f279278 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -241,6 +241,7 @@ static struct macsec_cb *macsec_skb_cb(struct sk_buff *skb)
 #define DEFAULT_SEND_SCI true
 #define DEFAULT_ENCRYPT false
 #define DEFAULT_ENCODING_SA 0
+#define MACSEC_XPN_MAX_REPLAY_WINDOW (((1 << 30) - 1))
 
 static bool send_sci(const struct macsec_secy *secy)
 {
@@ -446,11 +447,6 @@ static struct macsec_eth_header *macsec_ethhdr(struct sk_buff *skb)
 	return (struct macsec_eth_header *)skb_mac_header(skb);
 }
 
-static sci_t dev_to_sci(struct net_device *dev, __be16 port)
-{
-	return make_sci(dev->dev_addr, port);
-}
-
 static void __macsec_pn_wrapped(struct macsec_secy *secy,
 				struct macsec_tx_sa *tx_sa)
 {
@@ -1695,7 +1691,7 @@ static bool validate_add_rxsa(struct nlattr **attrs)
 		return false;
 
 	if (attrs[MACSEC_SA_ATTR_PN] &&
-	    *(u64 *)nla_data(attrs[MACSEC_SA_ATTR_PN]) == 0)
+	    nla_get_u64(attrs[MACSEC_SA_ATTR_PN]) == 0)
 		return false;
 
 	if (attrs[MACSEC_SA_ATTR_ACTIVE]) {
@@ -1751,7 +1747,8 @@ static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	pn_len = secy->xpn ? MACSEC_XPN_PN_LEN : MACSEC_DEFAULT_PN_LEN;
-	if (nla_len(tb_sa[MACSEC_SA_ATTR_PN]) != pn_len) {
+	if (tb_sa[MACSEC_SA_ATTR_PN] &&
+	    nla_len(tb_sa[MACSEC_SA_ATTR_PN]) != pn_len) {
 		pr_notice("macsec: nl: add_rxsa: bad pn length: %d != %d\n",
 			  nla_len(tb_sa[MACSEC_SA_ATTR_PN]), pn_len);
 		rtnl_unlock();
@@ -1767,7 +1764,7 @@ static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info)
 		if (nla_len(tb_sa[MACSEC_SA_ATTR_SALT]) != MACSEC_SALT_LEN) {
 			pr_notice("macsec: nl: add_rxsa: bad salt length: %d != %d\n",
 				  nla_len(tb_sa[MACSEC_SA_ATTR_SALT]),
-				  MACSEC_SA_ATTR_SALT);
+				  MACSEC_SALT_LEN);
 			rtnl_unlock();
 			return -EINVAL;
 		}
@@ -1840,7 +1837,7 @@ static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info)
 	return 0;
 
 cleanup:
-	kfree(rx_sa);
+	macsec_rxsa_put(rx_sa);
 	rtnl_unlock();
 	return err;
 }
@@ -1937,7 +1934,7 @@ static bool validate_add_txsa(struct nlattr **attrs)
 	if (nla_get_u8(attrs[MACSEC_SA_ATTR_AN]) >= MACSEC_NUM_AN)
 		return false;
 
-	if (nla_get_u32(attrs[MACSEC_SA_ATTR_PN]) == 0)
+	if (nla_get_u64(attrs[MACSEC_SA_ATTR_PN]) == 0)
 		return false;
 
 	if (attrs[MACSEC_SA_ATTR_ACTIVE]) {
@@ -2009,7 +2006,7 @@ static int macsec_add_txsa(struct sk_buff *skb, struct genl_info *info)
 		if (nla_len(tb_sa[MACSEC_SA_ATTR_SALT]) != MACSEC_SALT_LEN) {
 			pr_notice("macsec: nl: add_txsa: bad salt length: %d != %d\n",
 				  nla_len(tb_sa[MACSEC_SA_ATTR_SALT]),
-				  MACSEC_SA_ATTR_SALT);
+				  MACSEC_SALT_LEN);
 			rtnl_unlock();
 			return -EINVAL;
 		}
@@ -2083,7 +2080,7 @@ static int macsec_add_txsa(struct sk_buff *skb, struct genl_info *info)
 
 cleanup:
 	secy->operational = was_operational;
-	kfree(tx_sa);
+	macsec_txsa_put(tx_sa);
 	rtnl_unlock();
 	return err;
 }
@@ -2291,7 +2288,7 @@ static bool validate_upd_sa(struct nlattr **attrs)
 	if (nla_get_u8(attrs[MACSEC_SA_ATTR_AN]) >= MACSEC_NUM_AN)
 		return false;
 
-	if (attrs[MACSEC_SA_ATTR_PN] && nla_get_u32(attrs[MACSEC_SA_ATTR_PN]) == 0)
+	if (attrs[MACSEC_SA_ATTR_PN] && nla_get_u64(attrs[MACSEC_SA_ATTR_PN]) == 0)
 		return false;
 
 	if (attrs[MACSEC_SA_ATTR_ACTIVE]) {
@@ -3614,8 +3611,7 @@ static int macsec_set_mac_address(struct net_device *dev, void *p)
 	dev_uc_del(real_dev, dev->dev_addr);
 
 out:
-	ether_addr_copy(dev->dev_addr, addr->sa_data);
-	macsec->secy.sci = dev_to_sci(dev, MACSEC_PORT_ES);
+	eth_hw_addr_set(dev, addr->sa_data);
 
 	/* If h/w offloading is available, propagate to the device */
 	if (macsec_is_offloaded(macsec)) {
@@ -3738,9 +3734,6 @@ static int macsec_changelink_common(struct net_device *dev,
 		secy->operational = tx_sa && tx_sa->active;
 	}
 
-	if (data[IFLA_MACSEC_WINDOW])
-		secy->replay_window = nla_get_u32(data[IFLA_MACSEC_WINDOW]);
-
 	if (data[IFLA_MACSEC_ENCRYPT])
 		tx_sc->encrypt = !!nla_get_u8(data[IFLA_MACSEC_ENCRYPT]);
 
@@ -3786,6 +3779,16 @@ static int macsec_changelink_common(struct net_device *dev,
 		}
 	}
 
+	if (data[IFLA_MACSEC_WINDOW]) {
+		secy->replay_window = nla_get_u32(data[IFLA_MACSEC_WINDOW]);
+
+		/* IEEE 802.1AEbw-2013 10.7.8 - maximum replay window
+		 * for XPN cipher suites */
+		if (secy->xpn &&
+		    secy->replay_window > MACSEC_XPN_MAX_REPLAY_WINDOW)
+			return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -3815,7 +3818,7 @@ static int macsec_changelink(struct net_device *dev, struct nlattr *tb[],
 
 	ret = macsec_changelink_common(dev, data);
 	if (ret)
-		return ret;
+		goto cleanup;
 
 	/* If h/w offloading is available, propagate to the device */
 	if (macsec_is_offloaded(macsec)) {
@@ -3944,6 +3947,11 @@ static bool sci_exists(struct net_device *dev, sci_t sci)
 	return false;
 }
 
+static sci_t dev_to_sci(struct net_device *dev, __be16 port)
+{
+	return make_sci(dev->dev_addr, port);
+}
+
 static int macsec_add_dev(struct net_device *dev, sci_t sci, u8 icv_len)
 {
 	struct macsec_dev *macsec = macsec_priv(dev);
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index a9a515cf5a46..6363459ba1d0 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -711,7 +711,7 @@ static int macvlan_sync_address(struct net_device *dev, unsigned char *addr)
 
 	if (!(dev->flags & IFF_UP)) {
 		/* Just copy in the new address */
-		ether_addr_copy(dev->dev_addr, addr);
+		eth_hw_addr_set(dev, addr);
 	} else {
 		/* Rehash and update the device filters */
 		if (macvlan_addr_busy(vlan->port, addr))
diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c
index a43820212932..50854265864d 100644
--- a/drivers/net/netdevsim/bpf.c
+++ b/drivers/net/netdevsim/bpf.c
@@ -351,10 +351,12 @@ nsim_map_alloc_elem(struct bpf_offloaded_map *offmap, unsigned int idx)
 {
 	struct nsim_bpf_bound_map *nmap = offmap->dev_priv;
 
-	nmap->entry[idx].key = kmalloc(offmap->map.key_size, GFP_USER);
+	nmap->entry[idx].key = kmalloc(offmap->map.key_size,
+				       GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
 	if (!nmap->entry[idx].key)
 		return -ENOMEM;
-	nmap->entry[idx].value = kmalloc(offmap->map.value_size, GFP_USER);
+	nmap->entry[idx].value = kmalloc(offmap->map.value_size,
+					 GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
 	if (!nmap->entry[idx].value) {
 		kfree(nmap->entry[idx].key);
 		nmap->entry[idx].key = NULL;
@@ -496,7 +498,7 @@ nsim_bpf_map_alloc(struct netdevsim *ns, struct bpf_offloaded_map *offmap)
 	if (offmap->map.map_flags)
 		return -EINVAL;
 
-	nmap = kzalloc(sizeof(*nmap), GFP_USER);
+	nmap = kzalloc(sizeof(*nmap), GFP_KERNEL_ACCOUNT);
 	if (!nmap)
 		return -ENOMEM;
 
diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c
index 378ee779061c..14787d17f703 100644
--- a/drivers/net/netdevsim/fib.c
+++ b/drivers/net/netdevsim/fib.c
@@ -53,6 +53,7 @@ struct nsim_fib_data {
 	struct rhashtable nexthop_ht;
 	struct devlink *devlink;
 	struct work_struct fib_event_work;
+	struct work_struct fib_flush_work;
 	struct list_head fib_event_queue;
 	spinlock_t fib_event_queue_lock; /* Protects fib event queue list */
 	struct mutex nh_lock; /* Protects NH HT */
@@ -977,7 +978,7 @@ static int nsim_fib_event_schedule_work(struct nsim_fib_data *data,
 
 	fib_event = kzalloc(sizeof(*fib_event), GFP_ATOMIC);
 	if (!fib_event)
-		return NOTIFY_BAD;
+		goto err_fib_event_alloc;
 
 	fib_event->data = data;
 	fib_event->event = event;
@@ -1005,6 +1006,9 @@ static int nsim_fib_event_schedule_work(struct nsim_fib_data *data,
 
 err_fib_prepare_event:
 	kfree(fib_event);
+err_fib_event_alloc:
+	if (event == FIB_EVENT_ENTRY_DEL)
+		schedule_work(&data->fib_flush_work);
 	return NOTIFY_BAD;
 }
 
@@ -1482,6 +1486,24 @@ static void nsim_fib_event_work(struct work_struct *work)
 	mutex_unlock(&data->fib_lock);
 }
 
+static void nsim_fib_flush_work(struct work_struct *work)
+{
+	struct nsim_fib_data *data = container_of(work, struct nsim_fib_data,
+						  fib_flush_work);
+	struct nsim_fib_rt *fib_rt, *fib_rt_tmp;
+
+	/* Process pending work. */
+	flush_work(&data->fib_event_work);
+
+	mutex_lock(&data->fib_lock);
+	list_for_each_entry_safe(fib_rt, fib_rt_tmp, &data->fib_rt_list, list) {
+		rhashtable_remove_fast(&data->fib_rt_ht, &fib_rt->ht_node,
+				       nsim_fib_rt_ht_params);
+		nsim_fib_rt_free(fib_rt, data);
+	}
+	mutex_unlock(&data->fib_lock);
+}
+
 static int
 nsim_fib_debugfs_init(struct nsim_fib_data *data, struct nsim_dev *nsim_dev)
 {
@@ -1540,6 +1562,7 @@ struct nsim_fib_data *nsim_fib_create(struct devlink *devlink,
 		goto err_rhashtable_nexthop_destroy;
 
 	INIT_WORK(&data->fib_event_work, nsim_fib_event_work);
+	INIT_WORK(&data->fib_flush_work, nsim_fib_flush_work);
 	INIT_LIST_HEAD(&data->fib_event_queue);
 	spin_lock_init(&data->fib_event_queue_lock);
 
@@ -1586,6 +1609,7 @@ struct nsim_fib_data *nsim_fib_create(struct devlink *devlink,
 err_nexthop_nb_unregister:
 	unregister_nexthop_notifier(devlink_net(devlink), &data->nexthop_nb);
 err_rhashtable_fib_destroy:
+	cancel_work_sync(&data->fib_flush_work);
 	flush_work(&data->fib_event_work);
 	rhashtable_free_and_destroy(&data->fib_rt_ht, nsim_fib_rt_free,
 				    data);
@@ -1615,6 +1639,7 @@ void nsim_fib_destroy(struct devlink *devlink, struct nsim_fib_data *data)
 					    NSIM_RESOURCE_IPV4_FIB);
 	unregister_fib_notifier(devlink_net(devlink), &data->fib_nb);
 	unregister_nexthop_notifier(devlink_net(devlink), &data->nexthop_nb);
+	cancel_work_sync(&data->fib_flush_work);
 	flush_work(&data->fib_event_work);
 	rhashtable_free_and_destroy(&data->fib_rt_ht, nsim_fib_rt_free,
 				    data);
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index 50572e0f1f52..84741715f670 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -67,10 +67,10 @@ nsim_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	unsigned int start;
 
 	do {
-		start = u64_stats_fetch_begin(&ns->syncp);
+		start = u64_stats_fetch_begin_irq(&ns->syncp);
 		stats->tx_bytes = ns->tx_bytes;
 		stats->tx_packets = ns->tx_packets;
-	} while (u64_stats_fetch_retry(&ns->syncp, start));
+	} while (u64_stats_fetch_retry_irq(&ns->syncp, start));
 }
 
 static int
diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c
index 7de631f5356f..fd4cbf8a55ad 100644
--- a/drivers/net/pcs/pcs-xpcs.c
+++ b/drivers/net/pcs/pcs-xpcs.c
@@ -890,7 +890,7 @@ static int xpcs_get_state_c37_sgmii(struct dw_xpcs *xpcs,
 	 */
 	ret = xpcs_read(xpcs, MDIO_MMD_VEND2, DW_VR_MII_AN_INTR_STS);
 	if (ret < 0)
-		return false;
+		return ret;
 
 	if (ret & DW_VR_MII_C37_ANSGM_SP_LNKSTS) {
 		int speed_value;
diff --git a/drivers/net/phy/ax88796b.c b/drivers/net/phy/ax88796b.c
index 457896337505..0f1e617a26c9 100644
--- a/drivers/net/phy/ax88796b.c
+++ b/drivers/net/phy/ax88796b.c
@@ -88,8 +88,10 @@ static void asix_ax88772a_link_change_notify(struct phy_device *phydev)
 	/* Reset PHY, otherwise MII_LPA will provide outdated information.
 	 * This issue is reproducible only with some link partner PHYs
 	 */
-	if (phydev->state == PHY_NOLINK && phydev->drv->soft_reset)
-		phydev->drv->soft_reset(phydev);
+	if (phydev->state == PHY_NOLINK) {
+		phy_init_hw(phydev);
+		phy_start_aneg(phydev);
+	}
 }
 
 static struct phy_driver asix_driver[] = {
diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c
index ce17b2af3218..a792dd6d2ec3 100644
--- a/drivers/net/phy/dp83822.c
+++ b/drivers/net/phy/dp83822.c
@@ -228,9 +228,7 @@ static int dp83822_config_intr(struct phy_device *phydev)
 		if (misr_status < 0)
 			return misr_status;
 
-		misr_status |= (DP83822_RX_ERR_HF_INT_EN |
-				DP83822_FALSE_CARRIER_HF_INT_EN |
-				DP83822_LINK_STAT_INT_EN |
+		misr_status |= (DP83822_LINK_STAT_INT_EN |
 				DP83822_ENERGY_DET_INT_EN |
 				DP83822_LINK_QUAL_INT_EN);
 
diff --git a/drivers/net/phy/meson-gxl.c b/drivers/net/phy/meson-gxl.c
index 73f7962a37d3..c49062ad72c6 100644
--- a/drivers/net/phy/meson-gxl.c
+++ b/drivers/net/phy/meson-gxl.c
@@ -243,13 +243,7 @@ static irqreturn_t meson_gxl_handle_interrupt(struct phy_device *phydev)
 	    irq_status == INTSRC_ENERGY_DETECT)
 		return IRQ_HANDLED;
 
-	/* Give PHY some time before MAC starts sending data. This works
-	 * around an issue where network doesn't come up properly.
-	 */
-	if (!(irq_status & INTSRC_LINK_DOWN))
-		phy_queue_state_machine(phydev, msecs_to_jiffies(100));
-	else
-		phy_trigger_machine(phydev);
+	phy_trigger_machine(phydev);
 
 	return IRQ_HANDLED;
 }
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index b28db9e276d6..fc300dabbe50 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -31,6 +31,7 @@
 #include <linux/io.h>
 #include <linux/uaccess.h>
 #include <linux/atomic.h>
+#include <linux/suspend.h>
 #include <net/netlink.h>
 #include <net/genetlink.h>
 #include <net/sock.h>
@@ -998,6 +999,28 @@ static irqreturn_t phy_interrupt(int irq, void *phy_dat)
 	struct phy_driver *drv = phydev->drv;
 	irqreturn_t ret;
 
+	/* Wakeup interrupts may occur during a system sleep transition.
+	 * Postpone handling until the PHY has resumed.
+	 */
+	if (IS_ENABLED(CONFIG_PM_SLEEP) && phydev->irq_suspended) {
+		struct net_device *netdev = phydev->attached_dev;
+
+		if (netdev) {
+			struct device *parent = netdev->dev.parent;
+
+			if (netdev->wol_enabled)
+				pm_system_wakeup();
+			else if (device_may_wakeup(&netdev->dev))
+				pm_wakeup_dev_event(&netdev->dev, 0, true);
+			else if (parent && device_may_wakeup(parent))
+				pm_wakeup_dev_event(parent, 0, true);
+		}
+
+		phydev->irq_rerun = 1;
+		disable_irq_nosync(irq);
+		return IRQ_HANDLED;
+	}
+
 	mutex_lock(&phydev->lock);
 	ret = drv->handle_interrupt(phydev);
 	mutex_unlock(&phydev->lock);
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 66408f2f7fa0..179f2eaa3fbb 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -286,6 +286,15 @@ static __maybe_unused int mdio_bus_phy_suspend(struct device *dev)
 	if (phydev->mac_managed_pm)
 		return 0;
 
+	/* Wakeup interrupts may occur during the system sleep transition when
+	 * the PHY is inaccessible. Set flag to postpone handling until the PHY
+	 * has resumed. Wait for concurrent interrupt handler to complete.
+	 */
+	if (phy_interrupt_is_valid(phydev)) {
+		phydev->irq_suspended = 1;
+		synchronize_irq(phydev->irq);
+	}
+
 	/* We must stop the state machine manually, otherwise it stops out of
 	 * control, possibly with the phydev->lock held. Upon resume, netdev
 	 * may call phy routines that try to grab the same lock, and that may
@@ -315,6 +324,12 @@ static __maybe_unused int mdio_bus_phy_resume(struct device *dev)
 
 	phydev->suspended_by_mdio_bus = 0;
 
+	/* If we manged to get here with the PHY state machine in a state neither
+	 * PHY_HALTED nor PHY_READY this is an indication that something went wrong
+	 * and we should most likely be using MAC managed PM and we are not.
+	 */
+	WARN_ON(phydev->state != PHY_HALTED && phydev->state != PHY_READY);
+
 	ret = phy_init_hw(phydev);
 	if (ret < 0)
 		return ret;
@@ -323,6 +338,20 @@ static __maybe_unused int mdio_bus_phy_resume(struct device *dev)
 	if (ret < 0)
 		return ret;
 no_resume:
+	if (phy_interrupt_is_valid(phydev)) {
+		phydev->irq_suspended = 0;
+		synchronize_irq(phydev->irq);
+
+		/* Rerun interrupts which were postponed by phy_interrupt()
+		 * because they occurred during the system sleep transition.
+		 */
+		if (phydev->irq_rerun) {
+			phydev->irq_rerun = 0;
+			enable_irq(phydev->irq);
+			irq_wake_thread(phydev->irq, phydev);
+		}
+	}
+
 	if (phydev->attached_dev && phydev->adjust_link)
 		phy_start_machine(phydev);
 
diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index 90dfefc1f5f8..028a5df5c538 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -2504,7 +2504,7 @@ static int sfp_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, sfp);
 
-	err = devm_add_action(sfp->dev, sfp_cleanup, sfp);
+	err = devm_add_action_or_reset(sfp->dev, sfp_cleanup, sfp);
 	if (err < 0)
 		return err;
 
diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c
index d8cac02a79b9..636b0907a598 100644
--- a/drivers/net/phy/smsc.c
+++ b/drivers/net/phy/smsc.c
@@ -110,7 +110,7 @@ static int smsc_phy_config_init(struct phy_device *phydev)
 	struct smsc_phy_priv *priv = phydev->priv;
 	int rc;
 
-	if (!priv->energy_enable)
+	if (!priv->energy_enable || phydev->irq != PHY_POLL)
 		return 0;
 
 	rc = phy_read(phydev, MII_LAN83C185_CTRL_STATUS);
@@ -210,6 +210,8 @@ static int lan95xx_config_aneg_ext(struct phy_device *phydev)
  * response on link pulses to detect presence of plugged Ethernet cable.
  * The Energy Detect Power-Down mode is enabled again in the end of procedure to
  * save approximately 220 mW of power if cable is unplugged.
+ * The workaround is only applicable to poll mode. Energy Detect Power-Down may
+ * not be used in interrupt mode lest link change detection becomes unreliable.
  */
 static int lan87xx_read_status(struct phy_device *phydev)
 {
@@ -217,7 +219,7 @@ static int lan87xx_read_status(struct phy_device *phydev)
 
 	int err = genphy_read_status(phydev);
 
-	if (!phydev->link && priv->energy_enable) {
+	if (!phydev->link && priv->energy_enable && phydev->irq == PHY_POLL) {
 		/* Disable EDPD to wake up PHY */
 		int rc = phy_read(phydev, MII_LAN83C185_CTRL_STATUS);
 		if (rc < 0)
diff --git a/drivers/net/plip/plip.c b/drivers/net/plip/plip.c
index 82d609401711..2a2cb9d453e8 100644
--- a/drivers/net/plip/plip.c
+++ b/drivers/net/plip/plip.c
@@ -1107,7 +1107,7 @@ plip_open(struct net_device *dev)
 		/* Any address will do - we take the first. We already
 		   have the first two bytes filled with 0xfc, from
 		   plip_init_dev(). */
-		const struct in_ifaddr *ifa = rcu_dereference(in_dev->ifa_list);
+		const struct in_ifaddr *ifa = rtnl_dereference(in_dev->ifa_list);
 		if (ifa != NULL) {
 			memcpy(dev->dev_addr+2, &ifa->ifa_local, 4);
 		}
diff --git a/drivers/net/sungem_phy.c b/drivers/net/sungem_phy.c
index 291fa449993f..45f295403cb5 100644
--- a/drivers/net/sungem_phy.c
+++ b/drivers/net/sungem_phy.c
@@ -454,6 +454,7 @@ static int bcm5421_init(struct mii_phy* phy)
 		int can_low_power = 1;
 		if (np == NULL || of_get_property(np, "no-autolowpower", NULL))
 			can_low_power = 0;
+		of_node_put(np);
 		if (can_low_power) {
 			/* Enable automatic low-power */
 			sungem_phy_write(phy, 0x1c, 0x9002);
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 02de8d998bfa..f92d6a12831f 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -274,6 +274,12 @@ static void tun_napi_init(struct tun_struct *tun, struct tun_file *tfile,
 	}
 }
 
+static void tun_napi_enable(struct tun_file *tfile)
+{
+	if (tfile->napi_enabled)
+		napi_enable(&tfile->napi);
+}
+
 static void tun_napi_disable(struct tun_file *tfile)
 {
 	if (tfile->napi_enabled)
@@ -635,7 +641,8 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
 	tun = rtnl_dereference(tfile->tun);
 
 	if (tun && clean) {
-		tun_napi_disable(tfile);
+		if (!tfile->detached)
+			tun_napi_disable(tfile);
 		tun_napi_del(tfile);
 	}
 
@@ -654,8 +661,10 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
 		if (clean) {
 			RCU_INIT_POINTER(tfile->tun, NULL);
 			sock_put(&tfile->sk);
-		} else
+		} else {
 			tun_disable_queue(tun, tfile);
+			tun_napi_disable(tfile);
+		}
 
 		synchronize_net();
 		tun_flow_delete_by_queue(tun, tun->numqueues + 1);
@@ -728,6 +737,7 @@ static void tun_detach_all(struct net_device *dev)
 		sock_put(&tfile->sk);
 	}
 	list_for_each_entry_safe(tfile, tmp, &tun->disabled, next) {
+		tun_napi_del(tfile);
 		tun_enable_queue(tfile);
 		tun_queue_purge(tfile);
 		xdp_rxq_info_unreg(&tfile->xdp_rxq);
@@ -808,6 +818,7 @@ static int tun_attach(struct tun_struct *tun, struct file *file,
 
 	if (tfile->detached) {
 		tun_enable_queue(tfile);
+		tun_napi_enable(tfile);
 	} else {
 		sock_hold(&tfile->sk);
 		tun_napi_init(tun, tfile, napi, napi_frags);
@@ -1086,7 +1097,10 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto drop;
 
 	len = run_ebpf_filter(tun, skb, len);
-	if (len == 0 || pskb_trim(skb, len))
+	if (len == 0)
+		goto drop;
+
+	if (pskb_trim(skb, len))
 		goto drop;
 
 	if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC)))
diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig
index b554054a7560..8939e5fbd50a 100644
--- a/drivers/net/usb/Kconfig
+++ b/drivers/net/usb/Kconfig
@@ -636,8 +636,9 @@ config USB_NET_AQC111
 	  * Aquantia AQtion USB to 5GbE
 
 config USB_RTL8153_ECM
-	tristate "RTL8153 ECM support"
+	tristate
 	depends on USB_NET_CDCETHER && (USB_RTL8152 || USB_RTL8152=n)
+	default y
 	help
 	  This option supports ECM mode for RTL8153 ethernet adapter, when
 	  CONFIG_USB_RTL8152 is not set, or the RTL8153 device is not
diff --git a/drivers/net/usb/asix.h b/drivers/net/usb/asix.h
index 4334aafab59a..c126df1c13ee 100644
--- a/drivers/net/usb/asix.h
+++ b/drivers/net/usb/asix.h
@@ -126,8 +126,7 @@
 	 AX_MEDIUM_RE)
 
 #define AX88772_MEDIUM_DEFAULT	\
-	(AX_MEDIUM_FD | AX_MEDIUM_RFC | \
-	 AX_MEDIUM_TFC | AX_MEDIUM_PS | \
+	(AX_MEDIUM_FD | AX_MEDIUM_PS | \
 	 AX_MEDIUM_AC | AX_MEDIUM_RE)
 
 /* AX88772 & AX88178 RX_CTL values */
diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c
index f39188b7717a..00c23f1d1c94 100644
--- a/drivers/net/usb/asix_common.c
+++ b/drivers/net/usb/asix_common.c
@@ -431,6 +431,7 @@ void asix_adjust_link(struct net_device *netdev)
 
 	asix_write_medium_mode(dev, mode, 0);
 	phy_print_status(phydev);
+	usbnet_link_change(dev, phydev->link, 0);
 }
 
 int asix_write_gpio(struct usbnet *dev, u16 value, int sleep, int in_pm)
diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c
index d5ce642200e8..0a2c3860179e 100644
--- a/drivers/net/usb/ax88179_178a.c
+++ b/drivers/net/usb/ax88179_178a.c
@@ -1471,6 +1471,42 @@ static int ax88179_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 	 * are bundled into this buffer and where we can find an array of
 	 * per-packet metadata (which contains elements encoded into u16).
 	 */
+
+	/* SKB contents for current firmware:
+	 *   <packet 1> <padding>
+	 *   ...
+	 *   <packet N> <padding>
+	 *   <per-packet metadata entry 1> <dummy header>
+	 *   ...
+	 *   <per-packet metadata entry N> <dummy header>
+	 *   <padding2> <rx_hdr>
+	 *
+	 * where:
+	 *   <packet N> contains pkt_len bytes:
+	 *		2 bytes of IP alignment pseudo header
+	 *		packet received
+	 *   <per-packet metadata entry N> contains 4 bytes:
+	 *		pkt_len and fields AX_RXHDR_*
+	 *   <padding>	0-7 bytes to terminate at
+	 *		8 bytes boundary (64-bit).
+	 *   <padding2> 4 bytes to make rx_hdr terminate at
+	 *		8 bytes boundary (64-bit)
+	 *   <dummy-header> contains 4 bytes:
+	 *		pkt_len=0 and AX_RXHDR_DROP_ERR
+	 *   <rx-hdr>	contains 4 bytes:
+	 *		pkt_cnt and hdr_off (offset of
+	 *		  <per-packet metadata entry 1>)
+	 *
+	 * pkt_cnt is number of entrys in the per-packet metadata.
+	 * In current firmware there is 2 entrys per packet.
+	 * The first points to the packet and the
+	 *  second is a dummy header.
+	 * This was done probably to align fields in 64-bit and
+	 *  maintain compatibility with old firmware.
+	 * This code assumes that <dummy header> and <padding2> are
+	 *  optional.
+	 */
+
 	if (skb->len < 4)
 		return 0;
 	skb_trim(skb, skb->len - 4);
@@ -1484,51 +1520,66 @@ static int ax88179_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 	/* Make sure that the bounds of the metadata array are inside the SKB
 	 * (and in front of the counter at the end).
 	 */
-	if (pkt_cnt * 2 + hdr_off > skb->len)
+	if (pkt_cnt * 4 + hdr_off > skb->len)
 		return 0;
 	pkt_hdr = (u32 *)(skb->data + hdr_off);
 
 	/* Packets must not overlap the metadata array */
 	skb_trim(skb, hdr_off);
 
-	for (; ; pkt_cnt--, pkt_hdr++) {
+	for (; pkt_cnt > 0; pkt_cnt--, pkt_hdr++) {
+		u16 pkt_len_plus_padd;
 		u16 pkt_len;
 
 		le32_to_cpus(pkt_hdr);
 		pkt_len = (*pkt_hdr >> 16) & 0x1fff;
+		pkt_len_plus_padd = (pkt_len + 7) & 0xfff8;
 
-		if (pkt_len > skb->len)
+		/* Skip dummy header used for alignment
+		 */
+		if (pkt_len == 0)
+			continue;
+
+		if (pkt_len_plus_padd > skb->len)
 			return 0;
 
 		/* Check CRC or runt packet */
-		if (((*pkt_hdr & (AX_RXHDR_CRC_ERR | AX_RXHDR_DROP_ERR)) == 0) &&
-		    pkt_len >= 2 + ETH_HLEN) {
-			bool last = (pkt_cnt == 0);
-
-			if (last) {
-				ax_skb = skb;
-			} else {
-				ax_skb = skb_clone(skb, GFP_ATOMIC);
-				if (!ax_skb)
-					return 0;
-			}
-			ax_skb->len = pkt_len;
-			/* Skip IP alignment pseudo header */
-			skb_pull(ax_skb, 2);
-			skb_set_tail_pointer(ax_skb, ax_skb->len);
-			ax_skb->truesize = pkt_len + sizeof(struct sk_buff);
-			ax88179_rx_checksum(ax_skb, pkt_hdr);
+		if ((*pkt_hdr & (AX_RXHDR_CRC_ERR | AX_RXHDR_DROP_ERR)) ||
+		    pkt_len < 2 + ETH_HLEN) {
+			dev->net->stats.rx_errors++;
+			skb_pull(skb, pkt_len_plus_padd);
+			continue;
+		}
 
-			if (last)
-				return 1;
+		/* last packet */
+		if (pkt_len_plus_padd == skb->len) {
+			skb_trim(skb, pkt_len);
 
-			usbnet_skb_return(dev, ax_skb);
+			/* Skip IP alignment pseudo header */
+			skb_pull(skb, 2);
+
+			skb->truesize = SKB_TRUESIZE(pkt_len_plus_padd);
+			ax88179_rx_checksum(skb, pkt_hdr);
+			return 1;
 		}
 
-		/* Trim this packet away from the SKB */
-		if (!skb_pull(skb, (pkt_len + 7) & 0xFFF8))
+		ax_skb = skb_clone(skb, GFP_ATOMIC);
+		if (!ax_skb)
 			return 0;
+		skb_trim(ax_skb, pkt_len);
+
+		/* Skip IP alignment pseudo header */
+		skb_pull(ax_skb, 2);
+
+		skb->truesize = pkt_len_plus_padd +
+				SKB_DATA_ALIGN(sizeof(struct sk_buff));
+		ax88179_rx_checksum(ax_skb, pkt_hdr);
+		usbnet_skb_return(dev, ax_skb);
+
+		skb_pull(skb, pkt_len_plus_padd);
 	}
+
+	return 0;
 }
 
 static struct sk_buff *
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 0c7f02ca6822..15c90441285c 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1085,6 +1085,7 @@ static const struct usb_device_id products[] = {
 	{QMI_MATCH_FF_FF_FF(0x2c7c, 0x0512)},	/* Quectel EG12/EM12 */
 	{QMI_MATCH_FF_FF_FF(0x2c7c, 0x0620)},	/* Quectel EM160R-GL */
 	{QMI_MATCH_FF_FF_FF(0x2c7c, 0x0800)},	/* Quectel RM500Q-GL */
+	{QMI_MATCH_FF_FF_FF(0x2c7c, 0x0801)},	/* Quectel RM520N */
 
 	/* 3. Combined interface devices matching on interface number */
 	{QMI_FIXED_INTF(0x0408, 0xea42, 4)},	/* Yota / Megafon M100-1 */
@@ -1355,6 +1356,7 @@ static const struct usb_device_id products[] = {
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)},	/* Telit LE922A */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1050, 2)},	/* Telit FN980 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1060, 2)},	/* Telit LN920 */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1070, 2)},	/* Telit FN990 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1100, 3)},	/* Telit ME910 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1101, 3)},	/* Telit ME910 dual modem */
 	{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)},	/* Telit LE920 */
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index d467a9f3bb44..7e821bed91ce 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -32,7 +32,7 @@
 #define NETNEXT_VERSION		"12"
 
 /* Information for net */
-#define NET_VERSION		"12"
+#define NET_VERSION		"13"
 
 #define DRIVER_VERSION		"v1." NETNEXT_VERSION "." NET_VERSION
 #define DRIVER_AUTHOR "Realtek linux nic maintainers <nic_swsd@realtek.com>"
@@ -5904,6 +5904,11 @@ static void r8153_enter_oob(struct r8152 *tp)
 	ocp_data &= ~NOW_IS_OOB;
 	ocp_write_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL, ocp_data);
 
+	/* RX FIFO settings for OOB */
+	ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RXFIFO_CTRL0, RXFIFO_THR1_OOB);
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_RXFIFO_CTRL1, RXFIFO_THR2_OOB);
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_RXFIFO_CTRL2, RXFIFO_THR3_OOB);
+
 	rtl_disable(tp);
 	rtl_reset_bmu(tp);
 
@@ -5915,7 +5920,8 @@ static void r8153_enter_oob(struct r8152 *tp)
 
 	wait_oob_link_list_ready(tp);
 
-	ocp_write_word(tp, MCU_TYPE_PLA, PLA_RMS, mtu_to_size(tp->netdev->mtu));
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_RMS, 1522);
+	ocp_write_byte(tp, MCU_TYPE_PLA, PLA_MTPS, MTPS_DEFAULT);
 
 	switch (tp->version) {
 	case RTL_VER_03:
@@ -5951,6 +5957,10 @@ static void r8153_enter_oob(struct r8152 *tp)
 	ocp_data |= NOW_IS_OOB | DIS_MCU_CLROOB;
 	ocp_write_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL, ocp_data);
 
+	ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_SFF_STS_7);
+	ocp_data |= MCU_BORW_EN;
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_SFF_STS_7, ocp_data);
+
 	rxdy_gated_en(tp, false);
 
 	ocp_data = ocp_read_dword(tp, MCU_TYPE_PLA, PLA_RCR);
@@ -6424,21 +6434,8 @@ static void r8156_fc_parameter(struct r8152 *tp)
 	u32 pause_on = tp->fc_pause_on ? tp->fc_pause_on : fc_pause_on_auto(tp);
 	u32 pause_off = tp->fc_pause_off ? tp->fc_pause_off : fc_pause_off_auto(tp);
 
-	switch (tp->version) {
-	case RTL_VER_10:
-	case RTL_VER_11:
-		ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_FULL, pause_on / 8);
-		ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_EMPTY, pause_off / 8);
-		break;
-	case RTL_VER_12:
-	case RTL_VER_13:
-	case RTL_VER_15:
-		ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_FULL, pause_on / 16);
-		ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_EMPTY, pause_off / 16);
-		break;
-	default:
-		break;
-	}
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_FULL, pause_on / 16);
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_EMPTY, pause_off / 16);
 }
 
 static void rtl8156_change_mtu(struct r8152 *tp)
@@ -6550,9 +6547,17 @@ static void rtl8156_down(struct r8152 *tp)
 	ocp_data &= ~NOW_IS_OOB;
 	ocp_write_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL, ocp_data);
 
+	/* RX FIFO settings for OOB */
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_RXFIFO_FULL, 64 / 16);
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_FULL, 1024 / 16);
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_EMPTY, 4096 / 16);
+
 	rtl_disable(tp);
 	rtl_reset_bmu(tp);
 
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_RMS, 1522);
+	ocp_write_byte(tp, MCU_TYPE_PLA, PLA_MTPS, MTPS_DEFAULT);
+
 	/* Clear teredo wake event. bit[15:8] is the teredo wakeup
 	 * type. Set it to zero. bits[7:0] are the W1C bits about
 	 * the events. Set them to all 1 to clear them.
@@ -6563,6 +6568,10 @@ static void rtl8156_down(struct r8152 *tp)
 	ocp_data |= NOW_IS_OOB;
 	ocp_write_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL, ocp_data);
 
+	ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_SFF_STS_7);
+	ocp_data |= MCU_BORW_EN;
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_SFF_STS_7, ocp_data);
+
 	rtl_rx_vlan_en(tp, true);
 	rxdy_gated_en(tp, false);
 
diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index 4e39e4345084..7cf9206638c3 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -564,16 +564,12 @@ static int smsc95xx_phy_update_flowcontrol(struct usbnet *dev)
 	return smsc95xx_write_reg(dev, AFC_CFG, afc_cfg);
 }
 
-static int smsc95xx_link_reset(struct usbnet *dev)
+static void smsc95xx_mac_update_fullduplex(struct usbnet *dev)
 {
 	struct smsc95xx_priv *pdata = dev->driver_priv;
 	unsigned long flags;
 	int ret;
 
-	ret = smsc95xx_write_reg(dev, INT_STS, INT_STS_CLEAR_ALL_);
-	if (ret < 0)
-		return ret;
-
 	spin_lock_irqsave(&pdata->mac_cr_lock, flags);
 	if (pdata->phydev->duplex != DUPLEX_FULL) {
 		pdata->mac_cr &= ~MAC_CR_FDPX_;
@@ -585,14 +581,16 @@ static int smsc95xx_link_reset(struct usbnet *dev)
 	spin_unlock_irqrestore(&pdata->mac_cr_lock, flags);
 
 	ret = smsc95xx_write_reg(dev, MAC_CR, pdata->mac_cr);
-	if (ret < 0)
-		return ret;
+	if (ret < 0) {
+		if (ret != -ENODEV)
+			netdev_warn(dev->net,
+				    "Error updating MAC full duplex mode\n");
+		return;
+	}
 
 	ret = smsc95xx_phy_update_flowcontrol(dev);
 	if (ret < 0)
 		netdev_warn(dev->net, "Error updating PHY flow control\n");
-
-	return ret;
 }
 
 static void smsc95xx_status(struct usbnet *dev, struct urb *urb)
@@ -609,7 +607,7 @@ static void smsc95xx_status(struct usbnet *dev, struct urb *urb)
 	netif_dbg(dev, link, dev->net, "intdata: 0x%08X\n", intdata);
 
 	if (intdata & INT_ENP_PHY_INT_)
-		usbnet_defer_kevent(dev, EVENT_LINK_RESET);
+		;
 	else
 		netdev_warn(dev->net, "unexpected interrupt, intdata=0x%08X\n",
 			    intdata);
@@ -1066,6 +1064,7 @@ static void smsc95xx_handle_link_change(struct net_device *net)
 	struct usbnet *dev = netdev_priv(net);
 
 	phy_print_status(net->phydev);
+	smsc95xx_mac_update_fullduplex(dev);
 	usbnet_defer_kevent(dev, EVENT_LINK_CHANGE);
 }
 
@@ -1971,7 +1970,6 @@ static const struct driver_info smsc95xx_info = {
 	.description	= "smsc95xx USB 2.0 Ethernet",
 	.bind		= smsc95xx_bind,
 	.unbind		= smsc95xx_unbind,
-	.link_reset	= smsc95xx_link_reset,
 	.reset		= smsc95xx_reset,
 	.check_connect	= smsc95xx_start_phy,
 	.stop		= smsc95xx_stop,
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index af2bbaff2478..5b7272fd25ee 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -847,13 +847,11 @@ int usbnet_stop (struct net_device *net)
 
 	mpn = !test_and_clear_bit(EVENT_NO_RUNTIME_PM, &dev->flags);
 
-	/* deferred work (task, timer, softirq) must also stop.
-	 * can't flush_scheduled_work() until we drop rtnl (later),
-	 * else workers could deadlock; so make workers a NOP.
-	 */
+	/* deferred work (timer, softirq, task) must also stop */
 	dev->flags = 0;
 	del_timer_sync (&dev->delay);
 	tasklet_kill (&dev->bh);
+	cancel_work_sync(&dev->kevent);
 	if (!pm)
 		usb_autopm_put_interface(dev->intf);
 
@@ -1617,8 +1615,6 @@ void usbnet_disconnect (struct usb_interface *intf)
 	net = dev->net;
 	unregister_netdev (net);
 
-	cancel_work_sync(&dev->kevent);
-
 	usb_scuttle_anchored_urbs(&dev->deferred);
 
 	if (dev->driver_info->unbind)
@@ -2002,7 +1998,7 @@ static int __usbnet_read_cmd(struct usbnet *dev, u8 cmd, u8 reqtype,
 		   cmd, reqtype, value, index, size);
 
 	if (size) {
-		buf = kmalloc(size, GFP_KERNEL);
+		buf = kmalloc(size, GFP_NOIO);
 		if (!buf)
 			goto out;
 	}
@@ -2034,7 +2030,7 @@ static int __usbnet_write_cmd(struct usbnet *dev, u8 cmd, u8 reqtype,
 		   cmd, reqtype, value, index, size);
 
 	if (data) {
-		buf = kmemdup(data, size, GFP_KERNEL);
+		buf = kmemdup(data, size, GFP_NOIO);
 		if (!buf)
 			goto out;
 	} else {
@@ -2135,7 +2131,7 @@ static void usbnet_async_cmd_cb(struct urb *urb)
 int usbnet_write_cmd_async(struct usbnet *dev, u8 cmd, u8 reqtype,
 			   u16 value, u16 index, const void *data, u16 size)
 {
-	struct usb_ctrlrequest *req = NULL;
+	struct usb_ctrlrequest *req;
 	struct urb *urb;
 	int err = -ENOMEM;
 	void *buf = NULL;
@@ -2153,7 +2149,7 @@ int usbnet_write_cmd_async(struct usbnet *dev, u8 cmd, u8 reqtype,
 		if (!buf) {
 			netdev_err(dev->net, "Error allocating buffer"
 				   " in %s!\n", __func__);
-			goto fail_free;
+			goto fail_free_urb;
 		}
 	}
 
@@ -2177,14 +2173,21 @@ int usbnet_write_cmd_async(struct usbnet *dev, u8 cmd, u8 reqtype,
 	if (err < 0) {
 		netdev_err(dev->net, "Error submitting the control"
 			   " message: status=%d\n", err);
-		goto fail_free;
+		goto fail_free_all;
 	}
 	return 0;
 
+fail_free_all:
+	kfree(req);
 fail_free_buf:
 	kfree(buf);
-fail_free:
-	kfree(req);
+	/*
+	 * avoid a double free
+	 * needed because the flag can be set only
+	 * after filling the URB
+	 */
+	urb->transfer_flags = 0;
+fail_free_urb:
 	usb_free_urb(urb);
 fail:
 	return err;
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 468d0ffc266b..48fb7bdc0f0b 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -213,9 +213,15 @@ struct virtnet_info {
 	/* Packet virtio header size */
 	u8 hdr_len;
 
-	/* Work struct for refilling if we run low on memory. */
+	/* Work struct for delayed refilling if we run low on memory. */
 	struct delayed_work refill;
 
+	/* Is delayed refill enabled? */
+	bool refill_enabled;
+
+	/* The lock to synchronize the access to refill_enabled */
+	spinlock_t refill_lock;
+
 	/* Work struct for config space updates */
 	struct work_struct config_work;
 
@@ -319,6 +325,20 @@ static struct page *get_a_page(struct receive_queue *rq, gfp_t gfp_mask)
 	return p;
 }
 
+static void enable_delayed_refill(struct virtnet_info *vi)
+{
+	spin_lock_bh(&vi->refill_lock);
+	vi->refill_enabled = true;
+	spin_unlock_bh(&vi->refill_lock);
+}
+
+static void disable_delayed_refill(struct virtnet_info *vi)
+{
+	spin_lock_bh(&vi->refill_lock);
+	vi->refill_enabled = false;
+	spin_unlock_bh(&vi->refill_lock);
+}
+
 static void virtqueue_napi_schedule(struct napi_struct *napi,
 				    struct virtqueue *vq)
 {
@@ -997,8 +1017,11 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 		case XDP_TX:
 			stats->xdp_tx++;
 			xdpf = xdp_convert_buff_to_frame(&xdp);
-			if (unlikely(!xdpf))
+			if (unlikely(!xdpf)) {
+				if (unlikely(xdp_page != page))
+					put_page(xdp_page);
 				goto err_xdp;
+			}
 			err = virtnet_xdp_xmit(dev, 1, &xdpf, 0);
 			if (unlikely(!err)) {
 				xdp_return_frame_rx_napi(xdpf);
@@ -1454,8 +1477,12 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
 	}
 
 	if (rq->vq->num_free > min((unsigned int)budget, virtqueue_get_vring_size(rq->vq)) / 2) {
-		if (!try_fill_recv(vi, rq, GFP_ATOMIC))
-			schedule_delayed_work(&vi->refill, 0);
+		if (!try_fill_recv(vi, rq, GFP_ATOMIC)) {
+			spin_lock(&vi->refill_lock);
+			if (vi->refill_enabled)
+				schedule_delayed_work(&vi->refill, 0);
+			spin_unlock(&vi->refill_lock);
+		}
 	}
 
 	u64_stats_update_begin(&rq->stats.syncp);
@@ -1578,6 +1605,8 @@ static int virtnet_open(struct net_device *dev)
 	struct virtnet_info *vi = netdev_priv(dev);
 	int i, err;
 
+	enable_delayed_refill(vi);
+
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		if (i < vi->curr_queue_pairs)
 			/* Make sure we have some buffers: if oom use wq. */
@@ -1958,6 +1987,8 @@ static int virtnet_close(struct net_device *dev)
 	struct virtnet_info *vi = netdev_priv(dev);
 	int i;
 
+	/* Make sure NAPI doesn't schedule refill work */
+	disable_delayed_refill(vi);
 	/* Make sure refill_work doesn't re-enable napi! */
 	cancel_delayed_work_sync(&vi->refill);
 
@@ -2455,6 +2486,8 @@ static int virtnet_restore_up(struct virtio_device *vdev)
 
 	virtio_device_ready(vdev);
 
+	enable_delayed_refill(vi);
+
 	if (netif_running(vi->dev)) {
 		err = virtnet_open(vi->dev);
 		if (err)
@@ -3162,6 +3195,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 	vdev->priv = vi;
 
 	INIT_WORK(&vi->config_work, virtnet_config_changed_work);
+	spin_lock_init(&vi->refill_lock);
 
 	/* If we can receive ANY GSO packets, we must allocate large ones. */
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||
@@ -3241,14 +3275,20 @@ static int virtnet_probe(struct virtio_device *vdev)
 		}
 	}
 
-	err = register_netdev(dev);
+	/* serialize netdev register + virtio_device_ready() with ndo_open() */
+	rtnl_lock();
+
+	err = register_netdevice(dev);
 	if (err) {
 		pr_debug("virtio_net: registering device failed\n");
+		rtnl_unlock();
 		goto free_failover;
 	}
 
 	virtio_device_ready(vdev);
 
+	rtnl_unlock();
+
 	err = virtnet_cpu_notif_add(vi);
 	if (err) {
 		pr_debug("virtio_net: registering cpu notifier failed\n");
diff --git a/drivers/net/wireguard/allowedips.c b/drivers/net/wireguard/allowedips.c
index 9a4c8ff32d9d..5bf7822c53f1 100644
--- a/drivers/net/wireguard/allowedips.c
+++ b/drivers/net/wireguard/allowedips.c
@@ -6,6 +6,8 @@
 #include "allowedips.h"
 #include "peer.h"
 
+enum { MAX_ALLOWEDIPS_BITS = 128 };
+
 static struct kmem_cache *node_cache;
 
 static void swap_endian(u8 *dst, const u8 *src, u8 bits)
@@ -40,7 +42,8 @@ static void push_rcu(struct allowedips_node **stack,
 		     struct allowedips_node __rcu *p, unsigned int *len)
 {
 	if (rcu_access_pointer(p)) {
-		WARN_ON(IS_ENABLED(DEBUG) && *len >= 128);
+		if (WARN_ON(IS_ENABLED(DEBUG) && *len >= MAX_ALLOWEDIPS_BITS))
+			return;
 		stack[(*len)++] = rcu_dereference_raw(p);
 	}
 }
@@ -52,7 +55,7 @@ static void node_free_rcu(struct rcu_head *rcu)
 
 static void root_free_rcu(struct rcu_head *rcu)
 {
-	struct allowedips_node *node, *stack[128] = {
+	struct allowedips_node *node, *stack[MAX_ALLOWEDIPS_BITS] = {
 		container_of(rcu, struct allowedips_node, rcu) };
 	unsigned int len = 1;
 
@@ -65,7 +68,7 @@ static void root_free_rcu(struct rcu_head *rcu)
 
 static void root_remove_peer_lists(struct allowedips_node *root)
 {
-	struct allowedips_node *node, *stack[128] = { root };
+	struct allowedips_node *node, *stack[MAX_ALLOWEDIPS_BITS] = { root };
 	unsigned int len = 1;
 
 	while (len > 0 && (node = stack[--len])) {
diff --git a/drivers/net/wireguard/selftest/allowedips.c b/drivers/net/wireguard/selftest/allowedips.c
index e173204ae7d7..41db10f9be49 100644
--- a/drivers/net/wireguard/selftest/allowedips.c
+++ b/drivers/net/wireguard/selftest/allowedips.c
@@ -593,10 +593,10 @@ bool __init wg_allowedips_selftest(void)
 	wg_allowedips_remove_by_peer(&t, a, &mutex);
 	test_negative(4, a, 192, 168, 0, 1);
 
-	/* These will hit the WARN_ON(len >= 128) in free_node if something
-	 * goes wrong.
+	/* These will hit the WARN_ON(len >= MAX_ALLOWEDIPS_BITS) in free_node
+	 * if something goes wrong.
 	 */
-	for (i = 0; i < 128; ++i) {
+	for (i = 0; i < MAX_ALLOWEDIPS_BITS; ++i) {
 		part = cpu_to_be64(~(1LLU << (i % 64)));
 		memset(&ip, 0xff, 16);
 		memcpy((u8 *)&ip + (i < 64) * 8, &part, 8);
diff --git a/drivers/net/wireguard/selftest/ratelimiter.c b/drivers/net/wireguard/selftest/ratelimiter.c
index 007cd4457c5f..ba87d294604f 100644
--- a/drivers/net/wireguard/selftest/ratelimiter.c
+++ b/drivers/net/wireguard/selftest/ratelimiter.c
@@ -6,28 +6,29 @@
 #ifdef DEBUG
 
 #include <linux/jiffies.h>
+#include <linux/hrtimer.h>
 
 static const struct {
 	bool result;
-	unsigned int msec_to_sleep_before;
+	u64 nsec_to_sleep_before;
 } expected_results[] __initconst = {
 	[0 ... PACKETS_BURSTABLE - 1] = { true, 0 },
 	[PACKETS_BURSTABLE] = { false, 0 },
-	[PACKETS_BURSTABLE + 1] = { true, MSEC_PER_SEC / PACKETS_PER_SECOND },
+	[PACKETS_BURSTABLE + 1] = { true, NSEC_PER_SEC / PACKETS_PER_SECOND },
 	[PACKETS_BURSTABLE + 2] = { false, 0 },
-	[PACKETS_BURSTABLE + 3] = { true, (MSEC_PER_SEC / PACKETS_PER_SECOND) * 2 },
+	[PACKETS_BURSTABLE + 3] = { true, (NSEC_PER_SEC / PACKETS_PER_SECOND) * 2 },
 	[PACKETS_BURSTABLE + 4] = { true, 0 },
 	[PACKETS_BURSTABLE + 5] = { false, 0 }
 };
 
 static __init unsigned int maximum_jiffies_at_index(int index)
 {
-	unsigned int total_msecs = 2 * MSEC_PER_SEC / PACKETS_PER_SECOND / 3;
+	u64 total_nsecs = 2 * NSEC_PER_SEC / PACKETS_PER_SECOND / 3;
 	int i;
 
 	for (i = 0; i <= index; ++i)
-		total_msecs += expected_results[i].msec_to_sleep_before;
-	return msecs_to_jiffies(total_msecs);
+		total_nsecs += expected_results[i].nsec_to_sleep_before;
+	return nsecs_to_jiffies(total_nsecs);
 }
 
 static __init int timings_test(struct sk_buff *skb4, struct iphdr *hdr4,
@@ -42,8 +43,12 @@ static __init int timings_test(struct sk_buff *skb4, struct iphdr *hdr4,
 	loop_start_time = jiffies;
 
 	for (i = 0; i < ARRAY_SIZE(expected_results); ++i) {
-		if (expected_results[i].msec_to_sleep_before)
-			msleep(expected_results[i].msec_to_sleep_before);
+		if (expected_results[i].nsec_to_sleep_before) {
+			ktime_t timeout = ktime_add(ktime_add_ns(ktime_get_coarse_boottime(), TICK_NSEC * 4 / 3),
+						    ns_to_ktime(expected_results[i].nsec_to_sleep_before));
+			set_current_state(TASK_UNINTERRUPTIBLE);
+			schedule_hrtimeout_range_clock(&timeout, 0, HRTIMER_MODE_ABS, CLOCK_BOOTTIME);
+		}
 
 		if (time_is_before_jiffies(loop_start_time +
 					   maximum_jiffies_at_index(i)))
@@ -127,7 +132,7 @@ bool __init wg_ratelimiter_selftest(void)
 	if (IS_ENABLED(CONFIG_KASAN) || IS_ENABLED(CONFIG_UBSAN))
 		return true;
 
-	BUILD_BUG_ON(MSEC_PER_SEC % PACKETS_PER_SECOND != 0);
+	BUILD_BUG_ON(NSEC_PER_SEC % PACKETS_PER_SECOND != 0);
 
 	if (wg_ratelimiter_init())
 		goto out;
@@ -176,7 +181,6 @@ bool __init wg_ratelimiter_selftest(void)
 				test += test_count;
 				goto err;
 			}
-			msleep(500);
 			continue;
 		} else if (ret < 0) {
 			test += test_count;
@@ -195,7 +199,6 @@ bool __init wg_ratelimiter_selftest(void)
 				test += test_count;
 				goto err;
 			}
-			msleep(50);
 			continue;
 		}
 		test += test_count;
diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c
index f79dd9a71690..73fe77e7824b 100644
--- a/drivers/net/wireless/ath/ath10k/snoc.c
+++ b/drivers/net/wireless/ath/ath10k/snoc.c
@@ -1249,13 +1249,12 @@ static void ath10k_snoc_init_napi(struct ath10k *ar)
 static int ath10k_snoc_request_irq(struct ath10k *ar)
 {
 	struct ath10k_snoc *ar_snoc = ath10k_snoc_priv(ar);
-	int irqflags = IRQF_TRIGGER_RISING;
 	int ret, id;
 
 	for (id = 0; id < CE_COUNT_MAX; id++) {
 		ret = request_irq(ar_snoc->ce_irqs[id].irq_line,
-				  ath10k_snoc_per_engine_handler,
-				  irqflags, ce_name[id], ar);
+				  ath10k_snoc_per_engine_handler, 0,
+				  ce_name[id], ar);
 		if (ret) {
 			ath10k_err(ar,
 				   "failed to register IRQ handler for CE %d: %d\n",
diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c
index 7dcf6b13f794..48a449fbd2bc 100644
--- a/drivers/net/wireless/ath/ath11k/core.c
+++ b/drivers/net/wireless/ath/ath11k/core.c
@@ -71,6 +71,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.supports_suspend = false,
 		.hal_desc_sz = sizeof(struct hal_rx_desc_ipq8074),
 		.fix_l1ss = true,
+		.wakeup_mhi = false,
 	},
 	{
 		.hw_rev = ATH11K_HW_IPQ6018_HW10,
@@ -112,6 +113,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.supports_suspend = false,
 		.hal_desc_sz = sizeof(struct hal_rx_desc_ipq8074),
 		.fix_l1ss = true,
+		.wakeup_mhi = false,
 	},
 	{
 		.name = "qca6390 hw2.0",
@@ -152,6 +154,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.supports_suspend = true,
 		.hal_desc_sz = sizeof(struct hal_rx_desc_ipq8074),
 		.fix_l1ss = true,
+		.wakeup_mhi = true,
 	},
 	{
 		.name = "qcn9074 hw1.0",
@@ -190,6 +193,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.supports_suspend = false,
 		.hal_desc_sz = sizeof(struct hal_rx_desc_qcn9074),
 		.fix_l1ss = true,
+		.wakeup_mhi = false,
 	},
 	{
 		.name = "wcn6855 hw2.0",
@@ -230,6 +234,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.supports_suspend = true,
 		.hal_desc_sz = sizeof(struct hal_rx_desc_wcn6855),
 		.fix_l1ss = false,
+		.wakeup_mhi = true,
 	},
 };
 
@@ -694,23 +699,23 @@ static int ath11k_core_pdev_create(struct ath11k_base *ab)
 		return ret;
 	}
 
-	ret = ath11k_mac_register(ab);
+	ret = ath11k_dp_pdev_alloc(ab);
 	if (ret) {
-		ath11k_err(ab, "failed register the radio with mac80211: %d\n", ret);
+		ath11k_err(ab, "failed to attach DP pdev: %d\n", ret);
 		goto err_pdev_debug;
 	}
 
-	ret = ath11k_dp_pdev_alloc(ab);
+	ret = ath11k_mac_register(ab);
 	if (ret) {
-		ath11k_err(ab, "failed to attach DP pdev: %d\n", ret);
-		goto err_mac_unregister;
+		ath11k_err(ab, "failed register the radio with mac80211: %d\n", ret);
+		goto err_dp_pdev_free;
 	}
 
 	ret = ath11k_thermal_register(ab);
 	if (ret) {
 		ath11k_err(ab, "could not register thermal device: %d\n",
 			   ret);
-		goto err_dp_pdev_free;
+		goto err_mac_unregister;
 	}
 
 	ret = ath11k_spectral_init(ab);
@@ -723,10 +728,10 @@ static int ath11k_core_pdev_create(struct ath11k_base *ab)
 
 err_thermal_unregister:
 	ath11k_thermal_unregister(ab);
-err_dp_pdev_free:
-	ath11k_dp_pdev_free(ab);
 err_mac_unregister:
 	ath11k_mac_unregister(ab);
+err_dp_pdev_free:
+	ath11k_dp_pdev_free(ab);
 err_pdev_debug:
 	ath11k_debugfs_pdev_destroy(ab);
 
diff --git a/drivers/net/wireless/ath/ath11k/debug.h b/drivers/net/wireless/ath/ath11k/debug.h
index 659a275e2eb3..694ebba17fad 100644
--- a/drivers/net/wireless/ath/ath11k/debug.h
+++ b/drivers/net/wireless/ath/ath11k/debug.h
@@ -23,8 +23,8 @@ enum ath11k_debug_mask {
 	ATH11K_DBG_TESTMODE	= 0x00000400,
 	ATH11k_DBG_HAL		= 0x00000800,
 	ATH11K_DBG_PCI		= 0x00001000,
-	ATH11K_DBG_DP_TX	= 0x00001000,
-	ATH11K_DBG_DP_RX	= 0x00002000,
+	ATH11K_DBG_DP_TX	= 0x00002000,
+	ATH11K_DBG_DP_RX	= 0x00004000,
 	ATH11K_DBG_ANY		= 0xffffffff,
 };
 
diff --git a/drivers/net/wireless/ath/ath11k/hw.h b/drivers/net/wireless/ath/ath11k/hw.h
index 62f5978b3005..4fe051625edf 100644
--- a/drivers/net/wireless/ath/ath11k/hw.h
+++ b/drivers/net/wireless/ath/ath11k/hw.h
@@ -163,6 +163,7 @@ struct ath11k_hw_params {
 	bool supports_suspend;
 	u32 hal_desc_sz;
 	bool fix_l1ss;
+	bool wakeup_mhi;
 };
 
 struct ath11k_hw_ops {
diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index f85fd341557e..c7ee373a9d2c 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -6566,7 +6566,7 @@ static int __ath11k_mac_register(struct ath11k *ar)
 	ar->hw->queues = ATH11K_HW_MAX_QUEUES;
 	ar->hw->wiphy->tx_queue_len = ATH11K_QUEUE_LEN;
 	ar->hw->offchannel_tx_hw_queue = ATH11K_HW_MAX_QUEUES - 1;
-	ar->hw->max_rx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF;
+	ar->hw->max_rx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF_HE;
 
 	ar->hw->vif_data_size = sizeof(struct ath11k_vif);
 	ar->hw->sta_data_size = sizeof(struct ath11k_sta);
diff --git a/drivers/net/wireless/ath/ath11k/pci.c b/drivers/net/wireless/ath/ath11k/pci.c
index 353a2d669fcd..7d0be9388f89 100644
--- a/drivers/net/wireless/ath/ath11k/pci.c
+++ b/drivers/net/wireless/ath/ath11k/pci.c
@@ -182,7 +182,8 @@ void ath11k_pci_write32(struct ath11k_base *ab, u32 offset, u32 value)
 	/* for offset beyond BAR + 4K - 32, may
 	 * need to wakeup MHI to access.
 	 */
-	if (test_bit(ATH11K_PCI_FLAG_INIT_DONE, &ab_pci->flags) &&
+	if (ab->hw_params.wakeup_mhi &&
+	    test_bit(ATH11K_PCI_FLAG_INIT_DONE, &ab_pci->flags) &&
 	    offset >= ACCESS_ALWAYS_OFF)
 		mhi_device_get_sync(ab_pci->mhi_ctrl->mhi_dev);
 
@@ -206,7 +207,8 @@ void ath11k_pci_write32(struct ath11k_base *ab, u32 offset, u32 value)
 		}
 	}
 
-	if (test_bit(ATH11K_PCI_FLAG_INIT_DONE, &ab_pci->flags) &&
+	if (ab->hw_params.wakeup_mhi &&
+	    test_bit(ATH11K_PCI_FLAG_INIT_DONE, &ab_pci->flags) &&
 	    offset >= ACCESS_ALWAYS_OFF)
 		mhi_device_put(ab_pci->mhi_ctrl->mhi_dev);
 }
@@ -219,7 +221,8 @@ u32 ath11k_pci_read32(struct ath11k_base *ab, u32 offset)
 	/* for offset beyond BAR + 4K - 32, may
 	 * need to wakeup MHI to access.
 	 */
-	if (test_bit(ATH11K_PCI_FLAG_INIT_DONE, &ab_pci->flags) &&
+	if (ab->hw_params.wakeup_mhi &&
+	    test_bit(ATH11K_PCI_FLAG_INIT_DONE, &ab_pci->flags) &&
 	    offset >= ACCESS_ALWAYS_OFF)
 		mhi_device_get_sync(ab_pci->mhi_ctrl->mhi_dev);
 
@@ -243,7 +246,8 @@ u32 ath11k_pci_read32(struct ath11k_base *ab, u32 offset)
 		}
 	}
 
-	if (test_bit(ATH11K_PCI_FLAG_INIT_DONE, &ab_pci->flags) &&
+	if (ab->hw_params.wakeup_mhi &&
+	    test_bit(ATH11K_PCI_FLAG_INIT_DONE, &ab_pci->flags) &&
 	    offset >= ACCESS_ALWAYS_OFF)
 		mhi_device_put(ab_pci->mhi_ctrl->mhi_dev);
 
diff --git a/drivers/net/wireless/ath/ath9k/htc.h b/drivers/net/wireless/ath/ath9k/htc.h
index 6b45e63fae4b..e3d546ef71dd 100644
--- a/drivers/net/wireless/ath/ath9k/htc.h
+++ b/drivers/net/wireless/ath/ath9k/htc.h
@@ -327,11 +327,11 @@ static inline struct ath9k_htc_tx_ctl *HTC_SKB_CB(struct sk_buff *skb)
 }
 
 #ifdef CONFIG_ATH9K_HTC_DEBUGFS
-
-#define TX_STAT_INC(c) (hif_dev->htc_handle->drv_priv->debug.tx_stats.c++)
-#define TX_STAT_ADD(c, a) (hif_dev->htc_handle->drv_priv->debug.tx_stats.c += a)
-#define RX_STAT_INC(c) (hif_dev->htc_handle->drv_priv->debug.skbrx_stats.c++)
-#define RX_STAT_ADD(c, a) (hif_dev->htc_handle->drv_priv->debug.skbrx_stats.c += a)
+#define __STAT_SAFE(expr) (hif_dev->htc_handle->drv_priv ? (expr) : 0)
+#define TX_STAT_INC(c) __STAT_SAFE(hif_dev->htc_handle->drv_priv->debug.tx_stats.c++)
+#define TX_STAT_ADD(c, a) __STAT_SAFE(hif_dev->htc_handle->drv_priv->debug.tx_stats.c += a)
+#define RX_STAT_INC(c) __STAT_SAFE(hif_dev->htc_handle->drv_priv->debug.skbrx_stats.c++)
+#define RX_STAT_ADD(c, a) __STAT_SAFE(hif_dev->htc_handle->drv_priv->debug.skbrx_stats.c += a)
 #define CAB_STAT_INC   priv->debug.tx_stats.cab_queued++
 
 #define TX_QSTAT_INC(q) (priv->debug.tx_stats.queue_stats[q]++)
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_init.c b/drivers/net/wireless/ath/ath9k/htc_drv_init.c
index ff61ae34ecdf..07ac88fb1c57 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_init.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_init.c
@@ -944,7 +944,6 @@ int ath9k_htc_probe_device(struct htc_target *htc_handle, struct device *dev,
 	priv->hw = hw;
 	priv->htc = htc_handle;
 	priv->dev = dev;
-	htc_handle->drv_priv = priv;
 	SET_IEEE80211_DEV(hw, priv->dev);
 
 	ret = ath9k_htc_wait_for_target(priv);
@@ -965,6 +964,8 @@ int ath9k_htc_probe_device(struct htc_target *htc_handle, struct device *dev,
 	if (ret)
 		goto err_init;
 
+	htc_handle->drv_priv = priv;
+
 	return 0;
 
 err_init:
diff --git a/drivers/net/wireless/ath/wil6210/debugfs.c b/drivers/net/wireless/ath/wil6210/debugfs.c
index 4c944e595978..ac7787e1a7f6 100644
--- a/drivers/net/wireless/ath/wil6210/debugfs.c
+++ b/drivers/net/wireless/ath/wil6210/debugfs.c
@@ -1010,20 +1010,14 @@ static ssize_t wil_write_file_wmi(struct file *file, const char __user *buf,
 	void *cmd;
 	int cmdlen = len - sizeof(struct wmi_cmd_hdr);
 	u16 cmdid;
-	int rc, rc1;
+	int rc1;
 
-	if (cmdlen < 0)
+	if (cmdlen < 0 || *ppos != 0)
 		return -EINVAL;
 
-	wmi = kmalloc(len, GFP_KERNEL);
-	if (!wmi)
-		return -ENOMEM;
-
-	rc = simple_write_to_buffer(wmi, len, ppos, buf, len);
-	if (rc < 0) {
-		kfree(wmi);
-		return rc;
-	}
+	wmi = memdup_user(buf, len);
+	if (IS_ERR(wmi))
+		return PTR_ERR(wmi);
 
 	cmd = (cmdlen > 0) ? &wmi[1] : NULL;
 	cmdid = le16_to_cpu(wmi->command_id);
@@ -1033,7 +1027,7 @@ static ssize_t wil_write_file_wmi(struct file *file, const char __user *buf,
 
 	wil_info(wil, "0x%04x[%d] -> %d\n", cmdid, cmdlen, rc1);
 
-	return rc;
+	return len;
 }
 
 static const struct file_operations fops_wmi = {
diff --git a/drivers/net/wireless/intel/iwlegacy/4965-rs.c b/drivers/net/wireless/intel/iwlegacy/4965-rs.c
index 9a491e5db75b..150805aec407 100644
--- a/drivers/net/wireless/intel/iwlegacy/4965-rs.c
+++ b/drivers/net/wireless/intel/iwlegacy/4965-rs.c
@@ -2403,7 +2403,7 @@ il4965_rs_fill_link_cmd(struct il_priv *il, struct il_lq_sta *lq_sta,
 		/* Repeat initial/next rate.
 		 * For legacy IL_NUMBER_TRY == 1, this loop will not execute.
 		 * For HT IL_HT_NUMBER_TRY == 3, this executes twice. */
-		while (repeat_rate > 0 && idx < LINK_QUAL_MAX_RETRY_NUM) {
+		while (repeat_rate > 0 && idx < (LINK_QUAL_MAX_RETRY_NUM - 1)) {
 			if (is_legacy(tbl_type.lq_type)) {
 				if (ant_toggle_cnt < NUM_TRY_BEFORE_ANT_TOGGLE)
 					ant_toggle_cnt++;
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/uefi.h b/drivers/net/wireless/intel/iwlwifi/fw/uefi.h
index 45d0b36d79b5..d552c656ac9f 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/uefi.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/uefi.h
@@ -2,7 +2,8 @@
 /*
  * Copyright(c) 2021 Intel Corporation
  */
-
+#ifndef __iwl_fw_uefi__
+#define __iwl_fw_uefi__
 
 #define IWL_UEFI_OEM_PNVM_NAME		L"UefiCnvWlanOemSignedPnvm"
 #define IWL_UEFI_REDUCED_POWER_NAME	L"UefiCnvWlanReducedPower"
@@ -40,3 +41,5 @@ void *iwl_uefi_get_reduced_power(struct iwl_trans *trans, size_t *len)
 	return ERR_PTR(-EOPNOTSUPP);
 }
 #endif /* CONFIG_EFI */
+
+#endif /* __iwl_fw_uefi__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index c77d98c88811..eeb81808db08 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -761,12 +761,12 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 	if (!hw)
 		return NULL;
 
-	hw->max_rx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF;
+	hw->max_rx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF_HE;
 
 	if (cfg->max_tx_agg_size)
 		hw->max_tx_aggregation_subframes = cfg->max_tx_agg_size;
 	else
-		hw->max_tx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF;
+		hw->max_tx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF_HE;
 
 	op_mode = hw->priv;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index a64874c05ced..1bb456daff9e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -1794,6 +1794,7 @@ static void iwl_mvm_disable_sta_queues(struct iwl_mvm *mvm,
 			iwl_mvm_txq_from_mac80211(sta->txq[i]);
 
 		mvmtxq->txq_id = IWL_MVM_INVALID_QUEUE;
+		list_del_init(&mvmtxq->list);
 	}
 }
 
diff --git a/drivers/net/wireless/intersil/p54/main.c b/drivers/net/wireless/intersil/p54/main.c
index a3ca6620dc0c..8fa3ec71603e 100644
--- a/drivers/net/wireless/intersil/p54/main.c
+++ b/drivers/net/wireless/intersil/p54/main.c
@@ -682,7 +682,7 @@ static void p54_flush(struct ieee80211_hw *dev, struct ieee80211_vif *vif,
 	 * queues have already been stopped and no new frames can sneak
 	 * up from behind.
 	 */
-	while ((total = p54_flush_count(priv) && i--)) {
+	while ((total = p54_flush_count(priv)) && i--) {
 		/* waste time */
 		msleep(20);
 	}
diff --git a/drivers/net/wireless/intersil/p54/p54spi.c b/drivers/net/wireless/intersil/p54/p54spi.c
index ab0fe8565851..cdb57819684a 100644
--- a/drivers/net/wireless/intersil/p54/p54spi.c
+++ b/drivers/net/wireless/intersil/p54/p54spi.c
@@ -164,7 +164,7 @@ static int p54spi_request_firmware(struct ieee80211_hw *dev)
 
 	ret = p54_parse_firmware(dev, priv->firmware);
 	if (ret) {
-		release_firmware(priv->firmware);
+		/* the firmware is released by the caller */
 		return ret;
 	}
 
@@ -659,6 +659,7 @@ static int p54spi_probe(struct spi_device *spi)
 	return 0;
 
 err_free_common:
+	release_firmware(priv->firmware);
 	free_irq(gpio_to_irq(p54spi_gpio_irq), spi);
 err_free_gpio_irq:
 	gpio_free(p54spi_gpio_irq);
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index c3189e2c7c93..52a2574b7d13 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -663,7 +663,7 @@ struct mac80211_hwsim_data {
 	bool ps_poll_pending;
 	struct dentry *debugfs;
 
-	uintptr_t pending_cookie;
+	atomic_t pending_cookie;
 	struct sk_buff_head pending;	/* packets pending */
 	/*
 	 * Only radios in the same group can communicate together (the
@@ -1339,8 +1339,7 @@ static void mac80211_hwsim_tx_frame_nl(struct ieee80211_hw *hw,
 		goto nla_put_failure;
 
 	/* We create a cookie to identify this skb */
-	data->pending_cookie++;
-	cookie = data->pending_cookie;
+	cookie = atomic_inc_return(&data->pending_cookie);
 	info->rate_driver_data[0] = (void *)cookie;
 	if (nla_put_u64_64bit(skb, HWSIM_ATTR_COOKIE, cookie, HWSIM_ATTR_PAD))
 		goto nla_put_failure;
@@ -3582,6 +3581,7 @@ static int hwsim_tx_info_frame_received_nl(struct sk_buff *skb_2,
 	const u8 *src;
 	unsigned int hwsim_flags;
 	int i;
+	unsigned long flags;
 	bool found = false;
 
 	if (!info->attrs[HWSIM_ATTR_ADDR_TRANSMITTER] ||
@@ -3609,18 +3609,20 @@ static int hwsim_tx_info_frame_received_nl(struct sk_buff *skb_2,
 	}
 
 	/* look for the skb matching the cookie passed back from user */
+	spin_lock_irqsave(&data2->pending.lock, flags);
 	skb_queue_walk_safe(&data2->pending, skb, tmp) {
-		u64 skb_cookie;
+		uintptr_t skb_cookie;
 
 		txi = IEEE80211_SKB_CB(skb);
-		skb_cookie = (u64)(uintptr_t)txi->rate_driver_data[0];
+		skb_cookie = (uintptr_t)txi->rate_driver_data[0];
 
 		if (skb_cookie == ret_skb_cookie) {
-			skb_unlink(skb, &data2->pending);
+			__skb_unlink(skb, &data2->pending);
 			found = true;
 			break;
 		}
 	}
+	spin_unlock_irqrestore(&data2->pending.lock, flags);
 
 	/* not found */
 	if (!found)
@@ -4276,6 +4278,10 @@ static int hwsim_virtio_handle_cmd(struct sk_buff *skb)
 
 	nlh = nlmsg_hdr(skb);
 	gnlh = nlmsg_data(nlh);
+
+	if (skb->len < nlh->nlmsg_len)
+		return -EINVAL;
+
 	err = genlmsg_parse(nlh, &hwsim_genl_family, tb, HWSIM_ATTR_MAX,
 			    hwsim_genl_policy, NULL);
 	if (err) {
@@ -4318,7 +4324,8 @@ static void hwsim_virtio_rx_work(struct work_struct *work)
 	spin_unlock_irqrestore(&hwsim_virtio_lock, flags);
 
 	skb->data = skb->head;
-	skb_set_tail_pointer(skb, len);
+	skb_reset_tail_pointer(skb);
+	skb_put(skb, len);
 	hwsim_virtio_handle_cmd(skb);
 
 	spin_lock_irqsave(&hwsim_virtio_lock, flags);
diff --git a/drivers/net/wireless/marvell/libertas/if_usb.c b/drivers/net/wireless/marvell/libertas/if_usb.c
index 5d6dc1dd050d..32fdc4150b60 100644
--- a/drivers/net/wireless/marvell/libertas/if_usb.c
+++ b/drivers/net/wireless/marvell/libertas/if_usb.c
@@ -287,6 +287,7 @@ static int if_usb_probe(struct usb_interface *intf,
 	return 0;
 
 err_get_fw:
+	usb_put_dev(udev);
 	lbs_remove_card(priv);
 err_add_card:
 	if_usb_reset_device(cardp);
diff --git a/drivers/net/wireless/marvell/mwifiex/main.h b/drivers/net/wireless/marvell/mwifiex/main.h
index 5923c5c14c8d..f4e3dce10d65 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.h
+++ b/drivers/net/wireless/marvell/mwifiex/main.h
@@ -1054,6 +1054,8 @@ struct mwifiex_adapter {
 	void *devdump_data;
 	int devdump_len;
 	struct timer_list devdump_timer;
+
+	bool ignore_btcoex_events;
 };
 
 void mwifiex_process_tx_queue(struct mwifiex_adapter *adapter);
diff --git a/drivers/net/wireless/marvell/mwifiex/pcie.c b/drivers/net/wireless/marvell/mwifiex/pcie.c
index c3f5583ea70d..d5fb29400bad 100644
--- a/drivers/net/wireless/marvell/mwifiex/pcie.c
+++ b/drivers/net/wireless/marvell/mwifiex/pcie.c
@@ -3152,6 +3152,9 @@ static int mwifiex_init_pcie(struct mwifiex_adapter *adapter)
 	if (ret)
 		goto err_alloc_buffers;
 
+	if (pdev->device == PCIE_DEVICE_ID_MARVELL_88W8897)
+		adapter->ignore_btcoex_events = true;
+
 	return 0;
 
 err_alloc_buffers:
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_event.c b/drivers/net/wireless/marvell/mwifiex/sta_event.c
index 2b2e6e0166e1..7d42c5d2dbf6 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_event.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_event.c
@@ -1062,6 +1062,9 @@ int mwifiex_process_sta_event(struct mwifiex_private *priv)
 		break;
 	case EVENT_BT_COEX_WLAN_PARA_CHANGE:
 		dev_dbg(adapter->dev, "EVENT: BT coex wlan param update\n");
+		if (adapter->ignore_btcoex_events)
+			break;
+
 		mwifiex_bt_coex_wlan_param_update_event(priv,
 							adapter->event_skb);
 		break;
diff --git a/drivers/net/wireless/mediatek/mt76/eeprom.c b/drivers/net/wireless/mediatek/mt76/eeprom.c
index 3b47e85e95e7..db0cd56c8dc7 100644
--- a/drivers/net/wireless/mediatek/mt76/eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/eeprom.c
@@ -146,10 +146,13 @@ mt76_find_power_limits_node(struct mt76_dev *dev)
 		}
 
 		if (mt76_string_prop_find(country, dev->alpha2) ||
-		    mt76_string_prop_find(regd, region_name))
+		    mt76_string_prop_find(regd, region_name)) {
+			of_node_put(np);
 			return cur;
+		}
 	}
 
+	of_node_put(np);
 	return fallback;
 }
 
diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index d03aedc3286b..028519a739fd 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -123,6 +123,7 @@ static int mt76_led_init(struct mt76_dev *dev)
 		if (!of_property_read_u32(np, "led-sources", &led_pin))
 			dev->led_pin = led_pin;
 		dev->led_al = of_property_read_bool(np, "led-active-low");
+		of_node_put(np);
 	}
 
 	return led_classdev_register(dev->dev, &dev->led_cdev);
@@ -1100,7 +1101,7 @@ mt76_sta_add(struct mt76_dev *dev, struct ieee80211_vif *vif,
 			continue;
 
 		mtxq = (struct mt76_txq *)sta->txq[i]->drv_priv;
-		mtxq->wcid = wcid;
+		mtxq->wcid = wcid->idx;
 	}
 
 	ewma_signal_init(&wcid->rssi);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 6e4d69715927..d1f00706d41e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -263,7 +263,7 @@ struct mt76_wcid {
 };
 
 struct mt76_txq {
-	struct mt76_wcid *wcid;
+	u16 wcid;
 
 	u16 agg_ssn;
 	bool send_bar;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/main.c b/drivers/net/wireless/mediatek/mt76/mt7603/main.c
index 7f52a4a11cea..0b7b87b4cc21 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/main.c
@@ -74,7 +74,7 @@ mt7603_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 	mt7603_wtbl_init(dev, idx, mvif->idx, bc_addr);
 
 	mtxq = (struct mt76_txq *)vif->txq->drv_priv;
-	mtxq->wcid = &mvif->sta.wcid;
+	mtxq->wcid = idx;
 	rcu_assign_pointer(dev->mt76.wcid[idx], &mvif->sta.wcid);
 
 out:
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/main.c b/drivers/net/wireless/mediatek/mt76/mt7615/main.c
index 60a41d082961..7c52a4d85cea 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/main.c
@@ -235,7 +235,7 @@ static int mt7615_add_interface(struct ieee80211_hw *hw,
 	rcu_assign_pointer(dev->mt76.wcid[idx], &mvif->sta.wcid);
 	if (vif->txq) {
 		mtxq = (struct mt76_txq *)vif->txq->drv_priv;
-		mtxq->wcid = &mvif->sta.wcid;
+		mtxq->wcid = idx;
 	}
 
 	ret = mt7615_mcu_add_dev_info(phy, vif, true);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
index 4fed3afad67c..bde65af72fed 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
@@ -385,10 +385,11 @@ static int mt7615_mcu_fw_pmctrl(struct mt7615_dev *dev)
 	}
 
 	mt7622_trigger_hif_int(dev, false);
-
-	pm->stats.last_doze_event = jiffies;
-	pm->stats.awake_time += pm->stats.last_doze_event -
-				pm->stats.last_wake_event;
+	if (!err) {
+		pm->stats.last_doze_event = jiffies;
+		pm->stats.awake_time += pm->stats.last_doze_event -
+					pm->stats.last_wake_event;
+	}
 out:
 	mutex_unlock(&pm->mutex);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
index af43bcb54578..306e9eaea917 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
@@ -7,9 +7,6 @@ int mt76_connac_pm_wake(struct mt76_phy *phy, struct mt76_connac_pm *pm)
 {
 	struct mt76_dev *dev = phy->dev;
 
-	if (!pm->enable)
-		return 0;
-
 	if (mt76_is_usb(dev))
 		return 0;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
index 77d4435e4581..72a70a7046fb 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
@@ -556,7 +556,7 @@ enum {
 	MCU_CMD_SET_BSS_CONNECTED = MCU_CE_PREFIX | 0x16,
 	MCU_CMD_SET_BSS_ABORT = MCU_CE_PREFIX | 0x17,
 	MCU_CMD_CANCEL_HW_SCAN = MCU_CE_PREFIX | 0x1b,
-	MCU_CMD_SET_ROC = MCU_CE_PREFIX | 0x1d,
+	MCU_CMD_SET_ROC = MCU_CE_PREFIX | 0x1c,
 	MCU_CMD_SET_P2P_OPPPS = MCU_CE_PREFIX | 0x33,
 	MCU_CMD_SET_RATE_TX_POWER = MCU_CE_PREFIX | 0x5d,
 	MCU_CMD_SCHED_SCAN_ENABLE = MCU_CE_PREFIX | 0x61,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_mcu.c
index 2953df7d8388..c6c16fe8ee85 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_mcu.c
@@ -108,7 +108,7 @@ __mt76x02u_mcu_send_msg(struct mt76_dev *dev, struct sk_buff *skb,
 	ret = mt76u_bulk_msg(dev, skb->data, skb->len, NULL, 500,
 			     MT_EP_OUT_INBAND_CMD);
 	if (ret)
-		return ret;
+		goto out;
 
 	if (wait_resp)
 		ret = mt76x02u_mcu_wait_resp(dev, seq);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
index ccdbab341271..db7a4ffcad55 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
@@ -288,7 +288,8 @@ mt76x02_vif_init(struct mt76x02_dev *dev, struct ieee80211_vif *vif,
 	mvif->group_wcid.idx = MT_VIF_WCID(idx);
 	mvif->group_wcid.hw_key_idx = -1;
 	mtxq = (struct mt76_txq *)vif->txq->drv_priv;
-	mtxq->wcid = &mvif->group_wcid;
+	rcu_assign_pointer(dev->mt76.wcid[MT_VIF_WCID(idx)], &mvif->group_wcid);
+	mtxq->wcid = MT_VIF_WCID(idx);
 }
 
 int
@@ -341,6 +342,7 @@ void mt76x02_remove_interface(struct ieee80211_hw *hw,
 	struct mt76x02_vif *mvif = (struct mt76x02_vif *)vif->drv_priv;
 
 	dev->mt76.vif_mask &= ~BIT(mvif->idx);
+	rcu_assign_pointer(dev->mt76.wcid[mvif->group_wcid.idx], NULL);
 }
 EXPORT_SYMBOL_GPL(mt76x02_remove_interface);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/init.c b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
index b171027e0cfa..1ae42ef147c8 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
@@ -217,8 +217,8 @@ mt7915_init_wiphy(struct ieee80211_hw *hw)
 	struct wiphy *wiphy = hw->wiphy;
 
 	hw->queues = 4;
-	hw->max_rx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF;
-	hw->max_tx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF;
+	hw->max_rx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF_HE;
+	hw->max_tx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF_HE;
 	hw->netdev_features = NETIF_F_RXCSUM;
 
 	hw->radiotap_timestamp.units_pos =
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
index c25f8da590dd..6aca470e2401 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
@@ -243,7 +243,7 @@ static int mt7915_add_interface(struct ieee80211_hw *hw,
 	rcu_assign_pointer(dev->mt76.wcid[idx], &mvif->sta.wcid);
 	if (vif->txq) {
 		mtxq = (struct mt76_txq *)vif->txq->drv_priv;
-		mtxq->wcid = &mvif->sta.wcid;
+		mtxq->wcid = idx;
 	}
 
 	if (vif->type != NL80211_IFTYPE_AP &&
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c
index 8d5e261cd10f..cfcf7964c688 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c
@@ -262,31 +262,44 @@ mt7921_txpwr(struct seq_file *s, void *data)
 	return 0;
 }
 
+static void
+mt7921_pm_interface_iter(void *priv, u8 *mac, struct ieee80211_vif *vif)
+{
+	struct mt7921_dev *dev = priv;
+
+	mt7921_mcu_set_beacon_filter(dev, vif, dev->pm.enable);
+}
+
 static int
 mt7921_pm_set(void *data, u64 val)
 {
 	struct mt7921_dev *dev = data;
 	struct mt76_connac_pm *pm = &dev->pm;
-	struct mt76_phy *mphy = dev->phy.mt76;
 
-	if (val == pm->enable)
-		return 0;
+	mutex_lock(&dev->mt76.mutex);
 
-	mt7921_mutex_acquire(dev);
+	if (val == pm->enable)
+		goto out;
 
 	if (!pm->enable) {
 		pm->stats.last_wake_event = jiffies;
 		pm->stats.last_doze_event = jiffies;
 	}
-	pm->enable = val;
+	/* make sure the chip is awake here and ps_work is scheduled
+	 * just at end of the this routine.
+	 */
+	pm->enable = false;
+	mt76_connac_pm_wake(&dev->mphy, pm);
 
-	ieee80211_iterate_active_interfaces(mphy->hw,
+	pm->enable = val;
+	ieee80211_iterate_active_interfaces(mt76_hw(dev),
 					    IEEE80211_IFACE_ITER_RESUME_ALL,
-					    mt7921_pm_interface_iter, mphy->priv);
+					    mt7921_pm_interface_iter, dev);
 
 	mt76_connac_mcu_set_deep_sleep(&dev->mt76, pm->ds_enable);
-
-	mt7921_mutex_release(dev);
+	mt76_connac_power_save_sched(&dev->mphy, pm);
+out:
+	mutex_unlock(&dev->mt76.mutex);
 
 	return 0;
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
index 78a00028137b..c059cb419efd 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
@@ -49,8 +49,8 @@ mt7921_init_wiphy(struct ieee80211_hw *hw)
 	struct wiphy *wiphy = hw->wiphy;
 
 	hw->queues = 4;
-	hw->max_rx_aggregation_subframes = 64;
-	hw->max_tx_aggregation_subframes = 128;
+	hw->max_rx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF_HE;
+	hw->max_tx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF_HE;
 	hw->netdev_features = NETIF_F_RXCSUM;
 
 	hw->radiotap_timestamp.units_pos =
@@ -219,7 +219,7 @@ int mt7921_register_device(struct mt7921_dev *dev)
 			IEEE80211_HT_CAP_LDPC_CODING |
 			IEEE80211_HT_CAP_MAX_AMSDU;
 	dev->mphy.sband_5g.sband.vht_cap.cap |=
-			IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 |
+			IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 |
 			IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK |
 			IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE |
 			IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE |
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
index bef8d4a76ed9..426e7a32bdc8 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
@@ -1573,34 +1573,6 @@ out:
 	queue_delayed_work(dev->mt76.wq, &dev->pm.ps_work, delta);
 }
 
-int mt7921_mac_set_beacon_filter(struct mt7921_phy *phy,
-				 struct ieee80211_vif *vif,
-				 bool enable)
-{
-	struct mt7921_dev *dev = phy->dev;
-	bool ext_phy = phy != &dev->phy;
-	int err;
-
-	if (!dev->pm.enable)
-		return -EOPNOTSUPP;
-
-	err = mt7921_mcu_set_bss_pm(dev, vif, enable);
-	if (err)
-		return err;
-
-	if (enable) {
-		vif->driver_flags |= IEEE80211_VIF_BEACON_FILTER;
-		mt76_set(dev, MT_WF_RFCR(ext_phy),
-			 MT_WF_RFCR_DROP_OTHER_BEACON);
-	} else {
-		vif->driver_flags &= ~IEEE80211_VIF_BEACON_FILTER;
-		mt76_clear(dev, MT_WF_RFCR(ext_phy),
-			   MT_WF_RFCR_DROP_OTHER_BEACON);
-	}
-
-	return 0;
-}
-
 void mt7921_coredump_work(struct work_struct *work)
 {
 	struct mt7921_dev *dev;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index 30252f408ddc..6cb65391427f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -283,7 +283,7 @@ static int mt7921_add_interface(struct ieee80211_hw *hw,
 	rcu_assign_pointer(dev->mt76.wcid[idx], &mvif->sta.wcid);
 	if (vif->txq) {
 		mtxq = (struct mt76_txq *)vif->txq->drv_priv;
-		mtxq->wcid = &mvif->sta.wcid;
+		mtxq->wcid = idx;
 	}
 
 out:
@@ -528,36 +528,6 @@ static void mt7921_configure_filter(struct ieee80211_hw *hw,
 	mt7921_mutex_release(dev);
 }
 
-static int
-mt7921_bss_bcnft_apply(struct mt7921_dev *dev, struct ieee80211_vif *vif,
-		       bool assoc)
-{
-	int ret;
-
-	if (!dev->pm.enable)
-		return 0;
-
-	if (assoc) {
-		ret = mt7921_mcu_uni_bss_bcnft(dev, vif, true);
-		if (ret)
-			return ret;
-
-		vif->driver_flags |= IEEE80211_VIF_BEACON_FILTER;
-		mt76_set(dev, MT_WF_RFCR(0), MT_WF_RFCR_DROP_OTHER_BEACON);
-
-		return 0;
-	}
-
-	ret = mt7921_mcu_set_bss_pm(dev, vif, false);
-	if (ret)
-		return ret;
-
-	vif->driver_flags &= ~IEEE80211_VIF_BEACON_FILTER;
-	mt76_clear(dev, MT_WF_RFCR(0), MT_WF_RFCR_DROP_OTHER_BEACON);
-
-	return 0;
-}
-
 static void mt7921_bss_info_changed(struct ieee80211_hw *hw,
 				    struct ieee80211_vif *vif,
 				    struct ieee80211_bss_conf *info,
@@ -587,7 +557,8 @@ static void mt7921_bss_info_changed(struct ieee80211_hw *hw,
 	if (changed & BSS_CHANGED_ASSOC) {
 		mt7921_mcu_sta_update(dev, NULL, vif, true,
 				      MT76_STA_INFO_STATE_ASSOC);
-		mt7921_bss_bcnft_apply(dev, vif, info->assoc);
+		if (dev->pm.enable)
+			mt7921_mcu_set_beacon_filter(dev, vif, info->assoc);
 	}
 
 	if (changed & BSS_CHANGED_ARP_FILTER) {
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
index 4119f8efd896..9b490ff36bd6 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
@@ -1205,8 +1205,9 @@ int mt7921_mcu_uni_bss_ps(struct mt7921_dev *dev, struct ieee80211_vif *vif)
 				 &ps_req, sizeof(ps_req), true);
 }
 
-int mt7921_mcu_uni_bss_bcnft(struct mt7921_dev *dev, struct ieee80211_vif *vif,
-			     bool enable)
+static int
+mt7921_mcu_uni_bss_bcnft(struct mt7921_dev *dev, struct ieee80211_vif *vif,
+			 bool enable)
 {
 	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
 	struct {
@@ -1240,8 +1241,9 @@ int mt7921_mcu_uni_bss_bcnft(struct mt7921_dev *dev, struct ieee80211_vif *vif,
 				 &bcnft_req, sizeof(bcnft_req), true);
 }
 
-int mt7921_mcu_set_bss_pm(struct mt7921_dev *dev, struct ieee80211_vif *vif,
-			  bool enable)
+static int
+mt7921_mcu_set_bss_pm(struct mt7921_dev *dev, struct ieee80211_vif *vif,
+		      bool enable)
 {
 	struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv;
 	struct {
@@ -1304,7 +1306,7 @@ int mt7921_mcu_sta_update(struct mt7921_dev *dev, struct ieee80211_sta *sta,
 	return mt76_connac_mcu_sta_cmd(&dev->mphy, &info);
 }
 
-int __mt7921_mcu_drv_pmctrl(struct mt7921_dev *dev)
+int __mt7921e_mcu_drv_pmctrl(struct mt7921_dev *dev)
 {
 	int i, err = 0;
 
@@ -1323,28 +1325,38 @@ int __mt7921_mcu_drv_pmctrl(struct mt7921_dev *dev)
 	return err;
 }
 
-int mt7921_mcu_drv_pmctrl(struct mt7921_dev *dev)
+int __mt7921_mcu_drv_pmctrl(struct mt7921_dev *dev)
 {
 	struct mt76_phy *mphy = &dev->mt76.phy;
 	struct mt76_connac_pm *pm = &dev->pm;
-	int err = 0;
-
-	mutex_lock(&pm->mutex);
+	int err;
 
-	if (!test_bit(MT76_STATE_PM, &mphy->state))
+	err = __mt7921e_mcu_drv_pmctrl(dev);
+	if (err < 0)
 		goto out;
 
-	err = __mt7921_mcu_drv_pmctrl(dev);
-        if (err < 0)
-            goto out;
-
 	mt7921_wpdma_reinit_cond(dev);
 	clear_bit(MT76_STATE_PM, &mphy->state);
 
 	pm->stats.last_wake_event = jiffies;
 	pm->stats.doze_time += pm->stats.last_wake_event -
 			       pm->stats.last_doze_event;
+out:
+	return err;
+}
 
+int mt7921_mcu_drv_pmctrl(struct mt7921_dev *dev)
+{
+	struct mt76_phy *mphy = &dev->mt76.phy;
+	struct mt76_connac_pm *pm = &dev->pm;
+	int err = 0;
+
+	mutex_lock(&pm->mutex);
+
+	if (!test_bit(MT76_STATE_PM, &mphy->state))
+		goto out;
+
+	err = __mt7921_mcu_drv_pmctrl(dev);
 out:
 	mutex_unlock(&pm->mutex);
 
@@ -1390,31 +1402,34 @@ out:
 	return err;
 }
 
-void
-mt7921_pm_interface_iter(void *priv, u8 *mac, struct ieee80211_vif *vif)
+int mt7921_mcu_set_beacon_filter(struct mt7921_dev *dev,
+				 struct ieee80211_vif *vif,
+				 bool enable)
 {
-	struct mt7921_phy *phy = priv;
-	struct mt7921_dev *dev = phy->dev;
 	struct ieee80211_hw *hw = mt76_hw(dev);
-	int ret;
-
-	if (dev->pm.enable)
-		ret = mt7921_mcu_uni_bss_bcnft(dev, vif, true);
-	else
-		ret = mt7921_mcu_set_bss_pm(dev, vif, false);
+	int err;
 
-	if (ret)
-		return;
+	if (enable) {
+		err = mt7921_mcu_uni_bss_bcnft(dev, vif, true);
+		if (err)
+			return err;
 
-	if (dev->pm.enable) {
 		vif->driver_flags |= IEEE80211_VIF_BEACON_FILTER;
 		ieee80211_hw_set(hw, CONNECTION_MONITOR);
 		mt76_set(dev, MT_WF_RFCR(0), MT_WF_RFCR_DROP_OTHER_BEACON);
-	} else {
-		vif->driver_flags &= ~IEEE80211_VIF_BEACON_FILTER;
-		__clear_bit(IEEE80211_HW_CONNECTION_MONITOR, hw->flags);
-		mt76_clear(dev, MT_WF_RFCR(0), MT_WF_RFCR_DROP_OTHER_BEACON);
+
+		return 0;
 	}
+
+	err = mt7921_mcu_set_bss_pm(dev, vif, false);
+	if (err)
+		return err;
+
+	vif->driver_flags &= ~IEEE80211_VIF_BEACON_FILTER;
+	__clear_bit(IEEE80211_HW_CONNECTION_MONITOR, hw->flags);
+	mt76_clear(dev, MT_WF_RFCR(0), MT_WF_RFCR_DROP_OTHER_BEACON);
+
+	return 0;
 }
 
 int mt7921_get_txpwr_info(struct mt7921_dev *dev, struct mt7921_txpwr *txpwr)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index 2d8bd6bfc820..6eb03d6705a1 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -363,6 +363,9 @@ void mt7921_set_stream_he_caps(struct mt7921_phy *phy);
 void mt7921_update_channel(struct mt76_phy *mphy);
 int mt7921_init_debugfs(struct mt7921_dev *dev);
 
+int mt7921_mcu_set_beacon_filter(struct mt7921_dev *dev,
+				 struct ieee80211_vif *vif,
+				 bool enable);
 int mt7921_mcu_uni_tx_ba(struct mt7921_dev *dev,
 			 struct ieee80211_ampdu_params *params,
 			 bool enable);
@@ -371,20 +374,13 @@ int mt7921_mcu_uni_rx_ba(struct mt7921_dev *dev,
 			 bool enable);
 void mt7921_scan_work(struct work_struct *work);
 int mt7921_mcu_uni_bss_ps(struct mt7921_dev *dev, struct ieee80211_vif *vif);
-int mt7921_mcu_uni_bss_bcnft(struct mt7921_dev *dev, struct ieee80211_vif *vif,
-			     bool enable);
-int mt7921_mcu_set_bss_pm(struct mt7921_dev *dev, struct ieee80211_vif *vif,
-			  bool enable);
+int __mt7921e_mcu_drv_pmctrl(struct mt7921_dev *dev);
 int __mt7921_mcu_drv_pmctrl(struct mt7921_dev *dev);
 int mt7921_mcu_drv_pmctrl(struct mt7921_dev *dev);
 int mt7921_mcu_fw_pmctrl(struct mt7921_dev *dev);
 void mt7921_pm_wake_work(struct work_struct *work);
 void mt7921_pm_power_save_work(struct work_struct *work);
 bool mt7921_wait_for_mcu_init(struct mt7921_dev *dev);
-int mt7921_mac_set_beacon_filter(struct mt7921_phy *phy,
-				 struct ieee80211_vif *vif,
-				 bool enable);
-void mt7921_pm_interface_iter(void *priv, u8 *mac, struct ieee80211_vif *vif);
 void mt7921_coredump_work(struct work_struct *work);
 int mt7921_wfsys_reset(struct mt7921_dev *dev);
 int mt7921_get_txpwr_info(struct mt7921_dev *dev, struct mt7921_txpwr *txpwr);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
index 3d35838ef306..36e6495ae658 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
@@ -95,36 +95,37 @@ static u32 __mt7921_reg_addr(struct mt7921_dev *dev, u32 addr)
 		u32 mapped;
 		u32 size;
 	} fixed_map[] = {
-		{ 0x00400000, 0x80000, 0x10000}, /* WF_MCU_SYSRAM */
-		{ 0x00410000, 0x90000, 0x10000}, /* WF_MCU_SYSRAM (configure register) */
-		{ 0x40000000, 0x70000, 0x10000}, /* WF_UMAC_SYSRAM */
+		{ 0x820d0000, 0x30000, 0x10000 }, /* WF_LMAC_TOP (WF_WTBLON) */
+		{ 0x820ed000, 0x24800, 0x0800 }, /* WF_LMAC_TOP BN0 (WF_MIB) */
+		{ 0x820e4000, 0x21000, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_TMAC) */
+		{ 0x820e7000, 0x21e00, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_DMA) */
+		{ 0x820eb000, 0x24200, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_LPON) */
+		{ 0x820e2000, 0x20800, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_AGG) */
+		{ 0x820e3000, 0x20c00, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_ARB) */
+		{ 0x820e5000, 0x21400, 0x0800 }, /* WF_LMAC_TOP BN0 (WF_RMAC) */
+		{ 0x00400000, 0x80000, 0x10000 }, /* WF_MCU_SYSRAM */
+		{ 0x00410000, 0x90000, 0x10000 }, /* WF_MCU_SYSRAM (configure register) */
+		{ 0x40000000, 0x70000, 0x10000 }, /* WF_UMAC_SYSRAM */
 		{ 0x54000000, 0x02000, 0x1000 }, /* WFDMA PCIE0 MCU DMA0 */
 		{ 0x55000000, 0x03000, 0x1000 }, /* WFDMA PCIE0 MCU DMA1 */
 		{ 0x58000000, 0x06000, 0x1000 }, /* WFDMA PCIE1 MCU DMA0 (MEM_DMA) */
 		{ 0x59000000, 0x07000, 0x1000 }, /* WFDMA PCIE1 MCU DMA1 */
 		{ 0x7c000000, 0xf0000, 0x10000 }, /* CONN_INFRA */
 		{ 0x7c020000, 0xd0000, 0x10000 }, /* CONN_INFRA, WFDMA */
-		{ 0x7c060000, 0xe0000, 0x10000}, /* CONN_INFRA, conn_host_csr_top */
+		{ 0x7c060000, 0xe0000, 0x10000 }, /* CONN_INFRA, conn_host_csr_top */
 		{ 0x80020000, 0xb0000, 0x10000 }, /* WF_TOP_MISC_OFF */
 		{ 0x81020000, 0xc0000, 0x10000 }, /* WF_TOP_MISC_ON */
 		{ 0x820c0000, 0x08000, 0x4000 }, /* WF_UMAC_TOP (PLE) */
 		{ 0x820c8000, 0x0c000, 0x2000 }, /* WF_UMAC_TOP (PSE) */
-		{ 0x820cc000, 0x0e000, 0x2000 }, /* WF_UMAC_TOP (PP) */
+		{ 0x820cc000, 0x0e000, 0x1000 }, /* WF_UMAC_TOP (PP) */
+		{ 0x820cd000, 0x0f000, 0x1000 }, /* WF_MDP_TOP */
 		{ 0x820ce000, 0x21c00, 0x0200 }, /* WF_LMAC_TOP (WF_SEC) */
 		{ 0x820cf000, 0x22000, 0x1000 }, /* WF_LMAC_TOP (WF_PF) */
-		{ 0x820d0000, 0x30000, 0x10000 }, /* WF_LMAC_TOP (WF_WTBLON) */
 		{ 0x820e0000, 0x20000, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_CFG) */
 		{ 0x820e1000, 0x20400, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_TRB) */
-		{ 0x820e2000, 0x20800, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_AGG) */
-		{ 0x820e3000, 0x20c00, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_ARB) */
-		{ 0x820e4000, 0x21000, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_TMAC) */
-		{ 0x820e5000, 0x21400, 0x0800 }, /* WF_LMAC_TOP BN0 (WF_RMAC) */
-		{ 0x820e7000, 0x21e00, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_DMA) */
 		{ 0x820e9000, 0x23400, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_WTBLOFF) */
 		{ 0x820ea000, 0x24000, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_ETBF) */
-		{ 0x820eb000, 0x24200, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_LPON) */
 		{ 0x820ec000, 0x24600, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_INT) */
-		{ 0x820ed000, 0x24800, 0x0800 }, /* WF_LMAC_TOP BN0 (WF_MIB) */
 		{ 0x820f0000, 0xa0000, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_CFG) */
 		{ 0x820f1000, 0xa0600, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_TRB) */
 		{ 0x820f2000, 0xa0800, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_AGG) */
@@ -191,7 +192,6 @@ static u32 mt7921_rmw(struct mt76_dev *mdev, u32 offset, u32 mask, u32 val)
 	return dev->bus_ops->rmw(mdev, addr, mask, val);
 }
 
-
 static int mt7921_pci_probe(struct pci_dev *pdev,
 			    const struct pci_device_id *id)
 {
@@ -264,7 +264,7 @@ static int mt7921_pci_probe(struct pci_dev *pdev,
 	bus_ops->rmw = mt7921_rmw;
 	dev->mt76.bus = bus_ops;
 
-	ret = __mt7921_mcu_drv_pmctrl(dev);
+	ret = __mt7921e_mcu_drv_pmctrl(dev);
 	if (ret)
 		goto err_free_dev;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/regs.h b/drivers/net/wireless/mediatek/mt76/mt7921/regs.h
index 41c2855e7a3d..9266fb3909ca 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/regs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/regs.h
@@ -14,7 +14,7 @@
 #define MT_MCU_INT_EVENT_SER_TRIGGER	BIT(2)
 #define MT_MCU_INT_EVENT_RESET_DONE	BIT(3)
 
-#define MT_PLE_BASE			0x8000
+#define MT_PLE_BASE			0x820c0000
 #define MT_PLE(ofs)			(MT_PLE_BASE + (ofs))
 
 #define MT_PLE_FL_Q0_CTRL		MT_PLE(0x3e0)
@@ -25,7 +25,7 @@
 #define MT_PLE_AC_QEMPTY(_n)		MT_PLE(0x500 + 0x40 * (_n))
 #define MT_PLE_AMSDU_PACK_MSDU_CNT(n)	MT_PLE(0x10e0 + ((n) << 2))
 
-#define MT_MDP_BASE			0xf000
+#define MT_MDP_BASE			0x820cd000
 #define MT_MDP(ofs)			(MT_MDP_BASE + (ofs))
 
 #define MT_MDP_DCR0			MT_MDP(0x000)
@@ -48,7 +48,7 @@
 #define MT_MDP_TO_WM			1
 
 /* TMAC: band 0(0x21000), band 1(0xa1000) */
-#define MT_WF_TMAC_BASE(_band)		((_band) ? 0xa1000 : 0x21000)
+#define MT_WF_TMAC_BASE(_band)		((_band) ? 0x820f4000 : 0x820e4000)
 #define MT_WF_TMAC(_band, ofs)		(MT_WF_TMAC_BASE(_band) + (ofs))
 
 #define MT_TMAC_TCR0(_band)		MT_WF_TMAC(_band, 0)
@@ -73,7 +73,7 @@
 #define MT_TMAC_TRCR0(_band)		MT_WF_TMAC(_band, 0x09c)
 #define MT_TMAC_TFCR0(_band)		MT_WF_TMAC(_band, 0x1e0)
 
-#define MT_WF_DMA_BASE(_band)		((_band) ? 0xa1e00 : 0x21e00)
+#define MT_WF_DMA_BASE(_band)		((_band) ? 0x820f7000 : 0x820e7000)
 #define MT_WF_DMA(_band, ofs)		(MT_WF_DMA_BASE(_band) + (ofs))
 
 #define MT_DMA_DCR0(_band)		MT_WF_DMA(_band, 0x000)
@@ -81,7 +81,7 @@
 #define MT_DMA_DCR0_RXD_G5_EN		BIT(23)
 
 /* LPON: band 0(0x24200), band 1(0xa4200) */
-#define MT_WF_LPON_BASE(_band)		((_band) ? 0xa4200 : 0x24200)
+#define MT_WF_LPON_BASE(_band)		((_band) ? 0x820fb000 : 0x820eb000)
 #define MT_WF_LPON(_band, ofs)		(MT_WF_LPON_BASE(_band) + (ofs))
 
 #define MT_LPON_UTTR0(_band)		MT_WF_LPON(_band, 0x080)
@@ -92,7 +92,7 @@
 #define MT_LPON_TCR_SW_WRITE		BIT(0)
 
 /* MIB: band 0(0x24800), band 1(0xa4800) */
-#define MT_WF_MIB_BASE(_band)		((_band) ? 0xa4800 : 0x24800)
+#define MT_WF_MIB_BASE(_band)		((_band) ? 0x820fd000 : 0x820ed000)
 #define MT_WF_MIB(_band, ofs)		(MT_WF_MIB_BASE(_band) + (ofs))
 
 #define MT_MIB_SCR1(_band)		MT_WF_MIB(_band, 0x004)
@@ -141,7 +141,7 @@
 #define MT_MIB_ARNG(_band, n)		MT_WF_MIB(_band, 0x0b0 + ((n) << 2))
 #define MT_MIB_ARNCR_RANGE(val, n)	(((val) >> ((n) << 3)) & GENMASK(7, 0))
 
-#define MT_WTBLON_TOP_BASE		0x34000
+#define MT_WTBLON_TOP_BASE		0x820d4000
 #define MT_WTBLON_TOP(ofs)		(MT_WTBLON_TOP_BASE + (ofs))
 #define MT_WTBLON_TOP_WDUCR		MT_WTBLON_TOP(0x200)
 #define MT_WTBLON_TOP_WDUCR_GROUP	GENMASK(2, 0)
@@ -151,7 +151,7 @@
 #define MT_WTBL_UPDATE_ADM_COUNT_CLEAR	BIT(12)
 #define MT_WTBL_UPDATE_BUSY		BIT(31)
 
-#define MT_WTBL_BASE			0x38000
+#define MT_WTBL_BASE			0x820d8000
 #define MT_WTBL_LMAC_ID			GENMASK(14, 8)
 #define MT_WTBL_LMAC_DW			GENMASK(7, 2)
 #define MT_WTBL_LMAC_OFFS(_id, _dw)	(MT_WTBL_BASE | \
@@ -159,7 +159,7 @@
 					FIELD_PREP(MT_WTBL_LMAC_DW, _dw))
 
 /* AGG: band 0(0x20800), band 1(0xa0800) */
-#define MT_WF_AGG_BASE(_band)		((_band) ? 0xa0800 : 0x20800)
+#define MT_WF_AGG_BASE(_band)		((_band) ? 0x820f2000 : 0x820e2000)
 #define MT_WF_AGG(_band, ofs)		(MT_WF_AGG_BASE(_band) + (ofs))
 
 #define MT_AGG_AWSCR0(_band, _n)	MT_WF_AGG(_band, 0x05c + (_n) * 4)
@@ -190,7 +190,7 @@
 #define MT_AGG_ATCR3(_band)		MT_WF_AGG(_band, 0x0f4)
 
 /* ARB: band 0(0x20c00), band 1(0xa0c00) */
-#define MT_WF_ARB_BASE(_band)		((_band) ? 0xa0c00 : 0x20c00)
+#define MT_WF_ARB_BASE(_band)		((_band) ? 0x820f3000 : 0x820e3000)
 #define MT_WF_ARB(_band, ofs)		(MT_WF_ARB_BASE(_band) + (ofs))
 
 #define MT_ARB_SCR(_band)		MT_WF_ARB(_band, 0x080)
@@ -200,7 +200,7 @@
 #define MT_ARB_DRNGR0(_band, _n)	MT_WF_ARB(_band, 0x194 + (_n) * 4)
 
 /* RMAC: band 0(0x21400), band 1(0xa1400) */
-#define MT_WF_RMAC_BASE(_band)		((_band) ? 0xa1400 : 0x21400)
+#define MT_WF_RMAC_BASE(_band)		((_band) ? 0x820f5000 : 0x820e5000)
 #define MT_WF_RMAC(_band, ofs)		(MT_WF_RMAC_BASE(_band) + (ofs))
 
 #define MT_WF_RFCR(_band)		MT_WF_RMAC(_band, 0x000)
diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c
index f0f7a913eaab..dce6f6b5f071 100644
--- a/drivers/net/wireless/mediatek/mt76/tx.c
+++ b/drivers/net/wireless/mediatek/mt76/tx.c
@@ -406,12 +406,11 @@ mt76_txq_stopped(struct mt76_queue *q)
 
 static int
 mt76_txq_send_burst(struct mt76_phy *phy, struct mt76_queue *q,
-		    struct mt76_txq *mtxq)
+		    struct mt76_txq *mtxq, struct mt76_wcid *wcid)
 {
 	struct mt76_dev *dev = phy->dev;
 	struct ieee80211_txq *txq = mtxq_to_txq(mtxq);
 	enum mt76_txq_id qid = mt76_txq_get_qid(txq);
-	struct mt76_wcid *wcid = mtxq->wcid;
 	struct ieee80211_tx_info *info;
 	struct sk_buff *skb;
 	int n_frames = 1;
@@ -491,8 +490,8 @@ mt76_txq_schedule_list(struct mt76_phy *phy, enum mt76_txq_id qid)
 			break;
 
 		mtxq = (struct mt76_txq *)txq->drv_priv;
-		wcid = mtxq->wcid;
-		if (wcid && test_bit(MT_WCID_FLAG_PS, &wcid->flags))
+		wcid = rcu_dereference(dev->wcid[mtxq->wcid]);
+		if (!wcid || test_bit(MT_WCID_FLAG_PS, &wcid->flags))
 			continue;
 
 		spin_lock_bh(&q->lock);
@@ -511,7 +510,7 @@ mt76_txq_schedule_list(struct mt76_phy *phy, enum mt76_txq_id qid)
 		}
 
 		if (!mt76_txq_stopped(q))
-			n_frames = mt76_txq_send_burst(phy, q, mtxq);
+			n_frames = mt76_txq_send_burst(phy, q, mtxq, wcid);
 
 		spin_unlock_bh(&q->lock);
 
diff --git a/drivers/net/wireless/microchip/wilc1000/netdev.h b/drivers/net/wireless/microchip/wilc1000/netdev.h
index 86209b391a3d..e6e23fc585ee 100644
--- a/drivers/net/wireless/microchip/wilc1000/netdev.h
+++ b/drivers/net/wireless/microchip/wilc1000/netdev.h
@@ -252,6 +252,7 @@ struct wilc {
 	u8 *rx_buffer;
 	u32 rx_buffer_offset;
 	u8 *tx_buffer;
+	u32 *vmm_table;
 
 	struct txq_handle txq[NQUEUES];
 	int txq_entries;
diff --git a/drivers/net/wireless/microchip/wilc1000/sdio.c b/drivers/net/wireless/microchip/wilc1000/sdio.c
index 8b3b73523108..6c0727fc4abd 100644
--- a/drivers/net/wireless/microchip/wilc1000/sdio.c
+++ b/drivers/net/wireless/microchip/wilc1000/sdio.c
@@ -27,6 +27,7 @@ struct wilc_sdio {
 	bool irq_gpio;
 	u32 block_size;
 	int has_thrpt_enh3;
+	u8 *cmd53_buf;
 };
 
 struct sdio_cmd52 {
@@ -46,6 +47,7 @@ struct sdio_cmd53 {
 	u32 count:		9;
 	u8 *buffer;
 	u32 block_size;
+	bool use_global_buf;
 };
 
 static const struct wilc_hif_func wilc_hif_sdio;
@@ -90,6 +92,8 @@ static int wilc_sdio_cmd53(struct wilc *wilc, struct sdio_cmd53 *cmd)
 {
 	struct sdio_func *func = container_of(wilc->dev, struct sdio_func, dev);
 	int size, ret;
+	struct wilc_sdio *sdio_priv = wilc->bus_data;
+	u8 *buf = cmd->buffer;
 
 	sdio_claim_host(func);
 
@@ -100,12 +104,23 @@ static int wilc_sdio_cmd53(struct wilc *wilc, struct sdio_cmd53 *cmd)
 	else
 		size = cmd->count;
 
+	if (cmd->use_global_buf) {
+		if (size > sizeof(u32))
+			return -EINVAL;
+
+		buf = sdio_priv->cmd53_buf;
+	}
+
 	if (cmd->read_write) {  /* write */
-		ret = sdio_memcpy_toio(func, cmd->address,
-				       (void *)cmd->buffer, size);
+		if (cmd->use_global_buf)
+			memcpy(buf, cmd->buffer, size);
+
+		ret = sdio_memcpy_toio(func, cmd->address, buf, size);
 	} else {        /* read */
-		ret = sdio_memcpy_fromio(func, (void *)cmd->buffer,
-					 cmd->address,  size);
+		ret = sdio_memcpy_fromio(func, buf, cmd->address, size);
+
+		if (cmd->use_global_buf)
+			memcpy(cmd->buffer, buf, size);
 	}
 
 	sdio_release_host(func);
@@ -127,6 +142,12 @@ static int wilc_sdio_probe(struct sdio_func *func,
 	if (!sdio_priv)
 		return -ENOMEM;
 
+	sdio_priv->cmd53_buf = kzalloc(sizeof(u32), GFP_KERNEL);
+	if (!sdio_priv->cmd53_buf) {
+		ret = -ENOMEM;
+		goto free;
+	}
+
 	ret = wilc_cfg80211_init(&wilc, &func->dev, WILC_HIF_SDIO,
 				 &wilc_hif_sdio);
 	if (ret)
@@ -160,6 +181,7 @@ dispose_irq:
 	irq_dispose_mapping(wilc->dev_irq_num);
 	wilc_netdev_cleanup(wilc);
 free:
+	kfree(sdio_priv->cmd53_buf);
 	kfree(sdio_priv);
 	return ret;
 }
@@ -171,6 +193,7 @@ static void wilc_sdio_remove(struct sdio_func *func)
 
 	clk_disable_unprepare(wilc->rtc_clk);
 	wilc_netdev_cleanup(wilc);
+	kfree(sdio_priv->cmd53_buf);
 	kfree(sdio_priv);
 }
 
@@ -367,8 +390,9 @@ static int wilc_sdio_write_reg(struct wilc *wilc, u32 addr, u32 data)
 		cmd.address = WILC_SDIO_FBR_DATA_REG;
 		cmd.block_mode = 0;
 		cmd.increment = 1;
-		cmd.count = 4;
+		cmd.count = sizeof(u32);
 		cmd.buffer = (u8 *)&data;
+		cmd.use_global_buf = true;
 		cmd.block_size = sdio_priv->block_size;
 		ret = wilc_sdio_cmd53(wilc, &cmd);
 		if (ret)
@@ -406,6 +430,7 @@ static int wilc_sdio_write(struct wilc *wilc, u32 addr, u8 *buf, u32 size)
 	nblk = size / block_size;
 	nleft = size % block_size;
 
+	cmd.use_global_buf = false;
 	if (nblk > 0) {
 		cmd.block_mode = 1;
 		cmd.increment = 1;
@@ -484,8 +509,9 @@ static int wilc_sdio_read_reg(struct wilc *wilc, u32 addr, u32 *data)
 		cmd.address = WILC_SDIO_FBR_DATA_REG;
 		cmd.block_mode = 0;
 		cmd.increment = 1;
-		cmd.count = 4;
+		cmd.count = sizeof(u32);
 		cmd.buffer = (u8 *)data;
+		cmd.use_global_buf = true;
 
 		cmd.block_size = sdio_priv->block_size;
 		ret = wilc_sdio_cmd53(wilc, &cmd);
@@ -527,6 +553,7 @@ static int wilc_sdio_read(struct wilc *wilc, u32 addr, u8 *buf, u32 size)
 	nblk = size / block_size;
 	nleft = size % block_size;
 
+	cmd.use_global_buf = false;
 	if (nblk > 0) {
 		cmd.block_mode = 1;
 		cmd.increment = 1;
diff --git a/drivers/net/wireless/microchip/wilc1000/wlan.c b/drivers/net/wireless/microchip/wilc1000/wlan.c
index 200a103a0a85..380699983a75 100644
--- a/drivers/net/wireless/microchip/wilc1000/wlan.c
+++ b/drivers/net/wireless/microchip/wilc1000/wlan.c
@@ -701,7 +701,7 @@ int wilc_wlan_handle_txq(struct wilc *wilc, u32 *txq_count)
 	int ret = 0;
 	int counter;
 	int timeout;
-	u32 vmm_table[WILC_VMM_TBL_SIZE];
+	u32 *vmm_table = wilc->vmm_table;
 	u8 ac_pkt_num_to_chip[NQUEUES] = {0, 0, 0, 0};
 	const struct wilc_hif_func *func;
 	int srcu_idx;
@@ -1220,6 +1220,8 @@ void wilc_wlan_cleanup(struct net_device *dev)
 	while ((rqe = wilc_wlan_rxq_remove(wilc)))
 		kfree(rqe);
 
+	kfree(wilc->vmm_table);
+	wilc->vmm_table = NULL;
 	kfree(wilc->rx_buffer);
 	wilc->rx_buffer = NULL;
 	kfree(wilc->tx_buffer);
@@ -1455,6 +1457,14 @@ int wilc_wlan_init(struct net_device *dev)
 		goto fail;
 	}
 
+	if (!wilc->vmm_table)
+		wilc->vmm_table = kzalloc(WILC_VMM_TBL_SIZE, GFP_KERNEL);
+
+	if (!wilc->vmm_table) {
+		ret = -ENOBUFS;
+		goto fail;
+	}
+
 	if (!wilc->tx_buffer)
 		wilc->tx_buffer = kmalloc(WILC_TX_BUFF_SIZE, GFP_KERNEL);
 
@@ -1479,7 +1489,8 @@ int wilc_wlan_init(struct net_device *dev)
 	return 0;
 
 fail:
-
+	kfree(wilc->vmm_table);
+	wilc->vmm_table = NULL;
 	kfree(wilc->rx_buffer);
 	wilc->rx_buffer = NULL;
 	kfree(wilc->tx_buffer);
diff --git a/drivers/net/wireless/realtek/rtlwifi/debug.c b/drivers/net/wireless/realtek/rtlwifi/debug.c
index 901cdfe3723c..0b1bc04cb6ad 100644
--- a/drivers/net/wireless/realtek/rtlwifi/debug.c
+++ b/drivers/net/wireless/realtek/rtlwifi/debug.c
@@ -329,8 +329,8 @@ static ssize_t rtl_debugfs_set_write_h2c(struct file *filp,
 
 	tmp_len = (count > sizeof(tmp) - 1 ? sizeof(tmp) - 1 : count);
 
-	if (!buffer || copy_from_user(tmp, buffer, tmp_len))
-		return count;
+	if (copy_from_user(tmp, buffer, tmp_len))
+		return -EFAULT;
 
 	tmp[tmp_len] = '\0';
 
@@ -340,8 +340,8 @@ static ssize_t rtl_debugfs_set_write_h2c(struct file *filp,
 			 &h2c_data[4], &h2c_data[5],
 			 &h2c_data[6], &h2c_data[7]);
 
-	if (h2c_len <= 0)
-		return count;
+	if (h2c_len == 0)
+		return -EINVAL;
 
 	for (i = 0; i < h2c_len; i++)
 		h2c_data_packed[i] = (u8)h2c_data[i];
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c
index 9b83c710c9b8..743e38a1aa51 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c
@@ -2386,10 +2386,7 @@ void rtl92d_phy_reload_iqk_setting(struct ieee80211_hw *hw, u8 channel)
 			rtl_dbg(rtlpriv, COMP_SCAN, DBG_LOUD,
 				"Just Read IQK Matrix reg for channel:%d....\n",
 				channel);
-			if ((rtlphy->iqk_matrix[indexforchannel].
-			     value[0] != NULL)
-				/*&&(regea4 != 0) */)
-				_rtl92d_phy_patha_fill_iqk_matrix(hw, true,
+			_rtl92d_phy_patha_fill_iqk_matrix(hw, true,
 					rtlphy->iqk_matrix[
 					indexforchannel].value,	0,
 					(rtlphy->iqk_matrix[
diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c
index 69512856bb46..5786995d90d4 100644
--- a/drivers/net/wireless/realtek/rtw88/main.c
+++ b/drivers/net/wireless/realtek/rtw88/main.c
@@ -1819,6 +1819,10 @@ int rtw_core_init(struct rtw_dev *rtwdev)
 	timer_setup(&rtwdev->tx_report.purge_timer,
 		    rtw_tx_report_purge_timer, 0);
 	rtwdev->tx_wq = alloc_workqueue("rtw_tx_wq", WQ_UNBOUND | WQ_HIGHPRI, 0);
+	if (!rtwdev->tx_wq) {
+		rtw_warn(rtwdev, "alloc_workqueue rtw_tx_wq failed\n");
+		return -ENOMEM;
+	}
 
 	INIT_DELAYED_WORK(&rtwdev->watch_dog_work, rtw_watch_dog_work);
 	INIT_DELAYED_WORK(&coex->bt_relink_work, rtw_coex_bt_relink_work);
diff --git a/drivers/net/wwan/iosm/iosm_ipc_protocol_ops.c b/drivers/net/wwan/iosm/iosm_ipc_protocol_ops.c
index c6b032f95d2e..4627847c6daa 100644
--- a/drivers/net/wwan/iosm/iosm_ipc_protocol_ops.c
+++ b/drivers/net/wwan/iosm/iosm_ipc_protocol_ops.c
@@ -372,8 +372,6 @@ bool ipc_protocol_dl_td_prepare(struct iosm_protocol *ipc_protocol,
 struct sk_buff *ipc_protocol_dl_td_process(struct iosm_protocol *ipc_protocol,
 					   struct ipc_pipe *pipe)
 {
-	u32 tail =
-		le32_to_cpu(ipc_protocol->p_ap_shm->tail_array[pipe->pipe_nr]);
 	struct ipc_protocol_td *p_td;
 	struct sk_buff *skb;
 
@@ -403,14 +401,6 @@ struct sk_buff *ipc_protocol_dl_td_process(struct iosm_protocol *ipc_protocol,
 		goto ret;
 	}
 
-	if (!IPC_CB(skb)) {
-		dev_err(ipc_protocol->dev, "pipe# %d, tail: %d skb_cb is NULL",
-			pipe->pipe_nr, tail);
-		ipc_pcie_kfree_skb(ipc_protocol->pcie, skb);
-		skb = NULL;
-		goto ret;
-	}
-
 	if (p_td->buffer.address != IPC_CB(skb)->mapping) {
 		dev_err(ipc_protocol->dev, "invalid buf=%llx or skb=%p",
 			(unsigned long long)p_td->buffer.address, skb->data);
diff --git a/drivers/net/xen-netback/rx.c b/drivers/net/xen-netback/rx.c
index dbac4c03d21a..a0335407be42 100644
--- a/drivers/net/xen-netback/rx.c
+++ b/drivers/net/xen-netback/rx.c
@@ -495,6 +495,7 @@ void xenvif_rx_action(struct xenvif_queue *queue)
 	queue->rx_copy.completed = &completed_skbs;
 
 	while (xenvif_rx_ring_slots_available(queue) &&
+	       !skb_queue_empty(&queue->rx_queue) &&
 	       work_done < RX_BATCH_SIZE) {
 		xenvif_rx_skb(queue);
 		work_done++;
diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index 990360d75cb6..e85b3c5d4acc 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -256,7 +256,6 @@ static void backend_disconnect(struct backend_info *be)
 		unsigned int queue_index;
 
 		xen_unregister_watchers(vif);
-		xenbus_rm(XBT_NIL, be->dev->nodename, "hotplug-status");
 #ifdef CONFIG_DEBUG_FS
 		xenvif_debugfs_delif(vif);
 #endif /* CONFIG_DEBUG_FS */
@@ -984,6 +983,7 @@ static int netback_remove(struct xenbus_device *dev)
 	struct backend_info *be = dev_get_drvdata(&dev->dev);
 
 	unregister_hotplug_status_watch(be);
+	xenbus_rm(XBT_NIL, dev->nodename, "hotplug-status");
 	if (be->vif) {
 		kobject_uevent(&dev->dev.kobj, KOBJ_OFFLINE);
 		backend_disconnect(be);
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 2492a27467b4..074dceb1930b 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -66,6 +66,10 @@ module_param_named(max_queues, xennet_max_queues, uint, 0644);
 MODULE_PARM_DESC(max_queues,
 		 "Maximum number of queues per virtual interface");
 
+static bool __read_mostly xennet_trusted = true;
+module_param_named(trusted, xennet_trusted, bool, 0644);
+MODULE_PARM_DESC(trusted, "Is the backend trusted");
+
 #define XENNET_TIMEOUT  (5 * HZ)
 
 static const struct ethtool_ops xennet_ethtool_ops;
@@ -175,6 +179,9 @@ struct netfront_info {
 	/* Is device behaving sane? */
 	bool broken;
 
+	/* Should skbs be bounced into a zeroed buffer? */
+	bool bounce;
+
 	atomic_t rx_gso_checksum_fixup;
 };
 
@@ -273,7 +280,8 @@ static struct sk_buff *xennet_alloc_one_rx_buffer(struct netfront_queue *queue)
 	if (unlikely(!skb))
 		return NULL;
 
-	page = page_pool_dev_alloc_pages(queue->page_pool);
+	page = page_pool_alloc_pages(queue->page_pool,
+				     GFP_ATOMIC | __GFP_NOWARN | __GFP_ZERO);
 	if (unlikely(!page)) {
 		kfree_skb(skb);
 		return NULL;
@@ -667,6 +675,33 @@ static int xennet_xdp_xmit(struct net_device *dev, int n,
 	return nxmit;
 }
 
+struct sk_buff *bounce_skb(const struct sk_buff *skb)
+{
+	unsigned int headerlen = skb_headroom(skb);
+	/* Align size to allocate full pages and avoid contiguous data leaks */
+	unsigned int size = ALIGN(skb_end_offset(skb) + skb->data_len,
+				  XEN_PAGE_SIZE);
+	struct sk_buff *n = alloc_skb(size, GFP_ATOMIC | __GFP_ZERO);
+
+	if (!n)
+		return NULL;
+
+	if (!IS_ALIGNED((uintptr_t)n->head, XEN_PAGE_SIZE)) {
+		WARN_ONCE(1, "misaligned skb allocated\n");
+		kfree_skb(n);
+		return NULL;
+	}
+
+	/* Set the data pointer */
+	skb_reserve(n, headerlen);
+	/* Set the tail pointer and length */
+	skb_put(n, skb->len);
+
+	BUG_ON(skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len));
+
+	skb_copy_header(n, skb);
+	return n;
+}
 
 #define MAX_XEN_SKB_FRAGS (65536 / XEN_PAGE_SIZE + 1)
 
@@ -720,9 +755,13 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev
 
 	/* The first req should be at least ETH_HLEN size or the packet will be
 	 * dropped by netback.
+	 *
+	 * If the backend is not trusted bounce all data to zeroed pages to
+	 * avoid exposing contiguous data on the granted page not belonging to
+	 * the skb.
 	 */
-	if (unlikely(PAGE_SIZE - offset < ETH_HLEN)) {
-		nskb = skb_copy(skb, GFP_ATOMIC);
+	if (np->bounce || unlikely(PAGE_SIZE - offset < ETH_HLEN)) {
+		nskb = bounce_skb(skb);
 		if (!nskb)
 			goto drop;
 		dev_consume_skb_any(skb);
@@ -1055,8 +1094,10 @@ static int xennet_get_responses(struct netfront_queue *queue,
 			}
 		}
 		rcu_read_unlock();
-next:
+
 		__skb_queue_tail(list, skb);
+
+next:
 		if (!(rx->flags & XEN_NETRXF_more_data))
 			break;
 
@@ -2246,6 +2287,10 @@ static int talk_to_netback(struct xenbus_device *dev,
 
 	info->netdev->irq = 0;
 
+	/* Check if backend is trusted. */
+	info->bounce = !xennet_trusted ||
+		       !xenbus_read_unsigned(dev->nodename, "trusted", 1);
+
 	/* Check if backend supports multiple queues */
 	max_queues = xenbus_read_unsigned(info->xbdev->otherend,
 					  "multi-queue-max-queues", 1);
@@ -2412,6 +2457,9 @@ static int xennet_connect(struct net_device *dev)
 		return err;
 	if (np->netback_has_xdp_headroom)
 		pr_info("backend supports XDP headroom\n");
+	if (np->bounce)
+		dev_info(&np->xbdev->dev,
+			 "bouncing transmitted data to zeroed pages\n");
 
 	/* talk_to_netback() sets the correct number of queues */
 	num_queues = dev->real_num_tx_queues;
diff --git a/drivers/nfc/nfcmrvl/i2c.c b/drivers/nfc/nfcmrvl/i2c.c
index ceef81d93ac9..01329b91d59d 100644
--- a/drivers/nfc/nfcmrvl/i2c.c
+++ b/drivers/nfc/nfcmrvl/i2c.c
@@ -167,9 +167,9 @@ static int nfcmrvl_i2c_parse_dt(struct device_node *node,
 		pdata->irq_polarity = IRQF_TRIGGER_RISING;
 
 	ret = irq_of_parse_and_map(node, 0);
-	if (ret < 0) {
-		pr_err("Unable to get irq, error: %d\n", ret);
-		return ret;
+	if (!ret) {
+		pr_err("Unable to get irq\n");
+		return -EINVAL;
 	}
 	pdata->irq = ret;
 
diff --git a/drivers/nfc/nfcmrvl/spi.c b/drivers/nfc/nfcmrvl/spi.c
index 5b833a9a83f8..abd75779194c 100644
--- a/drivers/nfc/nfcmrvl/spi.c
+++ b/drivers/nfc/nfcmrvl/spi.c
@@ -115,9 +115,9 @@ static int nfcmrvl_spi_parse_dt(struct device_node *node,
 	}
 
 	ret = irq_of_parse_and_map(node, 0);
-	if (ret < 0) {
-		pr_err("Unable to get irq, error: %d\n", ret);
-		return ret;
+	if (!ret) {
+		pr_err("Unable to get irq\n");
+		return -EINVAL;
 	}
 	pdata->irq = ret;
 
diff --git a/drivers/nfc/nxp-nci/i2c.c b/drivers/nfc/nxp-nci/i2c.c
index 7e451c10985d..ae2ba08d8ac3 100644
--- a/drivers/nfc/nxp-nci/i2c.c
+++ b/drivers/nfc/nxp-nci/i2c.c
@@ -122,7 +122,9 @@ static int nxp_nci_i2c_fw_read(struct nxp_nci_i2c_phy *phy,
 	skb_put_data(*skb, &header, NXP_NCI_FW_HDR_LEN);
 
 	r = i2c_master_recv(client, skb_put(*skb, frame_len), frame_len);
-	if (r != frame_len) {
+	if (r < 0) {
+		goto fw_read_exit_free_skb;
+	} else if (r != frame_len) {
 		nfc_err(&client->dev,
 			"Invalid frame length: %u (expected %zu)\n",
 			r, frame_len);
@@ -162,8 +164,13 @@ static int nxp_nci_i2c_nci_read(struct nxp_nci_i2c_phy *phy,
 
 	skb_put_data(*skb, (void *)&header, NCI_CTRL_HDR_SIZE);
 
+	if (!header.plen)
+		return 0;
+
 	r = i2c_master_recv(client, skb_put(*skb, header.plen), header.plen);
-	if (r != header.plen) {
+	if (r < 0) {
+		goto nci_read_exit_free_skb;
+	} else if (r != header.plen) {
 		nfc_err(&client->dev,
 			"Invalid frame payload length: %u (expected %u)\n",
 			r, header.plen);
diff --git a/drivers/nfc/pn533/uart.c b/drivers/nfc/pn533/uart.c
index 7bdaf8263070..7ad98973648c 100644
--- a/drivers/nfc/pn533/uart.c
+++ b/drivers/nfc/pn533/uart.c
@@ -310,6 +310,7 @@ static void pn532_uart_remove(struct serdev_device *serdev)
 	pn53x_unregister_nfc(pn532->priv);
 	serdev_device_close(serdev);
 	pn53x_common_clean(pn532->priv);
+	del_timer_sync(&pn532->cmd_timeout);
 	kfree_skb(pn532->recv_skb);
 	kfree(pn532);
 }
diff --git a/drivers/ntb/test/ntb_tool.c b/drivers/ntb/test/ntb_tool.c
index b7bf3f863d79..5ee0afa621a9 100644
--- a/drivers/ntb/test/ntb_tool.c
+++ b/drivers/ntb/test/ntb_tool.c
@@ -367,14 +367,16 @@ static ssize_t tool_fn_write(struct tool_ctx *tc,
 	u64 bits;
 	int n;
 
+	if (*offp)
+		return 0;
+
 	buf = kmalloc(size + 1, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
-	ret = simple_write_to_buffer(buf, size, offp, ubuf, size);
-	if (ret < 0) {
+	if (copy_from_user(buf, ubuf, size)) {
 		kfree(buf);
-		return ret;
+		return -EFAULT;
 	}
 
 	buf[size] = 0;
diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index 9dc7f3edd42b..84d197cc09f8 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -185,8 +185,8 @@ static int nvdimm_clear_badblocks_region(struct device *dev, void *data)
 	ndr_end = nd_region->ndr_start + nd_region->ndr_size - 1;
 
 	/* make sure we are in the region */
-	if (ctx->phys < nd_region->ndr_start
-			|| (ctx->phys + ctx->cleared) > ndr_end)
+	if (ctx->phys < nd_region->ndr_start ||
+	    (ctx->phys + ctx->cleared - 1) > ndr_end)
 		return 0;
 
 	sector = (ctx->phys - nd_region->ndr_start) / 512;
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 19054b791c67..ed2740585c5d 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1719,7 +1719,7 @@ static int nvme_setup_streams_ns(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	return 0;
 }
 
-static int nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id)
+static void nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id)
 {
 	struct nvme_ctrl *ctrl = ns->ctrl;
 
@@ -1735,7 +1735,8 @@ static int nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id)
 
 	ns->features &= ~(NVME_NS_METADATA_SUPPORTED | NVME_NS_EXT_LBAS);
 	if (!ns->ms || !(ctrl->ops->flags & NVME_F_METADATA_SUPPORTED))
-		return 0;
+		return;
+
 	if (ctrl->ops->flags & NVME_F_FABRICS) {
 		/*
 		 * The NVMe over Fabrics specification only supports metadata as
@@ -1743,10 +1744,21 @@ static int nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id)
 		 * remap the separate metadata buffer from the block layer.
 		 */
 		if (WARN_ON_ONCE(!(id->flbas & NVME_NS_FLBAS_META_EXT)))
-			return -EINVAL;
-		if (ctrl->max_integrity_segments)
-			ns->features |=
-				(NVME_NS_METADATA_SUPPORTED | NVME_NS_EXT_LBAS);
+			return;
+
+		ns->features |= NVME_NS_EXT_LBAS;
+
+		/*
+		 * The current fabrics transport drivers support namespace
+		 * metadata formats only if nvme_ns_has_pi() returns true.
+		 * Suppress support for all other formats so the namespace will
+		 * have a 0 capacity and not be usable through the block stack.
+		 *
+		 * Note, this check will need to be modified if any drivers
+		 * gain the ability to use other metadata formats.
+		 */
+		if (ctrl->max_integrity_segments && nvme_ns_has_pi(ns))
+			ns->features |= NVME_NS_METADATA_SUPPORTED;
 	} else {
 		/*
 		 * For PCIe controllers, we can't easily remap the separate
@@ -1759,8 +1771,6 @@ static int nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id)
 		else
 			ns->features |= NVME_NS_METADATA_SUPPORTED;
 	}
-
-	return 0;
 }
 
 static void nvme_set_queue_limits(struct nvme_ctrl *ctrl,
@@ -1898,16 +1908,16 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id)
 	ns->lba_shift = id->lbaf[lbaf].ds;
 	nvme_set_queue_limits(ns->ctrl, ns->queue);
 
-	ret = nvme_configure_metadata(ns, id);
-	if (ret)
-		goto out_unfreeze;
+	nvme_configure_metadata(ns, id);
 	nvme_set_chunk_sectors(ns, id);
 	nvme_update_disk_info(ns->disk, ns, id);
 
 	if (ns->head->ids.csi == NVME_CSI_ZNS) {
 		ret = nvme_update_zone_info(ns, lbaf);
-		if (ret)
-			goto out_unfreeze;
+		if (ret) {
+			blk_mq_unfreeze_queue(ns->disk->queue);
+			goto out;
+		}
 	}
 
 	set_disk_ro(ns->disk, (id->nsattr & NVME_NS_ATTR_RO) ||
@@ -1918,7 +1928,7 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id)
 	if (blk_queue_is_zoned(ns->queue)) {
 		ret = nvme_revalidate_zones(ns);
 		if (ret && !nvme_first_scan(ns->disk))
-			return ret;
+			goto out;
 	}
 
 	if (nvme_ns_head_multipath(ns->head)) {
@@ -1933,9 +1943,9 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id)
 		disk_update_readahead(ns->head->disk);
 		blk_mq_unfreeze_queue(ns->head->disk->queue);
 	}
-	return 0;
 
-out_unfreeze:
+	ret = 0;
+out:
 	/*
 	 * If probing fails due an unsupported feature, hide the block device,
 	 * but still allow other access.
@@ -1945,7 +1955,6 @@ out_unfreeze:
 		set_bit(NVME_NS_READY, &ns->flags);
 		ret = 0;
 	}
-	blk_mq_unfreeze_queue(ns->disk->queue);
 	return ret;
 }
 
@@ -2102,6 +2111,7 @@ static int nvme_report_zones(struct gendisk *disk, sector_t sector,
 static const struct block_device_operations nvme_bdev_ops = {
 	.owner		= THIS_MODULE,
 	.ioctl		= nvme_ioctl,
+	.compat_ioctl	= blkdev_compat_ptr_ioctl,
 	.open		= nvme_open,
 	.release	= nvme_release,
 	.getgeo		= nvme_getgeo,
@@ -3660,7 +3670,7 @@ static int nvme_add_ns_cdev(struct nvme_ns *ns)
 }
 
 static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
-		unsigned nsid, struct nvme_ns_ids *ids)
+		unsigned nsid, struct nvme_ns_ids *ids, bool is_shared)
 {
 	struct nvme_ns_head *head;
 	size_t size = sizeof(*head);
@@ -3684,15 +3694,9 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
 	head->subsys = ctrl->subsys;
 	head->ns_id = nsid;
 	head->ids = *ids;
+	head->shared = is_shared;
 	kref_init(&head->ref);
 
-	ret = nvme_subsys_check_duplicate_ids(ctrl->subsys, &head->ids);
-	if (ret) {
-		dev_err(ctrl->device,
-			"duplicate IDs for nsid %d\n", nsid);
-		goto out_cleanup_srcu;
-	}
-
 	if (head->ids.csi) {
 		ret = nvme_get_effects_log(ctrl, head->ids.csi, &head->effects);
 		if (ret)
@@ -3731,12 +3735,17 @@ static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid,
 	mutex_lock(&ctrl->subsys->lock);
 	head = nvme_find_ns_head(ctrl, nsid);
 	if (!head) {
-		head = nvme_alloc_ns_head(ctrl, nsid, ids);
+		ret = nvme_subsys_check_duplicate_ids(ctrl->subsys, ids);
+		if (ret) {
+			dev_err(ctrl->device,
+				"duplicate IDs for nsid %d\n", nsid);
+			goto out_unlock;
+		}
+		head = nvme_alloc_ns_head(ctrl, nsid, ids, is_shared);
 		if (IS_ERR(head)) {
 			ret = PTR_ERR(head);
 			goto out_unlock;
 		}
-		head->shared = is_shared;
 	} else {
 		ret = -EINVAL;
 		if (!is_shared || !head->shared) {
@@ -4385,6 +4394,8 @@ void nvme_stop_ctrl(struct nvme_ctrl *ctrl)
 	nvme_stop_failfast_work(ctrl);
 	flush_work(&ctrl->async_event_work);
 	cancel_work_sync(&ctrl->fw_act_work);
+	if (ctrl->ops->stop_ctrl)
+		ctrl->ops->stop_ctrl(ctrl);
 }
 EXPORT_SYMBOL_GPL(nvme_stop_ctrl);
 
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 064acad505d3..04fa276701d1 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -388,6 +388,7 @@ const struct block_device_operations nvme_ns_head_ops = {
 	.open		= nvme_ns_head_open,
 	.release	= nvme_ns_head_release,
 	.ioctl		= nvme_ns_head_ioctl,
+	.compat_ioctl	= blkdev_compat_ptr_ioctl,
 	.getgeo		= nvme_getgeo,
 	.report_zones	= nvme_ns_head_report_zones,
 	.pr_ops		= &nvme_pr_ops,
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 72bcd7e5716e..75a7e7baa1fc 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -495,6 +495,7 @@ struct nvme_ctrl_ops {
 	void (*free_ctrl)(struct nvme_ctrl *ctrl);
 	void (*submit_async_event)(struct nvme_ctrl *ctrl);
 	void (*delete_ctrl)(struct nvme_ctrl *ctrl);
+	void (*stop_ctrl)(struct nvme_ctrl *ctrl);
 	int (*get_address)(struct nvme_ctrl *ctrl, char *buf, int size);
 };
 
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 58b8461b2b0f..d820131d39b2 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -3337,12 +3337,16 @@ static const struct pci_device_id nvme_id_table[] = {
 				NVME_QUIRK_DISABLE_WRITE_ZEROES|
 				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
 	{ PCI_DEVICE(0x1987, 0x5016),	/* Phison E16 */
-		.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, },
+		.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN |
+				NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x1b4b, 0x1092),	/* Lexar 256 GB SSD */
 		.driver_data = NVME_QUIRK_NO_NS_DESC_LIST |
 				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
+	{ PCI_DEVICE(0x1cc1, 0x33f8),   /* ADATA IM2P33F8ABR1 1 TB */
+		.driver_data = NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x10ec, 0x5762),   /* ADATA SX6000LNP */
-		.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, },
+		.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN |
+				NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x1cc1, 0x8201),   /* ADATA SX8200PNP 512GB */
 		.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
 				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index d51f52e296f5..2db9c166a1b7 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1049,6 +1049,14 @@ static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
 	}
 }
 
+static void nvme_rdma_stop_ctrl(struct nvme_ctrl *nctrl)
+{
+	struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl);
+
+	cancel_work_sync(&ctrl->err_work);
+	cancel_delayed_work_sync(&ctrl->reconnect_work);
+}
+
 static void nvme_rdma_free_ctrl(struct nvme_ctrl *nctrl)
 {
 	struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl);
@@ -2230,9 +2238,6 @@ static const struct blk_mq_ops nvme_rdma_admin_mq_ops = {
 
 static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl, bool shutdown)
 {
-	cancel_work_sync(&ctrl->err_work);
-	cancel_delayed_work_sync(&ctrl->reconnect_work);
-
 	nvme_rdma_teardown_io_queues(ctrl, shutdown);
 	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
 	if (shutdown)
@@ -2282,6 +2287,7 @@ static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = {
 	.submit_async_event	= nvme_rdma_submit_async_event,
 	.delete_ctrl		= nvme_rdma_delete_ctrl,
 	.get_address		= nvmf_get_address,
+	.stop_ctrl		= nvme_rdma_stop_ctrl,
 };
 
 /*
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 10882d3d554c..96d8d7844e84 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -119,7 +119,6 @@ struct nvme_tcp_queue {
 	struct mutex		send_mutex;
 	struct llist_head	req_list;
 	struct list_head	send_list;
-	bool			more_requests;
 
 	/* recv state */
 	void			*pdu;
@@ -315,7 +314,7 @@ static inline void nvme_tcp_send_all(struct nvme_tcp_queue *queue)
 static inline bool nvme_tcp_queue_more(struct nvme_tcp_queue *queue)
 {
 	return !list_empty(&queue->send_list) ||
-		!llist_empty(&queue->req_list) || queue->more_requests;
+		!llist_empty(&queue->req_list);
 }
 
 static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req,
@@ -334,9 +333,7 @@ static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req,
 	 */
 	if (queue->io_cpu == raw_smp_processor_id() &&
 	    sync && empty && mutex_trylock(&queue->send_mutex)) {
-		queue->more_requests = !last;
 		nvme_tcp_send_all(queue);
-		queue->more_requests = false;
 		mutex_unlock(&queue->send_mutex);
 	}
 
@@ -1162,8 +1159,7 @@ done:
 	} else if (ret < 0) {
 		dev_err(queue->ctrl->ctrl.device,
 			"failed to send request %d\n", ret);
-		if (ret != -EPIPE && ret != -ECONNRESET)
-			nvme_tcp_fail_request(queue->request);
+		nvme_tcp_fail_request(queue->request);
 		nvme_tcp_done_send_req(queue);
 	}
 	return ret;
@@ -1210,7 +1206,7 @@ static void nvme_tcp_io_work(struct work_struct *w)
 		else if (unlikely(result < 0))
 			return;
 
-		if (!pending)
+		if (!pending || !queue->rd_enabled)
 			return;
 
 	} while (!time_after(jiffies, deadline)); /* quota is exhausted */
@@ -2164,9 +2160,6 @@ static void nvme_tcp_error_recovery_work(struct work_struct *work)
 
 static void nvme_tcp_teardown_ctrl(struct nvme_ctrl *ctrl, bool shutdown)
 {
-	cancel_work_sync(&to_tcp_ctrl(ctrl)->err_work);
-	cancel_delayed_work_sync(&to_tcp_ctrl(ctrl)->connect_work);
-
 	nvme_tcp_teardown_io_queues(ctrl, shutdown);
 	blk_mq_quiesce_queue(ctrl->admin_q);
 	if (shutdown)
@@ -2206,6 +2199,12 @@ out_fail:
 	nvme_tcp_reconnect_or_remove(ctrl);
 }
 
+static void nvme_tcp_stop_ctrl(struct nvme_ctrl *ctrl)
+{
+	cancel_work_sync(&to_tcp_ctrl(ctrl)->err_work);
+	cancel_delayed_work_sync(&to_tcp_ctrl(ctrl)->connect_work);
+}
+
 static void nvme_tcp_free_ctrl(struct nvme_ctrl *nctrl)
 {
 	struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
@@ -2529,6 +2528,7 @@ static const struct nvme_ctrl_ops nvme_tcp_ctrl_ops = {
 	.submit_async_event	= nvme_tcp_submit_async_event,
 	.delete_ctrl		= nvme_tcp_delete_ctrl,
 	.get_address		= nvmf_get_address,
+	.stop_ctrl		= nvme_tcp_stop_ctrl,
 };
 
 static bool
diff --git a/drivers/nvme/host/trace.h b/drivers/nvme/host/trace.h
index 35bac7a25422..aa8b0f86b2be 100644
--- a/drivers/nvme/host/trace.h
+++ b/drivers/nvme/host/trace.h
@@ -98,7 +98,7 @@ TRACE_EVENT(nvme_complete_rq,
 	    TP_fast_assign(
 		__entry->ctrl_id = nvme_req(req)->ctrl->instance;
 		__entry->qid = nvme_req_qid(req);
-		__entry->cid = req->tag;
+		__entry->cid = nvme_req(req)->cmd->common.command_id;
 		__entry->result = le64_to_cpu(nvme_req(req)->result.u64);
 		__entry->retries = nvme_req(req)->retries;
 		__entry->flags = nvme_req(req)->flags;
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index a8dafe8670f2..0a0c1d956c73 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -736,6 +736,8 @@ static void nvmet_set_error(struct nvmet_req *req, u16 status)
 
 static void __nvmet_req_complete(struct nvmet_req *req, u16 status)
 {
+	struct nvmet_ns *ns = req->ns;
+
 	if (!req->sq->sqhd_disabled)
 		nvmet_update_sq_head(req);
 	req->cqe->sq_id = cpu_to_le16(req->sq->qid);
@@ -746,9 +748,9 @@ static void __nvmet_req_complete(struct nvmet_req *req, u16 status)
 
 	trace_nvmet_req_complete(req);
 
-	if (req->ns)
-		nvmet_put_namespace(req->ns);
 	req->ops->queue_response(req);
+	if (ns)
+		nvmet_put_namespace(ns);
 }
 
 void nvmet_req_complete(struct nvmet_req *req, u16 status)
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index f592e5f7f5f3..fba5a77c58d6 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -1501,6 +1501,9 @@ static void nvmet_tcp_state_change(struct sock *sk)
 		goto done;
 
 	switch (sk->sk_state) {
+	case TCP_FIN_WAIT2:
+	case TCP_LAST_ACK:
+		break;
 	case TCP_FIN_WAIT1:
 	case TCP_CLOSE_WAIT:
 	case TCP_CLOSE:
@@ -1834,7 +1837,8 @@ static int __init nvmet_tcp_init(void)
 {
 	int ret;
 
-	nvmet_tcp_wq = alloc_workqueue("nvmet_tcp_wq", WQ_HIGHPRI, 0);
+	nvmet_tcp_wq = alloc_workqueue("nvmet_tcp_wq",
+				WQ_MEM_RECLAIM | WQ_HIGHPRI, 0);
 	if (!nvmet_tcp_wq)
 		return -ENOMEM;
 
diff --git a/drivers/nvme/target/zns.c b/drivers/nvme/target/zns.c
index 46bc30fe85d2..1466698751c5 100644
--- a/drivers/nvme/target/zns.c
+++ b/drivers/nvme/target/zns.c
@@ -34,8 +34,7 @@ static int validate_conv_zones_cb(struct blk_zone *z,
 
 bool nvmet_bdev_zns_enable(struct nvmet_ns *ns)
 {
-	struct request_queue *q = ns->bdev->bd_disk->queue;
-	u8 zasl = nvmet_zasl(queue_max_zone_append_sectors(q));
+	u8 zasl = nvmet_zasl(bdev_max_zone_append_sectors(ns->bdev));
 	struct gendisk *bd_disk = ns->bdev->bd_disk;
 	int ret;
 
@@ -101,6 +100,7 @@ void nvmet_execute_identify_cns_cs_ns(struct nvmet_req *req)
 	struct nvme_id_ns_zns *id_zns;
 	u64 zsze;
 	u16 status;
+	u32 mar, mor;
 
 	if (le32_to_cpu(req->cmd->identify.nsid) == NVME_NSID_ALL) {
 		req->error_loc = offsetof(struct nvme_identify, nsid);
@@ -127,8 +127,20 @@ void nvmet_execute_identify_cns_cs_ns(struct nvmet_req *req)
 	zsze = (bdev_zone_sectors(req->ns->bdev) << 9) >>
 					req->ns->blksize_shift;
 	id_zns->lbafe[0].zsze = cpu_to_le64(zsze);
-	id_zns->mor = cpu_to_le32(bdev_max_open_zones(req->ns->bdev));
-	id_zns->mar = cpu_to_le32(bdev_max_active_zones(req->ns->bdev));
+
+	mor = bdev_max_open_zones(req->ns->bdev);
+	if (!mor)
+		mor = U32_MAX;
+	else
+		mor--;
+	id_zns->mor = cpu_to_le32(mor);
+
+	mar = bdev_max_active_zones(req->ns->bdev);
+	if (!mar)
+		mar = U32_MAX;
+	else
+		mar--;
+	id_zns->mar = cpu_to_le32(mar);
 
 done:
 	status = nvmet_copy_to_sgl(req, 0, id_zns, sizeof(*id_zns));
diff --git a/drivers/of/device.c b/drivers/of/device.c
index b0800c260f64..45335fe523f7 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -81,8 +81,11 @@ of_dma_set_restricted_buffer(struct device *dev, struct device_node *np)
 		 * restricted-dma-pool region is allowed.
 		 */
 		if (of_device_is_compatible(node, "restricted-dma-pool") &&
-		    of_device_is_available(node))
+		    of_device_is_available(node)) {
+			of_node_put(node);
 			break;
+		}
+		of_node_put(node);
 	}
 
 	/*
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index a88f01174796..7d9b6e6dc9f4 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -245,7 +245,7 @@ static int populate_node(const void *blob,
 	}
 
 	*pnp = np;
-	return true;
+	return 0;
 }
 
 static void reverse_nodes(struct device_node *parent)
@@ -313,7 +313,7 @@ static int unflatten_dt_nodes(const void *blob,
 	for (offset = 0;
 	     offset >= 0 && depth >= initial_depth;
 	     offset = fdt_next_node(blob, offset, &depth)) {
-		if (WARN_ON_ONCE(depth >= FDT_MAX_DEPTH))
+		if (WARN_ON_ONCE(depth >= FDT_MAX_DEPTH - 1))
 			continue;
 
 		if (!IS_ENABLED(CONFIG_OF_KOBJ) &&
diff --git a/drivers/of/kexec.c b/drivers/of/kexec.c
index 72c790a3c910..8f9dba11873c 100644
--- a/drivers/of/kexec.c
+++ b/drivers/of/kexec.c
@@ -125,6 +125,7 @@ int ima_get_kexec_buffer(void **addr, size_t *size)
 {
 	int ret, len;
 	unsigned long tmp_addr;
+	unsigned long start_pfn, end_pfn;
 	size_t tmp_size;
 	const void *prop;
 
@@ -139,6 +140,22 @@ int ima_get_kexec_buffer(void **addr, size_t *size)
 	if (ret)
 		return ret;
 
+	/* Do some sanity on the returned size for the ima-kexec buffer */
+	if (!tmp_size)
+		return -ENOENT;
+
+	/*
+	 * Calculate the PFNs for the buffer and ensure
+	 * they are with in addressable memory.
+	 */
+	start_pfn = PHYS_PFN(tmp_addr);
+	end_pfn = PHYS_PFN(tmp_addr + tmp_size - 1);
+	if (!page_is_ram(start_pfn) || !page_is_ram(end_pfn)) {
+		pr_warn("IMA buffer at 0x%lx, size = 0x%zx beyond memory\n",
+			tmp_addr, tmp_size);
+		return -EINVAL;
+	}
+
 	*addr = __va(tmp_addr);
 	*size = tmp_size;
 
diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index 04b4691a8aac..b2da497dd378 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -2388,8 +2388,8 @@ struct opp_table *dev_pm_opp_attach_genpd(struct device *dev,
 		}
 
 		virt_dev = dev_pm_domain_attach_by_name(dev, *name);
-		if (IS_ERR(virt_dev)) {
-			ret = PTR_ERR(virt_dev);
+		if (IS_ERR_OR_NULL(virt_dev)) {
+			ret = PTR_ERR(virt_dev) ? : -ENODEV;
 			dev_err(dev, "Couldn't attach to pm_domain: %d\n", ret);
 			goto err;
 		}
diff --git a/drivers/parisc/ccio-dma.c b/drivers/parisc/ccio-dma.c
index 9be007c9420f..6052f264bbb0 100644
--- a/drivers/parisc/ccio-dma.c
+++ b/drivers/parisc/ccio-dma.c
@@ -1380,15 +1380,17 @@ ccio_init_resource(struct resource *res, char *name, void __iomem *ioaddr)
 	}
 }
 
-static void __init ccio_init_resources(struct ioc *ioc)
+static int __init ccio_init_resources(struct ioc *ioc)
 {
 	struct resource *res = ioc->mmio_region;
 	char *name = kmalloc(14, GFP_KERNEL);
-
+	if (unlikely(!name))
+		return -ENOMEM;
 	snprintf(name, 14, "GSC Bus [%d/]", ioc->hw_path);
 
 	ccio_init_resource(res, name, &ioc->ioc_regs->io_io_low);
 	ccio_init_resource(res + 1, name, &ioc->ioc_regs->io_io_low_hv);
+	return 0;
 }
 
 static int new_ioc_area(struct resource *res, unsigned long size,
@@ -1543,7 +1545,11 @@ static int __init ccio_probe(struct parisc_device *dev)
 		return -ENOMEM;
 	}
 	ccio_ioc_init(ioc);
-	ccio_init_resources(ioc);
+	if (ccio_init_resources(ioc)) {
+		iounmap(ioc->ioc_regs);
+		kfree(ioc);
+		return -ENOMEM;
+	}
 	hppa_dma_ops = &ccio_ops;
 
 	hba = kzalloc(sizeof(*hba), GFP_KERNEL);
diff --git a/drivers/parisc/lba_pci.c b/drivers/parisc/lba_pci.c
index 732b516c7bf8..afc6e66ddc31 100644
--- a/drivers/parisc/lba_pci.c
+++ b/drivers/parisc/lba_pci.c
@@ -1476,9 +1476,13 @@ lba_driver_probe(struct parisc_device *dev)
 	u32 func_class;
 	void *tmp_obj;
 	char *version;
-	void __iomem *addr = ioremap(dev->hpa.start, 4096);
+	void __iomem *addr;
 	int max;
 
+	addr = ioremap(dev->hpa.start, 4096);
+	if (addr == NULL)
+		return -ENOMEM;
+
 	/* Read HW Rev First */
 	func_class = READ_REG32(addr + LBA_FCLASS);
 
diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index 998b698f4085..2af4ed90e12b 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -777,8 +777,9 @@ int dw_pcie_ep_init(struct dw_pcie_ep *ep)
 	ep->msi_mem = pci_epc_mem_alloc_addr(epc, &ep->msi_mem_phys,
 					     epc->mem->window.page_size);
 	if (!ep->msi_mem) {
+		ret = -ENOMEM;
 		dev_err(dev, "Failed to reserve memory for MSI/MSI-X\n");
-		return -ENOMEM;
+		goto err_exit_epc_mem;
 	}
 
 	if (ep->ops->get_features) {
@@ -787,6 +788,19 @@ int dw_pcie_ep_init(struct dw_pcie_ep *ep)
 			return 0;
 	}
 
-	return dw_pcie_ep_init_complete(ep);
+	ret = dw_pcie_ep_init_complete(ep);
+	if (ret)
+		goto err_free_epc_mem;
+
+	return 0;
+
+err_free_epc_mem:
+	pci_epc_mem_free_addr(epc, ep->msi_mem_phys, ep->msi_mem,
+			      epc->mem->window.page_size);
+
+err_exit_epc_mem:
+	pci_epc_mem_exit(epc);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(dw_pcie_ep_init);
diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c
index fba5b16f3272..37f5420c96c3 100644
--- a/drivers/pci/controller/dwc/pcie-designware-host.c
+++ b/drivers/pci/controller/dwc/pcie-designware-host.c
@@ -422,8 +422,14 @@ int dw_pcie_host_init(struct pcie_port *pp)
 	bridge->sysdata = pp;
 
 	ret = pci_host_probe(bridge);
-	if (!ret)
-		return 0;
+	if (ret)
+		goto err_stop_link;
+
+	return 0;
+
+err_stop_link:
+	if (pci->ops && pci->ops->stop_link)
+		pci->ops->stop_link(pci);
 
 err_free_msi:
 	if (pp->has_msi_ctrl)
@@ -434,8 +440,14 @@ EXPORT_SYMBOL_GPL(dw_pcie_host_init);
 
 void dw_pcie_host_deinit(struct pcie_port *pp)
 {
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+
 	pci_stop_root_bus(pp->bridge->bus);
 	pci_remove_root_bus(pp->bridge->bus);
+
+	if (pci->ops && pci->ops->stop_link)
+		pci->ops->stop_link(pci);
+
 	if (pp->has_msi_ctrl)
 		dw_pcie_free_msi(pp);
 }
@@ -532,7 +544,6 @@ static struct pci_ops dw_pcie_ops = {
 
 void dw_pcie_setup_rc(struct pcie_port *pp)
 {
-	int i;
 	u32 val, ctrl, num_ctrls;
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 
@@ -583,19 +594,22 @@ void dw_pcie_setup_rc(struct pcie_port *pp)
 		PCI_COMMAND_MASTER | PCI_COMMAND_SERR;
 	dw_pcie_writel_dbi(pci, PCI_COMMAND, val);
 
-	/* Ensure all outbound windows are disabled so there are multiple matches */
-	for (i = 0; i < pci->num_ob_windows; i++)
-		dw_pcie_disable_atu(pci, i, DW_PCIE_REGION_OUTBOUND);
-
 	/*
 	 * If the platform provides its own child bus config accesses, it means
 	 * the platform uses its own address translation component rather than
 	 * ATU, so we should not program the ATU here.
 	 */
 	if (pp->bridge->child_ops == &dw_child_pcie_ops) {
-		int atu_idx = 0;
+		int i, atu_idx = 0;
 		struct resource_entry *entry;
 
+		/*
+		 * Disable all outbound windows to make sure a transaction
+		 * can't match multiple windows.
+		 */
+		for (i = 0; i < pci->num_ob_windows; i++)
+			dw_pcie_disable_atu(pci, i, DW_PCIE_REGION_OUTBOUND);
+
 		/* Get last memory resource entry */
 		resource_list_for_each_entry(entry, &pp->bridge->windows) {
 			if (resource_type(entry->res) != IORESOURCE_MEM)
diff --git a/drivers/pci/controller/dwc/pcie-designware.c b/drivers/pci/controller/dwc/pcie-designware.c
index d92c8a25094f..5848cc520b52 100644
--- a/drivers/pci/controller/dwc/pcie-designware.c
+++ b/drivers/pci/controller/dwc/pcie-designware.c
@@ -287,8 +287,8 @@ static void dw_pcie_prog_outbound_atu_unroll(struct dw_pcie *pci, u8 func_no,
 	dw_pcie_writel_ob_unroll(pci, index, PCIE_ATU_UNR_UPPER_TARGET,
 				 upper_32_bits(pci_addr));
 	val = type | PCIE_ATU_FUNC_NUM(func_no);
-	val = upper_32_bits(size - 1) ?
-		val | PCIE_ATU_INCREASE_REGION_SIZE : val;
+	if (upper_32_bits(limit_addr) > upper_32_bits(cpu_addr))
+		val |= PCIE_ATU_INCREASE_REGION_SIZE;
 	if (pci->version == 0x490A)
 		val = dw_pcie_enable_ecrc(val);
 	dw_pcie_writel_ob_unroll(pci, index, PCIE_ATU_UNR_REGION_CTRL1, val);
@@ -315,6 +315,7 @@ static void __dw_pcie_prog_outbound_atu(struct dw_pcie *pci, u8 func_no,
 					u64 pci_addr, u64 size)
 {
 	u32 retries, val;
+	u64 limit_addr;
 
 	if (pci->ops && pci->ops->cpu_addr_fixup)
 		cpu_addr = pci->ops->cpu_addr_fixup(pci, cpu_addr);
@@ -325,6 +326,8 @@ static void __dw_pcie_prog_outbound_atu(struct dw_pcie *pci, u8 func_no,
 		return;
 	}
 
+	limit_addr = cpu_addr + size - 1;
+
 	dw_pcie_writel_dbi(pci, PCIE_ATU_VIEWPORT,
 			   PCIE_ATU_REGION_OUTBOUND | index);
 	dw_pcie_writel_dbi(pci, PCIE_ATU_LOWER_BASE,
@@ -332,17 +335,18 @@ static void __dw_pcie_prog_outbound_atu(struct dw_pcie *pci, u8 func_no,
 	dw_pcie_writel_dbi(pci, PCIE_ATU_UPPER_BASE,
 			   upper_32_bits(cpu_addr));
 	dw_pcie_writel_dbi(pci, PCIE_ATU_LIMIT,
-			   lower_32_bits(cpu_addr + size - 1));
+			   lower_32_bits(limit_addr));
 	if (pci->version >= 0x460A)
 		dw_pcie_writel_dbi(pci, PCIE_ATU_UPPER_LIMIT,
-				   upper_32_bits(cpu_addr + size - 1));
+				   upper_32_bits(limit_addr));
 	dw_pcie_writel_dbi(pci, PCIE_ATU_LOWER_TARGET,
 			   lower_32_bits(pci_addr));
 	dw_pcie_writel_dbi(pci, PCIE_ATU_UPPER_TARGET,
 			   upper_32_bits(pci_addr));
 	val = type | PCIE_ATU_FUNC_NUM(func_no);
-	val = ((upper_32_bits(size - 1)) && (pci->version >= 0x460A)) ?
-		val | PCIE_ATU_INCREASE_REGION_SIZE : val;
+	if (upper_32_bits(limit_addr) > upper_32_bits(cpu_addr) &&
+	    pci->version >= 0x460A)
+		val |= PCIE_ATU_INCREASE_REGION_SIZE;
 	if (pci->version == 0x490A)
 		val = dw_pcie_enable_ecrc(val);
 	dw_pcie_writel_dbi(pci, PCIE_ATU_CR1, val);
@@ -491,7 +495,7 @@ int dw_pcie_prog_inbound_atu(struct dw_pcie *pci, u8 func_no, int index,
 void dw_pcie_disable_atu(struct dw_pcie *pci, int index,
 			 enum dw_pcie_region_type type)
 {
-	int region;
+	u32 region;
 
 	switch (type) {
 	case DW_PCIE_REGION_INBOUND:
@@ -504,8 +508,18 @@ void dw_pcie_disable_atu(struct dw_pcie *pci, int index,
 		return;
 	}
 
-	dw_pcie_writel_dbi(pci, PCIE_ATU_VIEWPORT, region | index);
-	dw_pcie_writel_dbi(pci, PCIE_ATU_CR2, ~(u32)PCIE_ATU_ENABLE);
+	if (pci->iatu_unroll_enabled) {
+		if (region == PCIE_ATU_REGION_INBOUND) {
+			dw_pcie_writel_ib_unroll(pci, index, PCIE_ATU_UNR_REGION_CTRL2,
+						 ~(u32)PCIE_ATU_ENABLE);
+		} else {
+			dw_pcie_writel_ob_unroll(pci, index, PCIE_ATU_UNR_REGION_CTRL2,
+						 ~(u32)PCIE_ATU_ENABLE);
+		}
+	} else {
+		dw_pcie_writel_dbi(pci, PCIE_ATU_VIEWPORT, region | index);
+		dw_pcie_writel_dbi(pci, PCIE_ATU_CR2, ~(u32)PCIE_ATU_ENABLE);
+	}
 }
 
 int dw_pcie_wait_for_link(struct dw_pcie *pci)
@@ -726,6 +740,13 @@ void dw_pcie_setup(struct dw_pcie *pci)
 	val |= PORT_LINK_DLL_LINK_EN;
 	dw_pcie_writel_dbi(pci, PCIE_PORT_LINK_CONTROL, val);
 
+	if (of_property_read_bool(np, "snps,enable-cdm-check")) {
+		val = dw_pcie_readl_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS);
+		val |= PCIE_PL_CHK_REG_CHK_REG_CONTINUOUS |
+		       PCIE_PL_CHK_REG_CHK_REG_START;
+		dw_pcie_writel_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS, val);
+	}
+
 	of_property_read_u32(np, "num-lanes", &pci->num_lanes);
 	if (!pci->num_lanes) {
 		dev_dbg(pci->dev, "Using h/w default number of lanes\n");
@@ -772,11 +793,4 @@ void dw_pcie_setup(struct dw_pcie *pci)
 		break;
 	}
 	dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, val);
-
-	if (of_property_read_bool(np, "snps,enable-cdm-check")) {
-		val = dw_pcie_readl_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS);
-		val |= PCIE_PL_CHK_REG_CHK_REG_CONTINUOUS |
-		       PCIE_PL_CHK_REG_CHK_REG_START;
-		dw_pcie_writel_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS, val);
-	}
 }
diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
index b139a2e4af12..4c599699e3c8 100644
--- a/drivers/pci/controller/dwc/pcie-qcom.c
+++ b/drivers/pci/controller/dwc/pcie-qcom.c
@@ -325,8 +325,6 @@ static int qcom_pcie_init_2_1_0(struct qcom_pcie *pcie)
 	reset_control_assert(res->ext_reset);
 	reset_control_assert(res->phy_reset);
 
-	writel(1, pcie->parf + PCIE20_PARF_PHY_CTRL);
-
 	ret = regulator_bulk_enable(ARRAY_SIZE(res->supplies), res->supplies);
 	if (ret < 0) {
 		dev_err(dev, "cannot enable regulators\n");
@@ -369,15 +367,15 @@ static int qcom_pcie_init_2_1_0(struct qcom_pcie *pcie)
 		goto err_deassert_axi;
 	}
 
-	ret = clk_bulk_prepare_enable(ARRAY_SIZE(res->clks), res->clks);
-	if (ret)
-		goto err_clks;
-
 	/* enable PCIe clocks and resets */
 	val = readl(pcie->parf + PCIE20_PARF_PHY_CTRL);
 	val &= ~BIT(0);
 	writel(val, pcie->parf + PCIE20_PARF_PHY_CTRL);
 
+	ret = clk_bulk_prepare_enable(ARRAY_SIZE(res->clks), res->clks);
+	if (ret)
+		goto err_clks;
+
 	if (of_device_is_compatible(node, "qcom,pcie-ipq8064") ||
 	    of_device_is_compatible(node, "qcom,pcie-ipq8064-v2")) {
 		writel(PCS_DEEMPH_TX_DEEMPH_GEN1(24) |
@@ -1026,9 +1024,7 @@ static int qcom_pcie_init_2_3_3(struct qcom_pcie *pcie)
 	struct qcom_pcie_resources_2_3_3 *res = &pcie->res.v2_3_3;
 	struct dw_pcie *pci = pcie->pci;
 	struct device *dev = pci->dev;
-	u16 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP);
 	int i, ret;
-	u32 val;
 
 	for (i = 0; i < ARRAY_SIZE(res->rst); i++) {
 		ret = reset_control_assert(res->rst[i]);
@@ -1085,6 +1081,33 @@ static int qcom_pcie_init_2_3_3(struct qcom_pcie *pcie)
 		goto err_clk_aux;
 	}
 
+	return 0;
+
+err_clk_aux:
+	clk_disable_unprepare(res->ahb_clk);
+err_clk_ahb:
+	clk_disable_unprepare(res->axi_s_clk);
+err_clk_axi_s:
+	clk_disable_unprepare(res->axi_m_clk);
+err_clk_axi_m:
+	clk_disable_unprepare(res->iface);
+err_clk_iface:
+	/*
+	 * Not checking for failure, will anyway return
+	 * the original failure in 'ret'.
+	 */
+	for (i = 0; i < ARRAY_SIZE(res->rst); i++)
+		reset_control_assert(res->rst[i]);
+
+	return ret;
+}
+
+static int qcom_pcie_post_init_2_3_3(struct qcom_pcie *pcie)
+{
+	struct dw_pcie *pci = pcie->pci;
+	u16 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP);
+	u32 val;
+
 	writel(SLV_ADDR_SPACE_SZ,
 		pcie->parf + PCIE20_v3_PARF_SLV_ADDR_SPACE_SIZE);
 
@@ -1112,24 +1135,6 @@ static int qcom_pcie_init_2_3_3(struct qcom_pcie *pcie)
 		PCI_EXP_DEVCTL2);
 
 	return 0;
-
-err_clk_aux:
-	clk_disable_unprepare(res->ahb_clk);
-err_clk_ahb:
-	clk_disable_unprepare(res->axi_s_clk);
-err_clk_axi_s:
-	clk_disable_unprepare(res->axi_m_clk);
-err_clk_axi_m:
-	clk_disable_unprepare(res->iface);
-err_clk_iface:
-	/*
-	 * Not checking for failure, will anyway return
-	 * the original failure in 'ret'.
-	 */
-	for (i = 0; i < ARRAY_SIZE(res->rst); i++)
-		reset_control_assert(res->rst[i]);
-
-	return ret;
 }
 
 static int qcom_pcie_get_resources_2_7_0(struct qcom_pcie *pcie)
@@ -1425,6 +1430,7 @@ static const struct qcom_pcie_ops ops_2_4_0 = {
 static const struct qcom_pcie_ops ops_2_3_3 = {
 	.get_resources = qcom_pcie_get_resources_2_3_3,
 	.init = qcom_pcie_init_2_3_3,
+	.post_init = qcom_pcie_post_init_2_3_3,
 	.deinit = qcom_pcie_deinit_2_3_3,
 	.ltssm_enable = qcom_pcie_2_3_2_ltssm_enable,
 };
diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c
index 904976913081..bdd84765e646 100644
--- a/drivers/pci/controller/dwc/pcie-tegra194.c
+++ b/drivers/pci/controller/dwc/pcie-tegra194.c
@@ -352,15 +352,14 @@ static irqreturn_t tegra_pcie_rp_irq_handler(int irq, void *arg)
 	struct tegra_pcie_dw *pcie = arg;
 	struct dw_pcie *pci = &pcie->pci;
 	struct pcie_port *pp = &pci->pp;
-	u32 val, tmp;
+	u32 val, status_l0, status_l1;
 	u16 val_w;
 
-	val = appl_readl(pcie, APPL_INTR_STATUS_L0);
-	if (val & APPL_INTR_STATUS_L0_LINK_STATE_INT) {
-		val = appl_readl(pcie, APPL_INTR_STATUS_L1_0_0);
-		if (val & APPL_INTR_STATUS_L1_0_0_LINK_REQ_RST_NOT_CHGED) {
-			appl_writel(pcie, val, APPL_INTR_STATUS_L1_0_0);
-
+	status_l0 = appl_readl(pcie, APPL_INTR_STATUS_L0);
+	if (status_l0 & APPL_INTR_STATUS_L0_LINK_STATE_INT) {
+		status_l1 = appl_readl(pcie, APPL_INTR_STATUS_L1_0_0);
+		appl_writel(pcie, status_l1, APPL_INTR_STATUS_L1_0_0);
+		if (status_l1 & APPL_INTR_STATUS_L1_0_0_LINK_REQ_RST_NOT_CHGED) {
 			/* SBR & Surprise Link Down WAR */
 			val = appl_readl(pcie, APPL_CAR_RESET_OVRD);
 			val &= ~APPL_CAR_RESET_OVRD_CYA_OVERRIDE_CORE_RST_N;
@@ -376,15 +375,15 @@ static irqreturn_t tegra_pcie_rp_irq_handler(int irq, void *arg)
 		}
 	}
 
-	if (val & APPL_INTR_STATUS_L0_INT_INT) {
-		val = appl_readl(pcie, APPL_INTR_STATUS_L1_8_0);
-		if (val & APPL_INTR_STATUS_L1_8_0_AUTO_BW_INT_STS) {
+	if (status_l0 & APPL_INTR_STATUS_L0_INT_INT) {
+		status_l1 = appl_readl(pcie, APPL_INTR_STATUS_L1_8_0);
+		if (status_l1 & APPL_INTR_STATUS_L1_8_0_AUTO_BW_INT_STS) {
 			appl_writel(pcie,
 				    APPL_INTR_STATUS_L1_8_0_AUTO_BW_INT_STS,
 				    APPL_INTR_STATUS_L1_8_0);
 			apply_bad_link_workaround(pp);
 		}
-		if (val & APPL_INTR_STATUS_L1_8_0_BW_MGT_INT_STS) {
+		if (status_l1 & APPL_INTR_STATUS_L1_8_0_BW_MGT_INT_STS) {
 			appl_writel(pcie,
 				    APPL_INTR_STATUS_L1_8_0_BW_MGT_INT_STS,
 				    APPL_INTR_STATUS_L1_8_0);
@@ -396,25 +395,24 @@ static irqreturn_t tegra_pcie_rp_irq_handler(int irq, void *arg)
 		}
 	}
 
-	val = appl_readl(pcie, APPL_INTR_STATUS_L0);
-	if (val & APPL_INTR_STATUS_L0_CDM_REG_CHK_INT) {
-		val = appl_readl(pcie, APPL_INTR_STATUS_L1_18);
-		tmp = dw_pcie_readl_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS);
-		if (val & APPL_INTR_STATUS_L1_18_CDM_REG_CHK_CMPLT) {
+	if (status_l0 & APPL_INTR_STATUS_L0_CDM_REG_CHK_INT) {
+		status_l1 = appl_readl(pcie, APPL_INTR_STATUS_L1_18);
+		val = dw_pcie_readl_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS);
+		if (status_l1 & APPL_INTR_STATUS_L1_18_CDM_REG_CHK_CMPLT) {
 			dev_info(pci->dev, "CDM check complete\n");
-			tmp |= PCIE_PL_CHK_REG_CHK_REG_COMPLETE;
+			val |= PCIE_PL_CHK_REG_CHK_REG_COMPLETE;
 		}
-		if (val & APPL_INTR_STATUS_L1_18_CDM_REG_CHK_CMP_ERR) {
+		if (status_l1 & APPL_INTR_STATUS_L1_18_CDM_REG_CHK_CMP_ERR) {
 			dev_err(pci->dev, "CDM comparison mismatch\n");
-			tmp |= PCIE_PL_CHK_REG_CHK_REG_COMPARISON_ERROR;
+			val |= PCIE_PL_CHK_REG_CHK_REG_COMPARISON_ERROR;
 		}
-		if (val & APPL_INTR_STATUS_L1_18_CDM_REG_CHK_LOGIC_ERR) {
+		if (status_l1 & APPL_INTR_STATUS_L1_18_CDM_REG_CHK_LOGIC_ERR) {
 			dev_err(pci->dev, "CDM Logic error\n");
-			tmp |= PCIE_PL_CHK_REG_CHK_REG_LOGIC_ERROR;
+			val |= PCIE_PL_CHK_REG_CHK_REG_LOGIC_ERROR;
 		}
-		dw_pcie_writel_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS, tmp);
-		tmp = dw_pcie_readl_dbi(pci, PCIE_PL_CHK_REG_ERR_ADDR);
-		dev_err(pci->dev, "CDM Error Address Offset = 0x%08X\n", tmp);
+		dw_pcie_writel_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS, val);
+		val = dw_pcie_readl_dbi(pci, PCIE_PL_CHK_REG_ERR_ADDR);
+		dev_err(pci->dev, "CDM Error Address Offset = 0x%08X\n", val);
 	}
 
 	return IRQ_HANDLED;
@@ -980,7 +978,7 @@ retry_link:
 		offset = dw_pcie_find_ext_capability(pci, PCI_EXT_CAP_ID_DLF);
 		val = dw_pcie_readl_dbi(pci, offset + PCI_DLF_CAP);
 		val &= ~PCI_DLF_EXCHANGE_ENABLE;
-		dw_pcie_writel_dbi(pci, offset, val);
+		dw_pcie_writel_dbi(pci, offset + PCI_DLF_CAP, val);
 
 		tegra_pcie_dw_host_init(pp);
 		dw_pcie_setup_rc(pp);
@@ -1951,6 +1949,7 @@ static int tegra_pcie_config_ep(struct tegra_pcie_dw *pcie,
 	if (ret) {
 		dev_err(dev, "Failed to initialize DWC Endpoint subsystem: %d\n",
 			ret);
+		pm_runtime_disable(dev);
 		return ret;
 	}
 
diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c
index 7cc2c54daad0..215f7510de9a 100644
--- a/drivers/pci/controller/pci-aardvark.c
+++ b/drivers/pci/controller/pci-aardvark.c
@@ -8,6 +8,7 @@
  * Author: Hezi Shahmoon <hezi.shahmoon@marvell.com>
  */
 
+#include <linux/bitfield.h>
 #include <linux/delay.h>
 #include <linux/gpio/consumer.h>
 #include <linux/interrupt.h>
@@ -857,14 +858,11 @@ advk_pci_bridge_emul_pcie_conf_read(struct pci_bridge_emul *bridge,
 
 
 	switch (reg) {
-	case PCI_EXP_SLTCTL:
-		*value = PCI_EXP_SLTSTA_PDS << 16;
-		return PCI_BRIDGE_EMUL_HANDLED;
-
 	/*
-	 * PCI_EXP_RTCTL and PCI_EXP_RTSTA are also supported, but do not need
-	 * to be handled here, because their values are stored in emulated
-	 * config space buffer, and we read them from there when needed.
+	 * PCI_EXP_SLTCAP, PCI_EXP_SLTCTL, PCI_EXP_RTCTL and PCI_EXP_RTSTA are
+	 * also supported, but do not need to be handled here, because their
+	 * values are stored in emulated config space buffer, and we read them
+	 * from there when needed.
 	 */
 
 	case PCI_EXP_LNKCAP: {
@@ -977,8 +975,25 @@ static int advk_sw_pci_bridge_init(struct advk_pcie *pcie)
 	/* Support interrupt A for MSI feature */
 	bridge->conf.intpin = PCI_INTERRUPT_INTA;
 
-	/* Aardvark HW provides PCIe Capability structure in version 2 */
-	bridge->pcie_conf.cap = cpu_to_le16(2);
+	/*
+	 * Aardvark HW provides PCIe Capability structure in version 2 and
+	 * indicate slot support, which is emulated.
+	 */
+	bridge->pcie_conf.cap = cpu_to_le16(2 | PCI_EXP_FLAGS_SLOT);
+
+	/*
+	 * Set Presence Detect State bit permanently since there is no support
+	 * for unplugging the card nor detecting whether it is plugged. (If a
+	 * platform exists in the future that supports it, via a GPIO for
+	 * example, it should be implemented via this bit.)
+	 *
+	 * Set physical slot number to 1 since there is only one port and zero
+	 * value is reserved for ports within the same silicon as Root Port
+	 * which is not our case.
+	 */
+	bridge->pcie_conf.slotcap = cpu_to_le32(FIELD_PREP(PCI_EXP_SLTCAP_PSN,
+							   1));
+	bridge->pcie_conf.slotsta = cpu_to_le16(PCI_EXP_SLTSTA_PDS);
 
 	/* Indicates supports for Completion Retry Status */
 	bridge->pcie_conf.rootcap = cpu_to_le16(PCI_EXP_RTCAP_CRSVIS);
diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index 5b156c563e3a..9b54715a4b63 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -1142,6 +1142,10 @@ static void hv_int_desc_free(struct hv_pci_dev *hpdev,
 		u8 buffer[sizeof(struct pci_delete_interrupt)];
 	} ctxt;
 
+	if (!int_desc->vector_count) {
+		kfree(int_desc);
+		return;
+	}
 	memset(&ctxt, 0, sizeof(ctxt));
 	int_pkt = (struct pci_delete_interrupt *)&ctxt.pkt.message;
 	int_pkt->message_type.type =
@@ -1204,6 +1208,28 @@ static void hv_irq_mask(struct irq_data *data)
 	pci_msi_mask_irq(data);
 }
 
+static unsigned int hv_msi_get_int_vector(struct irq_data *data)
+{
+	struct irq_cfg *cfg = irqd_cfg(data);
+
+	return cfg->vector;
+}
+
+static int hv_msi_prepare(struct irq_domain *domain, struct device *dev,
+			  int nvec, msi_alloc_info_t *info)
+{
+	int ret = pci_msi_prepare(domain, dev, nvec, info);
+
+	/*
+	 * By using the interrupt remapper in the hypervisor IOMMU, contiguous
+	 * CPU vectors is not needed for multi-MSI
+	 */
+	if (info->type == X86_IRQ_ALLOC_TYPE_PCI_MSI)
+		info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS;
+
+	return ret;
+}
+
 /**
  * hv_irq_unmask() - "Unmask" the IRQ by setting its current
  * affinity.
@@ -1219,6 +1245,7 @@ static void hv_irq_unmask(struct irq_data *data)
 	struct msi_desc *msi_desc = irq_data_get_msi_desc(data);
 	struct irq_cfg *cfg = irqd_cfg(data);
 	struct hv_retarget_device_interrupt *params;
+	struct tran_int_desc *int_desc;
 	struct hv_pcibus_device *hbus;
 	struct cpumask *dest;
 	cpumask_var_t tmp;
@@ -1233,6 +1260,7 @@ static void hv_irq_unmask(struct irq_data *data)
 	pdev = msi_desc_to_pci_dev(msi_desc);
 	pbus = pdev->bus;
 	hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata);
+	int_desc = data->chip_data;
 
 	spin_lock_irqsave(&hbus->retarget_msi_interrupt_lock, flags);
 
@@ -1240,7 +1268,8 @@ static void hv_irq_unmask(struct irq_data *data)
 	memset(params, 0, sizeof(*params));
 	params->partition_id = HV_PARTITION_ID_SELF;
 	params->int_entry.source = HV_INTERRUPT_SOURCE_MSI;
-	hv_set_msi_entry_from_desc(&params->int_entry.msi_entry, msi_desc);
+	params->int_entry.msi_entry.address.as_uint32 = int_desc->address & 0xffffffff;
+	params->int_entry.msi_entry.data.as_uint32 = int_desc->data;
 	params->device_id = (hbus->hdev->dev_instance.b[5] << 24) |
 			   (hbus->hdev->dev_instance.b[4] << 16) |
 			   (hbus->hdev->dev_instance.b[7] << 8) |
@@ -1341,12 +1370,12 @@ static void hv_pci_compose_compl(void *context, struct pci_response *resp,
 
 static u32 hv_compose_msi_req_v1(
 	struct pci_create_interrupt *int_pkt, struct cpumask *affinity,
-	u32 slot, u8 vector)
+	u32 slot, u8 vector, u8 vector_count)
 {
 	int_pkt->message_type.type = PCI_CREATE_INTERRUPT_MESSAGE;
 	int_pkt->wslot.slot = slot;
 	int_pkt->int_desc.vector = vector;
-	int_pkt->int_desc.vector_count = 1;
+	int_pkt->int_desc.vector_count = vector_count;
 	int_pkt->int_desc.delivery_mode = APIC_DELIVERY_MODE_FIXED;
 
 	/*
@@ -1369,14 +1398,14 @@ static int hv_compose_msi_req_get_cpu(struct cpumask *affinity)
 
 static u32 hv_compose_msi_req_v2(
 	struct pci_create_interrupt2 *int_pkt, struct cpumask *affinity,
-	u32 slot, u8 vector)
+	u32 slot, u8 vector, u8 vector_count)
 {
 	int cpu;
 
 	int_pkt->message_type.type = PCI_CREATE_INTERRUPT_MESSAGE2;
 	int_pkt->wslot.slot = slot;
 	int_pkt->int_desc.vector = vector;
-	int_pkt->int_desc.vector_count = 1;
+	int_pkt->int_desc.vector_count = vector_count;
 	int_pkt->int_desc.delivery_mode = APIC_DELIVERY_MODE_FIXED;
 	cpu = hv_compose_msi_req_get_cpu(affinity);
 	int_pkt->int_desc.processor_array[0] =
@@ -1388,7 +1417,7 @@ static u32 hv_compose_msi_req_v2(
 
 static u32 hv_compose_msi_req_v3(
 	struct pci_create_interrupt3 *int_pkt, struct cpumask *affinity,
-	u32 slot, u32 vector)
+	u32 slot, u32 vector, u8 vector_count)
 {
 	int cpu;
 
@@ -1396,7 +1425,7 @@ static u32 hv_compose_msi_req_v3(
 	int_pkt->wslot.slot = slot;
 	int_pkt->int_desc.vector = vector;
 	int_pkt->int_desc.reserved = 0;
-	int_pkt->int_desc.vector_count = 1;
+	int_pkt->int_desc.vector_count = vector_count;
 	int_pkt->int_desc.delivery_mode = APIC_DELIVERY_MODE_FIXED;
 	cpu = hv_compose_msi_req_get_cpu(affinity);
 	int_pkt->int_desc.processor_array[0] =
@@ -1419,7 +1448,6 @@ static u32 hv_compose_msi_req_v3(
  */
 static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 {
-	struct irq_cfg *cfg = irqd_cfg(data);
 	struct hv_pcibus_device *hbus;
 	struct vmbus_channel *channel;
 	struct hv_pci_dev *hpdev;
@@ -1428,6 +1456,8 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 	struct cpumask *dest;
 	struct compose_comp_ctxt comp;
 	struct tran_int_desc *int_desc;
+	struct msi_desc *msi_desc;
+	u8 vector, vector_count;
 	struct {
 		struct pci_packet pci_pkt;
 		union {
@@ -1440,7 +1470,17 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 	u32 size;
 	int ret;
 
-	pdev = msi_desc_to_pci_dev(irq_data_get_msi_desc(data));
+	/* Reuse the previous allocation */
+	if (data->chip_data) {
+		int_desc = data->chip_data;
+		msg->address_hi = int_desc->address >> 32;
+		msg->address_lo = int_desc->address & 0xffffffff;
+		msg->data = int_desc->data;
+		return;
+	}
+
+	msi_desc  = irq_data_get_msi_desc(data);
+	pdev = msi_desc_to_pci_dev(msi_desc);
 	dest = irq_data_get_effective_affinity_mask(data);
 	pbus = pdev->bus;
 	hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata);
@@ -1449,17 +1489,40 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 	if (!hpdev)
 		goto return_null_message;
 
-	/* Free any previous message that might have already been composed. */
-	if (data->chip_data) {
-		int_desc = data->chip_data;
-		data->chip_data = NULL;
-		hv_int_desc_free(hpdev, int_desc);
-	}
-
 	int_desc = kzalloc(sizeof(*int_desc), GFP_ATOMIC);
 	if (!int_desc)
 		goto drop_reference;
 
+	if (!msi_desc->msi_attrib.is_msix && msi_desc->nvec_used > 1) {
+		/*
+		 * If this is not the first MSI of Multi MSI, we already have
+		 * a mapping.  Can exit early.
+		 */
+		if (msi_desc->irq != data->irq) {
+			data->chip_data = int_desc;
+			int_desc->address = msi_desc->msg.address_lo |
+					    (u64)msi_desc->msg.address_hi << 32;
+			int_desc->data = msi_desc->msg.data +
+					 (data->irq - msi_desc->irq);
+			msg->address_hi = msi_desc->msg.address_hi;
+			msg->address_lo = msi_desc->msg.address_lo;
+			msg->data = int_desc->data;
+			put_pcichild(hpdev);
+			return;
+		}
+		/*
+		 * The vector we select here is a dummy value.  The correct
+		 * value gets sent to the hypervisor in unmask().  This needs
+		 * to be aligned with the count, and also not zero.  Multi-msi
+		 * is powers of 2 up to 32, so 32 will always work here.
+		 */
+		vector = 32;
+		vector_count = msi_desc->nvec_used;
+	} else {
+		vector = hv_msi_get_int_vector(data);
+		vector_count = 1;
+	}
+
 	memset(&ctxt, 0, sizeof(ctxt));
 	init_completion(&comp.comp_pkt.host_event);
 	ctxt.pci_pkt.completion_func = hv_pci_compose_compl;
@@ -1470,7 +1533,8 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 		size = hv_compose_msi_req_v1(&ctxt.int_pkts.v1,
 					dest,
 					hpdev->desc.win_slot.slot,
-					cfg->vector);
+					vector,
+					vector_count);
 		break;
 
 	case PCI_PROTOCOL_VERSION_1_2:
@@ -1478,14 +1542,16 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 		size = hv_compose_msi_req_v2(&ctxt.int_pkts.v2,
 					dest,
 					hpdev->desc.win_slot.slot,
-					cfg->vector);
+					vector,
+					vector_count);
 		break;
 
 	case PCI_PROTOCOL_VERSION_1_4:
 		size = hv_compose_msi_req_v3(&ctxt.int_pkts.v3,
 					dest,
 					hpdev->desc.win_slot.slot,
-					cfg->vector);
+					vector,
+					vector_count);
 		break;
 
 	default:
@@ -1601,7 +1667,7 @@ static struct irq_chip hv_msi_irq_chip = {
 };
 
 static struct msi_domain_ops hv_msi_ops = {
-	.msi_prepare	= pci_msi_prepare,
+	.msi_prepare	= hv_msi_prepare,
 	.msi_free	= hv_msi_free,
 };
 
diff --git a/drivers/pci/controller/pcie-mediatek-gen3.c b/drivers/pci/controller/pcie-mediatek-gen3.c
index 21207df680cc..36c8702439e9 100644
--- a/drivers/pci/controller/pcie-mediatek-gen3.c
+++ b/drivers/pci/controller/pcie-mediatek-gen3.c
@@ -600,7 +600,8 @@ static int mtk_pcie_init_irq_domains(struct mtk_pcie_port *port)
 						  &intx_domain_ops, port);
 	if (!port->intx_domain) {
 		dev_err(dev, "failed to create INTx IRQ domain\n");
-		return -ENODEV;
+		ret = -ENODEV;
+		goto out_put_node;
 	}
 
 	/* Setup MSI */
@@ -623,6 +624,7 @@ static int mtk_pcie_init_irq_domains(struct mtk_pcie_port *port)
 		goto err_msi_domain;
 	}
 
+	of_node_put(intc_node);
 	return 0;
 
 err_msi_domain:
@@ -630,6 +632,8 @@ err_msi_domain:
 err_msi_bottom_domain:
 	irq_domain_remove(port->intx_domain);
 
+out_put_node:
+	of_node_put(intc_node);
 	return ret;
 }
 
diff --git a/drivers/pci/controller/pcie-microchip-host.c b/drivers/pci/controller/pcie-microchip-host.c
index fa209ad067bf..6e8a6540b377 100644
--- a/drivers/pci/controller/pcie-microchip-host.c
+++ b/drivers/pci/controller/pcie-microchip-host.c
@@ -894,6 +894,7 @@ static int mc_pcie_init_irq_domains(struct mc_port *port)
 						   &event_domain_ops, port);
 	if (!port->event_domain) {
 		dev_err(dev, "failed to get event domain\n");
+		of_node_put(pcie_intc_node);
 		return -ENOMEM;
 	}
 
@@ -903,6 +904,7 @@ static int mc_pcie_init_irq_domains(struct mc_port *port)
 						  &intx_domain_ops, port);
 	if (!port->intx_domain) {
 		dev_err(dev, "failed to get an INTx IRQ domain\n");
+		of_node_put(pcie_intc_node);
 		return -ENOMEM;
 	}
 
diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c
index 5b833f00e980..a5ed779b0a51 100644
--- a/drivers/pci/endpoint/functions/pci-epf-test.c
+++ b/drivers/pci/endpoint/functions/pci-epf-test.c
@@ -627,7 +627,6 @@ static void pci_epf_test_unbind(struct pci_epf *epf)
 
 	cancel_delayed_work(&epf_test->cmd_handler);
 	pci_epf_test_clean_dma_chan(epf_test);
-	pci_epc_stop(epc);
 	for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) {
 		epf_bar = &epf->bar[bar];
 
diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h
index 10d7e7e1b553..e0a614acee05 100644
--- a/drivers/pci/hotplug/pciehp.h
+++ b/drivers/pci/hotplug/pciehp.h
@@ -192,6 +192,8 @@ int pciehp_get_attention_status(struct hotplug_slot *hotplug_slot, u8 *status);
 int pciehp_set_raw_indicator_status(struct hotplug_slot *h_slot, u8 status);
 int pciehp_get_raw_indicator_status(struct hotplug_slot *h_slot, u8 *status);
 
+int pciehp_slot_reset(struct pcie_device *dev);
+
 static inline const char *slot_name(struct controller *ctrl)
 {
 	return hotplug_slot_name(&ctrl->hotplug_slot);
diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
index e7fe4b42f039..4042d87d539d 100644
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -351,6 +351,8 @@ static struct pcie_port_service_driver hpdriver_portdrv = {
 	.runtime_suspend = pciehp_runtime_suspend,
 	.runtime_resume	= pciehp_runtime_resume,
 #endif	/* PM */
+
+	.slot_reset	= pciehp_slot_reset,
 };
 
 int __init pcie_hp_init(void)
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 8bedbc77fe95..60098a701e83 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -865,6 +865,32 @@ void pcie_disable_interrupt(struct controller *ctrl)
 	pcie_write_cmd(ctrl, 0, mask);
 }
 
+/**
+ * pciehp_slot_reset() - ignore link event caused by error-induced hot reset
+ * @dev: PCI Express port service device
+ *
+ * Called from pcie_portdrv_slot_reset() after AER or DPC initiated a reset
+ * further up in the hierarchy to recover from an error.  The reset was
+ * propagated down to this hotplug port.  Ignore the resulting link flap.
+ * If the link failed to retrain successfully, synthesize the ignored event.
+ * Surprise removal during reset is detected through Presence Detect Changed.
+ */
+int pciehp_slot_reset(struct pcie_device *dev)
+{
+	struct controller *ctrl = get_service_data(dev);
+
+	if (ctrl->state != ON_STATE)
+		return 0;
+
+	pcie_capability_write_word(dev->port, PCI_EXP_SLTSTA,
+				   PCI_EXP_SLTSTA_DLLSC);
+
+	if (!pciehp_check_link_active(ctrl))
+		pciehp_request(ctrl, PCI_EXP_SLTSTA_DLLSC);
+
+	return 0;
+}
+
 /*
  * pciehp has a 1:1 bus:slot relationship so we ultimately want a secondary
  * bus reset of the bridge, but at the same time we want to ensure that it is
diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c
index 50cdde3e9a8b..316fd2f44df4 100644
--- a/drivers/pci/p2pdma.c
+++ b/drivers/pci/p2pdma.c
@@ -219,7 +219,7 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size,
 	error = gen_pool_add_owner(p2pdma->pool, (unsigned long)addr,
 			pci_bus_address(pdev, bar) + offset,
 			range_len(&pgmap->range), dev_to_node(&pdev->dev),
-			pgmap->ref);
+			&pgmap->ref);
 	if (error)
 		goto pages_free;
 
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 80fe3e83c9f5..ca9ac8c6a202 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -538,7 +538,7 @@ static const char *aer_agent_string[] = {
 	u64 *stats = pdev->aer_stats->stats_array;			\
 	size_t len = 0;							\
 									\
-	for (i = 0; i < ARRAY_SIZE(strings_array); i++) {		\
+	for (i = 0; i < ARRAY_SIZE(pdev->aer_stats->stats_array); i++) {\
 		if (strings_array[i])					\
 			len += sysfs_emit_at(buf, len, "%s %llu\n",	\
 					     strings_array[i],		\
@@ -1347,6 +1347,11 @@ static int aer_probe(struct pcie_device *dev)
 	struct device *device = &dev->device;
 	struct pci_dev *port = dev->port;
 
+	BUILD_BUG_ON(ARRAY_SIZE(aer_correctable_error_string) <
+		     AER_MAX_TYPEOF_COR_ERRS);
+	BUILD_BUG_ON(ARRAY_SIZE(aer_uncorrectable_error_string) <
+		     AER_MAX_TYPEOF_UNCOR_ERRS);
+
 	/* Limit to Root Ports or Root Complex Event Collectors */
 	if ((pci_pcie_type(port) != PCI_EXP_TYPE_RC_EC) &&
 	    (pci_pcie_type(port) != PCI_EXP_TYPE_ROOT_PORT))
diff --git a/drivers/pci/pcie/portdrv.h b/drivers/pci/pcie/portdrv.h
index 2ff5724b8f13..41fe1ffd5907 100644
--- a/drivers/pci/pcie/portdrv.h
+++ b/drivers/pci/pcie/portdrv.h
@@ -85,6 +85,8 @@ struct pcie_port_service_driver {
 	int (*runtime_suspend)(struct pcie_device *dev);
 	int (*runtime_resume)(struct pcie_device *dev);
 
+	int (*slot_reset)(struct pcie_device *dev);
+
 	/* Device driver may resume normal operations */
 	void (*error_resume)(struct pci_dev *dev);
 
@@ -110,6 +112,7 @@ void pcie_port_service_unregister(struct pcie_port_service_driver *new);
 
 extern struct bus_type pcie_port_bus_type;
 int pcie_port_device_register(struct pci_dev *dev);
+int pcie_port_device_iter(struct device *dev, void *data);
 #ifdef CONFIG_PM
 int pcie_port_device_suspend(struct device *dev);
 int pcie_port_device_resume_noirq(struct device *dev);
diff --git a/drivers/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c
index 36b0c5c895bd..f0fab40ea531 100644
--- a/drivers/pci/pcie/portdrv_core.c
+++ b/drivers/pci/pcie/portdrv_core.c
@@ -396,24 +396,24 @@ error_disable:
 	return status;
 }
 
-#ifdef CONFIG_PM
-typedef int (*pcie_pm_callback_t)(struct pcie_device *);
+typedef int (*pcie_callback_t)(struct pcie_device *);
 
-static int pm_iter(struct device *dev, void *data)
+int pcie_port_device_iter(struct device *dev, void *data)
 {
 	struct pcie_port_service_driver *service_driver;
 	size_t offset = *(size_t *)data;
-	pcie_pm_callback_t cb;
+	pcie_callback_t cb;
 
 	if ((dev->bus == &pcie_port_bus_type) && dev->driver) {
 		service_driver = to_service_driver(dev->driver);
-		cb = *(pcie_pm_callback_t *)((void *)service_driver + offset);
+		cb = *(pcie_callback_t *)((void *)service_driver + offset);
 		if (cb)
 			return cb(to_pcie_device(dev));
 	}
 	return 0;
 }
 
+#ifdef CONFIG_PM
 /**
  * pcie_port_device_suspend - suspend port services associated with a PCIe port
  * @dev: PCI Express port to handle
@@ -421,13 +421,13 @@ static int pm_iter(struct device *dev, void *data)
 int pcie_port_device_suspend(struct device *dev)
 {
 	size_t off = offsetof(struct pcie_port_service_driver, suspend);
-	return device_for_each_child(dev, &off, pm_iter);
+	return device_for_each_child(dev, &off, pcie_port_device_iter);
 }
 
 int pcie_port_device_resume_noirq(struct device *dev)
 {
 	size_t off = offsetof(struct pcie_port_service_driver, resume_noirq);
-	return device_for_each_child(dev, &off, pm_iter);
+	return device_for_each_child(dev, &off, pcie_port_device_iter);
 }
 
 /**
@@ -437,7 +437,7 @@ int pcie_port_device_resume_noirq(struct device *dev)
 int pcie_port_device_resume(struct device *dev)
 {
 	size_t off = offsetof(struct pcie_port_service_driver, resume);
-	return device_for_each_child(dev, &off, pm_iter);
+	return device_for_each_child(dev, &off, pcie_port_device_iter);
 }
 
 /**
@@ -447,7 +447,7 @@ int pcie_port_device_resume(struct device *dev)
 int pcie_port_device_runtime_suspend(struct device *dev)
 {
 	size_t off = offsetof(struct pcie_port_service_driver, runtime_suspend);
-	return device_for_each_child(dev, &off, pm_iter);
+	return device_for_each_child(dev, &off, pcie_port_device_iter);
 }
 
 /**
@@ -457,7 +457,7 @@ int pcie_port_device_runtime_suspend(struct device *dev)
 int pcie_port_device_runtime_resume(struct device *dev)
 {
 	size_t off = offsetof(struct pcie_port_service_driver, runtime_resume);
-	return device_for_each_child(dev, &off, pm_iter);
+	return device_for_each_child(dev, &off, pcie_port_device_iter);
 }
 #endif /* PM */
 
diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c
index c7ff1eea225a..1af74c3d9d5d 100644
--- a/drivers/pci/pcie/portdrv_pci.c
+++ b/drivers/pci/pcie/portdrv_pci.c
@@ -160,6 +160,9 @@ static pci_ers_result_t pcie_portdrv_error_detected(struct pci_dev *dev,
 
 static pci_ers_result_t pcie_portdrv_slot_reset(struct pci_dev *dev)
 {
+	size_t off = offsetof(struct pcie_port_service_driver, slot_reset);
+	device_for_each_child(&dev->dev, &off, pcie_port_device_iter);
+
 	pci_restore_state(dev);
 	pci_save_state(dev);
 	return PCI_ERS_RESULT_RECOVERED;
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 4893b1e82403..a531064233f9 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -4923,6 +4923,9 @@ static const struct pci_dev_acs_enabled {
 	{ PCI_VENDOR_ID_AMPERE, 0xE00C, pci_quirk_xgene_acs },
 	/* Broadcom multi-function device */
 	{ PCI_VENDOR_ID_BROADCOM, 0x16D7, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_BROADCOM, 0x1750, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_BROADCOM, 0x1751, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_BROADCOM, 0x1752, pci_quirk_mf_endpoint_acs },
 	{ PCI_VENDOR_ID_BROADCOM, 0xD714, pci_quirk_brcm_acs },
 	/* Amazon Annapurna Labs */
 	{ PCI_VENDOR_ID_AMAZON_ANNAPURNA_LABS, 0x0031, pci_quirk_al_acs },
diff --git a/drivers/perf/arm_pmu_platform.c b/drivers/perf/arm_pmu_platform.c
index 513de1f54e2d..933b96e243b8 100644
--- a/drivers/perf/arm_pmu_platform.c
+++ b/drivers/perf/arm_pmu_platform.c
@@ -117,7 +117,7 @@ static int pmu_parse_irqs(struct arm_pmu *pmu)
 
 	if (num_irqs == 1) {
 		int irq = platform_get_irq(pdev, 0);
-		if (irq && irq_is_percpu_devid(irq))
+		if ((irq > 0) && irq_is_percpu_devid(irq))
 			return pmu_parse_percpu_irq(pmu, irq);
 	}
 
diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c
index d44bcc29d99c..cd5945e17fdf 100644
--- a/drivers/perf/arm_spe_pmu.c
+++ b/drivers/perf/arm_spe_pmu.c
@@ -39,6 +39,24 @@
 #include <asm/mmu.h>
 #include <asm/sysreg.h>
 
+/*
+ * Cache if the event is allowed to trace Context information.
+ * This allows us to perform the check, i.e, perfmon_capable(),
+ * in the context of the event owner, once, during the event_init().
+ */
+#define SPE_PMU_HW_FLAGS_CX			BIT(0)
+
+static void set_spe_event_has_cx(struct perf_event *event)
+{
+	if (IS_ENABLED(CONFIG_PID_IN_CONTEXTIDR) && perfmon_capable())
+		event->hw.flags |= SPE_PMU_HW_FLAGS_CX;
+}
+
+static bool get_spe_event_has_cx(struct perf_event *event)
+{
+	return !!(event->hw.flags & SPE_PMU_HW_FLAGS_CX);
+}
+
 #define ARM_SPE_BUF_PAD_BYTE			0
 
 struct arm_spe_pmu_buf {
@@ -272,7 +290,7 @@ static u64 arm_spe_event_to_pmscr(struct perf_event *event)
 	if (!attr->exclude_kernel)
 		reg |= BIT(SYS_PMSCR_EL1_E1SPE_SHIFT);
 
-	if (IS_ENABLED(CONFIG_PID_IN_CONTEXTIDR) && perfmon_capable())
+	if (get_spe_event_has_cx(event))
 		reg |= BIT(SYS_PMSCR_EL1_CX_SHIFT);
 
 	return reg;
@@ -709,10 +727,10 @@ static int arm_spe_pmu_event_init(struct perf_event *event)
 	    !(spe_pmu->features & SPE_PMU_FEAT_FILT_LAT))
 		return -EOPNOTSUPP;
 
+	set_spe_event_has_cx(event);
 	reg = arm_spe_event_to_pmscr(event);
 	if (!perfmon_capable() &&
 	    (reg & (BIT(SYS_PMSCR_EL1_PA_SHIFT) |
-		    BIT(SYS_PMSCR_EL1_CX_SHIFT) |
 		    BIT(SYS_PMSCR_EL1_PCT_SHIFT))))
 		return -EACCES;
 
diff --git a/drivers/phy/samsung/phy-exynos-pcie.c b/drivers/phy/samsung/phy-exynos-pcie.c
index 578cfe07d07a..53c9230c2907 100644
--- a/drivers/phy/samsung/phy-exynos-pcie.c
+++ b/drivers/phy/samsung/phy-exynos-pcie.c
@@ -51,6 +51,13 @@ static int exynos5433_pcie_phy_init(struct phy *phy)
 {
 	struct exynos_pcie_phy *ep = phy_get_drvdata(phy);
 
+	regmap_update_bits(ep->pmureg, EXYNOS5433_PMU_PCIE_PHY_OFFSET,
+			   BIT(0), 1);
+	regmap_update_bits(ep->fsysreg, PCIE_EXYNOS5433_PHY_GLOBAL_RESET,
+			   PCIE_APP_REQ_EXIT_L1_MODE, 0);
+	regmap_update_bits(ep->fsysreg, PCIE_EXYNOS5433_PHY_L1SUB_CM_CON,
+			   PCIE_REFCLK_GATING_EN, 0);
+
 	regmap_update_bits(ep->fsysreg,	PCIE_EXYNOS5433_PHY_COMMON_RESET,
 			   PCIE_PHY_RESET, 1);
 	regmap_update_bits(ep->fsysreg, PCIE_EXYNOS5433_PHY_MAC_RESET,
@@ -109,20 +116,7 @@ static int exynos5433_pcie_phy_init(struct phy *phy)
 	return 0;
 }
 
-static int exynos5433_pcie_phy_power_on(struct phy *phy)
-{
-	struct exynos_pcie_phy *ep = phy_get_drvdata(phy);
-
-	regmap_update_bits(ep->pmureg, EXYNOS5433_PMU_PCIE_PHY_OFFSET,
-			   BIT(0), 1);
-	regmap_update_bits(ep->fsysreg, PCIE_EXYNOS5433_PHY_GLOBAL_RESET,
-			   PCIE_APP_REQ_EXIT_L1_MODE, 0);
-	regmap_update_bits(ep->fsysreg, PCIE_EXYNOS5433_PHY_L1SUB_CM_CON,
-			   PCIE_REFCLK_GATING_EN, 0);
-	return 0;
-}
-
-static int exynos5433_pcie_phy_power_off(struct phy *phy)
+static int exynos5433_pcie_phy_exit(struct phy *phy)
 {
 	struct exynos_pcie_phy *ep = phy_get_drvdata(phy);
 
@@ -135,8 +129,7 @@ static int exynos5433_pcie_phy_power_off(struct phy *phy)
 
 static const struct phy_ops exynos5433_phy_ops = {
 	.init		= exynos5433_pcie_phy_init,
-	.power_on	= exynos5433_pcie_phy_power_on,
-	.power_off	= exynos5433_pcie_phy_power_off,
+	.exit		= exynos5433_pcie_phy_exit,
 	.owner		= THIS_MODULE,
 };
 
diff --git a/drivers/phy/samsung/phy-exynosautov9-ufs.c b/drivers/phy/samsung/phy-exynosautov9-ufs.c
index 36398a15c2db..d043dfdb598a 100644
--- a/drivers/phy/samsung/phy-exynosautov9-ufs.c
+++ b/drivers/phy/samsung/phy-exynosautov9-ufs.c
@@ -31,22 +31,22 @@ static const struct samsung_ufs_phy_cfg exynosautov9_pre_init_cfg[] = {
 	PHY_COMN_REG_CFG(0x023, 0xc0, PWR_MODE_ANY),
 	PHY_COMN_REG_CFG(0x023, 0x00, PWR_MODE_ANY),
 
-	PHY_TRSV_REG_CFG(0x042, 0x5d, PWR_MODE_ANY),
-	PHY_TRSV_REG_CFG(0x043, 0x80, PWR_MODE_ANY),
+	PHY_TRSV_REG_CFG_AUTOV9(0x042, 0x5d, PWR_MODE_ANY),
+	PHY_TRSV_REG_CFG_AUTOV9(0x043, 0x80, PWR_MODE_ANY),
 
 	END_UFS_PHY_CFG,
 };
 
 /* Calibration for HS mode series A/B */
 static const struct samsung_ufs_phy_cfg exynosautov9_pre_pwr_hs_cfg[] = {
-	PHY_TRSV_REG_CFG(0x032, 0xbc, PWR_MODE_HS_ANY),
-	PHY_TRSV_REG_CFG(0x03c, 0x7f, PWR_MODE_HS_ANY),
-	PHY_TRSV_REG_CFG(0x048, 0xc0, PWR_MODE_HS_ANY),
+	PHY_TRSV_REG_CFG_AUTOV9(0x032, 0xbc, PWR_MODE_HS_ANY),
+	PHY_TRSV_REG_CFG_AUTOV9(0x03c, 0x7f, PWR_MODE_HS_ANY),
+	PHY_TRSV_REG_CFG_AUTOV9(0x048, 0xc0, PWR_MODE_HS_ANY),
 
-	PHY_TRSV_REG_CFG(0x04a, 0x00, PWR_MODE_HS_G3_SER_B),
-	PHY_TRSV_REG_CFG(0x04b, 0x10, PWR_MODE_HS_G1_SER_B |
-				      PWR_MODE_HS_G3_SER_B),
-	PHY_TRSV_REG_CFG(0x04d, 0x63, PWR_MODE_HS_G3_SER_B),
+	PHY_TRSV_REG_CFG_AUTOV9(0x04a, 0x00, PWR_MODE_HS_G3_SER_B),
+	PHY_TRSV_REG_CFG_AUTOV9(0x04b, 0x10, PWR_MODE_HS_G1_SER_B |
+				PWR_MODE_HS_G3_SER_B),
+	PHY_TRSV_REG_CFG_AUTOV9(0x04d, 0x63, PWR_MODE_HS_G3_SER_B),
 
 	END_UFS_PHY_CFG,
 };
diff --git a/drivers/phy/st/phy-stm32-usbphyc.c b/drivers/phy/st/phy-stm32-usbphyc.c
index da05642d3bd4..cd0747ab6267 100644
--- a/drivers/phy/st/phy-stm32-usbphyc.c
+++ b/drivers/phy/st/phy-stm32-usbphyc.c
@@ -279,7 +279,9 @@ static int stm32_usbphyc_phy_init(struct phy *phy)
 	return 0;
 
 pll_disable:
-	return stm32_usbphyc_pll_disable(usbphyc);
+	stm32_usbphyc_pll_disable(usbphyc);
+
+	return ret;
 }
 
 static int stm32_usbphyc_phy_exit(struct phy *phy)
diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed.c b/drivers/pinctrl/aspeed/pinctrl-aspeed.c
index c94e24aadf92..83d47ff1cea8 100644
--- a/drivers/pinctrl/aspeed/pinctrl-aspeed.c
+++ b/drivers/pinctrl/aspeed/pinctrl-aspeed.c
@@ -236,11 +236,11 @@ int aspeed_pinmux_set_mux(struct pinctrl_dev *pctldev, unsigned int function,
 		const struct aspeed_sig_expr **funcs;
 		const struct aspeed_sig_expr ***prios;
 
-		pr_debug("Muxing pin %s for %s\n", pdesc->name, pfunc->name);
-
 		if (!pdesc)
 			return -EINVAL;
 
+		pr_debug("Muxing pin %s for %s\n", pdesc->name, pfunc->name);
+
 		prios = pdesc->prios;
 
 		if (!prios)
diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index 826d494f3cc6..48f55991ae8c 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -1626,16 +1626,14 @@ EXPORT_SYMBOL_GPL(intel_pinctrl_probe_by_uid);
 
 const struct intel_pinctrl_soc_data *intel_pinctrl_get_soc_data(struct platform_device *pdev)
 {
+	const struct intel_pinctrl_soc_data * const *table;
 	const struct intel_pinctrl_soc_data *data = NULL;
-	const struct intel_pinctrl_soc_data **table;
-	struct acpi_device *adev;
-	unsigned int i;
 
-	adev = ACPI_COMPANION(&pdev->dev);
-	if (adev) {
-		const void *match = device_get_match_data(&pdev->dev);
+	table = device_get_match_data(&pdev->dev);
+	if (table) {
+		struct acpi_device *adev = ACPI_COMPANION(&pdev->dev);
+		unsigned int i;
 
-		table = (const struct intel_pinctrl_soc_data **)match;
 		for (i = 0; table[i]; i++) {
 			if (!strcmp(adev->pnp.unique_id, table[i]->uid)) {
 				data = table[i];
@@ -1649,7 +1647,7 @@ const struct intel_pinctrl_soc_data *intel_pinctrl_get_soc_data(struct platform_
 		if (!id)
 			return ERR_PTR(-ENODEV);
 
-		table = (const struct intel_pinctrl_soc_data **)id->driver_data;
+		table = (const struct intel_pinctrl_soc_data * const *)id->driver_data;
 		data = table[pdev->id];
 	}
 
diff --git a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c
index 85a0052bb0e6..7338bc353347 100644
--- a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c
+++ b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c
@@ -341,12 +341,12 @@ static int armada_37xx_pmx_set_by_name(struct pinctrl_dev *pctldev,
 				       struct armada_37xx_pin_group *grp)
 {
 	struct armada_37xx_pinctrl *info = pinctrl_dev_get_drvdata(pctldev);
+	struct device *dev = info->dev;
 	unsigned int reg = SELECTION;
 	unsigned int mask = grp->reg_mask;
 	int func, val;
 
-	dev_dbg(info->dev, "enable function %s group %s\n",
-		name, grp->name);
+	dev_dbg(dev, "enable function %s group %s\n", name, grp->name);
 
 	func = match_string(grp->funcs, NB_FUNCS, name);
 	if (func < 0)
@@ -722,25 +722,22 @@ static unsigned int armada_37xx_irq_startup(struct irq_data *d)
 static int armada_37xx_irqchip_register(struct platform_device *pdev,
 					struct armada_37xx_pinctrl *info)
 {
-	struct device_node *np = info->dev->of_node;
 	struct gpio_chip *gc = &info->gpio_chip;
 	struct irq_chip *irqchip = &info->irq_chip;
 	struct gpio_irq_chip *girq = &gc->irq;
 	struct device *dev = &pdev->dev;
-	struct resource res;
+	struct device_node *np;
 	int ret = -ENODEV, i, nr_irq_parent;
 
 	/* Check if we have at least one gpio-controller child node */
-	for_each_child_of_node(info->dev->of_node, np) {
+	for_each_child_of_node(dev->of_node, np) {
 		if (of_property_read_bool(np, "gpio-controller")) {
 			ret = 0;
 			break;
 		}
 	}
-	if (ret) {
-		dev_err(dev, "no gpio-controller child node\n");
-		return ret;
-	}
+	if (ret)
+		return dev_err_probe(dev, ret, "no gpio-controller child node\n");
 
 	nr_irq_parent = of_irq_count(np);
 	spin_lock_init(&info->irq_lock);
@@ -750,12 +747,7 @@ static int armada_37xx_irqchip_register(struct platform_device *pdev,
 		return 0;
 	}
 
-	if (of_address_to_resource(info->dev->of_node, 1, &res)) {
-		dev_err(dev, "cannot find IO resource\n");
-		return -ENOENT;
-	}
-
-	info->base = devm_ioremap_resource(info->dev, &res);
+	info->base = devm_platform_ioremap_resource(pdev, 1);
 	if (IS_ERR(info->base))
 		return PTR_ERR(info->base);
 
@@ -774,8 +766,7 @@ static int armada_37xx_irqchip_register(struct platform_device *pdev,
 	 * the chained irq with all of them.
 	 */
 	girq->num_parents = nr_irq_parent;
-	girq->parents = devm_kcalloc(&pdev->dev, nr_irq_parent,
-				     sizeof(*girq->parents), GFP_KERNEL);
+	girq->parents = devm_kcalloc(dev, nr_irq_parent, sizeof(*girq->parents), GFP_KERNEL);
 	if (!girq->parents)
 		return -ENOMEM;
 	for (i = 0; i < nr_irq_parent; i++) {
@@ -794,11 +785,12 @@ static int armada_37xx_irqchip_register(struct platform_device *pdev,
 static int armada_37xx_gpiochip_register(struct platform_device *pdev,
 					struct armada_37xx_pinctrl *info)
 {
+	struct device *dev = &pdev->dev;
 	struct device_node *np;
 	struct gpio_chip *gc;
 	int ret = -ENODEV;
 
-	for_each_child_of_node(info->dev->of_node, np) {
+	for_each_child_of_node(dev->of_node, np) {
 		if (of_find_property(np, "gpio-controller", NULL)) {
 			ret = 0;
 			break;
@@ -811,7 +803,7 @@ static int armada_37xx_gpiochip_register(struct platform_device *pdev,
 
 	gc = &info->gpio_chip;
 	gc->ngpio = info->data->nr_pins;
-	gc->parent = &pdev->dev;
+	gc->parent = dev;
 	gc->base = -1;
 	gc->of_node = np;
 	gc->label = info->data->name;
@@ -819,11 +811,8 @@ static int armada_37xx_gpiochip_register(struct platform_device *pdev,
 	ret = armada_37xx_irqchip_register(pdev, info);
 	if (ret)
 		return ret;
-	ret = devm_gpiochip_add_data(&pdev->dev, gc, info);
-	if (ret)
-		return ret;
 
-	return 0;
+	return devm_gpiochip_add_data(dev, gc, info);
 }
 
 /**
@@ -874,13 +863,13 @@ static int armada_37xx_add_function(struct armada_37xx_pmx_func *funcs,
 static int armada_37xx_fill_group(struct armada_37xx_pinctrl *info)
 {
 	int n, num = 0, funcsize = info->data->nr_pins;
+	struct device *dev = info->dev;
 
 	for (n = 0; n < info->ngroups; n++) {
 		struct armada_37xx_pin_group *grp = &info->groups[n];
 		int i, j, f;
 
-		grp->pins = devm_kcalloc(info->dev,
-					 grp->npins + grp->extra_npins,
+		grp->pins = devm_kcalloc(dev, grp->npins + grp->extra_npins,
 					 sizeof(*grp->pins),
 					 GFP_KERNEL);
 		if (!grp->pins)
@@ -898,8 +887,7 @@ static int armada_37xx_fill_group(struct armada_37xx_pinctrl *info)
 			ret = armada_37xx_add_function(info->funcs, &funcsize,
 					    grp->funcs[f]);
 			if (ret == -EOVERFLOW)
-				dev_err(info->dev,
-					"More functions than pins(%d)\n",
+				dev_err(dev, "More functions than pins(%d)\n",
 					info->data->nr_pins);
 			if (ret < 0)
 				continue;
@@ -925,6 +913,7 @@ static int armada_37xx_fill_group(struct armada_37xx_pinctrl *info)
 static int armada_37xx_fill_func(struct armada_37xx_pinctrl *info)
 {
 	struct armada_37xx_pmx_func *funcs = info->funcs;
+	struct device *dev = info->dev;
 	int n;
 
 	for (n = 0; n < info->nfuncs; n++) {
@@ -932,8 +921,7 @@ static int armada_37xx_fill_func(struct armada_37xx_pinctrl *info)
 		const char **groups;
 		int g;
 
-		funcs[n].groups = devm_kcalloc(info->dev,
-					       funcs[n].ngroups,
+		funcs[n].groups = devm_kcalloc(dev, funcs[n].ngroups,
 					       sizeof(*(funcs[n].groups)),
 					       GFP_KERNEL);
 		if (!funcs[n].groups)
@@ -962,6 +950,7 @@ static int armada_37xx_pinctrl_register(struct platform_device *pdev,
 	const struct armada_37xx_pin_data *pin_data = info->data;
 	struct pinctrl_desc *ctrldesc = &info->pctl;
 	struct pinctrl_pin_desc *pindesc, *pdesc;
+	struct device *dev = &pdev->dev;
 	int pin, ret;
 
 	info->groups = pin_data->groups;
@@ -973,9 +962,7 @@ static int armada_37xx_pinctrl_register(struct platform_device *pdev,
 	ctrldesc->pmxops = &armada_37xx_pmx_ops;
 	ctrldesc->confops = &armada_37xx_pinconf_ops;
 
-	pindesc = devm_kcalloc(&pdev->dev,
-			       pin_data->nr_pins, sizeof(*pindesc),
-			       GFP_KERNEL);
+	pindesc = devm_kcalloc(dev, pin_data->nr_pins, sizeof(*pindesc), GFP_KERNEL);
 	if (!pindesc)
 		return -ENOMEM;
 
@@ -994,14 +981,10 @@ static int armada_37xx_pinctrl_register(struct platform_device *pdev,
 	 * we allocate functions for number of pins and hope there are
 	 * fewer unique functions than pins available
 	 */
-	info->funcs = devm_kcalloc(&pdev->dev,
-				   pin_data->nr_pins,
-				   sizeof(struct armada_37xx_pmx_func),
-				   GFP_KERNEL);
+	info->funcs = devm_kcalloc(dev, pin_data->nr_pins, sizeof(*info->funcs), GFP_KERNEL);
 	if (!info->funcs)
 		return -ENOMEM;
 
-
 	ret = armada_37xx_fill_group(info);
 	if (ret)
 		return ret;
@@ -1010,11 +993,9 @@ static int armada_37xx_pinctrl_register(struct platform_device *pdev,
 	if (ret)
 		return ret;
 
-	info->pctl_dev = devm_pinctrl_register(&pdev->dev, ctrldesc, info);
-	if (IS_ERR(info->pctl_dev)) {
-		dev_err(&pdev->dev, "could not register pinctrl driver\n");
-		return PTR_ERR(info->pctl_dev);
-	}
+	info->pctl_dev = devm_pinctrl_register(dev, ctrldesc, info);
+	if (IS_ERR(info->pctl_dev))
+		return dev_err_probe(dev, PTR_ERR(info->pctl_dev), "could not register pinctrl driver\n");
 
 	return 0;
 }
@@ -1135,28 +1116,40 @@ static const struct of_device_id armada_37xx_pinctrl_of_match[] = {
 	{ },
 };
 
+static const struct regmap_config armada_37xx_pinctrl_regmap_config = {
+	.reg_bits = 32,
+	.val_bits = 32,
+	.reg_stride = 4,
+	.use_raw_spinlock = true,
+};
+
 static int __init armada_37xx_pinctrl_probe(struct platform_device *pdev)
 {
 	struct armada_37xx_pinctrl *info;
 	struct device *dev = &pdev->dev;
-	struct device_node *np = dev->of_node;
 	struct regmap *regmap;
+	void __iomem *base;
 	int ret;
 
-	info = devm_kzalloc(dev, sizeof(struct armada_37xx_pinctrl),
-			    GFP_KERNEL);
-	if (!info)
-		return -ENOMEM;
-
-	info->dev = dev;
+	base = devm_platform_get_and_ioremap_resource(pdev, 0, NULL);
+	if (IS_ERR(base)) {
+		dev_err(dev, "failed to ioremap base address: %pe\n", base);
+		return PTR_ERR(base);
+	}
 
-	regmap = syscon_node_to_regmap(np);
+	regmap = devm_regmap_init_mmio(dev, base,
+				       &armada_37xx_pinctrl_regmap_config);
 	if (IS_ERR(regmap)) {
-		dev_err(&pdev->dev, "cannot get regmap\n");
+		dev_err(dev, "failed to create regmap: %pe\n", regmap);
 		return PTR_ERR(regmap);
 	}
-	info->regmap = regmap;
 
+	info = devm_kzalloc(dev, sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	info->dev = dev;
+	info->regmap = regmap;
 	info->data = of_device_get_match_data(dev);
 
 	ret = armada_37xx_pinctrl_register(pdev, info);
diff --git a/drivers/pinctrl/nomadik/pinctrl-nomadik.c b/drivers/pinctrl/nomadik/pinctrl-nomadik.c
index 4757bf964d3c..6dd930a839ec 100644
--- a/drivers/pinctrl/nomadik/pinctrl-nomadik.c
+++ b/drivers/pinctrl/nomadik/pinctrl-nomadik.c
@@ -1421,8 +1421,10 @@ static int nmk_pinctrl_dt_subnode_to_map(struct pinctrl_dev *pctldev,
 
 	has_config = nmk_pinctrl_dt_get_config(np, &configs);
 	np_config = of_parse_phandle(np, "ste,config", 0);
-	if (np_config)
+	if (np_config) {
 		has_config |= nmk_pinctrl_dt_get_config(np_config, &configs);
+		of_node_put(np_config);
+	}
 	if (has_config) {
 		const char *gpio_name;
 		const char *pin;
diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index ecab9064a845..5c4acf2308d4 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -912,6 +912,7 @@ static int amd_gpio_suspend(struct device *dev)
 {
 	struct amd_gpio *gpio_dev = dev_get_drvdata(dev);
 	struct pinctrl_desc *desc = gpio_dev->pctrl->desc;
+	unsigned long flags;
 	int i;
 
 	for (i = 0; i < desc->npins; i++) {
@@ -920,7 +921,9 @@ static int amd_gpio_suspend(struct device *dev)
 		if (!amd_gpio_should_save(gpio_dev, pin))
 			continue;
 
-		gpio_dev->saved_regs[i] = readl(gpio_dev->base + pin*4);
+		raw_spin_lock_irqsave(&gpio_dev->lock, flags);
+		gpio_dev->saved_regs[i] = readl(gpio_dev->base + pin * 4) & ~PIN_IRQ_PENDING;
+		raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
 	}
 
 	return 0;
@@ -930,6 +933,7 @@ static int amd_gpio_resume(struct device *dev)
 {
 	struct amd_gpio *gpio_dev = dev_get_drvdata(dev);
 	struct pinctrl_desc *desc = gpio_dev->pctrl->desc;
+	unsigned long flags;
 	int i;
 
 	for (i = 0; i < desc->npins; i++) {
@@ -938,7 +942,10 @@ static int amd_gpio_resume(struct device *dev)
 		if (!amd_gpio_should_save(gpio_dev, pin))
 			continue;
 
-		writel(gpio_dev->saved_regs[i], gpio_dev->base + pin*4);
+		raw_spin_lock_irqsave(&gpio_dev->lock, flags);
+		gpio_dev->saved_regs[i] |= readl(gpio_dev->base + pin * 4) & PIN_IRQ_PENDING;
+		writel(gpio_dev->saved_regs[i], gpio_dev->base + pin * 4);
+		raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
 	}
 
 	return 0;
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8916.c b/drivers/pinctrl/qcom/pinctrl-msm8916.c
index 396db12ae904..bf68913ba821 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8916.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8916.c
@@ -844,8 +844,8 @@ static const struct msm_pingroup msm8916_groups[] = {
 	PINGROUP(28, pwr_modem_enabled_a, NA, NA, NA, NA, NA, qdss_tracedata_b, NA, atest_combodac),
 	PINGROUP(29, cci_i2c, NA, NA, NA, NA, NA, qdss_tracedata_b, NA, atest_combodac),
 	PINGROUP(30, cci_i2c, NA, NA, NA, NA, NA, NA, NA, qdss_tracedata_b),
-	PINGROUP(31, cci_timer0, NA, NA, NA, NA, NA, NA, NA, NA),
-	PINGROUP(32, cci_timer1, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(31, cci_timer0, flash_strobe, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(32, cci_timer1, flash_strobe, NA, NA, NA, NA, NA, NA, NA),
 	PINGROUP(33, cci_async, NA, NA, NA, NA, NA, NA, NA, qdss_tracedata_b),
 	PINGROUP(34, pwr_nav_enabled_a, NA, NA, NA, NA, NA, NA, NA, qdss_tracedata_b),
 	PINGROUP(35, pwr_crypto_enabled_a, NA, NA, NA, NA, NA, NA, NA, qdss_tracedata_b),
diff --git a/drivers/pinctrl/qcom/pinctrl-sc8180x.c b/drivers/pinctrl/qcom/pinctrl-sc8180x.c
index 0d9654b4ab60..a4725ff12da0 100644
--- a/drivers/pinctrl/qcom/pinctrl-sc8180x.c
+++ b/drivers/pinctrl/qcom/pinctrl-sc8180x.c
@@ -530,10 +530,10 @@ DECLARE_MSM_GPIO_PINS(187);
 DECLARE_MSM_GPIO_PINS(188);
 DECLARE_MSM_GPIO_PINS(189);
 
-static const unsigned int sdc2_clk_pins[] = { 190 };
-static const unsigned int sdc2_cmd_pins[] = { 191 };
-static const unsigned int sdc2_data_pins[] = { 192 };
-static const unsigned int ufs_reset_pins[] = { 193 };
+static const unsigned int ufs_reset_pins[] = { 190 };
+static const unsigned int sdc2_clk_pins[] = { 191 };
+static const unsigned int sdc2_cmd_pins[] = { 192 };
+static const unsigned int sdc2_data_pins[] = { 193 };
 
 enum sc8180x_functions {
 	msm_mux_adsp_ext,
@@ -1582,7 +1582,7 @@ static const int sc8180x_acpi_reserved_gpios[] = {
 static const struct msm_gpio_wakeirq_map sc8180x_pdc_map[] = {
 	{ 3, 31 }, { 5, 32 }, { 8, 33 }, { 9, 34 }, { 10, 100 }, { 12, 104 },
 	{ 24, 37 }, { 26, 38 }, { 27, 41 }, { 28, 42 }, { 30, 39 }, { 36, 43 },
-	{ 37, 43 }, { 38, 45 }, { 39, 118 }, { 39, 125 }, { 41, 47 },
+	{ 37, 44 }, { 38, 45 }, { 39, 118 }, { 39, 125 }, { 41, 47 },
 	{ 42, 48 }, { 46, 50 }, { 47, 49 }, { 48, 51 }, { 49, 53 }, { 50, 52 },
 	{ 51, 116 }, { 51, 123 }, { 53, 54 }, { 54, 55 }, { 55, 56 },
 	{ 56, 57 }, { 58, 58 }, { 60, 60 }, { 68, 62 }, { 70, 63 }, { 76, 86 },
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8250.c b/drivers/pinctrl/qcom/pinctrl-sm8250.c
index af144e724bd9..3bd7f9fedcc3 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8250.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8250.c
@@ -1316,7 +1316,7 @@ static const struct msm_pingroup sm8250_groups[] = {
 static const struct msm_gpio_wakeirq_map sm8250_pdc_map[] = {
 	{ 0, 79 }, { 1, 84 }, { 2, 80 }, { 3, 82 }, { 4, 107 }, { 7, 43 },
 	{ 11, 42 }, { 14, 44 }, { 15, 52 }, { 19, 67 }, { 23, 68 }, { 24, 105 },
-	{ 27, 92 }, { 28, 106 }, { 31, 69 }, { 35, 70 }, { 39, 37 },
+	{ 27, 92 }, { 28, 106 }, { 31, 69 }, { 35, 70 }, { 39, 73 },
 	{ 40, 108 }, { 43, 71 }, { 45, 72 }, { 47, 83 }, { 51, 74 }, { 55, 77 },
 	{ 59, 78 }, { 63, 75 }, { 64, 81 }, { 65, 87 }, { 66, 88 }, { 67, 89 },
 	{ 68, 54 }, { 70, 85 }, { 77, 46 }, { 80, 90 }, { 81, 91 }, { 83, 97 },
diff --git a/drivers/pinctrl/ralink/Kconfig b/drivers/pinctrl/ralink/Kconfig
index a76ee3deb8c3..d0f0a8f2b9b7 100644
--- a/drivers/pinctrl/ralink/Kconfig
+++ b/drivers/pinctrl/ralink/Kconfig
@@ -3,37 +3,33 @@ menu "Ralink pinctrl drivers"
         depends on RALINK
 
 config PINCTRL_RALINK
-        bool "Ralink pin control support"
-        default y if RALINK
-
-config PINCTRL_RT2880
-        bool "RT2880 pinctrl driver for RALINK/Mediatek SOCs"
+        bool "Ralink pinctrl driver"
         select PINMUX
         select GENERIC_PINCONF
 
 config PINCTRL_MT7620
         bool "mt7620 pinctrl driver for RALINK/Mediatek SOCs"
         depends on RALINK && SOC_MT7620
-        select PINCTRL_RT2880
+        select PINCTRL_RALINK
 
 config PINCTRL_MT7621
         bool "mt7621 pinctrl driver for RALINK/Mediatek SOCs"
         depends on RALINK && SOC_MT7621
-        select PINCTRL_RT2880
+        select PINCTRL_RALINK
 
 config PINCTRL_RT288X
         bool "RT288X pinctrl driver for RALINK/Mediatek SOCs"
         depends on RALINK && SOC_RT288X
-        select PINCTRL_RT2880
+        select PINCTRL_RALINK
 
 config PINCTRL_RT305X
         bool "RT305X pinctrl driver for RALINK/Mediatek SOCs"
         depends on RALINK && SOC_RT305X
-        select PINCTRL_RT2880
+        select PINCTRL_RALINK
 
 config PINCTRL_RT3883
         bool "RT3883 pinctrl driver for RALINK/Mediatek SOCs"
         depends on RALINK && SOC_RT3883
-        select PINCTRL_RT2880
+        select PINCTRL_RALINK
 
 endmenu
diff --git a/drivers/pinctrl/ralink/Makefile b/drivers/pinctrl/ralink/Makefile
index a15610206ced..2c1323b74e96 100644
--- a/drivers/pinctrl/ralink/Makefile
+++ b/drivers/pinctrl/ralink/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_PINCTRL_RT2880)   += pinctrl-rt2880.o
+obj-$(CONFIG_PINCTRL_RALINK)   += pinctrl-ralink.o
 
 obj-$(CONFIG_PINCTRL_MT7620)   += pinctrl-mt7620.o
 obj-$(CONFIG_PINCTRL_MT7621)   += pinctrl-mt7621.o
diff --git a/drivers/pinctrl/ralink/pinctrl-mt7620.c b/drivers/pinctrl/ralink/pinctrl-mt7620.c
index 6853b5b8b0fe..51b863d85c51 100644
--- a/drivers/pinctrl/ralink/pinctrl-mt7620.c
+++ b/drivers/pinctrl/ralink/pinctrl-mt7620.c
@@ -5,7 +5,7 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/of.h>
-#include "pinmux.h"
+#include "pinctrl-ralink.h"
 
 #define MT7620_GPIO_MODE_UART0_SHIFT	2
 #define MT7620_GPIO_MODE_UART0_MASK	0x7
@@ -54,20 +54,20 @@
 #define MT7620_GPIO_MODE_EPHY		15
 #define MT7620_GPIO_MODE_PA		20
 
-static struct rt2880_pmx_func i2c_grp[] =  { FUNC("i2c", 0, 1, 2) };
-static struct rt2880_pmx_func spi_grp[] = { FUNC("spi", 0, 3, 4) };
-static struct rt2880_pmx_func uartlite_grp[] = { FUNC("uartlite", 0, 15, 2) };
-static struct rt2880_pmx_func mdio_grp[] = {
+static struct ralink_pmx_func i2c_grp[] =  { FUNC("i2c", 0, 1, 2) };
+static struct ralink_pmx_func spi_grp[] = { FUNC("spi", 0, 3, 4) };
+static struct ralink_pmx_func uartlite_grp[] = { FUNC("uartlite", 0, 15, 2) };
+static struct ralink_pmx_func mdio_grp[] = {
 	FUNC("mdio", MT7620_GPIO_MODE_MDIO, 22, 2),
 	FUNC("refclk", MT7620_GPIO_MODE_MDIO_REFCLK, 22, 2),
 };
-static struct rt2880_pmx_func rgmii1_grp[] = { FUNC("rgmii1", 0, 24, 12) };
-static struct rt2880_pmx_func refclk_grp[] = { FUNC("spi refclk", 0, 37, 3) };
-static struct rt2880_pmx_func ephy_grp[] = { FUNC("ephy", 0, 40, 5) };
-static struct rt2880_pmx_func rgmii2_grp[] = { FUNC("rgmii2", 0, 60, 12) };
-static struct rt2880_pmx_func wled_grp[] = { FUNC("wled", 0, 72, 1) };
-static struct rt2880_pmx_func pa_grp[] = { FUNC("pa", 0, 18, 4) };
-static struct rt2880_pmx_func uartf_grp[] = {
+static struct ralink_pmx_func rgmii1_grp[] = { FUNC("rgmii1", 0, 24, 12) };
+static struct ralink_pmx_func refclk_grp[] = { FUNC("spi refclk", 0, 37, 3) };
+static struct ralink_pmx_func ephy_grp[] = { FUNC("ephy", 0, 40, 5) };
+static struct ralink_pmx_func rgmii2_grp[] = { FUNC("rgmii2", 0, 60, 12) };
+static struct ralink_pmx_func wled_grp[] = { FUNC("wled", 0, 72, 1) };
+static struct ralink_pmx_func pa_grp[] = { FUNC("pa", 0, 18, 4) };
+static struct ralink_pmx_func uartf_grp[] = {
 	FUNC("uartf", MT7620_GPIO_MODE_UARTF, 7, 8),
 	FUNC("pcm uartf", MT7620_GPIO_MODE_PCM_UARTF, 7, 8),
 	FUNC("pcm i2s", MT7620_GPIO_MODE_PCM_I2S, 7, 8),
@@ -76,20 +76,20 @@ static struct rt2880_pmx_func uartf_grp[] = {
 	FUNC("gpio uartf", MT7620_GPIO_MODE_GPIO_UARTF, 7, 4),
 	FUNC("gpio i2s", MT7620_GPIO_MODE_GPIO_I2S, 7, 4),
 };
-static struct rt2880_pmx_func wdt_grp[] = {
+static struct ralink_pmx_func wdt_grp[] = {
 	FUNC("wdt rst", 0, 17, 1),
 	FUNC("wdt refclk", 0, 17, 1),
 	};
-static struct rt2880_pmx_func pcie_rst_grp[] = {
+static struct ralink_pmx_func pcie_rst_grp[] = {
 	FUNC("pcie rst", MT7620_GPIO_MODE_PCIE_RST, 36, 1),
 	FUNC("pcie refclk", MT7620_GPIO_MODE_PCIE_REF, 36, 1)
 };
-static struct rt2880_pmx_func nd_sd_grp[] = {
+static struct ralink_pmx_func nd_sd_grp[] = {
 	FUNC("nand", MT7620_GPIO_MODE_NAND, 45, 15),
 	FUNC("sd", MT7620_GPIO_MODE_SD, 47, 13)
 };
 
-static struct rt2880_pmx_group mt7620a_pinmux_data[] = {
+static struct ralink_pmx_group mt7620a_pinmux_data[] = {
 	GRP("i2c", i2c_grp, 1, MT7620_GPIO_MODE_I2C),
 	GRP("uartf", uartf_grp, MT7620_GPIO_MODE_UART0_MASK,
 		MT7620_GPIO_MODE_UART0_SHIFT),
@@ -112,262 +112,262 @@ static struct rt2880_pmx_group mt7620a_pinmux_data[] = {
 	{ 0 }
 };
 
-static struct rt2880_pmx_func pwm1_grp_mt7628[] = {
+static struct ralink_pmx_func pwm1_grp_mt76x8[] = {
 	FUNC("sdxc d6", 3, 19, 1),
 	FUNC("utif", 2, 19, 1),
 	FUNC("gpio", 1, 19, 1),
 	FUNC("pwm1", 0, 19, 1),
 };
 
-static struct rt2880_pmx_func pwm0_grp_mt7628[] = {
+static struct ralink_pmx_func pwm0_grp_mt76x8[] = {
 	FUNC("sdxc d7", 3, 18, 1),
 	FUNC("utif", 2, 18, 1),
 	FUNC("gpio", 1, 18, 1),
 	FUNC("pwm0", 0, 18, 1),
 };
 
-static struct rt2880_pmx_func uart2_grp_mt7628[] = {
+static struct ralink_pmx_func uart2_grp_mt76x8[] = {
 	FUNC("sdxc d5 d4", 3, 20, 2),
 	FUNC("pwm", 2, 20, 2),
 	FUNC("gpio", 1, 20, 2),
 	FUNC("uart2", 0, 20, 2),
 };
 
-static struct rt2880_pmx_func uart1_grp_mt7628[] = {
+static struct ralink_pmx_func uart1_grp_mt76x8[] = {
 	FUNC("sw_r", 3, 45, 2),
 	FUNC("pwm", 2, 45, 2),
 	FUNC("gpio", 1, 45, 2),
 	FUNC("uart1", 0, 45, 2),
 };
 
-static struct rt2880_pmx_func i2c_grp_mt7628[] = {
+static struct ralink_pmx_func i2c_grp_mt76x8[] = {
 	FUNC("-", 3, 4, 2),
 	FUNC("debug", 2, 4, 2),
 	FUNC("gpio", 1, 4, 2),
 	FUNC("i2c", 0, 4, 2),
 };
 
-static struct rt2880_pmx_func refclk_grp_mt7628[] = { FUNC("refclk", 0, 37, 1) };
-static struct rt2880_pmx_func perst_grp_mt7628[] = { FUNC("perst", 0, 36, 1) };
-static struct rt2880_pmx_func wdt_grp_mt7628[] = { FUNC("wdt", 0, 38, 1) };
-static struct rt2880_pmx_func spi_grp_mt7628[] = { FUNC("spi", 0, 7, 4) };
+static struct ralink_pmx_func refclk_grp_mt76x8[] = { FUNC("refclk", 0, 37, 1) };
+static struct ralink_pmx_func perst_grp_mt76x8[] = { FUNC("perst", 0, 36, 1) };
+static struct ralink_pmx_func wdt_grp_mt76x8[] = { FUNC("wdt", 0, 38, 1) };
+static struct ralink_pmx_func spi_grp_mt76x8[] = { FUNC("spi", 0, 7, 4) };
 
-static struct rt2880_pmx_func sd_mode_grp_mt7628[] = {
+static struct ralink_pmx_func sd_mode_grp_mt76x8[] = {
 	FUNC("jtag", 3, 22, 8),
 	FUNC("utif", 2, 22, 8),
 	FUNC("gpio", 1, 22, 8),
 	FUNC("sdxc", 0, 22, 8),
 };
 
-static struct rt2880_pmx_func uart0_grp_mt7628[] = {
+static struct ralink_pmx_func uart0_grp_mt76x8[] = {
 	FUNC("-", 3, 12, 2),
 	FUNC("-", 2, 12, 2),
 	FUNC("gpio", 1, 12, 2),
 	FUNC("uart0", 0, 12, 2),
 };
 
-static struct rt2880_pmx_func i2s_grp_mt7628[] = {
+static struct ralink_pmx_func i2s_grp_mt76x8[] = {
 	FUNC("antenna", 3, 0, 4),
 	FUNC("pcm", 2, 0, 4),
 	FUNC("gpio", 1, 0, 4),
 	FUNC("i2s", 0, 0, 4),
 };
 
-static struct rt2880_pmx_func spi_cs1_grp_mt7628[] = {
+static struct ralink_pmx_func spi_cs1_grp_mt76x8[] = {
 	FUNC("-", 3, 6, 1),
 	FUNC("refclk", 2, 6, 1),
 	FUNC("gpio", 1, 6, 1),
 	FUNC("spi cs1", 0, 6, 1),
 };
 
-static struct rt2880_pmx_func spis_grp_mt7628[] = {
+static struct ralink_pmx_func spis_grp_mt76x8[] = {
 	FUNC("pwm_uart2", 3, 14, 4),
 	FUNC("utif", 2, 14, 4),
 	FUNC("gpio", 1, 14, 4),
 	FUNC("spis", 0, 14, 4),
 };
 
-static struct rt2880_pmx_func gpio_grp_mt7628[] = {
+static struct ralink_pmx_func gpio_grp_mt76x8[] = {
 	FUNC("pcie", 3, 11, 1),
 	FUNC("refclk", 2, 11, 1),
 	FUNC("gpio", 1, 11, 1),
 	FUNC("gpio", 0, 11, 1),
 };
 
-static struct rt2880_pmx_func p4led_kn_grp_mt7628[] = {
+static struct ralink_pmx_func p4led_kn_grp_mt76x8[] = {
 	FUNC("jtag", 3, 30, 1),
 	FUNC("utif", 2, 30, 1),
 	FUNC("gpio", 1, 30, 1),
 	FUNC("p4led_kn", 0, 30, 1),
 };
 
-static struct rt2880_pmx_func p3led_kn_grp_mt7628[] = {
+static struct ralink_pmx_func p3led_kn_grp_mt76x8[] = {
 	FUNC("jtag", 3, 31, 1),
 	FUNC("utif", 2, 31, 1),
 	FUNC("gpio", 1, 31, 1),
 	FUNC("p3led_kn", 0, 31, 1),
 };
 
-static struct rt2880_pmx_func p2led_kn_grp_mt7628[] = {
+static struct ralink_pmx_func p2led_kn_grp_mt76x8[] = {
 	FUNC("jtag", 3, 32, 1),
 	FUNC("utif", 2, 32, 1),
 	FUNC("gpio", 1, 32, 1),
 	FUNC("p2led_kn", 0, 32, 1),
 };
 
-static struct rt2880_pmx_func p1led_kn_grp_mt7628[] = {
+static struct ralink_pmx_func p1led_kn_grp_mt76x8[] = {
 	FUNC("jtag", 3, 33, 1),
 	FUNC("utif", 2, 33, 1),
 	FUNC("gpio", 1, 33, 1),
 	FUNC("p1led_kn", 0, 33, 1),
 };
 
-static struct rt2880_pmx_func p0led_kn_grp_mt7628[] = {
+static struct ralink_pmx_func p0led_kn_grp_mt76x8[] = {
 	FUNC("jtag", 3, 34, 1),
 	FUNC("rsvd", 2, 34, 1),
 	FUNC("gpio", 1, 34, 1),
 	FUNC("p0led_kn", 0, 34, 1),
 };
 
-static struct rt2880_pmx_func wled_kn_grp_mt7628[] = {
+static struct ralink_pmx_func wled_kn_grp_mt76x8[] = {
 	FUNC("rsvd", 3, 35, 1),
 	FUNC("rsvd", 2, 35, 1),
 	FUNC("gpio", 1, 35, 1),
 	FUNC("wled_kn", 0, 35, 1),
 };
 
-static struct rt2880_pmx_func p4led_an_grp_mt7628[] = {
+static struct ralink_pmx_func p4led_an_grp_mt76x8[] = {
 	FUNC("jtag", 3, 39, 1),
 	FUNC("utif", 2, 39, 1),
 	FUNC("gpio", 1, 39, 1),
 	FUNC("p4led_an", 0, 39, 1),
 };
 
-static struct rt2880_pmx_func p3led_an_grp_mt7628[] = {
+static struct ralink_pmx_func p3led_an_grp_mt76x8[] = {
 	FUNC("jtag", 3, 40, 1),
 	FUNC("utif", 2, 40, 1),
 	FUNC("gpio", 1, 40, 1),
 	FUNC("p3led_an", 0, 40, 1),
 };
 
-static struct rt2880_pmx_func p2led_an_grp_mt7628[] = {
+static struct ralink_pmx_func p2led_an_grp_mt76x8[] = {
 	FUNC("jtag", 3, 41, 1),
 	FUNC("utif", 2, 41, 1),
 	FUNC("gpio", 1, 41, 1),
 	FUNC("p2led_an", 0, 41, 1),
 };
 
-static struct rt2880_pmx_func p1led_an_grp_mt7628[] = {
+static struct ralink_pmx_func p1led_an_grp_mt76x8[] = {
 	FUNC("jtag", 3, 42, 1),
 	FUNC("utif", 2, 42, 1),
 	FUNC("gpio", 1, 42, 1),
 	FUNC("p1led_an", 0, 42, 1),
 };
 
-static struct rt2880_pmx_func p0led_an_grp_mt7628[] = {
+static struct ralink_pmx_func p0led_an_grp_mt76x8[] = {
 	FUNC("jtag", 3, 43, 1),
 	FUNC("rsvd", 2, 43, 1),
 	FUNC("gpio", 1, 43, 1),
 	FUNC("p0led_an", 0, 43, 1),
 };
 
-static struct rt2880_pmx_func wled_an_grp_mt7628[] = {
+static struct ralink_pmx_func wled_an_grp_mt76x8[] = {
 	FUNC("rsvd", 3, 44, 1),
 	FUNC("rsvd", 2, 44, 1),
 	FUNC("gpio", 1, 44, 1),
 	FUNC("wled_an", 0, 44, 1),
 };
 
-#define MT7628_GPIO_MODE_MASK		0x3
-
-#define MT7628_GPIO_MODE_P4LED_KN	58
-#define MT7628_GPIO_MODE_P3LED_KN	56
-#define MT7628_GPIO_MODE_P2LED_KN	54
-#define MT7628_GPIO_MODE_P1LED_KN	52
-#define MT7628_GPIO_MODE_P0LED_KN	50
-#define MT7628_GPIO_MODE_WLED_KN	48
-#define MT7628_GPIO_MODE_P4LED_AN	42
-#define MT7628_GPIO_MODE_P3LED_AN	40
-#define MT7628_GPIO_MODE_P2LED_AN	38
-#define MT7628_GPIO_MODE_P1LED_AN	36
-#define MT7628_GPIO_MODE_P0LED_AN	34
-#define MT7628_GPIO_MODE_WLED_AN	32
-#define MT7628_GPIO_MODE_PWM1		30
-#define MT7628_GPIO_MODE_PWM0		28
-#define MT7628_GPIO_MODE_UART2		26
-#define MT7628_GPIO_MODE_UART1		24
-#define MT7628_GPIO_MODE_I2C		20
-#define MT7628_GPIO_MODE_REFCLK		18
-#define MT7628_GPIO_MODE_PERST		16
-#define MT7628_GPIO_MODE_WDT		14
-#define MT7628_GPIO_MODE_SPI		12
-#define MT7628_GPIO_MODE_SDMODE		10
-#define MT7628_GPIO_MODE_UART0		8
-#define MT7628_GPIO_MODE_I2S		6
-#define MT7628_GPIO_MODE_CS1		4
-#define MT7628_GPIO_MODE_SPIS		2
-#define MT7628_GPIO_MODE_GPIO		0
-
-static struct rt2880_pmx_group mt7628an_pinmux_data[] = {
-	GRP_G("pwm1", pwm1_grp_mt7628, MT7628_GPIO_MODE_MASK,
-				1, MT7628_GPIO_MODE_PWM1),
-	GRP_G("pwm0", pwm0_grp_mt7628, MT7628_GPIO_MODE_MASK,
-				1, MT7628_GPIO_MODE_PWM0),
-	GRP_G("uart2", uart2_grp_mt7628, MT7628_GPIO_MODE_MASK,
-				1, MT7628_GPIO_MODE_UART2),
-	GRP_G("uart1", uart1_grp_mt7628, MT7628_GPIO_MODE_MASK,
-				1, MT7628_GPIO_MODE_UART1),
-	GRP_G("i2c", i2c_grp_mt7628, MT7628_GPIO_MODE_MASK,
-				1, MT7628_GPIO_MODE_I2C),
-	GRP("refclk", refclk_grp_mt7628, 1, MT7628_GPIO_MODE_REFCLK),
-	GRP("perst", perst_grp_mt7628, 1, MT7628_GPIO_MODE_PERST),
-	GRP("wdt", wdt_grp_mt7628, 1, MT7628_GPIO_MODE_WDT),
-	GRP("spi", spi_grp_mt7628, 1, MT7628_GPIO_MODE_SPI),
-	GRP_G("sdmode", sd_mode_grp_mt7628, MT7628_GPIO_MODE_MASK,
-				1, MT7628_GPIO_MODE_SDMODE),
-	GRP_G("uart0", uart0_grp_mt7628, MT7628_GPIO_MODE_MASK,
-				1, MT7628_GPIO_MODE_UART0),
-	GRP_G("i2s", i2s_grp_mt7628, MT7628_GPIO_MODE_MASK,
-				1, MT7628_GPIO_MODE_I2S),
-	GRP_G("spi cs1", spi_cs1_grp_mt7628, MT7628_GPIO_MODE_MASK,
-				1, MT7628_GPIO_MODE_CS1),
-	GRP_G("spis", spis_grp_mt7628, MT7628_GPIO_MODE_MASK,
-				1, MT7628_GPIO_MODE_SPIS),
-	GRP_G("gpio", gpio_grp_mt7628, MT7628_GPIO_MODE_MASK,
-				1, MT7628_GPIO_MODE_GPIO),
-	GRP_G("wled_an", wled_an_grp_mt7628, MT7628_GPIO_MODE_MASK,
-				1, MT7628_GPIO_MODE_WLED_AN),
-	GRP_G("p0led_an", p0led_an_grp_mt7628, MT7628_GPIO_MODE_MASK,
-				1, MT7628_GPIO_MODE_P0LED_AN),
-	GRP_G("p1led_an", p1led_an_grp_mt7628, MT7628_GPIO_MODE_MASK,
-				1, MT7628_GPIO_MODE_P1LED_AN),
-	GRP_G("p2led_an", p2led_an_grp_mt7628, MT7628_GPIO_MODE_MASK,
-				1, MT7628_GPIO_MODE_P2LED_AN),
-	GRP_G("p3led_an", p3led_an_grp_mt7628, MT7628_GPIO_MODE_MASK,
-				1, MT7628_GPIO_MODE_P3LED_AN),
-	GRP_G("p4led_an", p4led_an_grp_mt7628, MT7628_GPIO_MODE_MASK,
-				1, MT7628_GPIO_MODE_P4LED_AN),
-	GRP_G("wled_kn", wled_kn_grp_mt7628, MT7628_GPIO_MODE_MASK,
-				1, MT7628_GPIO_MODE_WLED_KN),
-	GRP_G("p0led_kn", p0led_kn_grp_mt7628, MT7628_GPIO_MODE_MASK,
-				1, MT7628_GPIO_MODE_P0LED_KN),
-	GRP_G("p1led_kn", p1led_kn_grp_mt7628, MT7628_GPIO_MODE_MASK,
-				1, MT7628_GPIO_MODE_P1LED_KN),
-	GRP_G("p2led_kn", p2led_kn_grp_mt7628, MT7628_GPIO_MODE_MASK,
-				1, MT7628_GPIO_MODE_P2LED_KN),
-	GRP_G("p3led_kn", p3led_kn_grp_mt7628, MT7628_GPIO_MODE_MASK,
-				1, MT7628_GPIO_MODE_P3LED_KN),
-	GRP_G("p4led_kn", p4led_kn_grp_mt7628, MT7628_GPIO_MODE_MASK,
-				1, MT7628_GPIO_MODE_P4LED_KN),
+#define MT76X8_GPIO_MODE_MASK		0x3
+
+#define MT76X8_GPIO_MODE_P4LED_KN	58
+#define MT76X8_GPIO_MODE_P3LED_KN	56
+#define MT76X8_GPIO_MODE_P2LED_KN	54
+#define MT76X8_GPIO_MODE_P1LED_KN	52
+#define MT76X8_GPIO_MODE_P0LED_KN	50
+#define MT76X8_GPIO_MODE_WLED_KN	48
+#define MT76X8_GPIO_MODE_P4LED_AN	42
+#define MT76X8_GPIO_MODE_P3LED_AN	40
+#define MT76X8_GPIO_MODE_P2LED_AN	38
+#define MT76X8_GPIO_MODE_P1LED_AN	36
+#define MT76X8_GPIO_MODE_P0LED_AN	34
+#define MT76X8_GPIO_MODE_WLED_AN	32
+#define MT76X8_GPIO_MODE_PWM1		30
+#define MT76X8_GPIO_MODE_PWM0		28
+#define MT76X8_GPIO_MODE_UART2		26
+#define MT76X8_GPIO_MODE_UART1		24
+#define MT76X8_GPIO_MODE_I2C		20
+#define MT76X8_GPIO_MODE_REFCLK		18
+#define MT76X8_GPIO_MODE_PERST		16
+#define MT76X8_GPIO_MODE_WDT		14
+#define MT76X8_GPIO_MODE_SPI		12
+#define MT76X8_GPIO_MODE_SDMODE		10
+#define MT76X8_GPIO_MODE_UART0		8
+#define MT76X8_GPIO_MODE_I2S		6
+#define MT76X8_GPIO_MODE_CS1		4
+#define MT76X8_GPIO_MODE_SPIS		2
+#define MT76X8_GPIO_MODE_GPIO		0
+
+static struct ralink_pmx_group mt76x8_pinmux_data[] = {
+	GRP_G("pwm1", pwm1_grp_mt76x8, MT76X8_GPIO_MODE_MASK,
+				1, MT76X8_GPIO_MODE_PWM1),
+	GRP_G("pwm0", pwm0_grp_mt76x8, MT76X8_GPIO_MODE_MASK,
+				1, MT76X8_GPIO_MODE_PWM0),
+	GRP_G("uart2", uart2_grp_mt76x8, MT76X8_GPIO_MODE_MASK,
+				1, MT76X8_GPIO_MODE_UART2),
+	GRP_G("uart1", uart1_grp_mt76x8, MT76X8_GPIO_MODE_MASK,
+				1, MT76X8_GPIO_MODE_UART1),
+	GRP_G("i2c", i2c_grp_mt76x8, MT76X8_GPIO_MODE_MASK,
+				1, MT76X8_GPIO_MODE_I2C),
+	GRP("refclk", refclk_grp_mt76x8, 1, MT76X8_GPIO_MODE_REFCLK),
+	GRP("perst", perst_grp_mt76x8, 1, MT76X8_GPIO_MODE_PERST),
+	GRP("wdt", wdt_grp_mt76x8, 1, MT76X8_GPIO_MODE_WDT),
+	GRP("spi", spi_grp_mt76x8, 1, MT76X8_GPIO_MODE_SPI),
+	GRP_G("sdmode", sd_mode_grp_mt76x8, MT76X8_GPIO_MODE_MASK,
+				1, MT76X8_GPIO_MODE_SDMODE),
+	GRP_G("uart0", uart0_grp_mt76x8, MT76X8_GPIO_MODE_MASK,
+				1, MT76X8_GPIO_MODE_UART0),
+	GRP_G("i2s", i2s_grp_mt76x8, MT76X8_GPIO_MODE_MASK,
+				1, MT76X8_GPIO_MODE_I2S),
+	GRP_G("spi cs1", spi_cs1_grp_mt76x8, MT76X8_GPIO_MODE_MASK,
+				1, MT76X8_GPIO_MODE_CS1),
+	GRP_G("spis", spis_grp_mt76x8, MT76X8_GPIO_MODE_MASK,
+				1, MT76X8_GPIO_MODE_SPIS),
+	GRP_G("gpio", gpio_grp_mt76x8, MT76X8_GPIO_MODE_MASK,
+				1, MT76X8_GPIO_MODE_GPIO),
+	GRP_G("wled_an", wled_an_grp_mt76x8, MT76X8_GPIO_MODE_MASK,
+				1, MT76X8_GPIO_MODE_WLED_AN),
+	GRP_G("p0led_an", p0led_an_grp_mt76x8, MT76X8_GPIO_MODE_MASK,
+				1, MT76X8_GPIO_MODE_P0LED_AN),
+	GRP_G("p1led_an", p1led_an_grp_mt76x8, MT76X8_GPIO_MODE_MASK,
+				1, MT76X8_GPIO_MODE_P1LED_AN),
+	GRP_G("p2led_an", p2led_an_grp_mt76x8, MT76X8_GPIO_MODE_MASK,
+				1, MT76X8_GPIO_MODE_P2LED_AN),
+	GRP_G("p3led_an", p3led_an_grp_mt76x8, MT76X8_GPIO_MODE_MASK,
+				1, MT76X8_GPIO_MODE_P3LED_AN),
+	GRP_G("p4led_an", p4led_an_grp_mt76x8, MT76X8_GPIO_MODE_MASK,
+				1, MT76X8_GPIO_MODE_P4LED_AN),
+	GRP_G("wled_kn", wled_kn_grp_mt76x8, MT76X8_GPIO_MODE_MASK,
+				1, MT76X8_GPIO_MODE_WLED_KN),
+	GRP_G("p0led_kn", p0led_kn_grp_mt76x8, MT76X8_GPIO_MODE_MASK,
+				1, MT76X8_GPIO_MODE_P0LED_KN),
+	GRP_G("p1led_kn", p1led_kn_grp_mt76x8, MT76X8_GPIO_MODE_MASK,
+				1, MT76X8_GPIO_MODE_P1LED_KN),
+	GRP_G("p2led_kn", p2led_kn_grp_mt76x8, MT76X8_GPIO_MODE_MASK,
+				1, MT76X8_GPIO_MODE_P2LED_KN),
+	GRP_G("p3led_kn", p3led_kn_grp_mt76x8, MT76X8_GPIO_MODE_MASK,
+				1, MT76X8_GPIO_MODE_P3LED_KN),
+	GRP_G("p4led_kn", p4led_kn_grp_mt76x8, MT76X8_GPIO_MODE_MASK,
+				1, MT76X8_GPIO_MODE_P4LED_KN),
 	{ 0 }
 };
 
 static int mt7620_pinmux_probe(struct platform_device *pdev)
 {
 	if (is_mt76x8())
-		return rt2880_pinmux_init(pdev, mt7628an_pinmux_data);
+		return ralink_pinmux_init(pdev, mt76x8_pinmux_data);
 	else
-		return rt2880_pinmux_init(pdev, mt7620a_pinmux_data);
+		return ralink_pinmux_init(pdev, mt7620a_pinmux_data);
 }
 
 static const struct of_device_id mt7620_pinmux_match[] = {
diff --git a/drivers/pinctrl/ralink/pinctrl-mt7621.c b/drivers/pinctrl/ralink/pinctrl-mt7621.c
index 7d96144c474e..14b89cb43d4c 100644
--- a/drivers/pinctrl/ralink/pinctrl-mt7621.c
+++ b/drivers/pinctrl/ralink/pinctrl-mt7621.c
@@ -3,7 +3,7 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/of.h>
-#include "pinmux.h"
+#include "pinctrl-ralink.h"
 
 #define MT7621_GPIO_MODE_UART1		1
 #define MT7621_GPIO_MODE_I2C		2
@@ -34,40 +34,40 @@
 #define MT7621_GPIO_MODE_SDHCI_SHIFT	18
 #define MT7621_GPIO_MODE_SDHCI_GPIO	1
 
-static struct rt2880_pmx_func uart1_grp[] =  { FUNC("uart1", 0, 1, 2) };
-static struct rt2880_pmx_func i2c_grp[] =  { FUNC("i2c", 0, 3, 2) };
-static struct rt2880_pmx_func uart3_grp[] = {
+static struct ralink_pmx_func uart1_grp[] =  { FUNC("uart1", 0, 1, 2) };
+static struct ralink_pmx_func i2c_grp[] =  { FUNC("i2c", 0, 3, 2) };
+static struct ralink_pmx_func uart3_grp[] = {
 	FUNC("uart3", 0, 5, 4),
 	FUNC("i2s", 2, 5, 4),
 	FUNC("spdif3", 3, 5, 4),
 };
-static struct rt2880_pmx_func uart2_grp[] = {
+static struct ralink_pmx_func uart2_grp[] = {
 	FUNC("uart2", 0, 9, 4),
 	FUNC("pcm", 2, 9, 4),
 	FUNC("spdif2", 3, 9, 4),
 };
-static struct rt2880_pmx_func jtag_grp[] = { FUNC("jtag", 0, 13, 5) };
-static struct rt2880_pmx_func wdt_grp[] = {
+static struct ralink_pmx_func jtag_grp[] = { FUNC("jtag", 0, 13, 5) };
+static struct ralink_pmx_func wdt_grp[] = {
 	FUNC("wdt rst", 0, 18, 1),
 	FUNC("wdt refclk", 2, 18, 1),
 };
-static struct rt2880_pmx_func pcie_rst_grp[] = {
+static struct ralink_pmx_func pcie_rst_grp[] = {
 	FUNC("pcie rst", MT7621_GPIO_MODE_PCIE_RST, 19, 1),
 	FUNC("pcie refclk", MT7621_GPIO_MODE_PCIE_REF, 19, 1)
 };
-static struct rt2880_pmx_func mdio_grp[] = { FUNC("mdio", 0, 20, 2) };
-static struct rt2880_pmx_func rgmii2_grp[] = { FUNC("rgmii2", 0, 22, 12) };
-static struct rt2880_pmx_func spi_grp[] = {
+static struct ralink_pmx_func mdio_grp[] = { FUNC("mdio", 0, 20, 2) };
+static struct ralink_pmx_func rgmii2_grp[] = { FUNC("rgmii2", 0, 22, 12) };
+static struct ralink_pmx_func spi_grp[] = {
 	FUNC("spi", 0, 34, 7),
 	FUNC("nand1", 2, 34, 7),
 };
-static struct rt2880_pmx_func sdhci_grp[] = {
+static struct ralink_pmx_func sdhci_grp[] = {
 	FUNC("sdhci", 0, 41, 8),
 	FUNC("nand2", 2, 41, 8),
 };
-static struct rt2880_pmx_func rgmii1_grp[] = { FUNC("rgmii1", 0, 49, 12) };
+static struct ralink_pmx_func rgmii1_grp[] = { FUNC("rgmii1", 0, 49, 12) };
 
-static struct rt2880_pmx_group mt7621_pinmux_data[] = {
+static struct ralink_pmx_group mt7621_pinmux_data[] = {
 	GRP("uart1", uart1_grp, 1, MT7621_GPIO_MODE_UART1),
 	GRP("i2c", i2c_grp, 1, MT7621_GPIO_MODE_I2C),
 	GRP_G("uart3", uart3_grp, MT7621_GPIO_MODE_UART3_MASK,
@@ -92,7 +92,7 @@ static struct rt2880_pmx_group mt7621_pinmux_data[] = {
 
 static int mt7621_pinmux_probe(struct platform_device *pdev)
 {
-	return rt2880_pinmux_init(pdev, mt7621_pinmux_data);
+	return ralink_pinmux_init(pdev, mt7621_pinmux_data);
 }
 
 static const struct of_device_id mt7621_pinmux_match[] = {
diff --git a/drivers/pinctrl/ralink/pinctrl-rt2880.c b/drivers/pinctrl/ralink/pinctrl-ralink.c
index 96fc06d1b8b9..3a8268a43d74 100644
--- a/drivers/pinctrl/ralink/pinctrl-rt2880.c
+++ b/drivers/pinctrl/ralink/pinctrl-ralink.c
@@ -19,23 +19,23 @@
 #include <asm/mach-ralink/ralink_regs.h>
 #include <asm/mach-ralink/mt7620.h>
 
-#include "pinmux.h"
+#include "pinctrl-ralink.h"
 #include "../core.h"
 #include "../pinctrl-utils.h"
 
 #define SYSC_REG_GPIO_MODE	0x60
 #define SYSC_REG_GPIO_MODE2	0x64
 
-struct rt2880_priv {
+struct ralink_priv {
 	struct device *dev;
 
 	struct pinctrl_pin_desc *pads;
 	struct pinctrl_desc *desc;
 
-	struct rt2880_pmx_func **func;
+	struct ralink_pmx_func **func;
 	int func_count;
 
-	struct rt2880_pmx_group *groups;
+	struct ralink_pmx_group *groups;
 	const char **group_names;
 	int group_count;
 
@@ -43,27 +43,27 @@ struct rt2880_priv {
 	int max_pins;
 };
 
-static int rt2880_get_group_count(struct pinctrl_dev *pctrldev)
+static int ralink_get_group_count(struct pinctrl_dev *pctrldev)
 {
-	struct rt2880_priv *p = pinctrl_dev_get_drvdata(pctrldev);
+	struct ralink_priv *p = pinctrl_dev_get_drvdata(pctrldev);
 
 	return p->group_count;
 }
 
-static const char *rt2880_get_group_name(struct pinctrl_dev *pctrldev,
+static const char *ralink_get_group_name(struct pinctrl_dev *pctrldev,
 					 unsigned int group)
 {
-	struct rt2880_priv *p = pinctrl_dev_get_drvdata(pctrldev);
+	struct ralink_priv *p = pinctrl_dev_get_drvdata(pctrldev);
 
 	return (group >= p->group_count) ? NULL : p->group_names[group];
 }
 
-static int rt2880_get_group_pins(struct pinctrl_dev *pctrldev,
+static int ralink_get_group_pins(struct pinctrl_dev *pctrldev,
 				 unsigned int group,
 				 const unsigned int **pins,
 				 unsigned int *num_pins)
 {
-	struct rt2880_priv *p = pinctrl_dev_get_drvdata(pctrldev);
+	struct ralink_priv *p = pinctrl_dev_get_drvdata(pctrldev);
 
 	if (group >= p->group_count)
 		return -EINVAL;
@@ -74,35 +74,35 @@ static int rt2880_get_group_pins(struct pinctrl_dev *pctrldev,
 	return 0;
 }
 
-static const struct pinctrl_ops rt2880_pctrl_ops = {
-	.get_groups_count	= rt2880_get_group_count,
-	.get_group_name		= rt2880_get_group_name,
-	.get_group_pins		= rt2880_get_group_pins,
+static const struct pinctrl_ops ralink_pctrl_ops = {
+	.get_groups_count	= ralink_get_group_count,
+	.get_group_name		= ralink_get_group_name,
+	.get_group_pins		= ralink_get_group_pins,
 	.dt_node_to_map		= pinconf_generic_dt_node_to_map_all,
 	.dt_free_map		= pinconf_generic_dt_free_map,
 };
 
-static int rt2880_pmx_func_count(struct pinctrl_dev *pctrldev)
+static int ralink_pmx_func_count(struct pinctrl_dev *pctrldev)
 {
-	struct rt2880_priv *p = pinctrl_dev_get_drvdata(pctrldev);
+	struct ralink_priv *p = pinctrl_dev_get_drvdata(pctrldev);
 
 	return p->func_count;
 }
 
-static const char *rt2880_pmx_func_name(struct pinctrl_dev *pctrldev,
+static const char *ralink_pmx_func_name(struct pinctrl_dev *pctrldev,
 					unsigned int func)
 {
-	struct rt2880_priv *p = pinctrl_dev_get_drvdata(pctrldev);
+	struct ralink_priv *p = pinctrl_dev_get_drvdata(pctrldev);
 
 	return p->func[func]->name;
 }
 
-static int rt2880_pmx_group_get_groups(struct pinctrl_dev *pctrldev,
+static int ralink_pmx_group_get_groups(struct pinctrl_dev *pctrldev,
 				       unsigned int func,
 				       const char * const **groups,
 				       unsigned int * const num_groups)
 {
-	struct rt2880_priv *p = pinctrl_dev_get_drvdata(pctrldev);
+	struct ralink_priv *p = pinctrl_dev_get_drvdata(pctrldev);
 
 	if (p->func[func]->group_count == 1)
 		*groups = &p->group_names[p->func[func]->groups[0]];
@@ -114,10 +114,10 @@ static int rt2880_pmx_group_get_groups(struct pinctrl_dev *pctrldev,
 	return 0;
 }
 
-static int rt2880_pmx_group_enable(struct pinctrl_dev *pctrldev,
+static int ralink_pmx_group_enable(struct pinctrl_dev *pctrldev,
 				   unsigned int func, unsigned int group)
 {
-	struct rt2880_priv *p = pinctrl_dev_get_drvdata(pctrldev);
+	struct ralink_priv *p = pinctrl_dev_get_drvdata(pctrldev);
 	u32 mode = 0;
 	u32 reg = SYSC_REG_GPIO_MODE;
 	int i;
@@ -158,11 +158,11 @@ static int rt2880_pmx_group_enable(struct pinctrl_dev *pctrldev,
 	return 0;
 }
 
-static int rt2880_pmx_group_gpio_request_enable(struct pinctrl_dev *pctrldev,
+static int ralink_pmx_group_gpio_request_enable(struct pinctrl_dev *pctrldev,
 						struct pinctrl_gpio_range *range,
 						unsigned int pin)
 {
-	struct rt2880_priv *p = pinctrl_dev_get_drvdata(pctrldev);
+	struct ralink_priv *p = pinctrl_dev_get_drvdata(pctrldev);
 
 	if (!p->gpio[pin]) {
 		dev_err(p->dev, "pin %d is not set to gpio mux\n", pin);
@@ -172,28 +172,28 @@ static int rt2880_pmx_group_gpio_request_enable(struct pinctrl_dev *pctrldev,
 	return 0;
 }
 
-static const struct pinmux_ops rt2880_pmx_group_ops = {
-	.get_functions_count	= rt2880_pmx_func_count,
-	.get_function_name	= rt2880_pmx_func_name,
-	.get_function_groups	= rt2880_pmx_group_get_groups,
-	.set_mux		= rt2880_pmx_group_enable,
-	.gpio_request_enable	= rt2880_pmx_group_gpio_request_enable,
+static const struct pinmux_ops ralink_pmx_group_ops = {
+	.get_functions_count	= ralink_pmx_func_count,
+	.get_function_name	= ralink_pmx_func_name,
+	.get_function_groups	= ralink_pmx_group_get_groups,
+	.set_mux		= ralink_pmx_group_enable,
+	.gpio_request_enable	= ralink_pmx_group_gpio_request_enable,
 };
 
-static struct pinctrl_desc rt2880_pctrl_desc = {
+static struct pinctrl_desc ralink_pctrl_desc = {
 	.owner		= THIS_MODULE,
-	.name		= "rt2880-pinmux",
-	.pctlops	= &rt2880_pctrl_ops,
-	.pmxops		= &rt2880_pmx_group_ops,
+	.name		= "ralink-pinmux",
+	.pctlops	= &ralink_pctrl_ops,
+	.pmxops		= &ralink_pmx_group_ops,
 };
 
-static struct rt2880_pmx_func gpio_func = {
+static struct ralink_pmx_func gpio_func = {
 	.name = "gpio",
 };
 
-static int rt2880_pinmux_index(struct rt2880_priv *p)
+static int ralink_pinmux_index(struct ralink_priv *p)
 {
-	struct rt2880_pmx_group *mux = p->groups;
+	struct ralink_pmx_group *mux = p->groups;
 	int i, j, c = 0;
 
 	/* count the mux functions */
@@ -248,7 +248,7 @@ static int rt2880_pinmux_index(struct rt2880_priv *p)
 	return 0;
 }
 
-static int rt2880_pinmux_pins(struct rt2880_priv *p)
+static int ralink_pinmux_pins(struct ralink_priv *p)
 {
 	int i, j;
 
@@ -266,6 +266,8 @@ static int rt2880_pinmux_pins(struct rt2880_priv *p)
 						p->func[i]->pin_count,
 						sizeof(int),
 						GFP_KERNEL);
+		if (!p->func[i]->pins)
+			return -ENOMEM;
 		for (j = 0; j < p->func[i]->pin_count; j++)
 			p->func[i]->pins[j] = p->func[i]->pin_first + j;
 
@@ -311,10 +313,10 @@ static int rt2880_pinmux_pins(struct rt2880_priv *p)
 	return 0;
 }
 
-int rt2880_pinmux_init(struct platform_device *pdev,
-		       struct rt2880_pmx_group *data)
+int ralink_pinmux_init(struct platform_device *pdev,
+		       struct ralink_pmx_group *data)
 {
-	struct rt2880_priv *p;
+	struct ralink_priv *p;
 	struct pinctrl_dev *dev;
 	int err;
 
@@ -322,23 +324,23 @@ int rt2880_pinmux_init(struct platform_device *pdev,
 		return -ENOTSUPP;
 
 	/* setup the private data */
-	p = devm_kzalloc(&pdev->dev, sizeof(struct rt2880_priv), GFP_KERNEL);
+	p = devm_kzalloc(&pdev->dev, sizeof(struct ralink_priv), GFP_KERNEL);
 	if (!p)
 		return -ENOMEM;
 
 	p->dev = &pdev->dev;
-	p->desc = &rt2880_pctrl_desc;
+	p->desc = &ralink_pctrl_desc;
 	p->groups = data;
 	platform_set_drvdata(pdev, p);
 
 	/* init the device */
-	err = rt2880_pinmux_index(p);
+	err = ralink_pinmux_index(p);
 	if (err) {
 		dev_err(&pdev->dev, "failed to load index\n");
 		return err;
 	}
 
-	err = rt2880_pinmux_pins(p);
+	err = ralink_pinmux_pins(p);
 	if (err) {
 		dev_err(&pdev->dev, "failed to load pins\n");
 		return err;
diff --git a/drivers/pinctrl/ralink/pinmux.h b/drivers/pinctrl/ralink/pinctrl-ralink.h
index 0046abe3bcc7..134969409585 100644
--- a/drivers/pinctrl/ralink/pinmux.h
+++ b/drivers/pinctrl/ralink/pinctrl-ralink.h
@@ -3,8 +3,8 @@
  *  Copyright (C) 2012 John Crispin <john@phrozen.org>
  */
 
-#ifndef _RT288X_PINMUX_H__
-#define _RT288X_PINMUX_H__
+#ifndef _PINCTRL_RALINK_H__
+#define _PINCTRL_RALINK_H__
 
 #define FUNC(name, value, pin_first, pin_count) \
 	{ name, value, pin_first, pin_count }
@@ -19,9 +19,9 @@
 	  .func = _func, .gpio = _gpio, \
 	  .func_count = ARRAY_SIZE(_func) }
 
-struct rt2880_pmx_group;
+struct ralink_pmx_group;
 
-struct rt2880_pmx_func {
+struct ralink_pmx_func {
 	const char *name;
 	const char value;
 
@@ -35,7 +35,7 @@ struct rt2880_pmx_func {
 	int enabled;
 };
 
-struct rt2880_pmx_group {
+struct ralink_pmx_group {
 	const char *name;
 	int enabled;
 
@@ -43,11 +43,11 @@ struct rt2880_pmx_group {
 	const char mask;
 	const char gpio;
 
-	struct rt2880_pmx_func *func;
+	struct ralink_pmx_func *func;
 	int func_count;
 };
 
-int rt2880_pinmux_init(struct platform_device *pdev,
-		       struct rt2880_pmx_group *data);
+int ralink_pinmux_init(struct platform_device *pdev,
+		       struct ralink_pmx_group *data);
 
 #endif
diff --git a/drivers/pinctrl/ralink/pinctrl-rt288x.c b/drivers/pinctrl/ralink/pinctrl-rt288x.c
index 0744aebbace5..40c45140ff8a 100644
--- a/drivers/pinctrl/ralink/pinctrl-rt288x.c
+++ b/drivers/pinctrl/ralink/pinctrl-rt288x.c
@@ -4,7 +4,7 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/of.h>
-#include "pinmux.h"
+#include "pinctrl-ralink.h"
 
 #define RT2880_GPIO_MODE_I2C		BIT(0)
 #define RT2880_GPIO_MODE_UART0		BIT(1)
@@ -15,15 +15,15 @@
 #define RT2880_GPIO_MODE_SDRAM		BIT(6)
 #define RT2880_GPIO_MODE_PCI		BIT(7)
 
-static struct rt2880_pmx_func i2c_func[] = { FUNC("i2c", 0, 1, 2) };
-static struct rt2880_pmx_func spi_func[] = { FUNC("spi", 0, 3, 4) };
-static struct rt2880_pmx_func uartlite_func[] = { FUNC("uartlite", 0, 7, 8) };
-static struct rt2880_pmx_func jtag_func[] = { FUNC("jtag", 0, 17, 5) };
-static struct rt2880_pmx_func mdio_func[] = { FUNC("mdio", 0, 22, 2) };
-static struct rt2880_pmx_func sdram_func[] = { FUNC("sdram", 0, 24, 16) };
-static struct rt2880_pmx_func pci_func[] = { FUNC("pci", 0, 40, 32) };
+static struct ralink_pmx_func i2c_func[] = { FUNC("i2c", 0, 1, 2) };
+static struct ralink_pmx_func spi_func[] = { FUNC("spi", 0, 3, 4) };
+static struct ralink_pmx_func uartlite_func[] = { FUNC("uartlite", 0, 7, 8) };
+static struct ralink_pmx_func jtag_func[] = { FUNC("jtag", 0, 17, 5) };
+static struct ralink_pmx_func mdio_func[] = { FUNC("mdio", 0, 22, 2) };
+static struct ralink_pmx_func sdram_func[] = { FUNC("sdram", 0, 24, 16) };
+static struct ralink_pmx_func pci_func[] = { FUNC("pci", 0, 40, 32) };
 
-static struct rt2880_pmx_group rt2880_pinmux_data_act[] = {
+static struct ralink_pmx_group rt2880_pinmux_data_act[] = {
 	GRP("i2c", i2c_func, 1, RT2880_GPIO_MODE_I2C),
 	GRP("spi", spi_func, 1, RT2880_GPIO_MODE_SPI),
 	GRP("uartlite", uartlite_func, 1, RT2880_GPIO_MODE_UART0),
@@ -36,7 +36,7 @@ static struct rt2880_pmx_group rt2880_pinmux_data_act[] = {
 
 static int rt288x_pinmux_probe(struct platform_device *pdev)
 {
-	return rt2880_pinmux_init(pdev, rt2880_pinmux_data_act);
+	return ralink_pinmux_init(pdev, rt2880_pinmux_data_act);
 }
 
 static const struct of_device_id rt288x_pinmux_match[] = {
diff --git a/drivers/pinctrl/ralink/pinctrl-rt305x.c b/drivers/pinctrl/ralink/pinctrl-rt305x.c
index 5d8fa156c003..25527ca1ccaa 100644
--- a/drivers/pinctrl/ralink/pinctrl-rt305x.c
+++ b/drivers/pinctrl/ralink/pinctrl-rt305x.c
@@ -5,7 +5,7 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/of.h>
-#include "pinmux.h"
+#include "pinctrl-ralink.h"
 
 #define RT305X_GPIO_MODE_UART0_SHIFT	2
 #define RT305X_GPIO_MODE_UART0_MASK	0x7
@@ -31,9 +31,9 @@
 #define RT3352_GPIO_MODE_LNA		18
 #define RT3352_GPIO_MODE_PA		20
 
-static struct rt2880_pmx_func i2c_func[] =  { FUNC("i2c", 0, 1, 2) };
-static struct rt2880_pmx_func spi_func[] = { FUNC("spi", 0, 3, 4) };
-static struct rt2880_pmx_func uartf_func[] = {
+static struct ralink_pmx_func i2c_func[] =  { FUNC("i2c", 0, 1, 2) };
+static struct ralink_pmx_func spi_func[] = { FUNC("spi", 0, 3, 4) };
+static struct ralink_pmx_func uartf_func[] = {
 	FUNC("uartf", RT305X_GPIO_MODE_UARTF, 7, 8),
 	FUNC("pcm uartf", RT305X_GPIO_MODE_PCM_UARTF, 7, 8),
 	FUNC("pcm i2s", RT305X_GPIO_MODE_PCM_I2S, 7, 8),
@@ -42,28 +42,28 @@ static struct rt2880_pmx_func uartf_func[] = {
 	FUNC("gpio uartf", RT305X_GPIO_MODE_GPIO_UARTF, 7, 4),
 	FUNC("gpio i2s", RT305X_GPIO_MODE_GPIO_I2S, 7, 4),
 };
-static struct rt2880_pmx_func uartlite_func[] = { FUNC("uartlite", 0, 15, 2) };
-static struct rt2880_pmx_func jtag_func[] = { FUNC("jtag", 0, 17, 5) };
-static struct rt2880_pmx_func mdio_func[] = { FUNC("mdio", 0, 22, 2) };
-static struct rt2880_pmx_func rt5350_led_func[] = { FUNC("led", 0, 22, 5) };
-static struct rt2880_pmx_func rt5350_cs1_func[] = {
+static struct ralink_pmx_func uartlite_func[] = { FUNC("uartlite", 0, 15, 2) };
+static struct ralink_pmx_func jtag_func[] = { FUNC("jtag", 0, 17, 5) };
+static struct ralink_pmx_func mdio_func[] = { FUNC("mdio", 0, 22, 2) };
+static struct ralink_pmx_func rt5350_led_func[] = { FUNC("led", 0, 22, 5) };
+static struct ralink_pmx_func rt5350_cs1_func[] = {
 	FUNC("spi_cs1", 0, 27, 1),
 	FUNC("wdg_cs1", 1, 27, 1),
 };
-static struct rt2880_pmx_func sdram_func[] = { FUNC("sdram", 0, 24, 16) };
-static struct rt2880_pmx_func rt3352_rgmii_func[] = {
+static struct ralink_pmx_func sdram_func[] = { FUNC("sdram", 0, 24, 16) };
+static struct ralink_pmx_func rt3352_rgmii_func[] = {
 	FUNC("rgmii", 0, 24, 12)
 };
-static struct rt2880_pmx_func rgmii_func[] = { FUNC("rgmii", 0, 40, 12) };
-static struct rt2880_pmx_func rt3352_lna_func[] = { FUNC("lna", 0, 36, 2) };
-static struct rt2880_pmx_func rt3352_pa_func[] = { FUNC("pa", 0, 38, 2) };
-static struct rt2880_pmx_func rt3352_led_func[] = { FUNC("led", 0, 40, 5) };
-static struct rt2880_pmx_func rt3352_cs1_func[] = {
+static struct ralink_pmx_func rgmii_func[] = { FUNC("rgmii", 0, 40, 12) };
+static struct ralink_pmx_func rt3352_lna_func[] = { FUNC("lna", 0, 36, 2) };
+static struct ralink_pmx_func rt3352_pa_func[] = { FUNC("pa", 0, 38, 2) };
+static struct ralink_pmx_func rt3352_led_func[] = { FUNC("led", 0, 40, 5) };
+static struct ralink_pmx_func rt3352_cs1_func[] = {
 	FUNC("spi_cs1", 0, 45, 1),
 	FUNC("wdg_cs1", 1, 45, 1),
 };
 
-static struct rt2880_pmx_group rt3050_pinmux_data[] = {
+static struct ralink_pmx_group rt3050_pinmux_data[] = {
 	GRP("i2c", i2c_func, 1, RT305X_GPIO_MODE_I2C),
 	GRP("spi", spi_func, 1, RT305X_GPIO_MODE_SPI),
 	GRP("uartf", uartf_func, RT305X_GPIO_MODE_UART0_MASK,
@@ -76,7 +76,7 @@ static struct rt2880_pmx_group rt3050_pinmux_data[] = {
 	{ 0 }
 };
 
-static struct rt2880_pmx_group rt3352_pinmux_data[] = {
+static struct ralink_pmx_group rt3352_pinmux_data[] = {
 	GRP("i2c", i2c_func, 1, RT305X_GPIO_MODE_I2C),
 	GRP("spi", spi_func, 1, RT305X_GPIO_MODE_SPI),
 	GRP("uartf", uartf_func, RT305X_GPIO_MODE_UART0_MASK,
@@ -92,7 +92,7 @@ static struct rt2880_pmx_group rt3352_pinmux_data[] = {
 	{ 0 }
 };
 
-static struct rt2880_pmx_group rt5350_pinmux_data[] = {
+static struct ralink_pmx_group rt5350_pinmux_data[] = {
 	GRP("i2c", i2c_func, 1, RT305X_GPIO_MODE_I2C),
 	GRP("spi", spi_func, 1, RT305X_GPIO_MODE_SPI),
 	GRP("uartf", uartf_func, RT305X_GPIO_MODE_UART0_MASK,
@@ -107,11 +107,11 @@ static struct rt2880_pmx_group rt5350_pinmux_data[] = {
 static int rt305x_pinmux_probe(struct platform_device *pdev)
 {
 	if (soc_is_rt5350())
-		return rt2880_pinmux_init(pdev, rt5350_pinmux_data);
+		return ralink_pinmux_init(pdev, rt5350_pinmux_data);
 	else if (soc_is_rt305x() || soc_is_rt3350())
-		return rt2880_pinmux_init(pdev, rt3050_pinmux_data);
+		return ralink_pinmux_init(pdev, rt3050_pinmux_data);
 	else if (soc_is_rt3352())
-		return rt2880_pinmux_init(pdev, rt3352_pinmux_data);
+		return ralink_pinmux_init(pdev, rt3352_pinmux_data);
 	else
 		return -EINVAL;
 }
diff --git a/drivers/pinctrl/ralink/pinctrl-rt3883.c b/drivers/pinctrl/ralink/pinctrl-rt3883.c
index 3e0e1b4caa64..0b8674dbe188 100644
--- a/drivers/pinctrl/ralink/pinctrl-rt3883.c
+++ b/drivers/pinctrl/ralink/pinctrl-rt3883.c
@@ -3,7 +3,7 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/of.h>
-#include "pinmux.h"
+#include "pinctrl-ralink.h"
 
 #define RT3883_GPIO_MODE_UART0_SHIFT	2
 #define RT3883_GPIO_MODE_UART0_MASK	0x7
@@ -39,9 +39,9 @@
 #define RT3883_GPIO_MODE_LNA_G_GPIO	0x3
 #define RT3883_GPIO_MODE_LNA_G		_RT3883_GPIO_MODE_LNA_G(RT3883_GPIO_MODE_LNA_G_MASK)
 
-static struct rt2880_pmx_func i2c_func[] =  { FUNC("i2c", 0, 1, 2) };
-static struct rt2880_pmx_func spi_func[] = { FUNC("spi", 0, 3, 4) };
-static struct rt2880_pmx_func uartf_func[] = {
+static struct ralink_pmx_func i2c_func[] =  { FUNC("i2c", 0, 1, 2) };
+static struct ralink_pmx_func spi_func[] = { FUNC("spi", 0, 3, 4) };
+static struct ralink_pmx_func uartf_func[] = {
 	FUNC("uartf", RT3883_GPIO_MODE_UARTF, 7, 8),
 	FUNC("pcm uartf", RT3883_GPIO_MODE_PCM_UARTF, 7, 8),
 	FUNC("pcm i2s", RT3883_GPIO_MODE_PCM_I2S, 7, 8),
@@ -50,21 +50,21 @@ static struct rt2880_pmx_func uartf_func[] = {
 	FUNC("gpio uartf", RT3883_GPIO_MODE_GPIO_UARTF, 7, 4),
 	FUNC("gpio i2s", RT3883_GPIO_MODE_GPIO_I2S, 7, 4),
 };
-static struct rt2880_pmx_func uartlite_func[] = { FUNC("uartlite", 0, 15, 2) };
-static struct rt2880_pmx_func jtag_func[] = { FUNC("jtag", 0, 17, 5) };
-static struct rt2880_pmx_func mdio_func[] = { FUNC("mdio", 0, 22, 2) };
-static struct rt2880_pmx_func lna_a_func[] = { FUNC("lna a", 0, 32, 3) };
-static struct rt2880_pmx_func lna_g_func[] = { FUNC("lna g", 0, 35, 3) };
-static struct rt2880_pmx_func pci_func[] = {
+static struct ralink_pmx_func uartlite_func[] = { FUNC("uartlite", 0, 15, 2) };
+static struct ralink_pmx_func jtag_func[] = { FUNC("jtag", 0, 17, 5) };
+static struct ralink_pmx_func mdio_func[] = { FUNC("mdio", 0, 22, 2) };
+static struct ralink_pmx_func lna_a_func[] = { FUNC("lna a", 0, 32, 3) };
+static struct ralink_pmx_func lna_g_func[] = { FUNC("lna g", 0, 35, 3) };
+static struct ralink_pmx_func pci_func[] = {
 	FUNC("pci-dev", 0, 40, 32),
 	FUNC("pci-host2", 1, 40, 32),
 	FUNC("pci-host1", 2, 40, 32),
 	FUNC("pci-fnc", 3, 40, 32)
 };
-static struct rt2880_pmx_func ge1_func[] = { FUNC("ge1", 0, 72, 12) };
-static struct rt2880_pmx_func ge2_func[] = { FUNC("ge2", 0, 84, 12) };
+static struct ralink_pmx_func ge1_func[] = { FUNC("ge1", 0, 72, 12) };
+static struct ralink_pmx_func ge2_func[] = { FUNC("ge2", 0, 84, 12) };
 
-static struct rt2880_pmx_group rt3883_pinmux_data[] = {
+static struct ralink_pmx_group rt3883_pinmux_data[] = {
 	GRP("i2c", i2c_func, 1, RT3883_GPIO_MODE_I2C),
 	GRP("spi", spi_func, 1, RT3883_GPIO_MODE_SPI),
 	GRP("uartf", uartf_func, RT3883_GPIO_MODE_UART0_MASK,
@@ -83,7 +83,7 @@ static struct rt2880_pmx_group rt3883_pinmux_data[] = {
 
 static int rt3883_pinmux_probe(struct platform_device *pdev)
 {
-	return rt2880_pinmux_init(pdev, rt3883_pinmux_data);
+	return ralink_pinmux_init(pdev, rt3883_pinmux_data);
 }
 
 static const struct of_device_id rt3883_pinmux_match[] = {
diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c
index 97a4fb5a9328..d3fa8cf0d72c 100644
--- a/drivers/pinctrl/stm32/pinctrl-stm32.c
+++ b/drivers/pinctrl/stm32/pinctrl-stm32.c
@@ -1299,15 +1299,17 @@ static int stm32_gpiolib_register_bank(struct stm32_pinctrl *pctl,
 	bank->bank_ioport_nr = bank_ioport_nr;
 	spin_lock_init(&bank->lock);
 
-	/* create irq hierarchical domain */
-	bank->fwnode = of_node_to_fwnode(np);
+	if (pctl->domain) {
+		/* create irq hierarchical domain */
+		bank->fwnode = of_node_to_fwnode(np);
 
-	bank->domain = irq_domain_create_hierarchy(pctl->domain, 0,
-					STM32_GPIO_IRQ_LINE, bank->fwnode,
-					&stm32_gpio_domain_ops, bank);
+		bank->domain = irq_domain_create_hierarchy(pctl->domain, 0, STM32_GPIO_IRQ_LINE,
+							   bank->fwnode, &stm32_gpio_domain_ops,
+							   bank);
 
-	if (!bank->domain)
-		return -ENODEV;
+		if (!bank->domain)
+			return -ENODEV;
+	}
 
 	err = gpiochip_add_data(&bank->gpio_chip, bank);
 	if (err) {
@@ -1477,6 +1479,8 @@ int stm32_pctl_probe(struct platform_device *pdev)
 	pctl->domain = stm32_pctrl_get_irq_domain(np);
 	if (IS_ERR(pctl->domain))
 		return PTR_ERR(pctl->domain);
+	if (!pctl->domain)
+		dev_warn(dev, "pinctrl without interrupt support\n");
 
 	/* hwspinlock is optional */
 	hwlock_id = of_hwspin_lock_get_id(pdev->dev.of_node, 0);
diff --git a/drivers/pinctrl/sunxi/pinctrl-sun50i-a100-r.c b/drivers/pinctrl/sunxi/pinctrl-sun50i-a100-r.c
index 21054fcacd34..18088f6f44b2 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sun50i-a100-r.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sun50i-a100-r.c
@@ -98,7 +98,7 @@ MODULE_DEVICE_TABLE(of, a100_r_pinctrl_match);
 static struct platform_driver a100_r_pinctrl_driver = {
 	.probe	= a100_r_pinctrl_probe,
 	.driver	= {
-		.name		= "sun50iw10p1-r-pinctrl",
+		.name		= "sun50i-a100-r-pinctrl",
 		.of_match_table	= a100_r_pinctrl_match,
 	},
 };
diff --git a/drivers/pinctrl/sunxi/pinctrl-sun50i-h6-r.c b/drivers/pinctrl/sunxi/pinctrl-sun50i-h6-r.c
index c7d90c44e87a..7b4b9f3d4555 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sun50i-h6-r.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sun50i-h6-r.c
@@ -107,6 +107,7 @@ static const struct sunxi_pinctrl_desc sun50i_h6_r_pinctrl_data = {
 	.npins = ARRAY_SIZE(sun50i_h6_r_pins),
 	.pin_base = PL_BASE,
 	.irq_banks = 2,
+	.io_bias_cfg_variant = BIAS_VOLTAGE_PIO_POW_MODE_SEL,
 };
 
 static int sun50i_h6_r_pinctrl_probe(struct platform_device *pdev)
diff --git a/drivers/pinctrl/sunxi/pinctrl-sun8i-a83t.c b/drivers/pinctrl/sunxi/pinctrl-sun8i-a83t.c
index 4ada80317a3b..b5c1a8f363f3 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sun8i-a83t.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sun8i-a83t.c
@@ -158,26 +158,26 @@ static const struct sunxi_desc_pin sun8i_a83t_pins[] = {
 	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 14),
 		  SUNXI_FUNCTION(0x0, "gpio_in"),
 		  SUNXI_FUNCTION(0x1, "gpio_out"),
-		  SUNXI_FUNCTION(0x2, "nand"),		/* DQ6 */
+		  SUNXI_FUNCTION(0x2, "nand0"),		/* DQ6 */
 		  SUNXI_FUNCTION(0x3, "mmc2")),		/* D6 */
 	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 15),
 		  SUNXI_FUNCTION(0x0, "gpio_in"),
 		  SUNXI_FUNCTION(0x1, "gpio_out"),
-		  SUNXI_FUNCTION(0x2, "nand"),		/* DQ7 */
+		  SUNXI_FUNCTION(0x2, "nand0"),		/* DQ7 */
 		  SUNXI_FUNCTION(0x3, "mmc2")),		/* D7 */
 	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 16),
 		  SUNXI_FUNCTION(0x0, "gpio_in"),
 		  SUNXI_FUNCTION(0x1, "gpio_out"),
-		  SUNXI_FUNCTION(0x2, "nand"),		/* DQS */
+		  SUNXI_FUNCTION(0x2, "nand0"),		/* DQS */
 		  SUNXI_FUNCTION(0x3, "mmc2")),		/* RST */
 	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 17),
 		  SUNXI_FUNCTION(0x0, "gpio_in"),
 		  SUNXI_FUNCTION(0x1, "gpio_out"),
-		  SUNXI_FUNCTION(0x2, "nand")),		/* CE2 */
+		  SUNXI_FUNCTION(0x2, "nand0")),	/* CE2 */
 	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 18),
 		  SUNXI_FUNCTION(0x0, "gpio_in"),
 		  SUNXI_FUNCTION(0x1, "gpio_out"),
-		  SUNXI_FUNCTION(0x2, "nand")),		/* CE3 */
+		  SUNXI_FUNCTION(0x2, "nand0")),	/* CE3 */
 	/* Hole */
 	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 2),
 		  SUNXI_FUNCTION(0x0, "gpio_in"),
diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
index ce3f9ea41511..30ca0fe5c31a 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
@@ -544,6 +544,8 @@ static int sunxi_pconf_set(struct pinctrl_dev *pctldev, unsigned pin,
 	struct sunxi_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
 	int i;
 
+	pin -= pctl->desc->pin_base;
+
 	for (i = 0; i < num_configs; i++) {
 		enum pin_config_param param;
 		unsigned long flags;
@@ -622,7 +624,7 @@ static int sunxi_pinctrl_set_io_bias_cfg(struct sunxi_pinctrl *pctl,
 					 unsigned pin,
 					 struct regulator *supply)
 {
-	unsigned short bank = pin / PINS_PER_BANK;
+	unsigned short bank;
 	unsigned long flags;
 	u32 val, reg;
 	int uV;
@@ -638,6 +640,9 @@ static int sunxi_pinctrl_set_io_bias_cfg(struct sunxi_pinctrl *pctl,
 	if (uV == 0)
 		return 0;
 
+	pin -= pctl->desc->pin_base;
+	bank = pin / PINS_PER_BANK;
+
 	switch (pctl->desc->io_bias_cfg_variant) {
 	case BIAS_VOLTAGE_GRP_CONFIG:
 		/*
@@ -655,8 +660,6 @@ static int sunxi_pinctrl_set_io_bias_cfg(struct sunxi_pinctrl *pctl,
 		else
 			val = 0xD; /* 3.3V */
 
-		pin -= pctl->desc->pin_base;
-
 		reg = readl(pctl->membase + sunxi_grp_config_reg(pin));
 		reg &= ~IO_BIAS_MASK;
 		writel(reg | val, pctl->membase + sunxi_grp_config_reg(pin));
diff --git a/drivers/platform/chrome/cros_ec.c b/drivers/platform/chrome/cros_ec.c
index ff2a24b0c611..4f0390b10cd3 100644
--- a/drivers/platform/chrome/cros_ec.c
+++ b/drivers/platform/chrome/cros_ec.c
@@ -135,16 +135,16 @@ static int cros_ec_sleep_event(struct cros_ec_device *ec_dev, u8 sleep_event)
 	buf.msg.command = EC_CMD_HOST_SLEEP_EVENT;
 
 	ret = cros_ec_cmd_xfer_status(ec_dev, &buf.msg);
-
-	/* For now, report failure to transition to S0ix with a warning. */
+	/* Report failure to transition to system wide suspend with a warning. */
 	if (ret >= 0 && ec_dev->host_sleep_v1 &&
-	    (sleep_event == HOST_SLEEP_EVENT_S0IX_RESUME)) {
+	    (sleep_event == HOST_SLEEP_EVENT_S0IX_RESUME ||
+	     sleep_event == HOST_SLEEP_EVENT_S3_RESUME)) {
 		ec_dev->last_resume_result =
 			buf.u.resp1.resume_response.sleep_transitions;
 
 		WARN_ONCE(buf.u.resp1.resume_response.sleep_transitions &
 			  EC_HOST_RESUME_SLEEP_TIMEOUT,
-			  "EC detected sleep transition timeout. Total slp_s0 transitions: %d",
+			  "EC detected sleep transition timeout. Total sleep transitions: %d",
 			  buf.u.resp1.resume_response.sleep_transitions &
 			  EC_HOST_RESUME_SLEEP_TRANSITIONS_MASK);
 	}
diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c
index ed2b4807328d..1575d603d3ff 100644
--- a/drivers/platform/chrome/cros_ec_proto.c
+++ b/drivers/platform/chrome/cros_ec_proto.c
@@ -507,13 +507,13 @@ int cros_ec_query_all(struct cros_ec_device *ec_dev)
 	ret = cros_ec_get_host_command_version_mask(ec_dev,
 						    EC_CMD_GET_NEXT_EVENT,
 						    &ver_mask);
-	if (ret < 0 || ver_mask == 0)
+	if (ret < 0 || ver_mask == 0) {
 		ec_dev->mkbp_event_supported = 0;
-	else
+	} else {
 		ec_dev->mkbp_event_supported = fls(ver_mask);
 
-	dev_dbg(ec_dev->dev, "MKBP support version %u\n",
-		ec_dev->mkbp_event_supported - 1);
+		dev_dbg(ec_dev->dev, "MKBP support version %u\n", ec_dev->mkbp_event_supported - 1);
+	}
 
 	/* Probe if host sleep v1 is supported for S0ix failure detection. */
 	ret = cros_ec_get_host_command_version_mask(ec_dev,
diff --git a/drivers/platform/olpc/olpc-ec.c b/drivers/platform/olpc/olpc-ec.c
index 4ff5c3a12991..921520475ff6 100644
--- a/drivers/platform/olpc/olpc-ec.c
+++ b/drivers/platform/olpc/olpc-ec.c
@@ -264,7 +264,7 @@ static ssize_t ec_dbgfs_cmd_write(struct file *file, const char __user *buf,
 	int i, m;
 	unsigned char ec_cmd[EC_MAX_CMD_ARGS];
 	unsigned int ec_cmd_int[EC_MAX_CMD_ARGS];
-	char cmdbuf[64];
+	char cmdbuf[64] = "";
 	int ec_cmd_bytes;
 
 	mutex_lock(&ec_dbgfs_lock);
diff --git a/drivers/platform/surface/surface_aggregator_registry.c b/drivers/platform/surface/surface_aggregator_registry.c
index 1679811eff50..5c0451c56ea8 100644
--- a/drivers/platform/surface/surface_aggregator_registry.c
+++ b/drivers/platform/surface/surface_aggregator_registry.c
@@ -558,6 +558,9 @@ static const struct acpi_device_id ssam_platform_hub_match[] = {
 	/* Surface Laptop Go 1 */
 	{ "MSHW0118", (unsigned long)ssam_node_group_slg1 },
 
+	/* Surface Laptop Go 2 */
+	{ "MSHW0290", (unsigned long)ssam_node_group_slg1 },
+
 	/* Surface Laptop Studio */
 	{ "MSHW0123", (unsigned long)ssam_node_group_sls },
 
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index e21ea3d23e6f..f1ff003bb14b 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -871,6 +871,8 @@ config PANASONIC_LAPTOP
 	tristate "Panasonic Laptop Extras"
 	depends on INPUT && ACPI
 	depends on BACKLIGHT_CLASS_DEVICE
+	depends on ACPI_VIDEO=n || ACPI_VIDEO
+	depends on SERIO_I8042 || SERIO_I8042 = n
 	select INPUT_SPARSEKMAP
 	help
 	  This driver adds support for access to backlight control and hotkeys
diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c
index 694b45ed06a2..8c2a73d5428d 100644
--- a/drivers/platform/x86/acer-wmi.c
+++ b/drivers/platform/x86/acer-wmi.c
@@ -99,6 +99,7 @@ static const struct key_entry acer_wmi_keymap[] __initconst = {
 	{KE_KEY, 0x22, {KEY_PROG2} },    /* Arcade */
 	{KE_KEY, 0x23, {KEY_PROG3} },    /* P_Key */
 	{KE_KEY, 0x24, {KEY_PROG4} },    /* Social networking_Key */
+	{KE_KEY, 0x27, {KEY_HELP} },
 	{KE_KEY, 0x29, {KEY_PROG3} },    /* P_Key for TM8372 */
 	{KE_IGNORE, 0x41, {KEY_MUTE} },
 	{KE_IGNORE, 0x42, {KEY_PREVIOUSSONG} },
@@ -112,7 +113,13 @@ static const struct key_entry acer_wmi_keymap[] __initconst = {
 	{KE_IGNORE, 0x48, {KEY_VOLUMEUP} },
 	{KE_IGNORE, 0x49, {KEY_VOLUMEDOWN} },
 	{KE_IGNORE, 0x4a, {KEY_VOLUMEDOWN} },
-	{KE_IGNORE, 0x61, {KEY_SWITCHVIDEOMODE} },
+	/*
+	 * 0x61 is KEY_SWITCHVIDEOMODE. Usually this is a duplicate input event
+	 * with the "Video Bus" input device events. But sometimes it is not
+	 * a dup. Map it to KEY_UNKNOWN instead of using KE_IGNORE so that
+	 * udev/hwdb can override it on systems where it is not a dup.
+	 */
+	{KE_KEY, 0x61, {KEY_UNKNOWN} },
 	{KE_IGNORE, 0x62, {KEY_BRIGHTNESSUP} },
 	{KE_IGNORE, 0x63, {KEY_BRIGHTNESSDOWN} },
 	{KE_KEY, 0x64, {KEY_SWITCHVIDEOMODE} },	/* Display Switch */
diff --git a/drivers/platform/x86/hp-wmi.c b/drivers/platform/x86/hp-wmi.c
index 027a1467d009..1cd168e32810 100644
--- a/drivers/platform/x86/hp-wmi.c
+++ b/drivers/platform/x86/hp-wmi.c
@@ -63,6 +63,7 @@ enum hp_wmi_event_ids {
 	HPWMI_BACKLIT_KB_BRIGHTNESS	= 0x0D,
 	HPWMI_PEAKSHIFT_PERIOD		= 0x0F,
 	HPWMI_BATTERY_CHARGE_PERIOD	= 0x10,
+	HPWMI_SANITIZATION_MODE		= 0x17,
 };
 
 struct bios_args {
@@ -638,6 +639,8 @@ static void hp_wmi_notify(u32 value, void *context)
 		break;
 	case HPWMI_BATTERY_CHARGE_PERIOD:
 		break;
+	case HPWMI_SANITIZATION_MODE:
+		break;
 	default:
 		pr_info("Unknown event_id - %d - 0x%x\n", event_id, event_data);
 		break;
diff --git a/drivers/platform/x86/panasonic-laptop.c b/drivers/platform/x86/panasonic-laptop.c
index d4f444401496..7ca49b3fc6c2 100644
--- a/drivers/platform/x86/panasonic-laptop.c
+++ b/drivers/platform/x86/panasonic-laptop.c
@@ -119,20 +119,22 @@
  *		- v0.1  start from toshiba_acpi driver written by John Belmonte
  */
 
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/types.h>
+#include <linux/acpi.h>
 #include <linux/backlight.h>
 #include <linux/ctype.h>
-#include <linux/seq_file.h>
-#include <linux/uaccess.h>
-#include <linux/slab.h>
-#include <linux/acpi.h>
+#include <linux/i8042.h>
+#include <linux/init.h>
 #include <linux/input.h>
 #include <linux/input/sparse-keymap.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/platform_device.h>
-
+#include <linux/seq_file.h>
+#include <linux/serio.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <acpi/video.h>
 
 MODULE_AUTHOR("Hiroshi Miura <miura@da-cha.org>");
 MODULE_AUTHOR("David Bronaugh <dbronaugh@linuxboxen.org>");
@@ -241,6 +243,42 @@ struct pcc_acpi {
 	struct platform_device	*platform;
 };
 
+/*
+ * On some Panasonic models the volume up / down / mute keys send duplicate
+ * keypress events over the PS/2 kbd interface, filter these out.
+ */
+static bool panasonic_i8042_filter(unsigned char data, unsigned char str,
+				   struct serio *port)
+{
+	static bool extended;
+
+	if (str & I8042_STR_AUXDATA)
+		return false;
+
+	if (data == 0xe0) {
+		extended = true;
+		return true;
+	} else if (extended) {
+		extended = false;
+
+		switch (data & 0x7f) {
+		case 0x20: /* e0 20 / e0 a0, Volume Mute press / release */
+		case 0x2e: /* e0 2e / e0 ae, Volume Down press / release */
+		case 0x30: /* e0 30 / e0 b0, Volume Up press / release */
+			return true;
+		default:
+			/*
+			 * Report the previously filtered e0 before continuing
+			 * with the next non-filtered byte.
+			 */
+			serio_interrupt(port, 0xe0, 0);
+			return false;
+		}
+	}
+
+	return false;
+}
+
 /* method access functions */
 static int acpi_pcc_write_sset(struct pcc_acpi *pcc, int func, int val)
 {
@@ -762,6 +800,8 @@ static void acpi_pcc_generate_keyinput(struct pcc_acpi *pcc)
 	struct input_dev *hotk_input_dev = pcc->input_dev;
 	int rc;
 	unsigned long long result;
+	unsigned int key;
+	unsigned int updown;
 
 	rc = acpi_evaluate_integer(pcc->handle, METHOD_HKEY_QUERY,
 				   NULL, &result);
@@ -770,20 +810,27 @@ static void acpi_pcc_generate_keyinput(struct pcc_acpi *pcc)
 		return;
 	}
 
+	key = result & 0xf;
+	updown = result & 0x80; /* 0x80 == key down; 0x00 = key up */
+
 	/* hack: some firmware sends no key down for sleep / hibernate */
-	if ((result & 0xf) == 0x7 || (result & 0xf) == 0xa) {
-		if (result & 0x80)
+	if (key == 7 || key == 10) {
+		if (updown)
 			sleep_keydown_seen = 1;
 		if (!sleep_keydown_seen)
 			sparse_keymap_report_event(hotk_input_dev,
-					result & 0xf, 0x80, false);
+					key, 0x80, false);
 	}
 
-	if ((result & 0xf) == 0x7 || (result & 0xf) == 0x9 || (result & 0xf) == 0xa) {
-		if (!sparse_keymap_report_event(hotk_input_dev,
-						result & 0xf, result & 0x80, false))
-			pr_err("Unknown hotkey event: 0x%04llx\n", result);
-	}
+	/*
+	 * Don't report brightness key-presses if they are also reported
+	 * by the ACPI video bus.
+	 */
+	if ((key == 1 || key == 2) && acpi_video_handles_brightness_key_presses())
+		return;
+
+	if (!sparse_keymap_report_event(hotk_input_dev, key, updown, false))
+		pr_err("Unknown hotkey event: 0x%04llx\n", result);
 }
 
 static void acpi_pcc_hotkey_notify(struct acpi_device *device, u32 event)
@@ -997,6 +1044,7 @@ static int acpi_pcc_hotkey_add(struct acpi_device *device)
 		pcc->platform = NULL;
 	}
 
+	i8042_install_filter(panasonic_i8042_filter);
 	return 0;
 
 out_platform:
@@ -1020,6 +1068,8 @@ static int acpi_pcc_hotkey_remove(struct acpi_device *device)
 	if (!device || !pcc)
 		return -EINVAL;
 
+	i8042_remove_filter(panasonic_i8042_filter);
+
 	if (pcc->platform) {
 		device_remove_file(&pcc->platform->dev, &dev_attr_cdpower);
 		platform_device_unregister(pcc->platform);
diff --git a/drivers/platform/x86/pmc_atom.c b/drivers/platform/x86/pmc_atom.c
index a9d2a4b98e57..4b0739f95f8b 100644
--- a/drivers/platform/x86/pmc_atom.c
+++ b/drivers/platform/x86/pmc_atom.c
@@ -244,7 +244,7 @@ static void pmc_power_off(void)
 	pm1_cnt_port = acpi_base_addr + PM1_CNT;
 
 	pm1_cnt_value = inl(pm1_cnt_port);
-	pm1_cnt_value &= SLEEP_TYPE_MASK;
+	pm1_cnt_value &= ~SLEEP_TYPE_MASK;
 	pm1_cnt_value |= SLEEP_TYPE_S5;
 	pm1_cnt_value |= SLEEP_ENABLE;
 
diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c
index 1b65bb61ce88..c4f917d45b51 100644
--- a/drivers/platform/x86/wmi.c
+++ b/drivers/platform/x86/wmi.c
@@ -51,6 +51,11 @@ struct guid_block {
 	u8 flags;
 };
 
+enum {	/* wmi_block flags */
+	WMI_READ_TAKES_NO_ARGS,
+	WMI_PROBED,
+};
+
 struct wmi_block {
 	struct wmi_device dev;
 	struct list_head list;
@@ -61,8 +66,7 @@ struct wmi_block {
 	wmi_notify_handler handler;
 	void *handler_data;
 	u64 req_buf_size;
-
-	bool read_takes_no_args;
+	unsigned long flags;
 };
 
 
@@ -325,7 +329,7 @@ static acpi_status __query_block(struct wmi_block *wblock, u8 instance,
 	wq_params[0].type = ACPI_TYPE_INTEGER;
 	wq_params[0].integer.value = instance;
 
-	if (instance == 0 && wblock->read_takes_no_args)
+	if (instance == 0 && test_bit(WMI_READ_TAKES_NO_ARGS, &wblock->flags))
 		input.count = 0;
 
 	/*
@@ -676,6 +680,11 @@ static struct wmi_device *dev_to_wdev(struct device *dev)
 	return container_of(dev, struct wmi_device, dev);
 }
 
+static inline struct wmi_driver *drv_to_wdrv(struct device_driver *drv)
+{
+	return container_of(drv, struct wmi_driver, driver);
+}
+
 /*
  * sysfs interface
  */
@@ -794,8 +803,7 @@ static void wmi_dev_release(struct device *dev)
 
 static int wmi_dev_match(struct device *dev, struct device_driver *driver)
 {
-	struct wmi_driver *wmi_driver =
-		container_of(driver, struct wmi_driver, driver);
+	struct wmi_driver *wmi_driver = drv_to_wdrv(driver);
 	struct wmi_block *wblock = dev_to_wblock(dev);
 	const struct wmi_device_id *id = wmi_driver->id_table;
 
@@ -892,8 +900,7 @@ static long wmi_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	}
 
 	/* let the driver do any filtering and do the call */
-	wdriver = container_of(wblock->dev.dev.driver,
-			       struct wmi_driver, driver);
+	wdriver = drv_to_wdrv(wblock->dev.dev.driver);
 	if (!try_module_get(wdriver->driver.owner)) {
 		ret = -EBUSY;
 		goto out_ioctl;
@@ -926,8 +933,7 @@ static const struct file_operations wmi_fops = {
 static int wmi_dev_probe(struct device *dev)
 {
 	struct wmi_block *wblock = dev_to_wblock(dev);
-	struct wmi_driver *wdriver =
-		container_of(dev->driver, struct wmi_driver, driver);
+	struct wmi_driver *wdriver = drv_to_wdrv(dev->driver);
 	int ret = 0;
 	char *buf;
 
@@ -975,6 +981,7 @@ static int wmi_dev_probe(struct device *dev)
 		}
 	}
 
+	set_bit(WMI_PROBED, &wblock->flags);
 	return 0;
 
 probe_misc_failure:
@@ -990,8 +997,9 @@ probe_failure:
 static void wmi_dev_remove(struct device *dev)
 {
 	struct wmi_block *wblock = dev_to_wblock(dev);
-	struct wmi_driver *wdriver =
-		container_of(dev->driver, struct wmi_driver, driver);
+	struct wmi_driver *wdriver = drv_to_wdrv(dev->driver);
+
+	clear_bit(WMI_PROBED, &wblock->flags);
 
 	if (wdriver->filter_callback) {
 		misc_deregister(&wblock->char_dev);
@@ -1086,7 +1094,7 @@ static int wmi_create_device(struct device *wmi_bus_dev,
 	 * laptops, WQxx may not be a method at all.)
 	 */
 	if (info->type != ACPI_TYPE_METHOD || info->param_count == 0)
-		wblock->read_takes_no_args = true;
+		set_bit(WMI_READ_TAKES_NO_ARGS, &wblock->flags);
 
 	kfree(info);
 
@@ -1295,16 +1303,13 @@ static void acpi_wmi_notify_handler(acpi_handle handle, u32 event,
 		return;
 
 	/* If a driver is bound, then notify the driver. */
-	if (wblock->dev.dev.driver) {
-		struct wmi_driver *driver;
+	if (test_bit(WMI_PROBED, &wblock->flags) && wblock->dev.dev.driver) {
+		struct wmi_driver *driver = drv_to_wdrv(wblock->dev.dev.driver);
 		struct acpi_object_list input;
 		union acpi_object params[1];
 		struct acpi_buffer evdata = { ACPI_ALLOCATE_BUFFER, NULL };
 		acpi_status status;
 
-		driver = container_of(wblock->dev.dev.driver,
-				      struct wmi_driver, driver);
-
 		input.count = 1;
 		input.pointer = params;
 		params[0].type = ACPI_TYPE_INTEGER;
diff --git a/drivers/power/reset/arm-versatile-reboot.c b/drivers/power/reset/arm-versatile-reboot.c
index 08d0a07b58ef..c7624d7611a7 100644
--- a/drivers/power/reset/arm-versatile-reboot.c
+++ b/drivers/power/reset/arm-versatile-reboot.c
@@ -146,6 +146,7 @@ static int __init versatile_reboot_probe(void)
 	versatile_reboot_type = (enum versatile_reboot)reboot_id->data;
 
 	syscon_regmap = syscon_node_to_regmap(np);
+	of_node_put(np);
 	if (IS_ERR(syscon_regmap))
 		return PTR_ERR(syscon_regmap);
 
diff --git a/drivers/pwm/pwm-lpc18xx-sct.c b/drivers/pwm/pwm-lpc18xx-sct.c
index 8cc8ae16553c..43b5509dde51 100644
--- a/drivers/pwm/pwm-lpc18xx-sct.c
+++ b/drivers/pwm/pwm-lpc18xx-sct.c
@@ -76,6 +76,8 @@
 #define LPC18XX_PWM_EVENT_PERIOD	0
 #define LPC18XX_PWM_EVENT_MAX		16
 
+#define LPC18XX_NUM_PWMS		16
+
 /* SCT conflict resolution */
 enum lpc18xx_pwm_res_action {
 	LPC18XX_PWM_RES_NONE,
@@ -96,11 +98,12 @@ struct lpc18xx_pwm_chip {
 	unsigned long clk_rate;
 	unsigned int period_ns;
 	unsigned int min_period_ns;
-	unsigned int max_period_ns;
+	u64 max_period_ns;
 	unsigned int period_event;
 	unsigned long event_map;
 	struct mutex res_lock;
 	struct mutex period_lock;
+	struct lpc18xx_pwm_data channeldata[LPC18XX_NUM_PWMS];
 };
 
 static inline struct lpc18xx_pwm_chip *
@@ -142,40 +145,48 @@ static void lpc18xx_pwm_set_conflict_res(struct lpc18xx_pwm_chip *lpc18xx_pwm,
 	mutex_unlock(&lpc18xx_pwm->res_lock);
 }
 
-static void lpc18xx_pwm_config_period(struct pwm_chip *chip, int period_ns)
+static void lpc18xx_pwm_config_period(struct pwm_chip *chip, u64 period_ns)
 {
 	struct lpc18xx_pwm_chip *lpc18xx_pwm = to_lpc18xx_pwm_chip(chip);
-	u64 val;
+	u32 val;
 
-	val = (u64)period_ns * lpc18xx_pwm->clk_rate;
-	do_div(val, NSEC_PER_SEC);
+	/*
+	 * With clk_rate < NSEC_PER_SEC this cannot overflow.
+	 * With period_ns < max_period_ns this also fits into an u32.
+	 * As period_ns >= min_period_ns = DIV_ROUND_UP(NSEC_PER_SEC, lpc18xx_pwm->clk_rate);
+	 * we have val >= 1.
+	 */
+	val = mul_u64_u64_div_u64(period_ns, lpc18xx_pwm->clk_rate, NSEC_PER_SEC);
 
 	lpc18xx_pwm_writel(lpc18xx_pwm,
 			   LPC18XX_PWM_MATCH(lpc18xx_pwm->period_event),
-			   (u32)val - 1);
+			   val - 1);
 
 	lpc18xx_pwm_writel(lpc18xx_pwm,
 			   LPC18XX_PWM_MATCHREL(lpc18xx_pwm->period_event),
-			   (u32)val - 1);
+			   val - 1);
 }
 
 static void lpc18xx_pwm_config_duty(struct pwm_chip *chip,
-				    struct pwm_device *pwm, int duty_ns)
+				    struct pwm_device *pwm, u64 duty_ns)
 {
 	struct lpc18xx_pwm_chip *lpc18xx_pwm = to_lpc18xx_pwm_chip(chip);
-	struct lpc18xx_pwm_data *lpc18xx_data = pwm_get_chip_data(pwm);
-	u64 val;
+	struct lpc18xx_pwm_data *lpc18xx_data = &lpc18xx_pwm->channeldata[pwm->hwpwm];
+	u32 val;
 
-	val = (u64)duty_ns * lpc18xx_pwm->clk_rate;
-	do_div(val, NSEC_PER_SEC);
+	/*
+	 * With clk_rate < NSEC_PER_SEC this cannot overflow.
+	 * With duty_ns <= period_ns < max_period_ns this also fits into an u32.
+	 */
+	val = mul_u64_u64_div_u64(duty_ns, lpc18xx_pwm->clk_rate, NSEC_PER_SEC);
 
 	lpc18xx_pwm_writel(lpc18xx_pwm,
 			   LPC18XX_PWM_MATCH(lpc18xx_data->duty_event),
-			   (u32)val);
+			   val);
 
 	lpc18xx_pwm_writel(lpc18xx_pwm,
 			   LPC18XX_PWM_MATCHREL(lpc18xx_data->duty_event),
-			   (u32)val);
+			   val);
 }
 
 static int lpc18xx_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
@@ -233,7 +244,7 @@ static int lpc18xx_pwm_set_polarity(struct pwm_chip *chip,
 static int lpc18xx_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm)
 {
 	struct lpc18xx_pwm_chip *lpc18xx_pwm = to_lpc18xx_pwm_chip(chip);
-	struct lpc18xx_pwm_data *lpc18xx_data = pwm_get_chip_data(pwm);
+	struct lpc18xx_pwm_data *lpc18xx_data = &lpc18xx_pwm->channeldata[pwm->hwpwm];
 	enum lpc18xx_pwm_res_action res_action;
 	unsigned int set_event, clear_event;
 
@@ -268,7 +279,7 @@ static int lpc18xx_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm)
 static void lpc18xx_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm)
 {
 	struct lpc18xx_pwm_chip *lpc18xx_pwm = to_lpc18xx_pwm_chip(chip);
-	struct lpc18xx_pwm_data *lpc18xx_data = pwm_get_chip_data(pwm);
+	struct lpc18xx_pwm_data *lpc18xx_data = &lpc18xx_pwm->channeldata[pwm->hwpwm];
 
 	lpc18xx_pwm_writel(lpc18xx_pwm,
 			   LPC18XX_PWM_EVCTRL(lpc18xx_data->duty_event), 0);
@@ -279,7 +290,7 @@ static void lpc18xx_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm)
 static int lpc18xx_pwm_request(struct pwm_chip *chip, struct pwm_device *pwm)
 {
 	struct lpc18xx_pwm_chip *lpc18xx_pwm = to_lpc18xx_pwm_chip(chip);
-	struct lpc18xx_pwm_data *lpc18xx_data = pwm_get_chip_data(pwm);
+	struct lpc18xx_pwm_data *lpc18xx_data = &lpc18xx_pwm->channeldata[pwm->hwpwm];
 	unsigned long event;
 
 	event = find_first_zero_bit(&lpc18xx_pwm->event_map,
@@ -300,7 +311,7 @@ static int lpc18xx_pwm_request(struct pwm_chip *chip, struct pwm_device *pwm)
 static void lpc18xx_pwm_free(struct pwm_chip *chip, struct pwm_device *pwm)
 {
 	struct lpc18xx_pwm_chip *lpc18xx_pwm = to_lpc18xx_pwm_chip(chip);
-	struct lpc18xx_pwm_data *lpc18xx_data = pwm_get_chip_data(pwm);
+	struct lpc18xx_pwm_data *lpc18xx_data = &lpc18xx_pwm->channeldata[pwm->hwpwm];
 
 	clear_bit(lpc18xx_data->duty_event, &lpc18xx_pwm->event_map);
 }
@@ -324,8 +335,7 @@ MODULE_DEVICE_TABLE(of, lpc18xx_pwm_of_match);
 static int lpc18xx_pwm_probe(struct platform_device *pdev)
 {
 	struct lpc18xx_pwm_chip *lpc18xx_pwm;
-	struct pwm_device *pwm;
-	int ret, i;
+	int ret;
 	u64 val;
 
 	lpc18xx_pwm = devm_kzalloc(&pdev->dev, sizeof(*lpc18xx_pwm),
@@ -358,19 +368,34 @@ static int lpc18xx_pwm_probe(struct platform_device *pdev)
 		goto disable_pwmclk;
 	}
 
+	/*
+	 * If clkrate is too fast, the calculations in .apply() might overflow.
+	 */
+	if (lpc18xx_pwm->clk_rate > NSEC_PER_SEC) {
+		ret = dev_err_probe(&pdev->dev, -EINVAL, "pwm clock to fast\n");
+		goto disable_pwmclk;
+	}
+
+	/*
+	 * If clkrate is too fast, the calculations in .apply() might overflow.
+	 */
+	if (lpc18xx_pwm->clk_rate > NSEC_PER_SEC) {
+		ret = dev_err_probe(&pdev->dev, -EINVAL, "pwm clock to fast\n");
+		goto disable_pwmclk;
+	}
+
 	mutex_init(&lpc18xx_pwm->res_lock);
 	mutex_init(&lpc18xx_pwm->period_lock);
 
-	val = (u64)NSEC_PER_SEC * LPC18XX_PWM_TIMER_MAX;
-	do_div(val, lpc18xx_pwm->clk_rate);
-	lpc18xx_pwm->max_period_ns = val;
+	lpc18xx_pwm->max_period_ns =
+		mul_u64_u64_div_u64(NSEC_PER_SEC, LPC18XX_PWM_TIMER_MAX, lpc18xx_pwm->clk_rate);
 
 	lpc18xx_pwm->min_period_ns = DIV_ROUND_UP(NSEC_PER_SEC,
 						  lpc18xx_pwm->clk_rate);
 
 	lpc18xx_pwm->chip.dev = &pdev->dev;
 	lpc18xx_pwm->chip.ops = &lpc18xx_pwm_ops;
-	lpc18xx_pwm->chip.npwm = 16;
+	lpc18xx_pwm->chip.npwm = LPC18XX_NUM_PWMS;
 
 	/* SCT counter must be in unify (32 bit) mode */
 	lpc18xx_pwm_writel(lpc18xx_pwm, LPC18XX_PWM_CONFIG,
@@ -395,21 +420,6 @@ static int lpc18xx_pwm_probe(struct platform_device *pdev)
 	lpc18xx_pwm_writel(lpc18xx_pwm, LPC18XX_PWM_LIMIT,
 			   BIT(lpc18xx_pwm->period_event));
 
-	for (i = 0; i < lpc18xx_pwm->chip.npwm; i++) {
-		struct lpc18xx_pwm_data *data;
-
-		pwm = &lpc18xx_pwm->chip.pwms[i];
-
-		data = devm_kzalloc(lpc18xx_pwm->dev, sizeof(*data),
-				    GFP_KERNEL);
-		if (!data) {
-			ret = -ENOMEM;
-			goto disable_pwmclk;
-		}
-
-		pwm_set_chip_data(pwm, data);
-	}
-
 	val = lpc18xx_pwm_readl(lpc18xx_pwm, LPC18XX_PWM_CTRL);
 	val &= ~LPC18XX_PWM_BIDIR;
 	val &= ~LPC18XX_PWM_CTRL_HALT;
diff --git a/drivers/pwm/pwm-sifive.c b/drivers/pwm/pwm-sifive.c
index 253c4a17d255..58347fcd4812 100644
--- a/drivers/pwm/pwm-sifive.c
+++ b/drivers/pwm/pwm-sifive.c
@@ -23,7 +23,7 @@
 #define PWM_SIFIVE_PWMCFG		0x0
 #define PWM_SIFIVE_PWMCOUNT		0x8
 #define PWM_SIFIVE_PWMS			0x10
-#define PWM_SIFIVE_PWMCMP0		0x20
+#define PWM_SIFIVE_PWMCMP(i)		(0x20 + 4 * (i))
 
 /* PWMCFG fields */
 #define PWM_SIFIVE_PWMCFG_SCALE		GENMASK(3, 0)
@@ -36,8 +36,6 @@
 #define PWM_SIFIVE_PWMCFG_GANG		BIT(24)
 #define PWM_SIFIVE_PWMCFG_IP		BIT(28)
 
-/* PWM_SIFIVE_SIZE_PWMCMP is used to calculate offset for pwmcmpX registers */
-#define PWM_SIFIVE_SIZE_PWMCMP		4
 #define PWM_SIFIVE_CMPWIDTH		16
 #define PWM_SIFIVE_DEFAULT_PERIOD	10000000
 
@@ -112,8 +110,7 @@ static void pwm_sifive_get_state(struct pwm_chip *chip, struct pwm_device *pwm,
 	struct pwm_sifive_ddata *ddata = pwm_sifive_chip_to_ddata(chip);
 	u32 duty, val;
 
-	duty = readl(ddata->regs + PWM_SIFIVE_PWMCMP0 +
-		     pwm->hwpwm * PWM_SIFIVE_SIZE_PWMCMP);
+	duty = readl(ddata->regs + PWM_SIFIVE_PWMCMP(pwm->hwpwm));
 
 	state->enabled = duty > 0;
 
@@ -194,8 +191,7 @@ static int pwm_sifive_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 		pwm_sifive_update_clock(ddata, clk_get_rate(ddata->clk));
 	}
 
-	writel(frac, ddata->regs + PWM_SIFIVE_PWMCMP0 +
-	       pwm->hwpwm * PWM_SIFIVE_SIZE_PWMCMP);
+	writel(frac, ddata->regs + PWM_SIFIVE_PWMCMP(pwm->hwpwm));
 
 	if (state->enabled != enabled)
 		pwm_sifive_enable(chip, state->enabled);
@@ -233,6 +229,8 @@ static int pwm_sifive_probe(struct platform_device *pdev)
 	struct pwm_sifive_ddata *ddata;
 	struct pwm_chip *chip;
 	int ret;
+	u32 val;
+	unsigned int enabled_pwms = 0, enabled_clks = 1;
 
 	ddata = devm_kzalloc(dev, sizeof(*ddata), GFP_KERNEL);
 	if (!ddata)
@@ -259,6 +257,33 @@ static int pwm_sifive_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	val = readl(ddata->regs + PWM_SIFIVE_PWMCFG);
+	if (val & PWM_SIFIVE_PWMCFG_EN_ALWAYS) {
+		unsigned int i;
+
+		for (i = 0; i < chip->npwm; ++i) {
+			val = readl(ddata->regs + PWM_SIFIVE_PWMCMP(i));
+			if (val > 0)
+				++enabled_pwms;
+		}
+	}
+
+	/* The clk should be on once for each running PWM. */
+	if (enabled_pwms) {
+		while (enabled_clks < enabled_pwms) {
+			/* This is not expected to fail as the clk is already on */
+			ret = clk_enable(ddata->clk);
+			if (unlikely(ret)) {
+				dev_err_probe(dev, ret, "Failed to enable clk\n");
+				goto disable_clk;
+			}
+			++enabled_clks;
+		}
+	} else {
+		clk_disable(ddata->clk);
+		enabled_clks = 0;
+	}
+
 	/* Watch for changes to underlying clock frequency */
 	ddata->notifier.notifier_call = pwm_sifive_clock_notifier;
 	ret = clk_notifier_register(ddata->clk, &ddata->notifier);
@@ -281,7 +306,11 @@ static int pwm_sifive_probe(struct platform_device *pdev)
 unregister_clk:
 	clk_notifier_unregister(ddata->clk, &ddata->notifier);
 disable_clk:
-	clk_disable_unprepare(ddata->clk);
+	while (enabled_clks) {
+		clk_disable(ddata->clk);
+		--enabled_clks;
+	}
+	clk_unprepare(ddata->clk);
 
 	return ret;
 }
@@ -289,23 +318,19 @@ disable_clk:
 static int pwm_sifive_remove(struct platform_device *dev)
 {
 	struct pwm_sifive_ddata *ddata = platform_get_drvdata(dev);
-	bool is_enabled = false;
 	struct pwm_device *pwm;
 	int ch;
 
+	pwmchip_remove(&ddata->chip);
+	clk_notifier_unregister(ddata->clk, &ddata->notifier);
+
 	for (ch = 0; ch < ddata->chip.npwm; ch++) {
 		pwm = &ddata->chip.pwms[ch];
-		if (pwm->state.enabled) {
-			is_enabled = true;
-			break;
-		}
+		if (pwm->state.enabled)
+			clk_disable(ddata->clk);
 	}
-	if (is_enabled)
-		clk_disable(ddata->clk);
 
-	clk_disable_unprepare(ddata->clk);
-	pwmchip_remove(&ddata->chip);
-	clk_notifier_unregister(ddata->clk, &ddata->notifier);
+	clk_unprepare(ddata->clk);
 
 	return 0;
 }
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 4d302bca4e0e..bc4c77a32643 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -2688,13 +2688,18 @@ static int _regulator_do_enable(struct regulator_dev *rdev)
  */
 static int _regulator_handle_consumer_enable(struct regulator *regulator)
 {
+	int ret;
 	struct regulator_dev *rdev = regulator->rdev;
 
 	lockdep_assert_held_once(&rdev->mutex.base);
 
 	regulator->enable_count++;
-	if (regulator->uA_load && regulator->enable_count == 1)
-		return drms_uA_update(rdev);
+	if (regulator->uA_load && regulator->enable_count == 1) {
+		ret = drms_uA_update(rdev);
+		if (ret)
+			regulator->enable_count--;
+		return ret;
+	}
 
 	return 0;
 }
diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c
index f54d4f176882..e12b681c72e5 100644
--- a/drivers/regulator/of_regulator.c
+++ b/drivers/regulator/of_regulator.c
@@ -264,8 +264,12 @@ static int of_get_regulation_constraints(struct device *dev,
 		}
 
 		suspend_np = of_get_child_by_name(np, regulator_states[i]);
-		if (!suspend_np || !suspend_state)
+		if (!suspend_np)
 			continue;
+		if (!suspend_state) {
+			of_node_put(suspend_np);
+			continue;
+		}
 
 		if (!of_property_read_u32(suspend_np, "regulator-mode",
 					  &pval)) {
diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c
index 5286dd043a4b..f21788f6d17d 100644
--- a/drivers/regulator/pfuze100-regulator.c
+++ b/drivers/regulator/pfuze100-regulator.c
@@ -774,7 +774,7 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 		((pfuze_chip->chip_id == PFUZE3000) ? "3000" : "3001"))));
 
 	memcpy(pfuze_chip->regulator_descs, pfuze_chip->pfuze_regulators,
-		sizeof(pfuze_chip->regulator_descs));
+		regulator_num * sizeof(struct pfuze_regulator));
 
 	ret = pfuze_parse_regulators_dt(pfuze_chip);
 	if (ret)
diff --git a/drivers/regulator/qcom_smd-regulator.c b/drivers/regulator/qcom_smd-regulator.c
index eb974b9c0b19..2fe13c765eff 100644
--- a/drivers/regulator/qcom_smd-regulator.c
+++ b/drivers/regulator/qcom_smd-regulator.c
@@ -357,10 +357,10 @@ static const struct regulator_desc pm8941_switch = {
 
 static const struct regulator_desc pm8916_pldo = {
 	.linear_ranges = (struct linear_range[]) {
-		REGULATOR_LINEAR_RANGE(750000, 0, 208, 12500),
+		REGULATOR_LINEAR_RANGE(1750000, 0, 127, 12500),
 	},
 	.n_linear_ranges = 1,
-	.n_voltages = 209,
+	.n_voltages = 128,
 	.ops = &rpm_smps_ldo_ops,
 };
 
diff --git a/drivers/remoteproc/imx_rproc.c b/drivers/remoteproc/imx_rproc.c
index 109990f21902..74e18c64a732 100644
--- a/drivers/remoteproc/imx_rproc.c
+++ b/drivers/remoteproc/imx_rproc.c
@@ -885,16 +885,17 @@ static int imx_rproc_addr_init(struct imx_rproc *priv,
 
 		node = of_parse_phandle(np, "memory-region", a);
 		/* Not map vdevbuffer, vdevring region */
-		if (!strncmp(node->name, "vdev", strlen("vdev")))
+		if (!strncmp(node->name, "vdev", strlen("vdev"))) {
+			of_node_put(node);
 			continue;
+		}
 		err = of_address_to_resource(node, 0, &res);
+		of_node_put(node);
 		if (err) {
 			dev_err(dev, "unable to resolve memory region\n");
 			return err;
 		}
 
-		of_node_put(node);
-
 		if (b >= IMX_RPROC_MEM_MAX)
 			break;
 
diff --git a/drivers/remoteproc/qcom_q6v5_pas.c b/drivers/remoteproc/qcom_q6v5_pas.c
index 699eaac5b760..78d90d856e40 100644
--- a/drivers/remoteproc/qcom_q6v5_pas.c
+++ b/drivers/remoteproc/qcom_q6v5_pas.c
@@ -87,6 +87,9 @@ static void adsp_minidump(struct rproc *rproc)
 {
 	struct qcom_adsp *adsp = rproc->priv;
 
+	if (rproc->dump_conf == RPROC_COREDUMP_DISABLED)
+		return;
+
 	qcom_minidump(rproc, adsp->minidump_id);
 }
 
diff --git a/drivers/remoteproc/qcom_sysmon.c b/drivers/remoteproc/qcom_sysmon.c
index 9fca81492863..a9f04dd83ab6 100644
--- a/drivers/remoteproc/qcom_sysmon.c
+++ b/drivers/remoteproc/qcom_sysmon.c
@@ -41,6 +41,7 @@ struct qcom_sysmon {
 	struct completion comp;
 	struct completion ind_comp;
 	struct completion shutdown_comp;
+	struct completion ssctl_comp;
 	struct mutex lock;
 
 	bool ssr_ack;
@@ -445,6 +446,8 @@ static int ssctl_new_server(struct qmi_handle *qmi, struct qmi_service *svc)
 
 	svc->priv = sysmon;
 
+	complete(&sysmon->ssctl_comp);
+
 	return 0;
 }
 
@@ -501,6 +504,7 @@ static int sysmon_start(struct rproc_subdev *subdev)
 		.ssr_event = SSCTL_SSR_EVENT_AFTER_POWERUP
 	};
 
+	reinit_completion(&sysmon->ssctl_comp);
 	mutex_lock(&sysmon->state_lock);
 	sysmon->state = SSCTL_SSR_EVENT_AFTER_POWERUP;
 	blocking_notifier_call_chain(&sysmon_notifiers, 0, (void *)&event);
@@ -545,6 +549,11 @@ static void sysmon_stop(struct rproc_subdev *subdev, bool crashed)
 	if (crashed)
 		return;
 
+	if (sysmon->ssctl_instance) {
+		if (!wait_for_completion_timeout(&sysmon->ssctl_comp, HZ / 2))
+			dev_err(sysmon->dev, "timeout waiting for ssctl service\n");
+	}
+
 	if (sysmon->ssctl_version)
 		sysmon->shutdown_acked = ssctl_request_shutdown(sysmon);
 	else if (sysmon->ept)
@@ -631,6 +640,7 @@ struct qcom_sysmon *qcom_add_sysmon_subdev(struct rproc *rproc,
 	init_completion(&sysmon->comp);
 	init_completion(&sysmon->ind_comp);
 	init_completion(&sysmon->shutdown_comp);
+	init_completion(&sysmon->ssctl_comp);
 	mutex_init(&sysmon->lock);
 	mutex_init(&sysmon->state_lock);
 
diff --git a/drivers/remoteproc/qcom_wcnss.c b/drivers/remoteproc/qcom_wcnss.c
index b17742eac9ff..97a0c0dc4c77 100644
--- a/drivers/remoteproc/qcom_wcnss.c
+++ b/drivers/remoteproc/qcom_wcnss.c
@@ -468,6 +468,7 @@ static int wcnss_request_irq(struct qcom_wcnss *wcnss,
 			     irq_handler_t thread_fn)
 {
 	int ret;
+	int irq_number;
 
 	ret = platform_get_irq_byname(pdev, name);
 	if (ret < 0 && optional) {
@@ -478,14 +479,19 @@ static int wcnss_request_irq(struct qcom_wcnss *wcnss,
 		return ret;
 	}
 
+	irq_number = ret;
+
 	ret = devm_request_threaded_irq(&pdev->dev, ret,
 					NULL, thread_fn,
 					IRQF_TRIGGER_RISING | IRQF_ONESHOT,
 					"wcnss", wcnss);
-	if (ret)
+	if (ret) {
 		dev_err(&pdev->dev, "request %s IRQ failed\n", name);
+		return ret;
+	}
 
-	return ret;
+	/* Return the IRQ number if the IRQ was successfully acquired */
+	return irq_number;
 }
 
 static int wcnss_alloc_memory_region(struct qcom_wcnss *wcnss)
diff --git a/drivers/remoteproc/ti_k3_r5_remoteproc.c b/drivers/remoteproc/ti_k3_r5_remoteproc.c
index 71615210df3e..54266ea69c84 100644
--- a/drivers/remoteproc/ti_k3_r5_remoteproc.c
+++ b/drivers/remoteproc/ti_k3_r5_remoteproc.c
@@ -1430,6 +1430,7 @@ static int k3_r5_cluster_of_init(struct platform_device *pdev)
 		if (!cpdev) {
 			ret = -ENODEV;
 			dev_err(dev, "could not get R5 core platform device\n");
+			of_node_put(child);
 			goto fail;
 		}
 
@@ -1438,6 +1439,7 @@ static int k3_r5_cluster_of_init(struct platform_device *pdev)
 			dev_err(dev, "k3_r5_core_of_init failed, ret = %d\n",
 				ret);
 			put_device(&cpdev->dev);
+			of_node_put(child);
 			goto fail;
 		}
 
diff --git a/drivers/rpmsg/mtk_rpmsg.c b/drivers/rpmsg/mtk_rpmsg.c
index 96a17ec29140..2d8cb596ad69 100644
--- a/drivers/rpmsg/mtk_rpmsg.c
+++ b/drivers/rpmsg/mtk_rpmsg.c
@@ -234,7 +234,9 @@ static void mtk_register_device_work_function(struct work_struct *register_work)
 		if (info->registered)
 			continue;
 
+		mutex_unlock(&subdev->channels_lock);
 		ret = mtk_rpmsg_register_device(subdev, &info->info);
+		mutex_lock(&subdev->channels_lock);
 		if (ret) {
 			dev_err(&pdev->dev, "Can't create rpmsg_device\n");
 			continue;
diff --git a/drivers/rpmsg/qcom_smd.c b/drivers/rpmsg/qcom_smd.c
index d9ed37de681a..b2cd71c350ee 100644
--- a/drivers/rpmsg/qcom_smd.c
+++ b/drivers/rpmsg/qcom_smd.c
@@ -1380,6 +1380,7 @@ static int qcom_smd_parse_edge(struct device *dev,
 		}
 
 		edge->ipc_regmap = syscon_node_to_regmap(syscon_np);
+		of_node_put(syscon_np);
 		if (IS_ERR(edge->ipc_regmap)) {
 			ret = PTR_ERR(edge->ipc_regmap);
 			goto put_node;
diff --git a/drivers/rtc/rtc-rx8025.c b/drivers/rtc/rtc-rx8025.c
index d38aaf08108c..dc9221393080 100644
--- a/drivers/rtc/rtc-rx8025.c
+++ b/drivers/rtc/rtc-rx8025.c
@@ -55,6 +55,8 @@
 #define RX8025_BIT_CTRL2_XST	BIT(5)
 #define RX8025_BIT_CTRL2_VDET	BIT(6)
 
+#define RX8035_BIT_HOUR_1224	BIT(7)
+
 /* Clock precision adjustment */
 #define RX8025_ADJ_RESOLUTION	3050 /* in ppb */
 #define RX8025_ADJ_DATA_MAX	62
@@ -78,6 +80,7 @@ struct rx8025_data {
 	struct rtc_device *rtc;
 	enum rx_model model;
 	u8 ctrl1;
+	int is_24;
 };
 
 static s32 rx8025_read_reg(const struct i2c_client *client, u8 number)
@@ -226,7 +229,7 @@ static int rx8025_get_time(struct device *dev, struct rtc_time *dt)
 
 	dt->tm_sec = bcd2bin(date[RX8025_REG_SEC] & 0x7f);
 	dt->tm_min = bcd2bin(date[RX8025_REG_MIN] & 0x7f);
-	if (rx8025->ctrl1 & RX8025_BIT_CTRL1_1224)
+	if (rx8025->is_24)
 		dt->tm_hour = bcd2bin(date[RX8025_REG_HOUR] & 0x3f);
 	else
 		dt->tm_hour = bcd2bin(date[RX8025_REG_HOUR] & 0x1f) % 12
@@ -257,7 +260,7 @@ static int rx8025_set_time(struct device *dev, struct rtc_time *dt)
 	 */
 	date[RX8025_REG_SEC] = bin2bcd(dt->tm_sec);
 	date[RX8025_REG_MIN] = bin2bcd(dt->tm_min);
-	if (rx8025->ctrl1 & RX8025_BIT_CTRL1_1224)
+	if (rx8025->is_24)
 		date[RX8025_REG_HOUR] = bin2bcd(dt->tm_hour);
 	else
 		date[RX8025_REG_HOUR] = (dt->tm_hour >= 12 ? 0x20 : 0)
@@ -282,6 +285,7 @@ static int rx8025_init_client(struct i2c_client *client)
 	struct rx8025_data *rx8025 = i2c_get_clientdata(client);
 	u8 ctrl[2], ctrl2;
 	int need_clear = 0;
+	int hour_reg;
 	int err;
 
 	err = rx8025_read_regs(client, RX8025_REG_CTRL1, 2, ctrl);
@@ -306,6 +310,16 @@ static int rx8025_init_client(struct i2c_client *client)
 
 		err = rx8025_write_reg(client, RX8025_REG_CTRL2, ctrl2);
 	}
+
+	if (rx8025->model == model_rx_8035) {
+		/* In RX-8035, 12/24 flag is in the hour register */
+		hour_reg = rx8025_read_reg(client, RX8025_REG_HOUR);
+		if (hour_reg < 0)
+			return hour_reg;
+		rx8025->is_24 = (hour_reg & RX8035_BIT_HOUR_1224);
+	} else {
+		rx8025->is_24 = (ctrl[1] & RX8025_BIT_CTRL1_1224);
+	}
 out:
 	return err;
 }
@@ -335,7 +349,7 @@ static int rx8025_read_alarm(struct device *dev, struct rtc_wkalrm *t)
 	/* Hardware alarms precision is 1 minute! */
 	t->time.tm_sec = 0;
 	t->time.tm_min = bcd2bin(ald[0] & 0x7f);
-	if (rx8025->ctrl1 & RX8025_BIT_CTRL1_1224)
+	if (rx8025->is_24)
 		t->time.tm_hour = bcd2bin(ald[1] & 0x3f);
 	else
 		t->time.tm_hour = bcd2bin(ald[1] & 0x1f) % 12
@@ -370,7 +384,7 @@ static int rx8025_set_alarm(struct device *dev, struct rtc_wkalrm *t)
 	}
 
 	ald[0] = bin2bcd(t->time.tm_min);
-	if (rx8025->ctrl1 & RX8025_BIT_CTRL1_1224)
+	if (rx8025->is_24)
 		ald[1] = bin2bcd(t->time.tm_hour);
 	else
 		ald[1] = (t->time.tm_hour >= 12 ? 0x20 : 0)
diff --git a/drivers/s390/char/keyboard.h b/drivers/s390/char/keyboard.h
index c467589c7f45..c06d399b9b1f 100644
--- a/drivers/s390/char/keyboard.h
+++ b/drivers/s390/char/keyboard.h
@@ -56,7 +56,7 @@ static inline void
 kbd_put_queue(struct tty_port *port, int ch)
 {
 	tty_insert_flip_char(port, ch, 0);
-	tty_schedule_flip(port);
+	tty_flip_buffer_push(port);
 }
 
 static inline void
@@ -64,5 +64,5 @@ kbd_puts_queue(struct tty_port *port, char *cp)
 {
 	while (*cp)
 		tty_insert_flip_char(port, *cp++, 0);
-	tty_schedule_flip(port);
+	tty_flip_buffer_push(port);
 }
diff --git a/drivers/s390/char/zcore.c b/drivers/s390/char/zcore.c
index 3ba2d934a3e8..92b32ce645b9 100644
--- a/drivers/s390/char/zcore.c
+++ b/drivers/s390/char/zcore.c
@@ -50,6 +50,7 @@ static struct dentry *zcore_reipl_file;
 static struct dentry *zcore_hsa_file;
 static struct ipl_parameter_block *zcore_ipl_block;
 
+static DEFINE_MUTEX(hsa_buf_mutex);
 static char hsa_buf[PAGE_SIZE] __aligned(PAGE_SIZE);
 
 /*
@@ -66,19 +67,24 @@ int memcpy_hsa_user(void __user *dest, unsigned long src, size_t count)
 	if (!hsa_available)
 		return -ENODATA;
 
+	mutex_lock(&hsa_buf_mutex);
 	while (count) {
 		if (sclp_sdias_copy(hsa_buf, src / PAGE_SIZE + 2, 1)) {
 			TRACE("sclp_sdias_copy() failed\n");
+			mutex_unlock(&hsa_buf_mutex);
 			return -EIO;
 		}
 		offset = src % PAGE_SIZE;
 		bytes = min(PAGE_SIZE - offset, count);
-		if (copy_to_user(dest, hsa_buf + offset, bytes))
+		if (copy_to_user(dest, hsa_buf + offset, bytes)) {
+			mutex_unlock(&hsa_buf_mutex);
 			return -EFAULT;
+		}
 		src += bytes;
 		dest += bytes;
 		count -= bytes;
 	}
+	mutex_unlock(&hsa_buf_mutex);
 	return 0;
 }
 
@@ -96,9 +102,11 @@ int memcpy_hsa_kernel(void *dest, unsigned long src, size_t count)
 	if (!hsa_available)
 		return -ENODATA;
 
+	mutex_lock(&hsa_buf_mutex);
 	while (count) {
 		if (sclp_sdias_copy(hsa_buf, src / PAGE_SIZE + 2, 1)) {
 			TRACE("sclp_sdias_copy() failed\n");
+			mutex_unlock(&hsa_buf_mutex);
 			return -EIO;
 		}
 		offset = src % PAGE_SIZE;
@@ -108,6 +116,7 @@ int memcpy_hsa_kernel(void *dest, unsigned long src, size_t count)
 		dest += bytes;
 		count -= bytes;
 	}
+	mutex_unlock(&hsa_buf_mutex);
 	return 0;
 }
 
@@ -229,8 +238,7 @@ static int __init zcore_reipl_init(void)
 		rc = memcpy_hsa_kernel(zcore_ipl_block, ipib_info.ipib,
 				       PAGE_SIZE);
 	else
-		rc = memcpy_real(zcore_ipl_block, (void *) ipib_info.ipib,
-				 PAGE_SIZE);
+		rc = memcpy_real(zcore_ipl_block, ipib_info.ipib, PAGE_SIZE);
 	if (rc || (__force u32)csum_partial(zcore_ipl_block, zcore_ipl_block->hdr.len, 0) !=
 	    ipib_info.checksum) {
 		TRACE("Checksum does not match\n");
diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
index 76099bcb765b..b9091e22ca57 100644
--- a/drivers/s390/cio/vfio_ccw_drv.c
+++ b/drivers/s390/cio/vfio_ccw_drv.c
@@ -287,19 +287,11 @@ static int vfio_ccw_sch_event(struct subchannel *sch, int process)
 	if (work_pending(&sch->todo_work))
 		goto out_unlock;
 
-	if (cio_update_schib(sch)) {
-		vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_NOT_OPER);
-		rc = 0;
-		goto out_unlock;
-	}
-
-	private = dev_get_drvdata(&sch->dev);
-	if (private->state == VFIO_CCW_STATE_NOT_OPER) {
-		private->state = private->mdev ? VFIO_CCW_STATE_IDLE :
-				 VFIO_CCW_STATE_STANDBY;
-	}
 	rc = 0;
 
+	if (cio_update_schib(sch))
+		vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_NOT_OPER);
+
 out_unlock:
 	spin_unlock_irqrestore(sch->lock, flags);
 
diff --git a/drivers/s390/scsi/zfcp_fc.c b/drivers/s390/scsi/zfcp_fc.c
index 511bf8e0a436..b61acbb09be3 100644
--- a/drivers/s390/scsi/zfcp_fc.c
+++ b/drivers/s390/scsi/zfcp_fc.c
@@ -145,27 +145,33 @@ void zfcp_fc_enqueue_event(struct zfcp_adapter *adapter,
 
 static int zfcp_fc_wka_port_get(struct zfcp_fc_wka_port *wka_port)
 {
+	int ret = -EIO;
+
 	if (mutex_lock_interruptible(&wka_port->mutex))
 		return -ERESTARTSYS;
 
 	if (wka_port->status == ZFCP_FC_WKA_PORT_OFFLINE ||
 	    wka_port->status == ZFCP_FC_WKA_PORT_CLOSING) {
 		wka_port->status = ZFCP_FC_WKA_PORT_OPENING;
-		if (zfcp_fsf_open_wka_port(wka_port))
+		if (zfcp_fsf_open_wka_port(wka_port)) {
+			/* could not even send request, nothing to wait for */
 			wka_port->status = ZFCP_FC_WKA_PORT_OFFLINE;
+			goto out;
+		}
 	}
 
-	mutex_unlock(&wka_port->mutex);
-
-	wait_event(wka_port->completion_wq,
+	wait_event(wka_port->opened,
 		   wka_port->status == ZFCP_FC_WKA_PORT_ONLINE ||
 		   wka_port->status == ZFCP_FC_WKA_PORT_OFFLINE);
 
 	if (wka_port->status == ZFCP_FC_WKA_PORT_ONLINE) {
 		atomic_inc(&wka_port->refcount);
-		return 0;
+		ret = 0;
+		goto out;
 	}
-	return -EIO;
+out:
+	mutex_unlock(&wka_port->mutex);
+	return ret;
 }
 
 static void zfcp_fc_wka_port_offline(struct work_struct *work)
@@ -181,9 +187,12 @@ static void zfcp_fc_wka_port_offline(struct work_struct *work)
 
 	wka_port->status = ZFCP_FC_WKA_PORT_CLOSING;
 	if (zfcp_fsf_close_wka_port(wka_port)) {
+		/* could not even send request, nothing to wait for */
 		wka_port->status = ZFCP_FC_WKA_PORT_OFFLINE;
-		wake_up(&wka_port->completion_wq);
+		goto out;
 	}
+	wait_event(wka_port->closed,
+		   wka_port->status == ZFCP_FC_WKA_PORT_OFFLINE);
 out:
 	mutex_unlock(&wka_port->mutex);
 }
@@ -193,13 +202,15 @@ static void zfcp_fc_wka_port_put(struct zfcp_fc_wka_port *wka_port)
 	if (atomic_dec_return(&wka_port->refcount) != 0)
 		return;
 	/* wait 10 milliseconds, other reqs might pop in */
-	schedule_delayed_work(&wka_port->work, HZ / 100);
+	queue_delayed_work(wka_port->adapter->work_queue, &wka_port->work,
+			   msecs_to_jiffies(10));
 }
 
 static void zfcp_fc_wka_port_init(struct zfcp_fc_wka_port *wka_port, u32 d_id,
 				  struct zfcp_adapter *adapter)
 {
-	init_waitqueue_head(&wka_port->completion_wq);
+	init_waitqueue_head(&wka_port->opened);
+	init_waitqueue_head(&wka_port->closed);
 
 	wka_port->adapter = adapter;
 	wka_port->d_id = d_id;
diff --git a/drivers/s390/scsi/zfcp_fc.h b/drivers/s390/scsi/zfcp_fc.h
index 8aaf409ce9cb..97755407ce1b 100644
--- a/drivers/s390/scsi/zfcp_fc.h
+++ b/drivers/s390/scsi/zfcp_fc.h
@@ -185,7 +185,8 @@ enum zfcp_fc_wka_status {
 /**
  * struct zfcp_fc_wka_port - representation of well-known-address (WKA) FC port
  * @adapter: Pointer to adapter structure this WKA port belongs to
- * @completion_wq: Wait for completion of open/close command
+ * @opened: Wait for completion of open command
+ * @closed: Wait for completion of close command
  * @status: Current status of WKA port
  * @refcount: Reference count to keep port open as long as it is in use
  * @d_id: FC destination id or well-known-address
@@ -195,7 +196,8 @@ enum zfcp_fc_wka_status {
  */
 struct zfcp_fc_wka_port {
 	struct zfcp_adapter	*adapter;
-	wait_queue_head_t	completion_wq;
+	wait_queue_head_t	opened;
+	wait_queue_head_t	closed;
 	enum zfcp_fc_wka_status	status;
 	atomic_t		refcount;
 	u32			d_id;
diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c
index c1f979296c1a..33b50b0990a0 100644
--- a/drivers/s390/scsi/zfcp_fsf.c
+++ b/drivers/s390/scsi/zfcp_fsf.c
@@ -1907,7 +1907,7 @@ static void zfcp_fsf_open_wka_port_handler(struct zfcp_fsf_req *req)
 		wka_port->status = ZFCP_FC_WKA_PORT_ONLINE;
 	}
 out:
-	wake_up(&wka_port->completion_wq);
+	wake_up(&wka_port->opened);
 }
 
 /**
@@ -1966,7 +1966,7 @@ static void zfcp_fsf_close_wka_port_handler(struct zfcp_fsf_req *req)
 	}
 
 	wka_port->status = ZFCP_FC_WKA_PORT_OFFLINE;
-	wake_up(&wka_port->completion_wq);
+	wake_up(&wka_port->closed);
 }
 
 /**
diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c
index e70f69f791db..7974c1326d46 100644
--- a/drivers/scsi/be2iscsi/be_main.c
+++ b/drivers/scsi/be2iscsi/be_main.c
@@ -5741,7 +5741,7 @@ static void beiscsi_remove(struct pci_dev *pcidev)
 	cancel_work_sync(&phba->sess_work);
 
 	beiscsi_iface_destroy_default(phba);
-	iscsi_host_remove(phba->shost);
+	iscsi_host_remove(phba->shost, false);
 	beiscsi_disable_port(phba, 1);
 
 	/* after cancelling boot_work */
diff --git a/drivers/scsi/bnx2i/bnx2i_iscsi.c b/drivers/scsi/bnx2i/bnx2i_iscsi.c
index 2e5241d12dc3..85b5aca4b497 100644
--- a/drivers/scsi/bnx2i/bnx2i_iscsi.c
+++ b/drivers/scsi/bnx2i/bnx2i_iscsi.c
@@ -909,7 +909,7 @@ void bnx2i_free_hba(struct bnx2i_hba *hba)
 {
 	struct Scsi_Host *shost = hba->shost;
 
-	iscsi_host_remove(shost);
+	iscsi_host_remove(shost, false);
 	INIT_LIST_HEAD(&hba->ep_ofld_list);
 	INIT_LIST_HEAD(&hba->ep_active_list);
 	INIT_LIST_HEAD(&hba->ep_destroy_list);
diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c
index 4365d52c6430..32abdf0fa9aa 100644
--- a/drivers/scsi/cxgbi/libcxgbi.c
+++ b/drivers/scsi/cxgbi/libcxgbi.c
@@ -328,7 +328,7 @@ void cxgbi_hbas_remove(struct cxgbi_device *cdev)
 		chba = cdev->hbas[i];
 		if (chba) {
 			cdev->hbas[i] = NULL;
-			iscsi_host_remove(chba->shost);
+			iscsi_host_remove(chba->shost, false);
 			pci_dev_put(cdev->pdev);
 			iscsi_host_free(chba->shost);
 		}
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 1f5e0688c0c8..fa22cb712be5 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -518,6 +518,8 @@ struct hisi_sas_err_record_v3 {
 #define CHNL_INT_STS_INT2_MSK BIT(3)
 #define CHNL_WIDTH 4
 
+#define BAR_NO_V3_HW	5
+
 enum {
 	DSM_FUNC_ERR_HANDLE_MSI = 0,
 };
@@ -2758,6 +2760,7 @@ static int slave_configure_v3_hw(struct scsi_device *sdev)
 	struct hisi_hba *hisi_hba = shost_priv(shost);
 	struct device *dev = hisi_hba->dev;
 	int ret = sas_slave_configure(sdev);
+	unsigned int max_sectors;
 
 	if (ret)
 		return ret;
@@ -2775,6 +2778,12 @@ static int slave_configure_v3_hw(struct scsi_device *sdev)
 		}
 	}
 
+	/* Set according to IOMMU IOVA caching limit */
+	max_sectors = min_t(size_t, queue_max_hw_sectors(sdev->request_queue),
+			    (PAGE_SIZE * 32) >> SECTOR_SHIFT);
+
+	blk_queue_max_hw_sectors(sdev->request_queue, max_sectors);
+
 	return 0;
 }
 
@@ -4733,15 +4742,15 @@ hisi_sas_v3_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	struct sas_ha_struct *sha;
 	int rc, phy_nr, port_nr, i;
 
-	rc = pci_enable_device(pdev);
+	rc = pcim_enable_device(pdev);
 	if (rc)
 		goto err_out;
 
 	pci_set_master(pdev);
 
-	rc = pci_request_regions(pdev, DRV_NAME);
+	rc = pcim_iomap_regions(pdev, 1 << BAR_NO_V3_HW, DRV_NAME);
 	if (rc)
-		goto err_out_disable_device;
+		goto err_out;
 
 	rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
 	if (rc)
@@ -4749,20 +4758,20 @@ hisi_sas_v3_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (rc) {
 		dev_err(dev, "No usable DMA addressing method\n");
 		rc = -ENODEV;
-		goto err_out_regions;
+		goto err_out;
 	}
 
 	shost = hisi_sas_shost_alloc_pci(pdev);
 	if (!shost) {
 		rc = -ENOMEM;
-		goto err_out_regions;
+		goto err_out;
 	}
 
 	sha = SHOST_TO_SAS_HA(shost);
 	hisi_hba = shost_priv(shost);
 	dev_set_drvdata(dev, sha);
 
-	hisi_hba->regs = pcim_iomap(pdev, 5, 0);
+	hisi_hba->regs = pcim_iomap_table(pdev)[BAR_NO_V3_HW];
 	if (!hisi_hba->regs) {
 		dev_err(dev, "cannot map register\n");
 		rc = -ENOMEM;
@@ -4854,10 +4863,6 @@ err_out_debugfs:
 err_out_ha:
 	hisi_sas_free(hisi_hba);
 	scsi_host_put(shost);
-err_out_regions:
-	pci_release_regions(pdev);
-err_out_disable_device:
-	pci_disable_device(pdev);
 err_out:
 	return rc;
 }
@@ -4894,8 +4899,6 @@ static void hisi_sas_v3_remove(struct pci_dev *pdev)
 	sas_remove_host(sha->core.shost);
 
 	hisi_sas_v3_destroy_irqs(pdev, hisi_hba);
-	pci_release_regions(pdev);
-	pci_disable_device(pdev);
 	hisi_sas_free(hisi_hba);
 	debugfs_exit_v3_hw(hisi_hba);
 	scsi_host_put(shost);
diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index 1bc37593c88f..0e52c6499eaf 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -898,7 +898,7 @@ iscsi_sw_tcp_session_create(struct iscsi_endpoint *ep, uint16_t cmds_max,
 remove_session:
 	iscsi_session_teardown(cls_session);
 remove_host:
-	iscsi_host_remove(shost);
+	iscsi_host_remove(shost, false);
 free_host:
 	iscsi_host_free(shost);
 	return NULL;
@@ -915,7 +915,7 @@ static void iscsi_sw_tcp_session_destroy(struct iscsi_cls_session *cls_session)
 	iscsi_tcp_r2tpool_free(cls_session->dd_data);
 	iscsi_session_teardown(cls_session);
 
-	iscsi_host_remove(shost);
+	iscsi_host_remove(shost, false);
 	iscsi_host_free(shost);
 }
 
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index 0f2c7098f9d6..78de36250b31 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -2830,11 +2830,12 @@ static void iscsi_notify_host_removed(struct iscsi_cls_session *cls_session)
 /**
  * iscsi_host_remove - remove host and sessions
  * @shost: scsi host
+ * @is_shutdown: true if called from a driver shutdown callout
  *
  * If there are any sessions left, this will initiate the removal and wait
  * for the completion.
  */
-void iscsi_host_remove(struct Scsi_Host *shost)
+void iscsi_host_remove(struct Scsi_Host *shost, bool is_shutdown)
 {
 	struct iscsi_host *ihost = shost_priv(shost);
 	unsigned long flags;
@@ -2843,7 +2844,11 @@ void iscsi_host_remove(struct Scsi_Host *shost)
 	ihost->state = ISCSI_HOST_REMOVED;
 	spin_unlock_irqrestore(&ihost->lock, flags);
 
-	iscsi_host_for_each_session(shost, iscsi_notify_host_removed);
+	if (!is_shutdown)
+		iscsi_host_for_each_session(shost, iscsi_notify_host_removed);
+	else
+		iscsi_host_for_each_session(shost, iscsi_force_destroy_session);
+
 	wait_event_interruptible(ihost->session_removal_wq,
 				 ihost->num_sessions == 0);
 	if (signal_pending(current))
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 1044832b6054..f3bcb56e9ef2 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -920,6 +920,10 @@ struct lpfc_hba {
 		(struct lpfc_vport *vport,
 		 struct lpfc_io_buf *lpfc_cmd,
 		 uint8_t tmo);
+	int (*lpfc_scsi_prep_task_mgmt_cmd)
+		(struct lpfc_vport *vport,
+		 struct lpfc_io_buf *lpfc_cmd,
+		 u64 lun, u8 task_mgmt_cmd);
 
 	/* IOCB interface function jump table entries */
 	int (*__lpfc_sli_issue_iocb)
@@ -1028,6 +1032,7 @@ struct lpfc_hba {
 					 * Firmware supports Forced Link Speed
 					 * capability
 					 */
+#define HBA_PCI_ERR		0x80000 /* The PCI slot is offline */
 #define HBA_FLOGI_ISSUED	0x100000 /* FLOGI was issued */
 #define HBA_CGN_RSVD1		0x200000 /* Reserved CGN flag */
 #define HBA_CGN_DAY_WRAP	0x400000 /* HBA Congestion info day wraps */
@@ -1802,3 +1807,39 @@ static inline int lpfc_is_vmid_enabled(struct lpfc_hba *phba)
 {
 	return phba->cfg_vmid_app_header || phba->cfg_vmid_priority_tagging;
 }
+
+static inline
+u8 get_job_ulpstatus(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq)
+{
+	if (phba->sli_rev == LPFC_SLI_REV4)
+		return bf_get(lpfc_wcqe_c_status, &iocbq->wcqe_cmpl);
+	else
+		return iocbq->iocb.ulpStatus;
+}
+
+static inline
+u32 get_job_word4(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq)
+{
+	if (phba->sli_rev == LPFC_SLI_REV4)
+		return iocbq->wcqe_cmpl.parameter;
+	else
+		return iocbq->iocb.un.ulpWord[4];
+}
+
+static inline
+u8 get_job_cmnd(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq)
+{
+	if (phba->sli_rev == LPFC_SLI_REV4)
+		return bf_get(wqe_cmnd, &iocbq->wqe.generic.wqe_com);
+	else
+		return iocbq->iocb.ulpCommand;
+}
+
+static inline
+u16 get_job_ulpcontext(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq)
+{
+	if (phba->sli_rev == LPFC_SLI_REV4)
+		return bf_get(wqe_ctxt_tag, &iocbq->wqe.generic.wqe_com);
+	else
+		return iocbq->iocb.ulpContext;
+}
diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c
index fdf08cb57207..6688a575904f 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.c
+++ b/drivers/scsi/lpfc/lpfc_bsg.c
@@ -325,7 +325,7 @@ lpfc_bsg_send_mgmt_cmd_cmp(struct lpfc_hba *phba,
 
 	/* Close the timeout handler abort window */
 	spin_lock_irqsave(&phba->hbalock, flags);
-	cmdiocbq->iocb_flag &= ~LPFC_IO_CMD_OUTSTANDING;
+	cmdiocbq->cmd_flag &= ~LPFC_IO_CMD_OUTSTANDING;
 	spin_unlock_irqrestore(&phba->hbalock, flags);
 
 	iocb = &dd_data->context_un.iocb;
@@ -481,11 +481,11 @@ lpfc_bsg_send_mgmt_cmd(struct bsg_job *job)
 	cmd->ulpOwner = OWN_CHIP;
 	cmdiocbq->vport = phba->pport;
 	cmdiocbq->context3 = bmp;
-	cmdiocbq->iocb_flag |= LPFC_IO_LIBDFC;
+	cmdiocbq->cmd_flag |= LPFC_IO_LIBDFC;
 	timeout = phba->fc_ratov * 2;
 	cmd->ulpTimeout = timeout;
 
-	cmdiocbq->iocb_cmpl = lpfc_bsg_send_mgmt_cmd_cmp;
+	cmdiocbq->cmd_cmpl = lpfc_bsg_send_mgmt_cmd_cmp;
 	cmdiocbq->context1 = dd_data;
 	cmdiocbq->context2 = cmp;
 	cmdiocbq->context3 = bmp;
@@ -516,9 +516,9 @@ lpfc_bsg_send_mgmt_cmd(struct bsg_job *job)
 	if (iocb_stat == IOCB_SUCCESS) {
 		spin_lock_irqsave(&phba->hbalock, flags);
 		/* make sure the I/O had not been completed yet */
-		if (cmdiocbq->iocb_flag & LPFC_IO_LIBDFC) {
+		if (cmdiocbq->cmd_flag & LPFC_IO_LIBDFC) {
 			/* open up abort window to timeout handler */
-			cmdiocbq->iocb_flag |= LPFC_IO_CMD_OUTSTANDING;
+			cmdiocbq->cmd_flag |= LPFC_IO_CMD_OUTSTANDING;
 		}
 		spin_unlock_irqrestore(&phba->hbalock, flags);
 		return 0; /* done for now */
@@ -600,7 +600,7 @@ lpfc_bsg_rport_els_cmp(struct lpfc_hba *phba,
 
 	/* Close the timeout handler abort window */
 	spin_lock_irqsave(&phba->hbalock, flags);
-	cmdiocbq->iocb_flag &= ~LPFC_IO_CMD_OUTSTANDING;
+	cmdiocbq->cmd_flag &= ~LPFC_IO_CMD_OUTSTANDING;
 	spin_unlock_irqrestore(&phba->hbalock, flags);
 
 	rsp = &rspiocbq->iocb;
@@ -726,10 +726,10 @@ lpfc_bsg_rport_els(struct bsg_job *job)
 		cmdiocbq->iocb.ulpContext = phba->sli4_hba.rpi_ids[rpi];
 	else
 		cmdiocbq->iocb.ulpContext = rpi;
-	cmdiocbq->iocb_flag |= LPFC_IO_LIBDFC;
+	cmdiocbq->cmd_flag |= LPFC_IO_LIBDFC;
 	cmdiocbq->context1 = dd_data;
 	cmdiocbq->context_un.ndlp = ndlp;
-	cmdiocbq->iocb_cmpl = lpfc_bsg_rport_els_cmp;
+	cmdiocbq->cmd_cmpl = lpfc_bsg_rport_els_cmp;
 	dd_data->type = TYPE_IOCB;
 	dd_data->set_job = job;
 	dd_data->context_un.iocb.cmdiocbq = cmdiocbq;
@@ -757,9 +757,9 @@ lpfc_bsg_rport_els(struct bsg_job *job)
 	if (rc == IOCB_SUCCESS) {
 		spin_lock_irqsave(&phba->hbalock, flags);
 		/* make sure the I/O had not been completed/released */
-		if (cmdiocbq->iocb_flag & LPFC_IO_LIBDFC) {
+		if (cmdiocbq->cmd_flag & LPFC_IO_LIBDFC) {
 			/* open up abort window to timeout handler */
-			cmdiocbq->iocb_flag |= LPFC_IO_CMD_OUTSTANDING;
+			cmdiocbq->cmd_flag |= LPFC_IO_CMD_OUTSTANDING;
 		}
 		spin_unlock_irqrestore(&phba->hbalock, flags);
 		return 0; /* done for now */
@@ -1053,7 +1053,7 @@ lpfc_bsg_ct_unsol_event(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 							lpfc_in_buf_free(phba,
 									dmabuf);
 						} else {
-							lpfc_post_buffer(phba,
+							lpfc_sli3_post_buffer(phba,
 									 pring,
 									 1);
 						}
@@ -1061,7 +1061,7 @@ lpfc_bsg_ct_unsol_event(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 					default:
 						if (!(phba->sli3_options &
 						      LPFC_SLI3_HBQ_ENABLED))
-							lpfc_post_buffer(phba,
+							lpfc_sli3_post_buffer(phba,
 									 pring,
 									 1);
 						break;
@@ -1395,7 +1395,7 @@ lpfc_issue_ct_rsp_cmp(struct lpfc_hba *phba,
 
 	/* Close the timeout handler abort window */
 	spin_lock_irqsave(&phba->hbalock, flags);
-	cmdiocbq->iocb_flag &= ~LPFC_IO_CMD_OUTSTANDING;
+	cmdiocbq->cmd_flag &= ~LPFC_IO_CMD_OUTSTANDING;
 	spin_unlock_irqrestore(&phba->hbalock, flags);
 
 	ndlp = dd_data->context_un.iocb.ndlp;
@@ -1549,13 +1549,13 @@ lpfc_issue_ct_rsp(struct lpfc_hba *phba, struct bsg_job *job, uint32_t tag,
 		"2722 Xmit CT response on exchange x%x Data: x%x x%x x%x\n",
 		icmd->ulpContext, icmd->ulpIoTag, tag, phba->link_state);
 
-	ctiocb->iocb_flag |= LPFC_IO_LIBDFC;
+	ctiocb->cmd_flag |= LPFC_IO_LIBDFC;
 	ctiocb->vport = phba->pport;
 	ctiocb->context1 = dd_data;
 	ctiocb->context2 = cmp;
 	ctiocb->context3 = bmp;
 	ctiocb->context_un.ndlp = ndlp;
-	ctiocb->iocb_cmpl = lpfc_issue_ct_rsp_cmp;
+	ctiocb->cmd_cmpl = lpfc_issue_ct_rsp_cmp;
 
 	dd_data->type = TYPE_IOCB;
 	dd_data->set_job = job;
@@ -1582,9 +1582,9 @@ lpfc_issue_ct_rsp(struct lpfc_hba *phba, struct bsg_job *job, uint32_t tag,
 	if (rc == IOCB_SUCCESS) {
 		spin_lock_irqsave(&phba->hbalock, flags);
 		/* make sure the I/O had not been completed/released */
-		if (ctiocb->iocb_flag & LPFC_IO_LIBDFC) {
+		if (ctiocb->cmd_flag & LPFC_IO_LIBDFC) {
 			/* open up abort window to timeout handler */
-			ctiocb->iocb_flag |= LPFC_IO_CMD_OUTSTANDING;
+			ctiocb->cmd_flag |= LPFC_IO_CMD_OUTSTANDING;
 		}
 		spin_unlock_irqrestore(&phba->hbalock, flags);
 		return 0; /* done for now */
@@ -2713,9 +2713,9 @@ static int lpfcdiag_loop_get_xri(struct lpfc_hba *phba, uint16_t rpi,
 	cmd->ulpClass = CLASS3;
 	cmd->ulpContext = rpi;
 
-	cmdiocbq->iocb_flag |= LPFC_IO_LIBDFC;
+	cmdiocbq->cmd_flag |= LPFC_IO_LIBDFC;
 	cmdiocbq->vport = phba->pport;
-	cmdiocbq->iocb_cmpl = NULL;
+	cmdiocbq->cmd_cmpl = NULL;
 
 	iocb_stat = lpfc_sli_issue_iocb_wait(phba, LPFC_ELS_RING, cmdiocbq,
 				rspiocbq,
@@ -3286,10 +3286,10 @@ lpfc_bsg_diag_loopback_run(struct bsg_job *job)
 		cmdiocbq->sli4_xritag = NO_XRI;
 		cmd->unsli3.rcvsli3.ox_id = 0xffff;
 	}
-	cmdiocbq->iocb_flag |= LPFC_IO_LIBDFC;
-	cmdiocbq->iocb_flag |= LPFC_IO_LOOPBACK;
+	cmdiocbq->cmd_flag |= LPFC_IO_LIBDFC;
+	cmdiocbq->cmd_flag |= LPFC_IO_LOOPBACK;
 	cmdiocbq->vport = phba->pport;
-	cmdiocbq->iocb_cmpl = NULL;
+	cmdiocbq->cmd_cmpl = NULL;
 	iocb_stat = lpfc_sli_issue_iocb_wait(phba, LPFC_ELS_RING, cmdiocbq,
 					     rspiocbq, (phba->fc_ratov * 2) +
 					     LPFC_DRVR_TIMEOUT);
@@ -5273,11 +5273,11 @@ lpfc_menlo_cmd(struct bsg_job *job)
 	cmd->ulpClass = CLASS3;
 	cmd->ulpOwner = OWN_CHIP;
 	cmd->ulpLe = 1; /* Limited Edition */
-	cmdiocbq->iocb_flag |= LPFC_IO_LIBDFC;
+	cmdiocbq->cmd_flag |= LPFC_IO_LIBDFC;
 	cmdiocbq->vport = phba->pport;
 	/* We want the firmware to timeout before we do */
 	cmd->ulpTimeout = MENLO_TIMEOUT - 5;
-	cmdiocbq->iocb_cmpl = lpfc_bsg_menlo_cmd_cmp;
+	cmdiocbq->cmd_cmpl = lpfc_bsg_menlo_cmd_cmp;
 	cmdiocbq->context1 = dd_data;
 	cmdiocbq->context2 = cmp;
 	cmdiocbq->context3 = bmp;
@@ -6001,7 +6001,7 @@ lpfc_bsg_timeout(struct bsg_job *job)
 
 		spin_lock_irqsave(&phba->hbalock, flags);
 		/* make sure the I/O abort window is still open */
-		if (!(cmdiocb->iocb_flag & LPFC_IO_CMD_OUTSTANDING)) {
+		if (!(cmdiocb->cmd_flag & LPFC_IO_CMD_OUTSTANDING)) {
 			spin_unlock_irqrestore(&phba->hbalock, flags);
 			return -EAGAIN;
 		}
diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index c9770b1d2366..f7bf589b63fb 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -129,6 +129,7 @@ void lpfc_disc_list_loopmap(struct lpfc_vport *);
 void lpfc_disc_start(struct lpfc_vport *);
 void lpfc_cleanup_discovery_resources(struct lpfc_vport *);
 void lpfc_cleanup(struct lpfc_vport *);
+void lpfc_prep_embed_io(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_ncmd);
 void lpfc_disc_timeout(struct timer_list *);
 
 int lpfc_unregister_fcf_prep(struct lpfc_hba *);
@@ -210,7 +211,7 @@ int lpfc_config_port_post(struct lpfc_hba *);
 int lpfc_hba_down_prep(struct lpfc_hba *);
 int lpfc_hba_down_post(struct lpfc_hba *);
 void lpfc_hba_init(struct lpfc_hba *, uint32_t *);
-int lpfc_post_buffer(struct lpfc_hba *, struct lpfc_sli_ring *, int);
+int lpfc_sli3_post_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring, int cnt);
 void lpfc_decode_firmware_rev(struct lpfc_hba *, char *, int);
 int lpfc_online(struct lpfc_hba *);
 void lpfc_unblock_mgmt_io(struct lpfc_hba *);
diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c
index dfcb7d4bd7fa..19e2f8086a6d 100644
--- a/drivers/scsi/lpfc/lpfc_ct.c
+++ b/drivers/scsi/lpfc/lpfc_ct.c
@@ -239,7 +239,7 @@ lpfc_ct_reject_event(struct lpfc_nodelist *ndlp,
 	cmdiocbq->context1 = lpfc_nlp_get(ndlp);
 	cmdiocbq->context2 = (uint8_t *)mp;
 	cmdiocbq->context3 = (uint8_t *)bmp;
-	cmdiocbq->iocb_cmpl = lpfc_ct_unsol_cmpl;
+	cmdiocbq->cmd_cmpl = lpfc_ct_unsol_cmpl;
 	icmd->ulpContext = rx_id;  /* Xri / rx_id */
 	icmd->unsli3.rcvsli3.ox_id = ox_id;
 	icmd->un.ulpWord[3] =
@@ -370,7 +370,7 @@ lpfc_ct_unsol_event(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		/* Not enough posted buffers; Try posting more buffers */
 		phba->fc_stat.NoRcvBuf++;
 		if (!(phba->sli3_options & LPFC_SLI3_HBQ_ENABLED))
-			lpfc_post_buffer(phba, pring, 2);
+			lpfc_sli3_post_buffer(phba, pring, 2);
 		return;
 	}
 
@@ -447,7 +447,7 @@ lpfc_ct_unsol_event(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 				lpfc_ct_unsol_buffer(phba, iocbq, mp, size);
 				lpfc_in_buf_free(phba, mp);
 			}
-			lpfc_post_buffer(phba, pring, i);
+			lpfc_sli3_post_buffer(phba, pring, i);
 		}
 		list_del(&head);
 	}
@@ -652,7 +652,7 @@ lpfc_gen_req(struct lpfc_vport *vport, struct lpfc_dmabuf *bmp,
 			 "Data: x%x x%x\n",
 			 ndlp->nlp_DID, icmd->ulpIoTag,
 			 vport->port_state);
-	geniocb->iocb_cmpl = cmpl;
+	geniocb->cmd_cmpl = cmpl;
 	geniocb->drvrTimeout = icmd->ulpTimeout + LPFC_DRVR_TIMEOUT;
 	geniocb->vport = vport;
 	geniocb->retry = retry;
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index 08b2e85dcd7d..79bc86ba59b3 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -2607,8 +2607,8 @@ lpfc_debugfs_multixripools_write(struct file *file, const char __user *buf,
 	struct lpfc_sli4_hdw_queue *qp;
 	struct lpfc_multixri_pool *multixri_pool;
 
-	if (nbytes > 64)
-		nbytes = 64;
+	if (nbytes > sizeof(mybuf) - 1)
+		nbytes = sizeof(mybuf) - 1;
 
 	memset(mybuf, 0, sizeof(mybuf));
 
@@ -2688,8 +2688,8 @@ lpfc_debugfs_nvmestat_write(struct file *file, const char __user *buf,
 	if (!phba->targetport)
 		return -ENXIO;
 
-	if (nbytes > 64)
-		nbytes = 64;
+	if (nbytes > sizeof(mybuf) - 1)
+		nbytes = sizeof(mybuf) - 1;
 
 	memset(mybuf, 0, sizeof(mybuf));
 
@@ -2826,8 +2826,8 @@ lpfc_debugfs_ioktime_write(struct file *file, const char __user *buf,
 	char mybuf[64];
 	char *pbuf;
 
-	if (nbytes > 64)
-		nbytes = 64;
+	if (nbytes > sizeof(mybuf) - 1)
+		nbytes = sizeof(mybuf) - 1;
 
 	memset(mybuf, 0, sizeof(mybuf));
 
@@ -2954,8 +2954,8 @@ lpfc_debugfs_nvmeio_trc_write(struct file *file, const char __user *buf,
 	char mybuf[64];
 	char *pbuf;
 
-	if (nbytes > 63)
-		nbytes = 63;
+	if (nbytes > sizeof(mybuf) - 1)
+		nbytes = sizeof(mybuf) - 1;
 
 	memset(mybuf, 0, sizeof(mybuf));
 
@@ -3060,8 +3060,8 @@ lpfc_debugfs_hdwqstat_write(struct file *file, const char __user *buf,
 	char *pbuf;
 	int i;
 
-	if (nbytes > 64)
-		nbytes = 64;
+	if (nbytes > sizeof(mybuf) - 1)
+		nbytes = sizeof(mybuf) - 1;
 
 	memset(mybuf, 0, sizeof(mybuf));
 
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 5f44a0763f37..0d34a03164f5 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -192,23 +192,23 @@ lpfc_prep_els_iocb(struct lpfc_vport *vport, uint8_t expectRsp,
 		 (elscmd == ELS_CMD_LOGO)))
 		switch (elscmd) {
 		case ELS_CMD_FLOGI:
-		elsiocb->iocb_flag |=
+		elsiocb->cmd_flag |=
 			((LPFC_ELS_ID_FLOGI << LPFC_FIP_ELS_ID_SHIFT)
 					& LPFC_FIP_ELS_ID_MASK);
 		break;
 		case ELS_CMD_FDISC:
-		elsiocb->iocb_flag |=
+		elsiocb->cmd_flag |=
 			((LPFC_ELS_ID_FDISC << LPFC_FIP_ELS_ID_SHIFT)
 					& LPFC_FIP_ELS_ID_MASK);
 		break;
 		case ELS_CMD_LOGO:
-		elsiocb->iocb_flag |=
+		elsiocb->cmd_flag |=
 			((LPFC_ELS_ID_LOGO << LPFC_FIP_ELS_ID_SHIFT)
 					& LPFC_FIP_ELS_ID_MASK);
 		break;
 		}
 	else
-		elsiocb->iocb_flag &= ~LPFC_FIP_ELS_ID_MASK;
+		elsiocb->cmd_flag &= ~LPFC_FIP_ELS_ID_MASK;
 
 	icmd = &elsiocb->iocb;
 
@@ -1252,10 +1252,10 @@ lpfc_cmpl_els_link_down(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 			"6445 ELS completes after LINK_DOWN: "
 			" Status %x/%x cmd x%x flg x%x\n",
 			irsp->ulpStatus, irsp->un.ulpWord[4], cmd,
-			cmdiocb->iocb_flag);
+			cmdiocb->cmd_flag);
 
-	if (cmdiocb->iocb_flag & LPFC_IO_FABRIC) {
-		cmdiocb->iocb_flag &= ~LPFC_IO_FABRIC;
+	if (cmdiocb->cmd_flag & LPFC_IO_FABRIC) {
+		cmdiocb->cmd_flag &= ~LPFC_IO_FABRIC;
 		atomic_dec(&phba->fabric_iocb_count);
 	}
 	lpfc_els_free_iocb(phba, cmdiocb);
@@ -1370,7 +1370,7 @@ lpfc_issue_els_flogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	phba->fc_ratov = tmo;
 
 	phba->fc_stat.elsXmitFLOGI++;
-	elsiocb->iocb_cmpl = lpfc_cmpl_els_flogi;
+	elsiocb->cmd_cmpl = lpfc_cmpl_els_flogi;
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_CMD,
 		"Issue FLOGI:     opt:x%x",
@@ -1463,7 +1463,7 @@ lpfc_els_abort_flogi(struct lpfc_hba *phba)
 			if (ndlp && ndlp->nlp_DID == Fabric_DID) {
 				if ((phba->pport->fc_flag & FC_PT2PT) &&
 				    !(phba->pport->fc_flag & FC_PT2PT_PLOGI))
-					iocb->fabric_iocb_cmpl =
+					iocb->fabric_cmd_cmpl =
 						lpfc_ignore_els_cmpl;
 				lpfc_sli_issue_abort_iotag(phba, pring, iocb,
 							   NULL);
@@ -2226,7 +2226,7 @@ lpfc_issue_els_plogi(struct lpfc_vport *vport, uint32_t did, uint8_t retry)
 	}
 
 	phba->fc_stat.elsXmitPLOGI++;
-	elsiocb->iocb_cmpl = lpfc_cmpl_els_plogi;
+	elsiocb->cmd_cmpl = lpfc_cmpl_els_plogi;
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_CMD,
 			      "Issue PLOGI:     did:x%x refcnt %d",
@@ -2478,7 +2478,7 @@ lpfc_issue_els_prli(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		/* For FCP support */
 		npr->prliType = PRLI_FCP_TYPE;
 		npr->initiatorFunc = 1;
-		elsiocb->iocb_flag |= LPFC_PRLI_FCP_REQ;
+		elsiocb->cmd_flag |= LPFC_PRLI_FCP_REQ;
 
 		/* Remove FCP type - processed. */
 		local_nlp_type &= ~NLP_FC4_FCP;
@@ -2512,14 +2512,14 @@ lpfc_issue_els_prli(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 
 		npr_nvme->word1 = cpu_to_be32(npr_nvme->word1);
 		npr_nvme->word4 = cpu_to_be32(npr_nvme->word4);
-		elsiocb->iocb_flag |= LPFC_PRLI_NVME_REQ;
+		elsiocb->cmd_flag |= LPFC_PRLI_NVME_REQ;
 
 		/* Remove NVME type - processed. */
 		local_nlp_type &= ~NLP_FC4_NVME;
 	}
 
 	phba->fc_stat.elsXmitPRLI++;
-	elsiocb->iocb_cmpl = lpfc_cmpl_els_prli;
+	elsiocb->cmd_cmpl = lpfc_cmpl_els_prli;
 	spin_lock_irq(&ndlp->lock);
 	ndlp->nlp_flag |= NLP_PRLI_SND;
 
@@ -2842,7 +2842,7 @@ lpfc_issue_els_adisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	ap->DID = be32_to_cpu(vport->fc_myDID);
 
 	phba->fc_stat.elsXmitADISC++;
-	elsiocb->iocb_cmpl = lpfc_cmpl_els_adisc;
+	elsiocb->cmd_cmpl = lpfc_cmpl_els_adisc;
 	spin_lock_irq(&ndlp->lock);
 	ndlp->nlp_flag |= NLP_ADISC_SND;
 	spin_unlock_irq(&ndlp->lock);
@@ -3065,7 +3065,7 @@ lpfc_issue_els_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	memcpy(pcmd, &vport->fc_portname, sizeof(struct lpfc_name));
 
 	phba->fc_stat.elsXmitLOGO++;
-	elsiocb->iocb_cmpl = lpfc_cmpl_els_logo;
+	elsiocb->cmd_cmpl = lpfc_cmpl_els_logo;
 	spin_lock_irq(&ndlp->lock);
 	ndlp->nlp_flag |= NLP_LOGO_SND;
 	ndlp->nlp_flag &= ~NLP_ISSUE_LOGO;
@@ -3417,7 +3417,7 @@ lpfc_issue_els_scr(struct lpfc_vport *vport, uint8_t retry)
 		ndlp->nlp_DID, 0, 0);
 
 	phba->fc_stat.elsXmitSCR++;
-	elsiocb->iocb_cmpl = lpfc_cmpl_els_disc_cmd;
+	elsiocb->cmd_cmpl = lpfc_cmpl_els_disc_cmd;
 	elsiocb->context1 = lpfc_nlp_get(ndlp);
 	if (!elsiocb->context1) {
 		lpfc_els_free_iocb(phba, elsiocb);
@@ -3514,7 +3514,7 @@ lpfc_issue_els_rscn(struct lpfc_vport *vport, uint8_t retry)
 	event->portid.rscn_fid[2] = nportid & 0x000000FF;
 
 	phba->fc_stat.elsXmitRSCN++;
-	elsiocb->iocb_cmpl = lpfc_cmpl_els_cmd;
+	elsiocb->cmd_cmpl = lpfc_cmpl_els_cmd;
 	elsiocb->context1 = lpfc_nlp_get(ndlp);
 	if (!elsiocb->context1) {
 		lpfc_els_free_iocb(phba, elsiocb);
@@ -3613,7 +3613,7 @@ lpfc_issue_els_farpr(struct lpfc_vport *vport, uint32_t nportid, uint8_t retry)
 		ndlp->nlp_DID, 0, 0);
 
 	phba->fc_stat.elsXmitFARPR++;
-	elsiocb->iocb_cmpl = lpfc_cmpl_els_cmd;
+	elsiocb->cmd_cmpl = lpfc_cmpl_els_cmd;
 	elsiocb->context1 = lpfc_nlp_get(ndlp);
 	if (!elsiocb->context1) {
 		lpfc_els_free_iocb(phba, elsiocb);
@@ -3704,7 +3704,7 @@ lpfc_issue_els_rdf(struct lpfc_vport *vport, uint8_t retry)
 			 phba->cgn_reg_fpin);
 
 	phba->cgn_fpin_frequency = LPFC_FPIN_INIT_FREQ;
-	elsiocb->iocb_cmpl = lpfc_cmpl_els_disc_cmd;
+	elsiocb->cmd_cmpl = lpfc_cmpl_els_disc_cmd;
 	elsiocb->context1 = lpfc_nlp_get(ndlp);
 	if (!elsiocb->context1) {
 		lpfc_els_free_iocb(phba, elsiocb);
@@ -4154,7 +4154,7 @@ lpfc_issue_els_edc(struct lpfc_vport *vport, uint8_t retry)
 			 ndlp->nlp_DID, phba->cgn_reg_signal,
 			 phba->cgn_reg_fpin);
 
-	elsiocb->iocb_cmpl = lpfc_cmpl_els_disc_cmd;
+	elsiocb->cmd_cmpl = lpfc_cmpl_els_disc_cmd;
 	elsiocb->context1 = lpfc_nlp_get(ndlp);
 	if (!elsiocb->context1) {
 		lpfc_els_free_iocb(phba, elsiocb);
@@ -4968,12 +4968,12 @@ lpfc_els_free_iocb(struct lpfc_hba *phba, struct lpfc_iocbq *elsiocb)
 
 	/* context2  = cmd,  context2->next = rsp, context3 = bpl */
 	if (elsiocb->context2) {
-		if (elsiocb->iocb_flag & LPFC_DELAY_MEM_FREE) {
+		if (elsiocb->cmd_flag & LPFC_DELAY_MEM_FREE) {
 			/* Firmware could still be in progress of DMAing
 			 * payload, so don't free data buffer till after
 			 * a hbeat.
 			 */
-			elsiocb->iocb_flag &= ~LPFC_DELAY_MEM_FREE;
+			elsiocb->cmd_flag &= ~LPFC_DELAY_MEM_FREE;
 			buf_ptr = elsiocb->context2;
 			elsiocb->context2 = NULL;
 			if (buf_ptr) {
@@ -5480,9 +5480,9 @@ lpfc_els_rsp_acc(struct lpfc_vport *vport, uint32_t flag,
 			ndlp->nlp_flag & NLP_REG_LOGIN_SEND))
 			ndlp->nlp_flag &= ~NLP_LOGO_ACC;
 		spin_unlock_irq(&ndlp->lock);
-		elsiocb->iocb_cmpl = lpfc_cmpl_els_logo_acc;
+		elsiocb->cmd_cmpl = lpfc_cmpl_els_logo_acc;
 	} else {
-		elsiocb->iocb_cmpl = lpfc_cmpl_els_rsp;
+		elsiocb->cmd_cmpl = lpfc_cmpl_els_rsp;
 	}
 
 	phba->fc_stat.elsXmitACC++;
@@ -5577,7 +5577,7 @@ lpfc_els_rsp_reject(struct lpfc_vport *vport, uint32_t rejectError,
 		ndlp->nlp_DID, ndlp->nlp_flag, rejectError);
 
 	phba->fc_stat.elsXmitLSRJT++;
-	elsiocb->iocb_cmpl = lpfc_cmpl_els_rsp;
+	elsiocb->cmd_cmpl = lpfc_cmpl_els_rsp;
 	elsiocb->context1 = lpfc_nlp_get(ndlp);
 	if (!elsiocb->context1) {
 		lpfc_els_free_iocb(phba, elsiocb);
@@ -5657,7 +5657,7 @@ lpfc_issue_els_edc_rsp(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
 			      "Issue EDC ACC:      did:x%x flg:x%x refcnt %d",
 			      ndlp->nlp_DID, ndlp->nlp_flag,
 			      kref_read(&ndlp->kref));
-	elsiocb->iocb_cmpl = lpfc_cmpl_els_rsp;
+	elsiocb->cmd_cmpl = lpfc_cmpl_els_rsp;
 
 	phba->fc_stat.elsXmitACC++;
 	elsiocb->context1 = lpfc_nlp_get(ndlp);
@@ -5750,7 +5750,7 @@ lpfc_els_rsp_adisc_acc(struct lpfc_vport *vport, struct lpfc_iocbq *oldiocb,
 		      ndlp->nlp_DID, ndlp->nlp_flag, kref_read(&ndlp->kref));
 
 	phba->fc_stat.elsXmitACC++;
-	elsiocb->iocb_cmpl = lpfc_cmpl_els_rsp;
+	elsiocb->cmd_cmpl = lpfc_cmpl_els_rsp;
 	elsiocb->context1 = lpfc_nlp_get(ndlp);
 	if (!elsiocb->context1) {
 		lpfc_els_free_iocb(phba, elsiocb);
@@ -5924,7 +5924,7 @@ lpfc_els_rsp_prli_acc(struct lpfc_vport *vport, struct lpfc_iocbq *oldiocb,
 		      ndlp->nlp_DID, ndlp->nlp_flag, kref_read(&ndlp->kref));
 
 	phba->fc_stat.elsXmitACC++;
-	elsiocb->iocb_cmpl = lpfc_cmpl_els_rsp;
+	elsiocb->cmd_cmpl = lpfc_cmpl_els_rsp;
 	elsiocb->context1 =  lpfc_nlp_get(ndlp);
 	if (!elsiocb->context1) {
 		lpfc_els_free_iocb(phba, elsiocb);
@@ -6025,7 +6025,7 @@ lpfc_els_rsp_rnid_acc(struct lpfc_vport *vport, uint8_t format,
 		      ndlp->nlp_DID, ndlp->nlp_flag, kref_read(&ndlp->kref));
 
 	phba->fc_stat.elsXmitACC++;
-	elsiocb->iocb_cmpl = lpfc_cmpl_els_rsp;
+	elsiocb->cmd_cmpl = lpfc_cmpl_els_rsp;
 	elsiocb->context1 = lpfc_nlp_get(ndlp);
 	if (!elsiocb->context1) {
 		lpfc_els_free_iocb(phba, elsiocb);
@@ -6139,7 +6139,7 @@ lpfc_els_rsp_echo_acc(struct lpfc_vport *vport, uint8_t *data,
 		      ndlp->nlp_DID, ndlp->nlp_flag, kref_read(&ndlp->kref));
 
 	phba->fc_stat.elsXmitACC++;
-	elsiocb->iocb_cmpl = lpfc_cmpl_els_rsp;
+	elsiocb->cmd_cmpl = lpfc_cmpl_els_rsp;
 	elsiocb->context1 =  lpfc_nlp_get(ndlp);
 	if (!elsiocb->context1) {
 		lpfc_els_free_iocb(phba, elsiocb);
@@ -6803,7 +6803,7 @@ lpfc_els_rdp_cmpl(struct lpfc_hba *phba, struct lpfc_rdp_context *rdp_context,
 				     rdp_context->page_a0, vport);
 
 	rdp_res->length = cpu_to_be32(len - 8);
-	elsiocb->iocb_cmpl = lpfc_cmpl_els_rsp;
+	elsiocb->cmd_cmpl = lpfc_cmpl_els_rsp;
 
 	/* Now that we know the true size of the payload, update the BPL */
 	bpl = (struct ulp_bde64 *)
@@ -6844,7 +6844,7 @@ error:
 	stat->un.b.lsRjtRsnCode = LSRJT_UNABLE_TPC;
 
 	phba->fc_stat.elsXmitLSRJT++;
-	elsiocb->iocb_cmpl = lpfc_cmpl_els_rsp;
+	elsiocb->cmd_cmpl = lpfc_cmpl_els_rsp;
 	elsiocb->context1 = lpfc_nlp_get(ndlp);
 	if (!elsiocb->context1) {
 		lpfc_els_free_iocb(phba, elsiocb);
@@ -7066,7 +7066,7 @@ lpfc_els_lcb_rsp(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	lcb_res->capability = lcb_context->capability;
 	lcb_res->lcb_frequency = lcb_context->frequency;
 	lcb_res->lcb_duration = lcb_context->duration;
-	elsiocb->iocb_cmpl = lpfc_cmpl_els_rsp;
+	elsiocb->cmd_cmpl = lpfc_cmpl_els_rsp;
 	phba->fc_stat.elsXmitACC++;
 
 	elsiocb->context1 = lpfc_nlp_get(ndlp);
@@ -7105,7 +7105,7 @@ error:
 	if (shdr_add_status == ADD_STATUS_OPERATION_ALREADY_ACTIVE)
 		stat->un.b.lsRjtRsnCodeExp = LSEXP_CMD_IN_PROGRESS;
 
-	elsiocb->iocb_cmpl = lpfc_cmpl_els_rsp;
+	elsiocb->cmd_cmpl = lpfc_cmpl_els_rsp;
 	phba->fc_stat.elsXmitLSRJT++;
 	elsiocb->context1 = lpfc_nlp_get(ndlp);
 	if (!elsiocb->context1) {
@@ -8172,7 +8172,7 @@ lpfc_els_rsp_rls_acc(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 			 elsiocb->iotag, elsiocb->iocb.ulpContext,
 			 ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state,
 			 ndlp->nlp_rpi);
-	elsiocb->iocb_cmpl = lpfc_cmpl_els_rsp;
+	elsiocb->cmd_cmpl = lpfc_cmpl_els_rsp;
 	phba->fc_stat.elsXmitACC++;
 	elsiocb->context1 = lpfc_nlp_get(ndlp);
 	if (!elsiocb->context1) {
@@ -8324,7 +8324,7 @@ lpfc_els_rcv_rtv(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
 			 ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state,
 			 ndlp->nlp_rpi,
 			rtv_rsp->ratov, rtv_rsp->edtov, rtv_rsp->qtov);
-	elsiocb->iocb_cmpl = lpfc_cmpl_els_rsp;
+	elsiocb->cmd_cmpl = lpfc_cmpl_els_rsp;
 	phba->fc_stat.elsXmitACC++;
 	elsiocb->context1 = lpfc_nlp_get(ndlp);
 	if (!elsiocb->context1) {
@@ -8401,7 +8401,7 @@ lpfc_issue_els_rrq(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		"Issue RRQ:     did:x%x",
 		did, rrq->xritag, rrq->rxid);
 	elsiocb->context_un.rrq = rrq;
-	elsiocb->iocb_cmpl = lpfc_cmpl_els_rrq;
+	elsiocb->cmd_cmpl = lpfc_cmpl_els_rrq;
 
 	lpfc_nlp_get(ndlp);
 	elsiocb->context1 = ndlp;
@@ -8507,7 +8507,7 @@ lpfc_els_rsp_rpl_acc(struct lpfc_vport *vport, uint16_t cmdsize,
 			 elsiocb->iotag, elsiocb->iocb.ulpContext,
 			 ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state,
 			 ndlp->nlp_rpi);
-	elsiocb->iocb_cmpl = lpfc_cmpl_els_rsp;
+	elsiocb->cmd_cmpl = lpfc_cmpl_els_rsp;
 	phba->fc_stat.elsXmitACC++;
 	elsiocb->context1 = lpfc_nlp_get(ndlp);
 	if (!elsiocb->context1) {
@@ -8947,7 +8947,7 @@ lpfc_els_timeout_handler(struct lpfc_vport *vport)
 	list_for_each_entry_safe(piocb, tmp_iocb, &pring->txcmplq, list) {
 		cmd = &piocb->iocb;
 
-		if ((piocb->iocb_flag & LPFC_IO_LIBDFC) != 0 ||
+		if ((piocb->cmd_flag & LPFC_IO_LIBDFC) != 0 ||
 		    piocb->iocb.ulpCommand == CMD_ABORT_XRI_CN ||
 		    piocb->iocb.ulpCommand == CMD_CLOSE_XRI_CN)
 			continue;
@@ -9060,13 +9060,13 @@ lpfc_els_flush_cmd(struct lpfc_vport *vport)
 
 	/* First we need to issue aborts to outstanding cmds on txcmpl */
 	list_for_each_entry_safe(piocb, tmp_iocb, &pring->txcmplq, list) {
-		if (piocb->iocb_flag & LPFC_IO_LIBDFC)
+		if (piocb->cmd_flag & LPFC_IO_LIBDFC)
 			continue;
 
 		if (piocb->vport != vport)
 			continue;
 
-		if (piocb->iocb_flag & LPFC_DRIVER_ABORTED)
+		if (piocb->cmd_flag & LPFC_DRIVER_ABORTED)
 			continue;
 
 		/* On the ELS ring we can have ELS_REQUESTs or
@@ -9084,7 +9084,7 @@ lpfc_els_flush_cmd(struct lpfc_vport *vport)
 			 * and avoid any retry logic.
 			 */
 			if (phba->link_state == LPFC_LINK_DOWN)
-				piocb->iocb_cmpl = lpfc_cmpl_els_link_down;
+				piocb->cmd_cmpl = lpfc_cmpl_els_link_down;
 		}
 		if (cmd->ulpCommand == CMD_GEN_REQUEST64_CR)
 			list_add_tail(&piocb->dlist, &abort_list);
@@ -9119,9 +9119,8 @@ lpfc_els_flush_cmd(struct lpfc_vport *vport)
 	list_for_each_entry_safe(piocb, tmp_iocb, &pring->txq, list) {
 		cmd = &piocb->iocb;
 
-		if (piocb->iocb_flag & LPFC_IO_LIBDFC) {
+		if (piocb->cmd_flag & LPFC_IO_LIBDFC)
 			continue;
-		}
 
 		/* Do not flush out the QUE_RING and ABORT/CLOSE iocbs */
 		if (cmd->ulpCommand == CMD_QUE_RING_BUF_CN ||
@@ -9766,7 +9765,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	payload_len = elsiocb->iocb.unsli3.rcvsli3.acc_len;
 	cmd = *payload;
 	if ((phba->sli3_options & LPFC_SLI3_HBQ_ENABLED) == 0)
-		lpfc_post_buffer(phba, pring, 1);
+		lpfc_sli3_post_buffer(phba, pring, 1);
 
 	did = icmd->un.rcvels.remoteID;
 	if (icmd->ulpStatus) {
@@ -10239,7 +10238,7 @@ lpfc_els_unsol_event(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		phba->fc_stat.NoRcvBuf++;
 		/* Not enough posted buffers; Try posting more buffers */
 		if (!(phba->sli3_options & LPFC_SLI3_HBQ_ENABLED))
-			lpfc_post_buffer(phba, pring, 0);
+			lpfc_sli3_post_buffer(phba, pring, 0);
 		return;
 	}
 
@@ -10875,7 +10874,7 @@ lpfc_issue_els_fdisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	lpfc_set_disctmo(vport);
 
 	phba->fc_stat.elsXmitFDISC++;
-	elsiocb->iocb_cmpl = lpfc_cmpl_els_fdisc;
+	elsiocb->cmd_cmpl = lpfc_cmpl_els_fdisc;
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_CMD,
 		"Issue FDISC:     did:x%x",
@@ -10999,7 +10998,7 @@ lpfc_issue_els_npiv_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 		"Issue LOGO npiv  did:x%x flg:x%x",
 		ndlp->nlp_DID, ndlp->nlp_flag, 0);
 
-	elsiocb->iocb_cmpl = lpfc_cmpl_els_npiv_logo;
+	elsiocb->cmd_cmpl = lpfc_cmpl_els_npiv_logo;
 	spin_lock_irq(&ndlp->lock);
 	ndlp->nlp_flag |= NLP_LOGO_SND;
 	spin_unlock_irq(&ndlp->lock);
@@ -11084,9 +11083,9 @@ repeat:
 	}
 	spin_unlock_irqrestore(&phba->hbalock, iflags);
 	if (iocb) {
-		iocb->fabric_iocb_cmpl = iocb->iocb_cmpl;
-		iocb->iocb_cmpl = lpfc_cmpl_fabric_iocb;
-		iocb->iocb_flag |= LPFC_IO_FABRIC;
+		iocb->fabric_cmd_cmpl = iocb->cmd_cmpl;
+		iocb->cmd_cmpl = lpfc_cmpl_fabric_iocb;
+		iocb->cmd_flag |= LPFC_IO_FABRIC;
 
 		lpfc_debugfs_disc_trc(iocb->vport, LPFC_DISC_TRC_ELS_CMD,
 			"Fabric sched1:   ste:x%x",
@@ -11095,13 +11094,13 @@ repeat:
 		ret = lpfc_sli_issue_iocb(phba, LPFC_ELS_RING, iocb, 0);
 
 		if (ret == IOCB_ERROR) {
-			iocb->iocb_cmpl = iocb->fabric_iocb_cmpl;
-			iocb->fabric_iocb_cmpl = NULL;
-			iocb->iocb_flag &= ~LPFC_IO_FABRIC;
+			iocb->cmd_cmpl = iocb->fabric_cmd_cmpl;
+			iocb->fabric_cmd_cmpl = NULL;
+			iocb->cmd_flag &= ~LPFC_IO_FABRIC;
 			cmd = &iocb->iocb;
 			cmd->ulpStatus = IOSTAT_LOCAL_REJECT;
 			cmd->un.ulpWord[4] = IOERR_SLI_ABORTED;
-			iocb->iocb_cmpl(phba, iocb, iocb);
+			iocb->cmd_cmpl(phba, iocb, iocb);
 
 			atomic_dec(&phba->fabric_iocb_count);
 			goto repeat;
@@ -11157,8 +11156,8 @@ lpfc_block_fabric_iocbs(struct lpfc_hba *phba)
  * @rspiocb: pointer to lpfc response iocb data structure.
  *
  * This routine is the callback function that is put to the fabric iocb's
- * callback function pointer (iocb->iocb_cmpl). The original iocb's callback
- * function pointer has been stored in iocb->fabric_iocb_cmpl. This callback
+ * callback function pointer (iocb->cmd_cmpl). The original iocb's callback
+ * function pointer has been stored in iocb->fabric_cmd_cmpl. This callback
  * function first restores and invokes the original iocb's callback function
  * and then invokes the lpfc_resume_fabric_iocbs() routine to issue the next
  * fabric bound iocb from the driver internal fabric iocb list onto the wire.
@@ -11169,7 +11168,7 @@ lpfc_cmpl_fabric_iocb(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 {
 	struct ls_rjt stat;
 
-	BUG_ON((cmdiocb->iocb_flag & LPFC_IO_FABRIC) != LPFC_IO_FABRIC);
+	WARN_ON((cmdiocb->cmd_flag & LPFC_IO_FABRIC) != LPFC_IO_FABRIC);
 
 	switch (rspiocb->iocb.ulpStatus) {
 		case IOSTAT_NPORT_RJT:
@@ -11195,10 +11194,10 @@ lpfc_cmpl_fabric_iocb(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 
 	BUG_ON(atomic_read(&phba->fabric_iocb_count) == 0);
 
-	cmdiocb->iocb_cmpl = cmdiocb->fabric_iocb_cmpl;
-	cmdiocb->fabric_iocb_cmpl = NULL;
-	cmdiocb->iocb_flag &= ~LPFC_IO_FABRIC;
-	cmdiocb->iocb_cmpl(phba, cmdiocb, rspiocb);
+	cmdiocb->cmd_cmpl = cmdiocb->fabric_cmd_cmpl;
+	cmdiocb->fabric_cmd_cmpl = NULL;
+	cmdiocb->cmd_flag &= ~LPFC_IO_FABRIC;
+	cmdiocb->cmd_cmpl(phba, cmdiocb, rspiocb);
 
 	atomic_dec(&phba->fabric_iocb_count);
 	if (!test_bit(FABRIC_COMANDS_BLOCKED, &phba->bit_flags)) {
@@ -11249,9 +11248,9 @@ lpfc_issue_fabric_iocb(struct lpfc_hba *phba, struct lpfc_iocbq *iocb)
 		atomic_inc(&phba->fabric_iocb_count);
 	spin_unlock_irqrestore(&phba->hbalock, iflags);
 	if (ready) {
-		iocb->fabric_iocb_cmpl = iocb->iocb_cmpl;
-		iocb->iocb_cmpl = lpfc_cmpl_fabric_iocb;
-		iocb->iocb_flag |= LPFC_IO_FABRIC;
+		iocb->fabric_cmd_cmpl = iocb->cmd_cmpl;
+		iocb->cmd_cmpl = lpfc_cmpl_fabric_iocb;
+		iocb->cmd_flag |= LPFC_IO_FABRIC;
 
 		lpfc_debugfs_disc_trc(iocb->vport, LPFC_DISC_TRC_ELS_CMD,
 			"Fabric sched2:   ste:x%x",
@@ -11260,9 +11259,9 @@ lpfc_issue_fabric_iocb(struct lpfc_hba *phba, struct lpfc_iocbq *iocb)
 		ret = lpfc_sli_issue_iocb(phba, LPFC_ELS_RING, iocb, 0);
 
 		if (ret == IOCB_ERROR) {
-			iocb->iocb_cmpl = iocb->fabric_iocb_cmpl;
-			iocb->fabric_iocb_cmpl = NULL;
-			iocb->iocb_flag &= ~LPFC_IO_FABRIC;
+			iocb->cmd_cmpl = iocb->fabric_cmd_cmpl;
+			iocb->fabric_cmd_cmpl = NULL;
+			iocb->cmd_flag &= ~LPFC_IO_FABRIC;
 			atomic_dec(&phba->fabric_iocb_count);
 		}
 	} else {
@@ -11655,7 +11654,7 @@ int lpfc_issue_els_qfpa(struct lpfc_vport *vport)
 	*((u32 *)(pcmd)) = ELS_CMD_QFPA;
 	pcmd += 4;
 
-	elsiocb->iocb_cmpl = lpfc_cmpl_els_qfpa;
+	elsiocb->cmd_cmpl = lpfc_cmpl_els_qfpa;
 
 	elsiocb->context1 = lpfc_nlp_get(ndlp);
 	if (!elsiocb->context1) {
@@ -11738,7 +11737,7 @@ lpfc_vmid_uvem(struct lpfc_vport *vport,
 	}
 	inst_desc->word6 = cpu_to_be32(inst_desc->word6);
 
-	elsiocb->iocb_cmpl = lpfc_cmpl_els_uvem;
+	elsiocb->cmd_cmpl = lpfc_cmpl_els_uvem;
 
 	elsiocb->context1 = lpfc_nlp_get(ndlp);
 	if (!elsiocb->context1) {
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 3bb7c2aa949f..4bb0a15cfcc0 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -5349,6 +5349,7 @@ lpfc_unreg_rpi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 
 			rc = lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT);
 			if (rc == MBX_NOT_FINISHED) {
+				ndlp->nlp_flag &= ~NLP_UNREG_INP;
 				mempool_free(mbox, phba->mbox_mem_pool);
 				acc_plogi = 1;
 			}
diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h
index 824fc8c08840..215fbf1c777e 100644
--- a/drivers/scsi/lpfc/lpfc_hw4.h
+++ b/drivers/scsi/lpfc/lpfc_hw4.h
@@ -60,6 +60,13 @@
 	((ptr)->name##_WORD = ((((value) & name##_MASK) << name##_SHIFT) | \
 		 ((ptr)->name##_WORD & ~(name##_MASK << name##_SHIFT))))
 
+#define get_wqe_reqtag(x)	(((x)->wqe.words[9] >>  0) & 0xFFFF)
+
+#define get_job_ulpword(x, y)	((x)->iocb.un.ulpWord[y])
+
+#define set_job_ulpstatus(x, y)	bf_set(lpfc_wcqe_c_status, &(x)->wcqe_cmpl, y)
+#define set_job_ulpword4(x, y)	((&(x)->wcqe_cmpl)->parameter = y)
+
 struct dma_address {
 	uint32_t addr_lo;
 	uint32_t addr_hi;
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index a2694fb32b5d..33e33fff8986 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -982,7 +982,7 @@ lpfc_hba_clean_txcmplq(struct lpfc_hba *phba)
 		spin_lock_irq(&pring->ring_lock);
 		list_for_each_entry_safe(piocb, next_iocb,
 					 &pring->txcmplq, list)
-			piocb->iocb_flag &= ~LPFC_IO_ON_TXCMPLQ;
+			piocb->cmd_flag &= ~LPFC_IO_ON_TXCMPLQ;
 		list_splice_init(&pring->txcmplq, &completions);
 		pring->txcmplq_cnt = 0;
 		spin_unlock_irq(&pring->ring_lock);
@@ -1606,6 +1606,11 @@ void
 lpfc_sli4_offline_eratt(struct lpfc_hba *phba)
 {
 	spin_lock_irq(&phba->hbalock);
+	if (phba->link_state == LPFC_HBA_ERROR &&
+	    phba->hba_flag & HBA_PCI_ERR) {
+		spin_unlock_irq(&phba->hbalock);
+		return;
+	}
 	phba->link_state = LPFC_HBA_ERROR;
 	spin_unlock_irq(&phba->hbalock);
 
@@ -1945,7 +1950,6 @@ lpfc_handle_eratt_s4(struct lpfc_hba *phba)
 	if (pci_channel_offline(phba->pcidev)) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT,
 				"3166 pci channel is offline\n");
-		lpfc_sli4_offline_eratt(phba);
 		return;
 	}
 
@@ -2639,7 +2643,7 @@ lpfc_get_hba_model_desc(struct lpfc_hba *phba, uint8_t *mdp, uint8_t *descp)
 }
 
 /**
- * lpfc_post_buffer - Post IOCB(s) with DMA buffer descriptor(s) to a IOCB ring
+ * lpfc_sli3_post_buffer - Post IOCB(s) with DMA buffer descriptor(s) to a IOCB ring
  * @phba: pointer to lpfc hba data structure.
  * @pring: pointer to a IOCB ring.
  * @cnt: the number of IOCBs to be posted to the IOCB ring.
@@ -2651,7 +2655,7 @@ lpfc_get_hba_model_desc(struct lpfc_hba *phba, uint8_t *mdp, uint8_t *descp)
  *   The number of IOCBs NOT able to be posted to the IOCB ring.
  **/
 int
-lpfc_post_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring, int cnt)
+lpfc_sli3_post_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring, int cnt)
 {
 	IOCB_t *icmd;
 	struct lpfc_iocbq *iocb;
@@ -2757,7 +2761,7 @@ lpfc_post_rcv_buf(struct lpfc_hba *phba)
 	struct lpfc_sli *psli = &phba->sli;
 
 	/* Ring 0, ELS / CT buffers */
-	lpfc_post_buffer(phba, &psli->sli3_ring[LPFC_ELS_RING], LPFC_BUF_RING0);
+	lpfc_sli3_post_buffer(phba, &psli->sli3_ring[LPFC_ELS_RING], LPFC_BUF_RING0);
 	/* Ring 2 - FCP no buffers needed */
 
 	return 0;
@@ -3643,6 +3647,7 @@ lpfc_offline_prep(struct lpfc_hba *phba, int mbx_action)
 	struct lpfc_vport **vports;
 	struct Scsi_Host *shost;
 	int i;
+	int offline = 0;
 
 	if (vport->fc_flag & FC_OFFLINE_MODE)
 		return;
@@ -3651,6 +3656,8 @@ lpfc_offline_prep(struct lpfc_hba *phba, int mbx_action)
 
 	lpfc_linkdown(phba);
 
+	offline =  pci_channel_offline(phba->pcidev);
+
 	/* Issue an unreg_login to all nodes on all vports */
 	vports = lpfc_create_vport_work_array(phba);
 	if (vports != NULL) {
@@ -3673,7 +3680,14 @@ lpfc_offline_prep(struct lpfc_hba *phba, int mbx_action)
 				ndlp->nlp_flag &= ~NLP_NPR_ADISC;
 				spin_unlock_irq(&ndlp->lock);
 
-				lpfc_unreg_rpi(vports[i], ndlp);
+				if (offline) {
+					spin_lock_irq(&ndlp->lock);
+					ndlp->nlp_flag &= ~(NLP_UNREG_INP |
+							    NLP_RPI_REGISTERED);
+					spin_unlock_irq(&ndlp->lock);
+				} else {
+					lpfc_unreg_rpi(vports[i], ndlp);
+				}
 				/*
 				 * Whenever an SLI4 port goes offline, free the
 				 * RPI. Get a new RPI when the adapter port
@@ -4201,8 +4215,7 @@ lpfc_io_buf_replenish(struct lpfc_hba *phba, struct list_head *cbuf)
 			qp = &phba->sli4_hba.hdwq[idx];
 			lpfc_cmd->hdwq_no = idx;
 			lpfc_cmd->hdwq = qp;
-			lpfc_cmd->cur_iocbq.wqe_cmpl = NULL;
-			lpfc_cmd->cur_iocbq.iocb_cmpl = NULL;
+			lpfc_cmd->cur_iocbq.cmd_cmpl = NULL;
 			spin_lock(&qp->io_buf_list_put_lock);
 			list_add_tail(&lpfc_cmd->list,
 				      &qp->lpfc_io_buf_list_put);
@@ -7880,7 +7893,7 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 	/* Allocate device driver memory */
 	rc = lpfc_mem_alloc(phba, SGL_ALIGN_SZ);
 	if (rc)
-		return -ENOMEM;
+		goto out_destroy_workqueue;
 
 	/* IF Type 2 ports get initialized now. */
 	if (bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) >=
@@ -8296,6 +8309,9 @@ out_free_bsmbx:
 	lpfc_destroy_bootstrap_mbox(phba);
 out_free_mem:
 	lpfc_mem_free(phba);
+out_destroy_workqueue:
+	destroy_workqueue(phba->wq);
+	phba->wq = NULL;
 	return rc;
 }
 
@@ -11951,7 +11967,7 @@ lpfc_sli_enable_msi(struct lpfc_hba *phba)
 	rc = pci_enable_msi(phba->pcidev);
 	if (!rc)
 		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
-				"0462 PCI enable MSI mode success.\n");
+				"0012 PCI enable MSI mode success.\n");
 	else {
 		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
 				"0471 PCI enable MSI mode failed (%d)\n", rc);
@@ -14070,6 +14086,10 @@ lpfc_pci_resume_one_s3(struct device *dev_d)
 		return error;
 	}
 
+	/* Init cpu_map array */
+	lpfc_cpu_map_array_init(phba);
+	/* Init hba_eq_hdl array */
+	lpfc_hba_eq_hdl_array_init(phba);
 	/* Configure and enable interrupt */
 	intr_mode = lpfc_sli_enable_intr(phba, phba->intr_mode);
 	if (intr_mode == LPFC_INTR_ERROR) {
@@ -15023,14 +15043,17 @@ lpfc_io_error_detected_s4(struct pci_dev *pdev, pci_channel_state_t state)
 		lpfc_sli4_prep_dev_for_recover(phba);
 		return PCI_ERS_RESULT_CAN_RECOVER;
 	case pci_channel_io_frozen:
+		phba->hba_flag |= HBA_PCI_ERR;
 		/* Fatal error, prepare for slot reset */
 		lpfc_sli4_prep_dev_for_reset(phba);
 		return PCI_ERS_RESULT_NEED_RESET;
 	case pci_channel_io_perm_failure:
+		phba->hba_flag |= HBA_PCI_ERR;
 		/* Permanent failure, prepare for device down */
 		lpfc_sli4_prep_dev_for_perm_failure(phba);
 		return PCI_ERS_RESULT_DISCONNECT;
 	default:
+		phba->hba_flag |= HBA_PCI_ERR;
 		/* Unknown state, prepare and request slot reset */
 		lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT,
 				"2825 Unknown PCI error state: x%x\n", state);
@@ -15074,6 +15097,7 @@ lpfc_io_slot_reset_s4(struct pci_dev *pdev)
 
 	pci_restore_state(pdev);
 
+	phba->hba_flag &= ~HBA_PCI_ERR;
 	/*
 	 * As the new kernel behavior of pci_restore_state() API call clears
 	 * device saved_state flag, need to save the restored state again.
@@ -15098,6 +15122,7 @@ lpfc_io_slot_reset_s4(struct pci_dev *pdev)
 		return PCI_ERS_RESULT_DISCONNECT;
 	} else
 		phba->intr_mode = intr_mode;
+	lpfc_cpu_affinity_check(phba, phba->cfg_irq_chann);
 
 	/* Log the current active interrupt mode */
 	lpfc_log_intr_mode(phba, phba->intr_mode);
@@ -15299,6 +15324,10 @@ lpfc_io_error_detected(struct pci_dev *pdev, pci_channel_state_t state)
 	struct lpfc_hba *phba = ((struct lpfc_vport *)shost->hostdata)->phba;
 	pci_ers_result_t rc = PCI_ERS_RESULT_DISCONNECT;
 
+	if (phba->link_state == LPFC_HBA_ERROR &&
+	    phba->hba_flag & HBA_IOQ_FLUSH)
+		return PCI_ERS_RESULT_NEED_RESET;
+
 	switch (phba->pci_dev_grp) {
 	case LPFC_PCI_DEV_LP:
 		rc = lpfc_io_error_detected_s3(pdev, state);
diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index 2bd35a7424c2..e788610bc996 100644
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -2139,9 +2139,9 @@ lpfc_cmpl_prli_prli_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	npr = NULL;
 	nvpr = NULL;
 	temp_ptr = lpfc_check_elscmpl_iocb(phba, cmdiocb, rspiocb);
-	if (cmdiocb->iocb_flag & LPFC_PRLI_FCP_REQ)
+	if (cmdiocb->cmd_flag & LPFC_PRLI_FCP_REQ)
 		npr = (PRLI *) temp_ptr;
-	else if (cmdiocb->iocb_flag & LPFC_PRLI_NVME_REQ)
+	else if (cmdiocb->cmd_flag & LPFC_PRLI_NVME_REQ)
 		nvpr = (struct lpfc_nvme_prli *) temp_ptr;
 
 	irsp = &rspiocb->iocb;
diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
index 4fb3dc5092f5..c74b2187dbad 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.c
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -352,11 +352,12 @@ __lpfc_nvme_ls_req_cmp(struct lpfc_hba *phba,  struct lpfc_vport *vport,
 
 static void
 lpfc_nvme_ls_req_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
-		       struct lpfc_wcqe_complete *wcqe)
+		     struct lpfc_iocbq *rspwqe)
 {
 	struct lpfc_vport *vport = cmdwqe->vport;
 	struct lpfc_nvme_lport *lport;
 	uint32_t status;
+	struct lpfc_wcqe_complete *wcqe = &rspwqe->wcqe_cmpl;
 
 	status = bf_get(lpfc_wcqe_c_status, wcqe) & LPFC_IOCB_STATUS_MASK;
 
@@ -380,7 +381,7 @@ lpfc_nvme_gen_req(struct lpfc_vport *vport, struct lpfc_dmabuf *bmp,
 		  struct lpfc_dmabuf *inp,
 		  struct nvmefc_ls_req *pnvme_lsreq,
 		  void (*cmpl)(struct lpfc_hba *, struct lpfc_iocbq *,
-			       struct lpfc_wcqe_complete *),
+			       struct lpfc_iocbq *),
 		  struct lpfc_nodelist *ndlp, uint32_t num_entry,
 		  uint32_t tmo, uint8_t retry)
 {
@@ -401,7 +402,7 @@ lpfc_nvme_gen_req(struct lpfc_vport *vport, struct lpfc_dmabuf *bmp,
 	memset(wqe, 0, sizeof(union lpfc_wqe));
 
 	genwqe->context3 = (uint8_t *)bmp;
-	genwqe->iocb_flag |= LPFC_IO_NVME_LS;
+	genwqe->cmd_flag |= LPFC_IO_NVME_LS;
 
 	/* Save for completion so we can release these resources */
 	genwqe->context1 = lpfc_nlp_get(ndlp);
@@ -432,7 +433,7 @@ lpfc_nvme_gen_req(struct lpfc_vport *vport, struct lpfc_dmabuf *bmp,
 			first_len = xmit_len;
 	}
 
-	genwqe->rsvd2 = num_entry;
+	genwqe->num_bdes = num_entry;
 	genwqe->hba_wqidx = 0;
 
 	/* Words 0 - 2 */
@@ -483,8 +484,7 @@ lpfc_nvme_gen_req(struct lpfc_vport *vport, struct lpfc_dmabuf *bmp,
 
 
 	/* Issue GEN REQ WQE for NPORT <did> */
-	genwqe->wqe_cmpl = cmpl;
-	genwqe->iocb_cmpl = NULL;
+	genwqe->cmd_cmpl = cmpl;
 	genwqe->drvrTimeout = tmo + LPFC_DRVR_TIMEOUT;
 	genwqe->vport = vport;
 	genwqe->retry = retry;
@@ -534,7 +534,7 @@ __lpfc_nvme_ls_req(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		      struct nvmefc_ls_req *pnvme_lsreq,
 		      void (*gen_req_cmp)(struct lpfc_hba *phba,
 				struct lpfc_iocbq *cmdwqe,
-				struct lpfc_wcqe_complete *wcqe))
+				struct lpfc_iocbq *rspwqe))
 {
 	struct lpfc_dmabuf *bmp;
 	struct ulp_bde64 *bpl;
@@ -722,7 +722,7 @@ __lpfc_nvme_ls_abort(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	spin_lock(&pring->ring_lock);
 	list_for_each_entry_safe(wqe, next_wqe, &pring->txcmplq, list) {
 		if (wqe->context2 == pnvme_lsreq) {
-			wqe->iocb_flag |= LPFC_DRIVER_ABORTED;
+			wqe->cmd_flag |= LPFC_DRIVER_ABORTED;
 			foundit = true;
 			break;
 		}
@@ -906,7 +906,7 @@ lpfc_nvme_adj_fcp_sgls(struct lpfc_vport *vport,
 
 
 /*
- * lpfc_nvme_io_cmd_wqe_cmpl - Complete an NVME-over-FCP IO
+ * lpfc_nvme_io_cmd_cmpl - Complete an NVME-over-FCP IO
  *
  * Driver registers this routine as it io request handler.  This
  * routine issues an fcp WQE with data from the @lpfc_nvme_fcpreq
@@ -917,11 +917,12 @@ lpfc_nvme_adj_fcp_sgls(struct lpfc_vport *vport,
  *   TODO: What are the failure codes.
  **/
 static void
-lpfc_nvme_io_cmd_wqe_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn,
-			  struct lpfc_wcqe_complete *wcqe)
+lpfc_nvme_io_cmd_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn,
+		      struct lpfc_iocbq *pwqeOut)
 {
 	struct lpfc_io_buf *lpfc_ncmd =
 		(struct lpfc_io_buf *)pwqeIn->context1;
+	struct lpfc_wcqe_complete *wcqe = &pwqeOut->wcqe_cmpl;
 	struct lpfc_vport *vport = pwqeIn->vport;
 	struct nvmefc_fcp_req *nCmd;
 	struct nvme_fc_ersp_iu *ep;
@@ -937,6 +938,7 @@ lpfc_nvme_io_cmd_wqe_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn,
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
 	int cpu;
 #endif
+	int offline = 0;
 
 	/* Sanity check on return of outstanding command */
 	if (!lpfc_ncmd) {
@@ -1098,11 +1100,12 @@ out_err:
 			nCmd->transferred_length = 0;
 			nCmd->rcv_rsplen = 0;
 			nCmd->status = NVME_SC_INTERNAL;
+			offline = pci_channel_offline(vport->phba->pcidev);
 		}
 	}
 
 	/* pick up SLI4 exhange busy condition */
-	if (bf_get(lpfc_wcqe_c_xb, wcqe))
+	if (bf_get(lpfc_wcqe_c_xb, wcqe) && !offline)
 		lpfc_ncmd->flags |= LPFC_SBUF_XBUSY;
 	else
 		lpfc_ncmd->flags &= ~LPFC_SBUF_XBUSY;
@@ -1871,7 +1874,7 @@ lpfc_nvme_fcp_abort(struct nvme_fc_local_port *pnvme_lport,
 	}
 
 	/* Don't abort IOs no longer on the pending queue. */
-	if (!(nvmereq_wqe->iocb_flag & LPFC_IO_ON_TXCMPLQ)) {
+	if (!(nvmereq_wqe->cmd_flag & LPFC_IO_ON_TXCMPLQ)) {
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT,
 				 "6142 NVME IO req x%px not queued - skipping "
 				 "abort req xri x%x\n",
@@ -1885,7 +1888,7 @@ lpfc_nvme_fcp_abort(struct nvme_fc_local_port *pnvme_lport,
 			 nvmereq_wqe->hba_wqidx, pnvme_rport->port_id);
 
 	/* Outstanding abort is in progress */
-	if (nvmereq_wqe->iocb_flag & LPFC_DRIVER_ABORTED) {
+	if (nvmereq_wqe->cmd_flag & LPFC_DRIVER_ABORTED) {
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT,
 				 "6144 Outstanding NVME I/O Abort Request "
 				 "still pending on nvme_fcreq x%px, "
@@ -1980,8 +1983,8 @@ lpfc_get_nvme_buf(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp,
 		/* Setup key fields in buffer that may have been changed
 		 * if other protocols used this buffer.
 		 */
-		pwqeq->iocb_flag = LPFC_IO_NVME;
-		pwqeq->wqe_cmpl = lpfc_nvme_io_cmd_wqe_cmpl;
+		pwqeq->cmd_flag = LPFC_IO_NVME;
+		pwqeq->cmd_cmpl = lpfc_nvme_io_cmd_cmpl;
 		lpfc_ncmd->start_time = jiffies;
 		lpfc_ncmd->flags = 0;
 
@@ -2174,6 +2177,10 @@ lpfc_nvme_lport_unreg_wait(struct lpfc_vport *vport,
 			abts_nvme = 0;
 			for (i = 0; i < phba->cfg_hdw_queue; i++) {
 				qp = &phba->sli4_hba.hdwq[i];
+				if (!vport || !vport->localport ||
+				    !qp || !qp->io_wq)
+					return;
+
 				pring = qp->io_wq->pring;
 				if (!pring)
 					continue;
@@ -2181,6 +2188,10 @@ lpfc_nvme_lport_unreg_wait(struct lpfc_vport *vport,
 				abts_scsi += qp->abts_scsi_io_bufs;
 				abts_nvme += qp->abts_nvme_io_bufs;
 			}
+			if (!vport || !vport->localport ||
+			    vport->phba->hba_flag & HBA_PCI_ERR)
+				return;
+
 			lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT,
 					 "6176 Lport x%px Localport x%px wait "
 					 "timed out. Pending %d [%d:%d]. "
@@ -2220,6 +2231,8 @@ lpfc_nvme_destroy_localport(struct lpfc_vport *vport)
 		return;
 
 	localport = vport->localport;
+	if (!localport)
+		return;
 	lport = (struct lpfc_nvme_lport *)localport->private;
 
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME,
@@ -2536,7 +2549,8 @@ lpfc_nvme_unregister_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 		 * return values is ignored.  The upcall is a courtesy to the
 		 * transport.
 		 */
-		if (vport->load_flag & FC_UNLOADING)
+		if (vport->load_flag & FC_UNLOADING ||
+		    unlikely(vport->phba->hba_flag & HBA_PCI_ERR))
 			(void)nvme_fc_set_remoteport_devloss(remoteport, 0);
 
 		ret = nvme_fc_unregister_remoteport(remoteport);
@@ -2565,6 +2579,42 @@ lpfc_nvme_unregister_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 }
 
 /**
+ * lpfc_sli4_nvme_pci_offline_aborted - Fast-path process of NVME xri abort
+ * @phba: pointer to lpfc hba data structure.
+ * @lpfc_ncmd: The nvme job structure for the request being aborted.
+ *
+ * This routine is invoked by the worker thread to process a SLI4 fast-path
+ * NVME aborted xri.  Aborted NVME IO commands are completed to the transport
+ * here.
+ **/
+void
+lpfc_sli4_nvme_pci_offline_aborted(struct lpfc_hba *phba,
+				   struct lpfc_io_buf *lpfc_ncmd)
+{
+	struct nvmefc_fcp_req *nvme_cmd = NULL;
+
+	lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+			"6533 %s nvme_cmd %p tag x%x abort complete and "
+			"xri released\n", __func__,
+			lpfc_ncmd->nvmeCmd,
+			lpfc_ncmd->cur_iocbq.iotag);
+
+	/* Aborted NVME commands are required to not complete
+	 * before the abort exchange command fully completes.
+	 * Once completed, it is available via the put list.
+	 */
+	if (lpfc_ncmd->nvmeCmd) {
+		nvme_cmd = lpfc_ncmd->nvmeCmd;
+		nvme_cmd->transferred_length = 0;
+		nvme_cmd->rcv_rsplen = 0;
+		nvme_cmd->status = NVME_SC_INTERNAL;
+		nvme_cmd->done(nvme_cmd);
+		lpfc_ncmd->nvmeCmd = NULL;
+	}
+	lpfc_release_nvme_buf(phba, lpfc_ncmd);
+}
+
+/**
  * lpfc_sli4_nvme_xri_aborted - Fast-path process of NVME xri abort
  * @phba: pointer to lpfc hba data structure.
  * @axri: pointer to the fcp xri abort wcqe structure.
@@ -2700,6 +2750,7 @@ lpfc_nvme_cancel_iocb(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn,
 	if (phba->sli.sli_flag & LPFC_SLI_ACTIVE)
 		bf_set(lpfc_wcqe_c_xb, wcqep, 1);
 
-	(pwqeIn->wqe_cmpl)(phba, pwqeIn, wcqep);
+	memcpy(&pwqeIn->wcqe_cmpl, wcqep, sizeof(*wcqep));
+	(pwqeIn->cmd_cmpl)(phba, pwqeIn, pwqeIn);
 #endif
 }
diff --git a/drivers/scsi/lpfc/lpfc_nvme.h b/drivers/scsi/lpfc/lpfc_nvme.h
index cc54ffb5c205..d7698977725e 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.h
+++ b/drivers/scsi/lpfc/lpfc_nvme.h
@@ -234,7 +234,7 @@ int __lpfc_nvme_ls_req(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		struct nvmefc_ls_req *pnvme_lsreq,
 		void (*gen_req_cmp)(struct lpfc_hba *phba,
 				struct lpfc_iocbq *cmdwqe,
-				struct lpfc_wcqe_complete *wcqe));
+				struct lpfc_iocbq *rspwqe));
 void __lpfc_nvme_ls_req_cmp(struct lpfc_hba *phba,  struct lpfc_vport *vport,
 		struct lpfc_iocbq *cmdwqe, struct lpfc_wcqe_complete *wcqe);
 int __lpfc_nvme_ls_abort(struct lpfc_vport *vport,
@@ -248,6 +248,6 @@ int __lpfc_nvme_xmt_ls_rsp(struct lpfc_async_xchg_ctx *axchg,
 			struct nvmefc_ls_rsp *ls_rsp,
 			void (*xmt_ls_rsp_cmp)(struct lpfc_hba *phba,
 				struct lpfc_iocbq *cmdwqe,
-				struct lpfc_wcqe_complete *wcqe));
+				struct lpfc_iocbq *rspwqe));
 void __lpfc_nvme_xmt_ls_rsp_cmp(struct lpfc_hba *phba,
-		struct lpfc_iocbq *cmdwqe, struct lpfc_wcqe_complete *wcqe);
+		struct lpfc_iocbq *cmdwqe, struct lpfc_iocbq *rspwqe);
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c
index 6e3dd0b9bcfa..5188cc8e2413 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.c
+++ b/drivers/scsi/lpfc/lpfc_nvmet.c
@@ -285,7 +285,7 @@ lpfc_nvmet_defer_release(struct lpfc_hba *phba,
  *         transmission of an NVME LS response.
  * @phba: Pointer to HBA context object.
  * @cmdwqe: Pointer to driver command WQE object.
- * @wcqe: Pointer to driver response CQE object.
+ * @rspwqe: Pointer to driver response WQE object.
  *
  * The function is called from SLI ring event handler with no
  * lock held. The function frees memory resources used for the command
@@ -293,9 +293,10 @@ lpfc_nvmet_defer_release(struct lpfc_hba *phba,
  **/
 void
 __lpfc_nvme_xmt_ls_rsp_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
-			   struct lpfc_wcqe_complete *wcqe)
+			   struct lpfc_iocbq *rspwqe)
 {
 	struct lpfc_async_xchg_ctx *axchg = cmdwqe->context2;
+	struct lpfc_wcqe_complete *wcqe = &rspwqe->wcqe_cmpl;
 	struct nvmefc_ls_rsp *ls_rsp = &axchg->ls_rsp;
 	uint32_t status, result;
 
@@ -331,7 +332,7 @@ __lpfc_nvme_xmt_ls_rsp_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
  * lpfc_nvmet_xmt_ls_rsp_cmp - Completion handler for LS Response
  * @phba: Pointer to HBA context object.
  * @cmdwqe: Pointer to driver command WQE object.
- * @wcqe: Pointer to driver response CQE object.
+ * @rspwqe: Pointer to driver response WQE object.
  *
  * The function is called from SLI ring event handler with no
  * lock held. This function is the completion handler for NVME LS commands
@@ -340,10 +341,11 @@ __lpfc_nvme_xmt_ls_rsp_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
  **/
 static void
 lpfc_nvmet_xmt_ls_rsp_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
-			  struct lpfc_wcqe_complete *wcqe)
+			  struct lpfc_iocbq *rspwqe)
 {
 	struct lpfc_nvmet_tgtport *tgtp;
 	uint32_t status, result;
+	struct lpfc_wcqe_complete *wcqe = &rspwqe->wcqe_cmpl;
 
 	if (!phba->targetport)
 		goto finish;
@@ -365,7 +367,7 @@ lpfc_nvmet_xmt_ls_rsp_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
 	}
 
 finish:
-	__lpfc_nvme_xmt_ls_rsp_cmp(phba, cmdwqe, wcqe);
+	__lpfc_nvme_xmt_ls_rsp_cmp(phba, cmdwqe, rspwqe);
 }
 
 /**
@@ -707,7 +709,7 @@ out:
  * lpfc_nvmet_xmt_fcp_op_cmp - Completion handler for FCP Response
  * @phba: Pointer to HBA context object.
  * @cmdwqe: Pointer to driver command WQE object.
- * @wcqe: Pointer to driver response CQE object.
+ * @rspwqe: Pointer to driver response WQE object.
  *
  * The function is called from SLI ring event handler with no
  * lock held. This function is the completion handler for NVME FCP commands
@@ -715,12 +717,13 @@ out:
  **/
 static void
 lpfc_nvmet_xmt_fcp_op_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
-			  struct lpfc_wcqe_complete *wcqe)
+			  struct lpfc_iocbq *rspwqe)
 {
 	struct lpfc_nvmet_tgtport *tgtp;
 	struct nvmefc_tgt_fcp_req *rsp;
 	struct lpfc_async_xchg_ctx *ctxp;
 	uint32_t status, result, op, start_clean, logerr;
+	struct lpfc_wcqe_complete *wcqe = &rspwqe->wcqe_cmpl;
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
 	int id;
 #endif
@@ -817,7 +820,7 @@ lpfc_nvmet_xmt_fcp_op_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
 		/* lpfc_nvmet_xmt_fcp_release() will recycle the context */
 	} else {
 		ctxp->entry_cnt++;
-		start_clean = offsetof(struct lpfc_iocbq, iocb_flag);
+		start_clean = offsetof(struct lpfc_iocbq, cmd_flag);
 		memset(((char *)cmdwqe) + start_clean, 0,
 		       (sizeof(struct lpfc_iocbq) - start_clean));
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
@@ -862,7 +865,7 @@ __lpfc_nvme_xmt_ls_rsp(struct lpfc_async_xchg_ctx *axchg,
 			struct nvmefc_ls_rsp *ls_rsp,
 			void (*xmt_ls_rsp_cmp)(struct lpfc_hba *phba,
 				struct lpfc_iocbq *cmdwqe,
-				struct lpfc_wcqe_complete *wcqe))
+				struct lpfc_iocbq *rspwqe))
 {
 	struct lpfc_hba *phba = axchg->phba;
 	struct hbq_dmabuf *nvmebuf = (struct hbq_dmabuf *)axchg->rqb_buffer;
@@ -898,7 +901,7 @@ __lpfc_nvme_xmt_ls_rsp(struct lpfc_async_xchg_ctx *axchg,
 	}
 
 	/* Save numBdes for bpl2sgl */
-	nvmewqeq->rsvd2 = 1;
+	nvmewqeq->num_bdes = 1;
 	nvmewqeq->hba_wqidx = 0;
 	nvmewqeq->context3 = &dmabuf;
 	dmabuf.virt = &bpl;
@@ -913,8 +916,7 @@ __lpfc_nvme_xmt_ls_rsp(struct lpfc_async_xchg_ctx *axchg,
 	 * be referenced after it returns back to this routine.
 	 */
 
-	nvmewqeq->wqe_cmpl = xmt_ls_rsp_cmp;
-	nvmewqeq->iocb_cmpl = NULL;
+	nvmewqeq->cmd_cmpl = xmt_ls_rsp_cmp;
 	nvmewqeq->context2 = axchg;
 
 	lpfc_nvmeio_data(phba, "NVMEx LS RSP: xri x%x wqidx x%x len x%x\n",
@@ -1072,10 +1074,9 @@ lpfc_nvmet_xmt_fcp_op(struct nvmet_fc_target_port *tgtport,
 		goto aerr;
 	}
 
-	nvmewqeq->wqe_cmpl = lpfc_nvmet_xmt_fcp_op_cmp;
-	nvmewqeq->iocb_cmpl = NULL;
+	nvmewqeq->cmd_cmpl = lpfc_nvmet_xmt_fcp_op_cmp;
 	nvmewqeq->context2 = ctxp;
-	nvmewqeq->iocb_flag |=  LPFC_IO_NVMET;
+	nvmewqeq->cmd_flag |=  LPFC_IO_NVMET;
 	ctxp->wqeq->hba_wqidx = rsp->hwqid;
 
 	lpfc_nvmeio_data(phba, "NVMET FCP CMND: xri x%x op x%x len x%x\n",
@@ -1275,7 +1276,7 @@ lpfc_nvmet_defer_rcv(struct nvmet_fc_target_port *tgtport,
  * lpfc_nvmet_ls_req_cmp - completion handler for a nvme ls request
  * @phba: Pointer to HBA context object
  * @cmdwqe: Pointer to driver command WQE object.
- * @wcqe: Pointer to driver response CQE object.
+ * @rspwqe: Pointer to driver response WQE object.
  *
  * This function is the completion handler for NVME LS requests.
  * The function updates any states and statistics, then calls the
@@ -1283,8 +1284,9 @@ lpfc_nvmet_defer_rcv(struct nvmet_fc_target_port *tgtport,
  **/
 static void
 lpfc_nvmet_ls_req_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
-		       struct lpfc_wcqe_complete *wcqe)
+		      struct lpfc_iocbq *rspwqe)
 {
+	struct lpfc_wcqe_complete *wcqe = &rspwqe->wcqe_cmpl;
 	__lpfc_nvme_ls_req_cmp(phba, cmdwqe->vport, cmdwqe, wcqe);
 }
 
@@ -1581,7 +1583,7 @@ lpfc_nvmet_setup_io_context(struct lpfc_hba *phba)
 					"6406 Ran out of NVMET iocb/WQEs\n");
 			return -ENOMEM;
 		}
-		ctx_buf->iocbq->iocb_flag = LPFC_IO_NVMET;
+		ctx_buf->iocbq->cmd_flag = LPFC_IO_NVMET;
 		nvmewqe = ctx_buf->iocbq;
 		wqe = &nvmewqe->wqe;
 
@@ -2027,8 +2029,10 @@ lpfc_nvmet_wqfull_flush(struct lpfc_hba *phba, struct lpfc_queue *wq,
 				list_del(&nvmewqeq->list);
 				spin_unlock_irqrestore(&pring->ring_lock,
 						       iflags);
+				memcpy(&nvmewqeq->wcqe_cmpl, wcqep,
+				       sizeof(*wcqep));
 				lpfc_nvmet_xmt_fcp_op_cmp(phba, nvmewqeq,
-							  wcqep);
+							  nvmewqeq);
 				return;
 			}
 			continue;
@@ -2036,7 +2040,8 @@ lpfc_nvmet_wqfull_flush(struct lpfc_hba *phba, struct lpfc_queue *wq,
 			/* Flush all IOs */
 			list_del(&nvmewqeq->list);
 			spin_unlock_irqrestore(&pring->ring_lock, iflags);
-			lpfc_nvmet_xmt_fcp_op_cmp(phba, nvmewqeq, wcqep);
+			memcpy(&nvmewqeq->wcqe_cmpl, wcqep, sizeof(*wcqep));
+			lpfc_nvmet_xmt_fcp_op_cmp(phba, nvmewqeq, nvmewqeq);
 			spin_lock_irqsave(&pring->ring_lock, iflags);
 		}
 	}
@@ -2676,7 +2681,7 @@ lpfc_nvmet_prep_ls_wqe(struct lpfc_hba *phba,
 	nvmewqe->retry = 1;
 	nvmewqe->vport = phba->pport;
 	nvmewqe->drvrTimeout = (phba->fc_ratov * 3) + LPFC_DRVR_TIMEOUT;
-	nvmewqe->iocb_flag |= LPFC_IO_NVME_LS;
+	nvmewqe->cmd_flag |= LPFC_IO_NVME_LS;
 
 	/* Xmit NVMET response to remote NPORT <did> */
 	lpfc_printf_log(phba, KERN_INFO, LOG_NVME_DISC,
@@ -3033,7 +3038,7 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba,
  * lpfc_nvmet_sol_fcp_abort_cmp - Completion handler for ABTS
  * @phba: Pointer to HBA context object.
  * @cmdwqe: Pointer to driver command WQE object.
- * @wcqe: Pointer to driver response CQE object.
+ * @rspwqe: Pointer to driver response WQE object.
  *
  * The function is called from SLI ring event handler with no
  * lock held. This function is the completion handler for NVME ABTS for FCP cmds
@@ -3041,13 +3046,14 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba,
  **/
 static void
 lpfc_nvmet_sol_fcp_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
-			     struct lpfc_wcqe_complete *wcqe)
+			     struct lpfc_iocbq *rspwqe)
 {
 	struct lpfc_async_xchg_ctx *ctxp;
 	struct lpfc_nvmet_tgtport *tgtp;
 	uint32_t result;
 	unsigned long flags;
 	bool released = false;
+	struct lpfc_wcqe_complete *wcqe = &rspwqe->wcqe_cmpl;
 
 	ctxp = cmdwqe->context2;
 	result = wcqe->parameter;
@@ -3102,7 +3108,7 @@ lpfc_nvmet_sol_fcp_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
  * lpfc_nvmet_unsol_fcp_abort_cmp - Completion handler for ABTS
  * @phba: Pointer to HBA context object.
  * @cmdwqe: Pointer to driver command WQE object.
- * @wcqe: Pointer to driver response CQE object.
+ * @rspwqe: Pointer to driver response WQE object.
  *
  * The function is called from SLI ring event handler with no
  * lock held. This function is the completion handler for NVME ABTS for FCP cmds
@@ -3110,13 +3116,14 @@ lpfc_nvmet_sol_fcp_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
  **/
 static void
 lpfc_nvmet_unsol_fcp_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
-			       struct lpfc_wcqe_complete *wcqe)
+			       struct lpfc_iocbq *rspwqe)
 {
 	struct lpfc_async_xchg_ctx *ctxp;
 	struct lpfc_nvmet_tgtport *tgtp;
 	unsigned long flags;
 	uint32_t result;
 	bool released = false;
+	struct lpfc_wcqe_complete *wcqe = &rspwqe->wcqe_cmpl;
 
 	ctxp = cmdwqe->context2;
 	result = wcqe->parameter;
@@ -3183,7 +3190,7 @@ lpfc_nvmet_unsol_fcp_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
  * lpfc_nvmet_xmt_ls_abort_cmp - Completion handler for ABTS
  * @phba: Pointer to HBA context object.
  * @cmdwqe: Pointer to driver command WQE object.
- * @wcqe: Pointer to driver response CQE object.
+ * @rspwqe: Pointer to driver response WQE object.
  *
  * The function is called from SLI ring event handler with no
  * lock held. This function is the completion handler for NVME ABTS for LS cmds
@@ -3191,11 +3198,12 @@ lpfc_nvmet_unsol_fcp_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
  **/
 static void
 lpfc_nvmet_xmt_ls_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
-			    struct lpfc_wcqe_complete *wcqe)
+			    struct lpfc_iocbq *rspwqe)
 {
 	struct lpfc_async_xchg_ctx *ctxp;
 	struct lpfc_nvmet_tgtport *tgtp;
 	uint32_t result;
+	struct lpfc_wcqe_complete *wcqe = &rspwqe->wcqe_cmpl;
 
 	ctxp = cmdwqe->context2;
 	result = wcqe->parameter;
@@ -3319,7 +3327,7 @@ lpfc_nvmet_unsol_issue_abort(struct lpfc_hba *phba,
 	abts_wqeq->context1 = ndlp;
 	abts_wqeq->context2 = ctxp;
 	abts_wqeq->context3 = NULL;
-	abts_wqeq->rsvd2 = 0;
+	abts_wqeq->num_bdes = 0;
 	/* hba_wqidx should already be setup from command we are aborting */
 	abts_wqeq->iocb.ulpCommand = CMD_XMIT_SEQUENCE64_CR;
 	abts_wqeq->iocb.ulpLe = 1;
@@ -3448,7 +3456,7 @@ lpfc_nvmet_sol_fcp_issue_abort(struct lpfc_hba *phba,
 	}
 
 	/* Outstanding abort is in progress */
-	if (abts_wqeq->iocb_flag & LPFC_DRIVER_ABORTED) {
+	if (abts_wqeq->cmd_flag & LPFC_DRIVER_ABORTED) {
 		spin_unlock_irqrestore(&phba->hbalock, flags);
 		atomic_inc(&tgtp->xmt_abort_rsp_error);
 		lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT,
@@ -3463,15 +3471,14 @@ lpfc_nvmet_sol_fcp_issue_abort(struct lpfc_hba *phba,
 	}
 
 	/* Ready - mark outstanding as aborted by driver. */
-	abts_wqeq->iocb_flag |= LPFC_DRIVER_ABORTED;
+	abts_wqeq->cmd_flag |= LPFC_DRIVER_ABORTED;
 
 	lpfc_nvmet_prep_abort_wqe(abts_wqeq, ctxp->wqeq->sli4_xritag, opt);
 
 	/* ABTS WQE must go to the same WQ as the WQE to be aborted */
 	abts_wqeq->hba_wqidx = ctxp->wqeq->hba_wqidx;
-	abts_wqeq->wqe_cmpl = lpfc_nvmet_sol_fcp_abort_cmp;
-	abts_wqeq->iocb_cmpl = NULL;
-	abts_wqeq->iocb_flag |= LPFC_IO_NVME;
+	abts_wqeq->cmd_cmpl = lpfc_nvmet_sol_fcp_abort_cmp;
+	abts_wqeq->cmd_flag |= LPFC_IO_NVME;
 	abts_wqeq->context2 = ctxp;
 	abts_wqeq->vport = phba->pport;
 	if (!ctxp->hdwq)
@@ -3528,9 +3535,8 @@ lpfc_nvmet_unsol_fcp_issue_abort(struct lpfc_hba *phba,
 
 	spin_lock_irqsave(&phba->hbalock, flags);
 	abts_wqeq = ctxp->wqeq;
-	abts_wqeq->wqe_cmpl = lpfc_nvmet_unsol_fcp_abort_cmp;
-	abts_wqeq->iocb_cmpl = NULL;
-	abts_wqeq->iocb_flag |= LPFC_IO_NVMET;
+	abts_wqeq->cmd_cmpl = lpfc_nvmet_unsol_fcp_abort_cmp;
+	abts_wqeq->cmd_flag |= LPFC_IO_NVMET;
 	if (!ctxp->hdwq)
 		ctxp->hdwq = &phba->sli4_hba.hdwq[abts_wqeq->hba_wqidx];
 
@@ -3614,9 +3620,8 @@ lpfc_nvme_unsol_ls_issue_abort(struct lpfc_hba *phba,
 	}
 
 	spin_lock_irqsave(&phba->hbalock, flags);
-	abts_wqeq->wqe_cmpl = lpfc_nvmet_xmt_ls_abort_cmp;
-	abts_wqeq->iocb_cmpl = NULL;
-	abts_wqeq->iocb_flag |=  LPFC_IO_NVME_LS;
+	abts_wqeq->cmd_cmpl = lpfc_nvmet_xmt_ls_abort_cmp;
+	abts_wqeq->cmd_flag |=  LPFC_IO_NVME_LS;
 	rc = lpfc_sli4_issue_wqe(phba, ctxp->hdwq, abts_wqeq);
 	spin_unlock_irqrestore(&phba->hbalock, flags);
 	if (rc == WQE_SUCCESS) {
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index c6944b282e21..41313fcaf84a 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -362,7 +362,7 @@ lpfc_new_scsi_buf_s3(struct lpfc_vport *vport, int num_to_alloc)
 			kfree(psb);
 			break;
 		}
-		psb->cur_iocbq.iocb_flag |= LPFC_IO_FCP;
+		psb->cur_iocbq.cmd_flag |= LPFC_IO_FCP;
 
 		psb->fcp_cmnd = psb->data;
 		psb->fcp_rsp = psb->data + sizeof(struct fcp_cmnd);
@@ -468,7 +468,7 @@ lpfc_sli4_vport_delete_fcp_xri_aborted(struct lpfc_vport *vport)
 		spin_lock(&qp->abts_io_buf_list_lock);
 		list_for_each_entry_safe(psb, next_psb,
 					 &qp->lpfc_abts_io_buf_list, list) {
-			if (psb->cur_iocbq.iocb_flag & LPFC_IO_NVME)
+			if (psb->cur_iocbq.cmd_flag & LPFC_IO_NVME)
 				continue;
 
 			if (psb->rdata && psb->rdata->pnode &&
@@ -493,8 +493,8 @@ void
 lpfc_sli4_io_xri_aborted(struct lpfc_hba *phba,
 			 struct sli4_wcqe_xri_aborted *axri, int idx)
 {
-	uint16_t xri = bf_get(lpfc_wcqe_xa_xri, axri);
-	uint16_t rxid = bf_get(lpfc_wcqe_xa_remote_xid, axri);
+	u16 xri = 0;
+	u16 rxid = 0;
 	struct lpfc_io_buf *psb, *next_psb;
 	struct lpfc_sli4_hdw_queue *qp;
 	unsigned long iflag = 0;
@@ -504,25 +504,39 @@ lpfc_sli4_io_xri_aborted(struct lpfc_hba *phba,
 	int rrq_empty = 0;
 	struct lpfc_sli_ring *pring = phba->sli4_hba.els_wq->pring;
 	struct scsi_cmnd *cmd;
+	int offline = 0;
 
 	if (!(phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP))
 		return;
-
+	offline = pci_channel_offline(phba->pcidev);
+	if (!offline) {
+		xri = bf_get(lpfc_wcqe_xa_xri, axri);
+		rxid = bf_get(lpfc_wcqe_xa_remote_xid, axri);
+	}
 	qp = &phba->sli4_hba.hdwq[idx];
 	spin_lock_irqsave(&phba->hbalock, iflag);
 	spin_lock(&qp->abts_io_buf_list_lock);
 	list_for_each_entry_safe(psb, next_psb,
 		&qp->lpfc_abts_io_buf_list, list) {
+		if (offline)
+			xri = psb->cur_iocbq.sli4_xritag;
 		if (psb->cur_iocbq.sli4_xritag == xri) {
 			list_del_init(&psb->list);
 			psb->flags &= ~LPFC_SBUF_XBUSY;
 			psb->status = IOSTAT_SUCCESS;
-			if (psb->cur_iocbq.iocb_flag & LPFC_IO_NVME) {
+			if (psb->cur_iocbq.cmd_flag & LPFC_IO_NVME) {
 				qp->abts_nvme_io_bufs--;
 				spin_unlock(&qp->abts_io_buf_list_lock);
 				spin_unlock_irqrestore(&phba->hbalock, iflag);
-				lpfc_sli4_nvme_xri_aborted(phba, axri, psb);
-				return;
+				if (!offline) {
+					lpfc_sli4_nvme_xri_aborted(phba, axri,
+								   psb);
+					return;
+				}
+				lpfc_sli4_nvme_pci_offline_aborted(phba, psb);
+				spin_lock_irqsave(&phba->hbalock, iflag);
+				spin_lock(&qp->abts_io_buf_list_lock);
+				continue;
 			}
 			qp->abts_scsi_io_bufs--;
 			spin_unlock(&qp->abts_io_buf_list_lock);
@@ -534,13 +548,13 @@ lpfc_sli4_io_xri_aborted(struct lpfc_hba *phba,
 
 			rrq_empty = list_empty(&phba->active_rrq_list);
 			spin_unlock_irqrestore(&phba->hbalock, iflag);
-			if (ndlp) {
+			if (ndlp && !offline) {
 				lpfc_set_rrq_active(phba, ndlp,
 					psb->cur_iocbq.sli4_lxritag, rxid, 1);
 				lpfc_sli4_abts_err_handler(phba, ndlp, axri);
 			}
 
-			if (phba->cfg_fcp_wait_abts_rsp) {
+			if (phba->cfg_fcp_wait_abts_rsp || offline) {
 				spin_lock_irqsave(&psb->buf_lock, iflag);
 				cmd = psb->pCmd;
 				psb->pCmd = NULL;
@@ -557,7 +571,7 @@ lpfc_sli4_io_xri_aborted(struct lpfc_hba *phba,
 				 * for command completion wake up the thread.
 				 */
 				spin_lock_irqsave(&psb->buf_lock, iflag);
-				psb->cur_iocbq.iocb_flag &=
+				psb->cur_iocbq.cmd_flag &=
 					~LPFC_DRIVER_ABORTED;
 				if (psb->waitq)
 					wake_up(psb->waitq);
@@ -567,25 +581,30 @@ lpfc_sli4_io_xri_aborted(struct lpfc_hba *phba,
 			lpfc_release_scsi_buf_s4(phba, psb);
 			if (rrq_empty)
 				lpfc_worker_wake_up(phba);
-			return;
+			if (!offline)
+				return;
+			spin_lock_irqsave(&phba->hbalock, iflag);
+			spin_lock(&qp->abts_io_buf_list_lock);
+			continue;
 		}
 	}
 	spin_unlock(&qp->abts_io_buf_list_lock);
-	for (i = 1; i <= phba->sli.last_iotag; i++) {
-		iocbq = phba->sli.iocbq_lookup[i];
-
-		if (!(iocbq->iocb_flag & LPFC_IO_FCP) ||
-		    (iocbq->iocb_flag & LPFC_IO_LIBDFC))
-			continue;
-		if (iocbq->sli4_xritag != xri)
-			continue;
-		psb = container_of(iocbq, struct lpfc_io_buf, cur_iocbq);
-		psb->flags &= ~LPFC_SBUF_XBUSY;
-		spin_unlock_irqrestore(&phba->hbalock, iflag);
-		if (!list_empty(&pring->txq))
-			lpfc_worker_wake_up(phba);
-		return;
+	if (!offline) {
+		for (i = 1; i <= phba->sli.last_iotag; i++) {
+			iocbq = phba->sli.iocbq_lookup[i];
 
+			if (!(iocbq->cmd_flag & LPFC_IO_FCP) ||
+			    (iocbq->cmd_flag & LPFC_IO_LIBDFC))
+				continue;
+			if (iocbq->sli4_xritag != xri)
+				continue;
+			psb = container_of(iocbq, struct lpfc_io_buf, cur_iocbq);
+			psb->flags &= ~LPFC_SBUF_XBUSY;
+			spin_unlock_irqrestore(&phba->hbalock, iflag);
+			if (!list_empty(&pring->txq))
+				lpfc_worker_wake_up(phba);
+			return;
+		}
 	}
 	spin_unlock_irqrestore(&phba->hbalock, iflag);
 }
@@ -676,7 +695,7 @@ lpfc_get_scsi_buf_s4(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp,
 	/* Setup key fields in buffer that may have been changed
 	 * if other protocols used this buffer.
 	 */
-	lpfc_cmd->cur_iocbq.iocb_flag = LPFC_IO_FCP;
+	lpfc_cmd->cur_iocbq.cmd_flag = LPFC_IO_FCP;
 	lpfc_cmd->prot_seg_cnt = 0;
 	lpfc_cmd->seg_cnt = 0;
 	lpfc_cmd->timeout = 0;
@@ -764,7 +783,7 @@ lpfc_release_scsi_buf_s3(struct lpfc_hba *phba, struct lpfc_io_buf *psb)
 
 	spin_lock_irqsave(&phba->scsi_buf_list_put_lock, iflag);
 	psb->pCmd = NULL;
-	psb->cur_iocbq.iocb_flag = LPFC_IO_FCP;
+	psb->cur_iocbq.cmd_flag = LPFC_IO_FCP;
 	list_add_tail(&psb->list, &phba->lpfc_scsi_buf_list_put);
 	spin_unlock_irqrestore(&phba->scsi_buf_list_put_lock, iflag);
 }
@@ -912,7 +931,7 @@ lpfc_scsi_prep_dma_buf_s3(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_cmd)
 			physaddr = sg_dma_address(sgel);
 			if (phba->sli_rev == 3 &&
 			    !(phba->sli3_options & LPFC_SLI3_BG_ENABLED) &&
-			    !(iocbq->iocb_flag & DSS_SECURITY_OP) &&
+			    !(iocbq->cmd_flag & DSS_SECURITY_OP) &&
 			    nseg <= LPFC_EXT_DATA_BDE_COUNT) {
 				data_bde->tus.f.bdeFlags = BUFF_TYPE_BDE_64;
 				data_bde->tus.f.bdeSize = sg_dma_len(sgel);
@@ -940,7 +959,7 @@ lpfc_scsi_prep_dma_buf_s3(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_cmd)
 	 */
 	if (phba->sli_rev == 3 &&
 	    !(phba->sli3_options & LPFC_SLI3_BG_ENABLED) &&
-	    !(iocbq->iocb_flag & DSS_SECURITY_OP)) {
+	    !(iocbq->cmd_flag & DSS_SECURITY_OP)) {
 		if (num_bde > LPFC_EXT_DATA_BDE_COUNT) {
 			/*
 			 * The extended IOCB format can only fit 3 BDE or a BPL.
@@ -2923,154 +2942,58 @@ out:
  * -1 - Internal error (bad profile, ...etc)
  */
 static int
-lpfc_sli4_parse_bg_err(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_cmd,
-		       struct lpfc_wcqe_complete *wcqe)
+lpfc_parse_bg_err(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_cmd,
+		  struct lpfc_iocbq *pIocbOut)
 {
 	struct scsi_cmnd *cmd = lpfc_cmd->pCmd;
+	struct sli3_bg_fields *bgf;
 	int ret = 0;
-	u32 status = bf_get(lpfc_wcqe_c_status, wcqe);
+	struct lpfc_wcqe_complete *wcqe;
+	u32 status;
 	u32 bghm = 0;
 	u32 bgstat = 0;
 	u64 failing_sector = 0;
 
-	if (status == CQE_STATUS_DI_ERROR) {
-		if (bf_get(lpfc_wcqe_c_bg_ge, wcqe)) /* Guard Check failed */
-			bgstat |= BGS_GUARD_ERR_MASK;
-		if (bf_get(lpfc_wcqe_c_bg_ae, wcqe)) /* AppTag Check failed */
-			bgstat |= BGS_APPTAG_ERR_MASK;
-		if (bf_get(lpfc_wcqe_c_bg_re, wcqe)) /* RefTag Check failed */
-			bgstat |= BGS_REFTAG_ERR_MASK;
-
-		/* Check to see if there was any good data before the error */
-		if (bf_get(lpfc_wcqe_c_bg_tdpv, wcqe)) {
-			bgstat |= BGS_HI_WATER_MARK_PRESENT_MASK;
-			bghm = wcqe->total_data_placed;
-		}
-
-		/*
-		 * Set ALL the error bits to indicate we don't know what
-		 * type of error it is.
-		 */
-		if (!bgstat)
-			bgstat |= (BGS_REFTAG_ERR_MASK | BGS_APPTAG_ERR_MASK |
-				BGS_GUARD_ERR_MASK);
-	}
-
-	if (lpfc_bgs_get_guard_err(bgstat)) {
-		ret = 1;
-
-		scsi_build_sense(cmd, 1, ILLEGAL_REQUEST, 0x10, 0x1);
-		set_host_byte(cmd, DID_ABORT);
-		phba->bg_guard_err_cnt++;
-		lpfc_printf_log(phba, KERN_WARNING, LOG_FCP | LOG_BG,
-				"9059 BLKGRD: Guard Tag error in cmd"
-				" 0x%x lba 0x%llx blk cnt 0x%x "
-				"bgstat=x%x bghm=x%x\n", cmd->cmnd[0],
-				(unsigned long long)scsi_get_lba(cmd),
-				scsi_logical_block_count(cmd), bgstat, bghm);
-	}
-
-	if (lpfc_bgs_get_reftag_err(bgstat)) {
-		ret = 1;
-
-		scsi_build_sense(cmd, 1, ILLEGAL_REQUEST, 0x10, 0x3);
-		set_host_byte(cmd, DID_ABORT);
-
-		phba->bg_reftag_err_cnt++;
-		lpfc_printf_log(phba, KERN_WARNING, LOG_FCP | LOG_BG,
-				"9060 BLKGRD: Ref Tag error in cmd"
-				" 0x%x lba 0x%llx blk cnt 0x%x "
-				"bgstat=x%x bghm=x%x\n", cmd->cmnd[0],
-				(unsigned long long)scsi_get_lba(cmd),
-				scsi_logical_block_count(cmd), bgstat, bghm);
-	}
+	if (phba->sli_rev == LPFC_SLI_REV4) {
+		wcqe = &pIocbOut->wcqe_cmpl;
+		status = bf_get(lpfc_wcqe_c_status, wcqe);
 
-	if (lpfc_bgs_get_apptag_err(bgstat)) {
-		ret = 1;
+		if (status == CQE_STATUS_DI_ERROR) {
+			/* Guard Check failed */
+			if (bf_get(lpfc_wcqe_c_bg_ge, wcqe))
+				bgstat |= BGS_GUARD_ERR_MASK;
 
-		scsi_build_sense(cmd, 1, ILLEGAL_REQUEST, 0x10, 0x2);
-		set_host_byte(cmd, DID_ABORT);
+			/* AppTag Check failed */
+			if (bf_get(lpfc_wcqe_c_bg_ae, wcqe))
+				bgstat |= BGS_APPTAG_ERR_MASK;
 
-		phba->bg_apptag_err_cnt++;
-		lpfc_printf_log(phba, KERN_WARNING, LOG_FCP | LOG_BG,
-				"9062 BLKGRD: App Tag error in cmd"
-				" 0x%x lba 0x%llx blk cnt 0x%x "
-				"bgstat=x%x bghm=x%x\n", cmd->cmnd[0],
-				(unsigned long long)scsi_get_lba(cmd),
-				scsi_logical_block_count(cmd), bgstat, bghm);
-	}
+			/* RefTag Check failed */
+			if (bf_get(lpfc_wcqe_c_bg_re, wcqe))
+				bgstat |= BGS_REFTAG_ERR_MASK;
 
-	if (lpfc_bgs_get_hi_water_mark_present(bgstat)) {
-		/*
-		 * setup sense data descriptor 0 per SPC-4 as an information
-		 * field, and put the failing LBA in it.
-		 * This code assumes there was also a guard/app/ref tag error
-		 * indication.
-		 */
-		cmd->sense_buffer[7] = 0xc;   /* Additional sense length */
-		cmd->sense_buffer[8] = 0;     /* Information descriptor type */
-		cmd->sense_buffer[9] = 0xa;   /* Additional descriptor length */
-		cmd->sense_buffer[10] = 0x80; /* Validity bit */
+			/* Check to see if there was any good data before the
+			 * error
+			 */
+			if (bf_get(lpfc_wcqe_c_bg_tdpv, wcqe)) {
+				bgstat |= BGS_HI_WATER_MARK_PRESENT_MASK;
+				bghm = wcqe->total_data_placed;
+			}
 
-		/* bghm is a "on the wire" FC frame based count */
-		switch (scsi_get_prot_op(cmd)) {
-		case SCSI_PROT_READ_INSERT:
-		case SCSI_PROT_WRITE_STRIP:
-			bghm /= cmd->device->sector_size;
-			break;
-		case SCSI_PROT_READ_STRIP:
-		case SCSI_PROT_WRITE_INSERT:
-		case SCSI_PROT_READ_PASS:
-		case SCSI_PROT_WRITE_PASS:
-			bghm /= (cmd->device->sector_size +
-				sizeof(struct scsi_dif_tuple));
-			break;
+			/*
+			 * Set ALL the error bits to indicate we don't know what
+			 * type of error it is.
+			 */
+			if (!bgstat)
+				bgstat |= (BGS_REFTAG_ERR_MASK |
+					   BGS_APPTAG_ERR_MASK |
+					   BGS_GUARD_ERR_MASK);
 		}
 
-		failing_sector = scsi_get_lba(cmd);
-		failing_sector += bghm;
-
-		/* Descriptor Information */
-		put_unaligned_be64(failing_sector, &cmd->sense_buffer[12]);
-	}
-
-	if (!ret) {
-		/* No error was reported - problem in FW? */
-		lpfc_printf_log(phba, KERN_WARNING, LOG_FCP | LOG_BG,
-				"9068 BLKGRD: Unknown error in cmd"
-				" 0x%x lba 0x%llx blk cnt 0x%x "
-				"bgstat=x%x bghm=x%x\n", cmd->cmnd[0],
-				(unsigned long long)scsi_get_lba(cmd),
-				scsi_logical_block_count(cmd), bgstat, bghm);
-
-		/* Calculate what type of error it was */
-		lpfc_calc_bg_err(phba, lpfc_cmd);
+	} else {
+		bgf = &pIocbOut->iocb.unsli3.sli3_bg;
+		bghm = bgf->bghm;
+		bgstat = bgf->bgstat;
 	}
-	return ret;
-}
-
-/*
- * This function checks for BlockGuard errors detected by
- * the HBA.  In case of errors, the ASC/ASCQ fields in the
- * sense buffer will be set accordingly, paired with
- * ILLEGAL_REQUEST to signal to the kernel that the HBA
- * detected corruption.
- *
- * Returns:
- *  0 - No error found
- *  1 - BlockGuard error found
- * -1 - Internal error (bad profile, ...etc)
- */
-static int
-lpfc_parse_bg_err(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_cmd,
-		  struct lpfc_iocbq *pIocbOut)
-{
-	struct scsi_cmnd *cmd = lpfc_cmd->pCmd;
-	struct sli3_bg_fields *bgf = &pIocbOut->iocb.unsli3.sli3_bg;
-	int ret = 0;
-	uint32_t bghm = bgf->bghm;
-	uint32_t bgstat = bgf->bgstat;
-	uint64_t failing_sector = 0;
 
 	if (lpfc_bgs_get_invalid_prof(bgstat)) {
 		cmd->result = DID_ERROR << 16;
@@ -3098,7 +3021,6 @@ lpfc_parse_bg_err(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_cmd,
 
 	if (lpfc_bgs_get_guard_err(bgstat)) {
 		ret = 1;
-
 		scsi_build_sense(cmd, 1, ILLEGAL_REQUEST, 0x10, 0x1);
 		set_host_byte(cmd, DID_ABORT);
 		phba->bg_guard_err_cnt++;
@@ -3112,10 +3034,8 @@ lpfc_parse_bg_err(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_cmd,
 
 	if (lpfc_bgs_get_reftag_err(bgstat)) {
 		ret = 1;
-
 		scsi_build_sense(cmd, 1, ILLEGAL_REQUEST, 0x10, 0x3);
 		set_host_byte(cmd, DID_ABORT);
-
 		phba->bg_reftag_err_cnt++;
 		lpfc_printf_log(phba, KERN_WARNING, LOG_FCP | LOG_BG,
 				"9056 BLKGRD: Ref Tag error in cmd "
@@ -3127,10 +3047,8 @@ lpfc_parse_bg_err(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_cmd,
 
 	if (lpfc_bgs_get_apptag_err(bgstat)) {
 		ret = 1;
-
 		scsi_build_sense(cmd, 1, ILLEGAL_REQUEST, 0x10, 0x2);
 		set_host_byte(cmd, DID_ABORT);
-
 		phba->bg_apptag_err_cnt++;
 		lpfc_printf_log(phba, KERN_WARNING, LOG_FCP | LOG_BG,
 				"9061 BLKGRD: App Tag error in cmd "
@@ -3415,7 +3333,7 @@ lpfc_scsi_prep_dma_buf_s4(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_cmd)
 	 */
 	if ((phba->cfg_fof) && ((struct lpfc_device_data *)
 		scsi_cmnd->device->hostdata)->oas_enabled) {
-		lpfc_cmd->cur_iocbq.iocb_flag |= (LPFC_IO_OAS | LPFC_IO_FOF);
+		lpfc_cmd->cur_iocbq.cmd_flag |= (LPFC_IO_OAS | LPFC_IO_FOF);
 		lpfc_cmd->cur_iocbq.priority = ((struct lpfc_device_data *)
 			scsi_cmnd->device->hostdata)->priority;
 
@@ -3572,15 +3490,15 @@ lpfc_bg_scsi_prep_dma_buf_s4(struct lpfc_hba *phba,
 	switch (scsi_get_prot_op(scsi_cmnd)) {
 	case SCSI_PROT_WRITE_STRIP:
 	case SCSI_PROT_READ_STRIP:
-		lpfc_cmd->cur_iocbq.iocb_flag |= LPFC_IO_DIF_STRIP;
+		lpfc_cmd->cur_iocbq.cmd_flag |= LPFC_IO_DIF_STRIP;
 		break;
 	case SCSI_PROT_WRITE_INSERT:
 	case SCSI_PROT_READ_INSERT:
-		lpfc_cmd->cur_iocbq.iocb_flag |= LPFC_IO_DIF_INSERT;
+		lpfc_cmd->cur_iocbq.cmd_flag |= LPFC_IO_DIF_INSERT;
 		break;
 	case SCSI_PROT_WRITE_PASS:
 	case SCSI_PROT_READ_PASS:
-		lpfc_cmd->cur_iocbq.iocb_flag |= LPFC_IO_DIF_PASS;
+		lpfc_cmd->cur_iocbq.cmd_flag |= LPFC_IO_DIF_PASS;
 		break;
 	}
 
@@ -3611,7 +3529,7 @@ lpfc_bg_scsi_prep_dma_buf_s4(struct lpfc_hba *phba,
 	 */
 	if ((phba->cfg_fof) && ((struct lpfc_device_data *)
 		scsi_cmnd->device->hostdata)->oas_enabled) {
-		lpfc_cmd->cur_iocbq.iocb_flag |= (LPFC_IO_OAS | LPFC_IO_FOF);
+		lpfc_cmd->cur_iocbq.cmd_flag |= (LPFC_IO_OAS | LPFC_IO_FOF);
 
 		/* Word 10 */
 		bf_set(wqe_oas, &wqe->generic.wqe_com, 1);
@@ -3621,14 +3539,14 @@ lpfc_bg_scsi_prep_dma_buf_s4(struct lpfc_hba *phba,
 	}
 
 	/* Word 7. DIF Flags */
-	if (lpfc_cmd->cur_iocbq.iocb_flag & LPFC_IO_DIF_PASS)
+	if (lpfc_cmd->cur_iocbq.cmd_flag & LPFC_IO_DIF_PASS)
 		bf_set(wqe_dif, &wqe->generic.wqe_com, LPFC_WQE_DIF_PASSTHRU);
-	else if (lpfc_cmd->cur_iocbq.iocb_flag & LPFC_IO_DIF_STRIP)
+	else if (lpfc_cmd->cur_iocbq.cmd_flag & LPFC_IO_DIF_STRIP)
 		bf_set(wqe_dif, &wqe->generic.wqe_com, LPFC_WQE_DIF_STRIP);
-	else if (lpfc_cmd->cur_iocbq.iocb_flag & LPFC_IO_DIF_INSERT)
+	else if (lpfc_cmd->cur_iocbq.cmd_flag & LPFC_IO_DIF_INSERT)
 		bf_set(wqe_dif, &wqe->generic.wqe_com, LPFC_WQE_DIF_INSERT);
 
-	lpfc_cmd->cur_iocbq.iocb_flag &= ~(LPFC_IO_DIF_PASS |
+	lpfc_cmd->cur_iocbq.cmd_flag &= ~(LPFC_IO_DIF_PASS |
 				 LPFC_IO_DIF_STRIP | LPFC_IO_DIF_INSERT);
 
 	return 0;
@@ -4153,7 +4071,7 @@ lpfc_handle_fcp_err(struct lpfc_vport *vport, struct lpfc_io_buf *lpfc_cmd,
  * lpfc_fcp_io_cmd_wqe_cmpl - Complete a FCP IO
  * @phba: The hba for which this call is being executed.
  * @pwqeIn: The command WQE for the scsi cmnd.
- * @wcqe: Pointer to driver response CQE object.
+ * @pwqeOut: Pointer to driver response WQE object.
  *
  * This routine assigns scsi command result by looking into response WQE
  * status field appropriately. This routine handles QUEUE FULL condition as
@@ -4161,10 +4079,11 @@ lpfc_handle_fcp_err(struct lpfc_vport *vport, struct lpfc_io_buf *lpfc_cmd,
  **/
 static void
 lpfc_fcp_io_cmd_wqe_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn,
-			 struct lpfc_wcqe_complete *wcqe)
+			 struct lpfc_iocbq *pwqeOut)
 {
 	struct lpfc_io_buf *lpfc_cmd =
 		(struct lpfc_io_buf *)pwqeIn->context1;
+	struct lpfc_wcqe_complete *wcqe = &pwqeOut->wcqe_cmpl;
 	struct lpfc_vport *vport = pwqeIn->vport;
 	struct lpfc_rport_data *rdata;
 	struct lpfc_nodelist *ndlp;
@@ -4174,7 +4093,6 @@ lpfc_fcp_io_cmd_wqe_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn,
 	struct Scsi_Host *shost;
 	u32 logit = LOG_FCP;
 	u32 status, idx;
-	unsigned long iflags = 0;
 	u32 lat;
 	u8 wait_xb_clr = 0;
 
@@ -4189,30 +4107,16 @@ lpfc_fcp_io_cmd_wqe_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn,
 	rdata = lpfc_cmd->rdata;
 	ndlp = rdata->pnode;
 
-	if (bf_get(lpfc_wcqe_c_xb, wcqe)) {
-		/* TOREMOVE - currently this flag is checked during
-		 * the release of lpfc_iocbq. Remove once we move
-		 * to lpfc_wqe_job construct.
-		 *
-		 * This needs to be done outside buf_lock
-		 */
-		spin_lock_irqsave(&phba->hbalock, iflags);
-		lpfc_cmd->cur_iocbq.iocb_flag |= LPFC_EXCHANGE_BUSY;
-		spin_unlock_irqrestore(&phba->hbalock, iflags);
-	}
-
-	/* Guard against abort handler being called at same time */
-	spin_lock(&lpfc_cmd->buf_lock);
-
 	/* Sanity check on return of outstanding command */
 	cmd = lpfc_cmd->pCmd;
 	if (!cmd) {
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT,
 				 "9042 I/O completion: Not an active IO\n");
-		spin_unlock(&lpfc_cmd->buf_lock);
 		lpfc_release_scsi_buf(phba, lpfc_cmd);
 		return;
 	}
+	/* Guard against abort handler being called at same time */
+	spin_lock(&lpfc_cmd->buf_lock);
 	idx = lpfc_cmd->cur_iocbq.hba_wqidx;
 	if (phba->sli4_hba.hdwq)
 		phba->sli4_hba.hdwq[idx].scsi_cstat.io_cmpls++;
@@ -4374,7 +4278,7 @@ lpfc_fcp_io_cmd_wqe_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn,
 		    lpfc_cmd->result == IOERR_NO_RESOURCES ||
 		    lpfc_cmd->result == IOERR_ABORT_REQUESTED ||
 		    lpfc_cmd->result == IOERR_SLER_CMD_RCV_FAILURE) {
-			cmd->result = DID_REQUEUE << 16;
+			cmd->result = DID_TRANSPORT_DISRUPTED << 16;
 			break;
 		}
 		if ((lpfc_cmd->result == IOERR_RX_DMA_FAILED ||
@@ -4386,12 +4290,14 @@ lpfc_fcp_io_cmd_wqe_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn,
 				 * This is a response for a BG enabled
 				 * cmd. Parse BG error
 				 */
-				lpfc_sli4_parse_bg_err(phba, lpfc_cmd,
-						       wcqe);
+				lpfc_parse_bg_err(phba, lpfc_cmd, pwqeOut);
 				break;
+			} else {
+				lpfc_printf_vlog(vport, KERN_WARNING,
+						 LOG_BG,
+						 "9040 non-zero BGSTAT "
+						 "on unprotected cmd\n");
 			}
-			lpfc_printf_vlog(vport, KERN_WARNING, LOG_BG,
-				 "9040 non-zero BGSTAT on unprotected cmd\n");
 		}
 		lpfc_printf_vlog(vport, KERN_WARNING, logit,
 				 "9036 Local Reject FCP cmd x%x failed"
@@ -4488,7 +4394,7 @@ lpfc_fcp_io_cmd_wqe_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn,
 	 * wake up the thread.
 	 */
 	spin_lock(&lpfc_cmd->buf_lock);
-	lpfc_cmd->cur_iocbq.iocb_flag &= ~LPFC_DRIVER_ABORTED;
+	lpfc_cmd->cur_iocbq.cmd_flag &= ~LPFC_DRIVER_ABORTED;
 	if (lpfc_cmd->waitq)
 		wake_up(lpfc_cmd->waitq);
 	spin_unlock(&lpfc_cmd->buf_lock);
@@ -4548,7 +4454,7 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 	lpfc_cmd->status = pIocbOut->iocb.ulpStatus;
 	/* pick up SLI4 exchange busy status from HBA */
 	lpfc_cmd->flags &= ~LPFC_SBUF_XBUSY;
-	if (pIocbOut->iocb_flag & LPFC_EXCHANGE_BUSY)
+	if (pIocbOut->cmd_flag & LPFC_EXCHANGE_BUSY)
 		lpfc_cmd->flags |= LPFC_SBUF_XBUSY;
 
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
@@ -4661,7 +4567,7 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 			    lpfc_cmd->result == IOERR_NO_RESOURCES ||
 			    lpfc_cmd->result == IOERR_ABORT_REQUESTED ||
 			    lpfc_cmd->result == IOERR_SLER_CMD_RCV_FAILURE) {
-				cmd->result = DID_REQUEUE << 16;
+				cmd->result = DID_TRANSPORT_DISRUPTED << 16;
 				break;
 			}
 			if ((lpfc_cmd->result == IOERR_RX_DMA_FAILED ||
@@ -4757,7 +4663,7 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 	 * wake up the thread.
 	 */
 	spin_lock(&lpfc_cmd->buf_lock);
-	lpfc_cmd->cur_iocbq.iocb_flag &= ~LPFC_DRIVER_ABORTED;
+	lpfc_cmd->cur_iocbq.cmd_flag &= ~LPFC_DRIVER_ABORTED;
 	if (lpfc_cmd->waitq)
 		wake_up(lpfc_cmd->waitq);
 	spin_unlock(&lpfc_cmd->buf_lock);
@@ -4835,8 +4741,8 @@ static int lpfc_scsi_prep_cmnd_buf_s3(struct lpfc_vport *vport,
 
 	piocbq->iocb.ulpClass = (pnode->nlp_fcp_info & 0x0f);
 	piocbq->context1  = lpfc_cmd;
-	if (!piocbq->iocb_cmpl)
-		piocbq->iocb_cmpl = lpfc_scsi_cmd_iocb_cmpl;
+	if (!piocbq->cmd_cmpl)
+		piocbq->cmd_cmpl = lpfc_scsi_cmd_iocb_cmpl;
 	piocbq->iocb.ulpTimeout = tmo;
 	piocbq->vport = vport;
 	return 0;
@@ -4949,7 +4855,7 @@ static int lpfc_scsi_prep_cmnd_buf_s4(struct lpfc_vport *vport,
 	pwqeq->vport = vport;
 	pwqeq->context1 = lpfc_cmd;
 	pwqeq->hba_wqidx = lpfc_cmd->hdwq_no;
-	pwqeq->wqe_cmpl = lpfc_fcp_io_cmd_wqe_cmpl;
+	pwqeq->cmd_cmpl = lpfc_fcp_io_cmd_wqe_cmpl;
 
 	return 0;
 }
@@ -4996,7 +4902,7 @@ lpfc_scsi_prep_cmnd(struct lpfc_vport *vport, struct lpfc_io_buf *lpfc_cmd,
 }
 
 /**
- * lpfc_scsi_prep_task_mgmt_cmd - Convert SLI3 scsi TM cmd to FCP info unit
+ * lpfc_scsi_prep_task_mgmt_cmd_s3 - Convert SLI3 scsi TM cmd to FCP info unit
  * @vport: The virtual port for which this call is being executed.
  * @lpfc_cmd: Pointer to lpfc_io_buf data structure.
  * @lun: Logical unit number.
@@ -5010,10 +4916,9 @@ lpfc_scsi_prep_cmnd(struct lpfc_vport *vport, struct lpfc_io_buf *lpfc_cmd,
  *   1 - Success
  **/
 static int
-lpfc_scsi_prep_task_mgmt_cmd(struct lpfc_vport *vport,
-			     struct lpfc_io_buf *lpfc_cmd,
-			     uint64_t lun,
-			     uint8_t task_mgmt_cmd)
+lpfc_scsi_prep_task_mgmt_cmd_s3(struct lpfc_vport *vport,
+				struct lpfc_io_buf *lpfc_cmd,
+				u64 lun, u8 task_mgmt_cmd)
 {
 	struct lpfc_iocbq *piocbq;
 	IOCB_t *piocb;
@@ -5034,15 +4939,10 @@ lpfc_scsi_prep_task_mgmt_cmd(struct lpfc_vport *vport,
 	memset(fcp_cmnd, 0, sizeof(struct fcp_cmnd));
 	int_to_scsilun(lun, &fcp_cmnd->fcp_lun);
 	fcp_cmnd->fcpCntl2 = task_mgmt_cmd;
-	if (vport->phba->sli_rev == 3 &&
-	    !(vport->phba->sli3_options & LPFC_SLI3_BG_ENABLED))
+	if (!(vport->phba->sli3_options & LPFC_SLI3_BG_ENABLED))
 		lpfc_fcpcmd_to_iocb(piocb->unsli3.fcp_ext.icd, fcp_cmnd);
 	piocb->ulpCommand = CMD_FCP_ICMND64_CR;
 	piocb->ulpContext = ndlp->nlp_rpi;
-	if (vport->phba->sli_rev == LPFC_SLI_REV4) {
-		piocb->ulpContext =
-		  vport->phba->sli4_hba.rpi_ids[ndlp->nlp_rpi];
-	}
 	piocb->ulpFCP2Rcvy = (ndlp->nlp_fcp_info & NLP_FCP_2_DEVICE) ? 1 : 0;
 	piocb->ulpClass = (ndlp->nlp_fcp_info & 0x0f);
 	piocb->ulpPU = 0;
@@ -5058,8 +4958,79 @@ lpfc_scsi_prep_task_mgmt_cmd(struct lpfc_vport *vport,
 	} else
 		piocb->ulpTimeout = lpfc_cmd->timeout;
 
-	if (vport->phba->sli_rev == LPFC_SLI_REV4)
-		lpfc_sli4_set_rsp_sgl_last(vport->phba, lpfc_cmd);
+	return 1;
+}
+
+/**
+ * lpfc_scsi_prep_task_mgmt_cmd_s4 - Convert SLI4 scsi TM cmd to FCP info unit
+ * @vport: The virtual port for which this call is being executed.
+ * @lpfc_cmd: Pointer to lpfc_io_buf data structure.
+ * @lun: Logical unit number.
+ * @task_mgmt_cmd: SCSI task management command.
+ *
+ * This routine creates FCP information unit corresponding to @task_mgmt_cmd
+ * for device with SLI-4 interface spec.
+ *
+ * Return codes:
+ *   0 - Error
+ *   1 - Success
+ **/
+static int
+lpfc_scsi_prep_task_mgmt_cmd_s4(struct lpfc_vport *vport,
+				struct lpfc_io_buf *lpfc_cmd,
+				u64 lun, u8 task_mgmt_cmd)
+{
+	struct lpfc_iocbq *pwqeq = &lpfc_cmd->cur_iocbq;
+	union lpfc_wqe128 *wqe = &pwqeq->wqe;
+	struct fcp_cmnd *fcp_cmnd;
+	struct lpfc_rport_data *rdata = lpfc_cmd->rdata;
+	struct lpfc_nodelist *ndlp = rdata->pnode;
+
+	if (!ndlp || ndlp->nlp_state != NLP_STE_MAPPED_NODE)
+		return 0;
+
+	pwqeq->vport = vport;
+	/* Initialize 64 bytes only */
+	memset(wqe, 0, sizeof(union lpfc_wqe128));
+
+	/* From the icmnd template, initialize words 4 - 11 */
+	memcpy(&wqe->words[4], &lpfc_icmnd_cmd_template.words[4],
+	       sizeof(uint32_t) * 8);
+
+	fcp_cmnd = lpfc_cmd->fcp_cmnd;
+	/* Clear out any old data in the FCP command area */
+	memset(fcp_cmnd, 0, sizeof(struct fcp_cmnd));
+	int_to_scsilun(lun, &fcp_cmnd->fcp_lun);
+	fcp_cmnd->fcpCntl3 = 0;
+	fcp_cmnd->fcpCntl2 = task_mgmt_cmd;
+
+	bf_set(payload_offset_len, &wqe->fcp_icmd,
+	       sizeof(struct fcp_cmnd) + sizeof(struct fcp_rsp));
+	bf_set(cmd_buff_len, &wqe->fcp_icmd, 0);
+	bf_set(wqe_ctxt_tag, &wqe->generic.wqe_com,  /* ulpContext */
+	       vport->phba->sli4_hba.rpi_ids[ndlp->nlp_rpi]);
+	bf_set(wqe_erp, &wqe->fcp_icmd.wqe_com,
+	       ((ndlp->nlp_fcp_info & NLP_FCP_2_DEVICE) ? 1 : 0));
+	bf_set(wqe_class, &wqe->fcp_icmd.wqe_com,
+	       (ndlp->nlp_fcp_info & 0x0f));
+
+	/* ulpTimeout is only one byte */
+	if (lpfc_cmd->timeout > 0xff) {
+		/*
+		 * Do not timeout the command at the firmware level.
+		 * The driver will provide the timeout mechanism.
+		 */
+		bf_set(wqe_tmo, &wqe->fcp_icmd.wqe_com, 0);
+	} else {
+		bf_set(wqe_tmo, &wqe->fcp_icmd.wqe_com, lpfc_cmd->timeout);
+	}
+
+	lpfc_prep_embed_io(vport->phba, lpfc_cmd);
+	bf_set(wqe_xri_tag, &wqe->generic.wqe_com, pwqeq->sli4_xritag);
+	wqe->generic.wqe_com.abort_tag = pwqeq->iotag;
+	bf_set(wqe_reqtag, &wqe->generic.wqe_com, pwqeq->iotag);
+
+	lpfc_sli4_set_rsp_sgl_last(vport->phba, lpfc_cmd);
 
 	return 1;
 }
@@ -5086,6 +5057,8 @@ lpfc_scsi_api_table_setup(struct lpfc_hba *phba, uint8_t dev_grp)
 		phba->lpfc_release_scsi_buf = lpfc_release_scsi_buf_s3;
 		phba->lpfc_get_scsi_buf = lpfc_get_scsi_buf_s3;
 		phba->lpfc_scsi_prep_cmnd_buf = lpfc_scsi_prep_cmnd_buf_s3;
+		phba->lpfc_scsi_prep_task_mgmt_cmd =
+					lpfc_scsi_prep_task_mgmt_cmd_s3;
 		break;
 	case LPFC_PCI_DEV_OC:
 		phba->lpfc_scsi_prep_dma_buf = lpfc_scsi_prep_dma_buf_s4;
@@ -5093,6 +5066,8 @@ lpfc_scsi_api_table_setup(struct lpfc_hba *phba, uint8_t dev_grp)
 		phba->lpfc_release_scsi_buf = lpfc_release_scsi_buf_s4;
 		phba->lpfc_get_scsi_buf = lpfc_get_scsi_buf_s4;
 		phba->lpfc_scsi_prep_cmnd_buf = lpfc_scsi_prep_cmnd_buf_s4;
+		phba->lpfc_scsi_prep_task_mgmt_cmd =
+					lpfc_scsi_prep_task_mgmt_cmd_s4;
 		break;
 	default:
 		lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT,
@@ -5571,6 +5546,7 @@ lpfc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *cmnd)
 {
 	struct lpfc_vport *vport = (struct lpfc_vport *) shost->hostdata;
 	struct lpfc_hba   *phba = vport->phba;
+	struct lpfc_iocbq *cur_iocbq = NULL;
 	struct lpfc_rport_data *rdata;
 	struct lpfc_nodelist *ndlp;
 	struct lpfc_io_buf *lpfc_cmd;
@@ -5664,6 +5640,7 @@ lpfc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *cmnd)
 	}
 	lpfc_cmd->rx_cmd_start = start;
 
+	cur_iocbq = &lpfc_cmd->cur_iocbq;
 	/*
 	 * Store the midlayer's command structure for the completion phase
 	 * and complete the command initialization.
@@ -5671,7 +5648,7 @@ lpfc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *cmnd)
 	lpfc_cmd->pCmd  = cmnd;
 	lpfc_cmd->rdata = rdata;
 	lpfc_cmd->ndlp = ndlp;
-	lpfc_cmd->cur_iocbq.iocb_cmpl = NULL;
+	cur_iocbq->cmd_cmpl = NULL;
 	cmnd->host_scribble = (unsigned char *)lpfc_cmd;
 
 	err = lpfc_scsi_prep_cmnd(vport, lpfc_cmd, ndlp);
@@ -5713,7 +5690,6 @@ lpfc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *cmnd)
 		goto out_host_busy_free_buf;
 	}
 
-
 	/* check the necessary and sufficient condition to support VMID */
 	if (lpfc_is_vmid_enabled(phba) &&
 	    (ndlp->vmid_support ||
@@ -5726,20 +5702,18 @@ lpfc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *cmnd)
 		if (uuid) {
 			err = lpfc_vmid_get_appid(vport, uuid, cmnd,
 				(union lpfc_vmid_io_tag *)
-					&lpfc_cmd->cur_iocbq.vmid_tag);
+					&cur_iocbq->vmid_tag);
 			if (!err)
-				lpfc_cmd->cur_iocbq.iocb_flag |= LPFC_IO_VMID;
+				cur_iocbq->cmd_flag |= LPFC_IO_VMID;
 		}
 	}
 
-	atomic_inc(&ndlp->cmd_pending);
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
 	if (unlikely(phba->hdwqstat_on & LPFC_CHECK_SCSI_IO))
 		this_cpu_inc(phba->sli4_hba.c_stat->xmt_io);
 #endif
 	/* Issue I/O to adapter */
-	err = lpfc_sli_issue_fcp_io(phba, LPFC_FCP_RING,
-				    &lpfc_cmd->cur_iocbq,
+	err = lpfc_sli_issue_fcp_io(phba, LPFC_FCP_RING, cur_iocbq,
 				    SLI_IOCB_RET_IOCB);
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
 	if (start) {
@@ -5752,25 +5726,25 @@ lpfc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *cmnd)
 #endif
 	if (err) {
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_FCP,
-				   "3376 FCP could not issue IOCB err %x "
-				   "FCP cmd x%x <%d/%llu> "
-				   "sid: x%x did: x%x oxid: x%x "
-				   "Data: x%x x%x x%x x%x\n",
-				   err, cmnd->cmnd[0],
-				   cmnd->device ? cmnd->device->id : 0xffff,
-				   cmnd->device ? cmnd->device->lun : (u64)-1,
-				   vport->fc_myDID, ndlp->nlp_DID,
-				   phba->sli_rev == LPFC_SLI_REV4 ?
-				   lpfc_cmd->cur_iocbq.sli4_xritag : 0xffff,
-				   phba->sli_rev == LPFC_SLI_REV4 ?
-				   phba->sli4_hba.rpi_ids[ndlp->nlp_rpi] :
-				   lpfc_cmd->cur_iocbq.iocb.ulpContext,
-				   lpfc_cmd->cur_iocbq.iotag,
-				   phba->sli_rev == LPFC_SLI_REV4 ?
-				   bf_get(wqe_tmo,
-				   &lpfc_cmd->cur_iocbq.wqe.generic.wqe_com) :
-				   lpfc_cmd->cur_iocbq.iocb.ulpTimeout,
-				   (uint32_t)(scsi_cmd_to_rq(cmnd)->timeout / 1000));
+				 "3376 FCP could not issue iocb err %x "
+				 "FCP cmd x%x <%d/%llu> "
+				 "sid: x%x did: x%x oxid: x%x "
+				 "Data: x%x x%x x%x x%x\n",
+				 err, cmnd->cmnd[0],
+				 cmnd->device ? cmnd->device->id : 0xffff,
+				 cmnd->device ? cmnd->device->lun : (u64)-1,
+				 vport->fc_myDID, ndlp->nlp_DID,
+				 phba->sli_rev == LPFC_SLI_REV4 ?
+				 cur_iocbq->sli4_xritag : 0xffff,
+				 phba->sli_rev == LPFC_SLI_REV4 ?
+				 phba->sli4_hba.rpi_ids[ndlp->nlp_rpi] :
+				 cur_iocbq->iocb.ulpContext,
+				 cur_iocbq->iotag,
+				 phba->sli_rev == LPFC_SLI_REV4 ?
+				 bf_get(wqe_tmo,
+					&cur_iocbq->wqe.generic.wqe_com) :
+				 cur_iocbq->iocb.ulpTimeout,
+				 (uint32_t)(scsi_cmd_to_rq(cmnd)->timeout / 1000));
 
 		goto out_host_busy_free_buf;
 	}
@@ -5916,7 +5890,7 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd)
 		spin_lock(&pring_s4->ring_lock);
 	}
 	/* the command is in process of being cancelled */
-	if (!(iocb->iocb_flag & LPFC_IO_ON_TXCMPLQ)) {
+	if (!(iocb->cmd_flag & LPFC_IO_ON_TXCMPLQ)) {
 		lpfc_printf_vlog(vport, KERN_WARNING, LOG_FCP,
 			"3169 SCSI Layer abort requested I/O has been "
 			"cancelled by LLD.\n");
@@ -5939,7 +5913,7 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd)
 	BUG_ON(iocb->context1 != lpfc_cmd);
 
 	/* abort issued in recovery is still in progress */
-	if (iocb->iocb_flag & LPFC_DRIVER_ABORTED) {
+	if (iocb->cmd_flag & LPFC_DRIVER_ABORTED) {
 		lpfc_printf_vlog(vport, KERN_WARNING, LOG_FCP,
 			 "3389 SCSI Layer I/O Abort Request is pending\n");
 		if (phba->sli_rev == LPFC_SLI_REV4)
@@ -5980,7 +5954,7 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd)
 
 wait_for_cmpl:
 	/*
-	 * iocb_flag is set to LPFC_DRIVER_ABORTED before we wait
+	 * cmd_flag is set to LPFC_DRIVER_ABORTED before we wait
 	 * for abort to complete.
 	 */
 	wait_event_timeout(waitq,
@@ -6147,7 +6121,7 @@ lpfc_send_taskmgmt(struct lpfc_vport *vport, struct scsi_cmnd *cmnd,
 		return FAILED;
 	pnode = rdata->pnode;
 
-	lpfc_cmd = lpfc_get_scsi_buf(phba, pnode, NULL);
+	lpfc_cmd = lpfc_get_scsi_buf(phba, rdata->pnode, NULL);
 	if (lpfc_cmd == NULL)
 		return FAILED;
 	lpfc_cmd->timeout = phba->cfg_task_mgmt_tmo;
@@ -6155,8 +6129,8 @@ lpfc_send_taskmgmt(struct lpfc_vport *vport, struct scsi_cmnd *cmnd,
 	lpfc_cmd->pCmd = cmnd;
 	lpfc_cmd->ndlp = pnode;
 
-	status = lpfc_scsi_prep_task_mgmt_cmd(vport, lpfc_cmd, lun_id,
-					   task_mgmt_cmd);
+	status = phba->lpfc_scsi_prep_task_mgmt_cmd(vport, lpfc_cmd, lun_id,
+						    task_mgmt_cmd);
 	if (!status) {
 		lpfc_release_scsi_buf(phba, lpfc_cmd);
 		return FAILED;
@@ -6168,38 +6142,41 @@ lpfc_send_taskmgmt(struct lpfc_vport *vport, struct scsi_cmnd *cmnd,
 		lpfc_release_scsi_buf(phba, lpfc_cmd);
 		return FAILED;
 	}
-	iocbq->iocb_cmpl = lpfc_tskmgmt_def_cmpl;
+	iocbq->cmd_cmpl = lpfc_tskmgmt_def_cmpl;
+	iocbq->vport = vport;
 
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_FCP,
 			 "0702 Issue %s to TGT %d LUN %llu "
 			 "rpi x%x nlp_flag x%x Data: x%x x%x\n",
 			 lpfc_taskmgmt_name(task_mgmt_cmd), tgt_id, lun_id,
 			 pnode->nlp_rpi, pnode->nlp_flag, iocbq->sli4_xritag,
-			 iocbq->iocb_flag);
+			 iocbq->cmd_flag);
 
 	status = lpfc_sli_issue_iocb_wait(phba, LPFC_FCP_RING,
 					  iocbq, iocbqrsp, lpfc_cmd->timeout);
 	if ((status != IOCB_SUCCESS) ||
-	    (iocbqrsp->iocb.ulpStatus != IOSTAT_SUCCESS)) {
+	    (get_job_ulpstatus(phba, iocbqrsp) != IOSTAT_SUCCESS)) {
 		if (status != IOCB_SUCCESS ||
-		    iocbqrsp->iocb.ulpStatus != IOSTAT_FCP_RSP_ERROR)
+		    get_job_ulpstatus(phba, iocbqrsp) != IOSTAT_FCP_RSP_ERROR)
 			lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT,
 					 "0727 TMF %s to TGT %d LUN %llu "
-					 "failed (%d, %d) iocb_flag x%x\n",
+					 "failed (%d, %d) cmd_flag x%x\n",
 					 lpfc_taskmgmt_name(task_mgmt_cmd),
 					 tgt_id, lun_id,
-					 iocbqrsp->iocb.ulpStatus,
-					 iocbqrsp->iocb.un.ulpWord[4],
-					 iocbq->iocb_flag);
+					 get_job_ulpstatus(phba, iocbqrsp),
+					 get_job_word4(phba, iocbqrsp),
+					 iocbq->cmd_flag);
 		/* if ulpStatus != IOCB_SUCCESS, then status == IOCB_SUCCESS */
 		if (status == IOCB_SUCCESS) {
-			if (iocbqrsp->iocb.ulpStatus == IOSTAT_FCP_RSP_ERROR)
+			if (get_job_ulpstatus(phba, iocbqrsp) ==
+			    IOSTAT_FCP_RSP_ERROR)
 				/* Something in the FCP_RSP was invalid.
 				 * Check conditions */
 				ret = lpfc_check_fcp_rsp(vport, lpfc_cmd);
 			else
 				ret = FAILED;
-		} else if (status == IOCB_TIMEDOUT) {
+		} else if ((status == IOCB_TIMEDOUT) ||
+			   (status == IOCB_ABORTED)) {
 			ret = TIMEOUT_ERROR;
 		} else {
 			ret = FAILED;
@@ -6209,7 +6186,7 @@ lpfc_send_taskmgmt(struct lpfc_vport *vport, struct scsi_cmnd *cmnd,
 
 	lpfc_sli_release_iocbq(phba, iocbqrsp);
 
-	if (ret != TIMEOUT_ERROR)
+	if (status != IOCB_TIMEDOUT)
 		lpfc_release_scsi_buf(phba, lpfc_cmd);
 
 	return ret;
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index d8d26cde70b6..f594a006d04c 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -70,8 +70,9 @@ static int lpfc_sli_issue_mbox_s4(struct lpfc_hba *, LPFC_MBOXQ_t *,
 				  uint32_t);
 static int lpfc_sli4_read_rev(struct lpfc_hba *, LPFC_MBOXQ_t *,
 			      uint8_t *, uint32_t *);
-static struct lpfc_iocbq *lpfc_sli4_els_wcqe_to_rspiocbq(struct lpfc_hba *,
-							 struct lpfc_iocbq *);
+static struct lpfc_iocbq *
+lpfc_sli4_els_preprocess_rspiocbq(struct lpfc_hba *phba,
+				  struct lpfc_iocbq *rspiocbq);
 static void lpfc_sli4_send_seq_to_ulp(struct lpfc_vport *,
 				      struct hbq_dmabuf *);
 static void lpfc_sli4_handle_mds_loopback(struct lpfc_vport *vport,
@@ -89,6 +90,9 @@ static struct lpfc_cqe *lpfc_sli4_cq_get(struct lpfc_queue *q);
 static void __lpfc_sli4_consume_cqe(struct lpfc_hba *phba,
 				    struct lpfc_queue *cq,
 				    struct lpfc_cqe *cqe);
+static uint16_t lpfc_wqe_bpl2sgl(struct lpfc_hba *phba,
+				 struct lpfc_iocbq *pwqeq,
+				 struct lpfc_sglq *sglq);
 
 union lpfc_wqe128 lpfc_iread_cmd_template;
 union lpfc_wqe128 lpfc_iwrite_cmd_template;
@@ -1254,21 +1258,21 @@ __lpfc_sli_get_els_sglq(struct lpfc_hba *phba, struct lpfc_iocbq *piocbq)
 	struct lpfc_sli_ring *pring = NULL;
 	int found = 0;
 
-	if (piocbq->iocb_flag & LPFC_IO_NVME_LS)
+	if (piocbq->cmd_flag & LPFC_IO_NVME_LS)
 		pring =  phba->sli4_hba.nvmels_wq->pring;
 	else
 		pring = lpfc_phba_elsring(phba);
 
 	lockdep_assert_held(&pring->ring_lock);
 
-	if (piocbq->iocb_flag &  LPFC_IO_FCP) {
+	if (piocbq->cmd_flag &  LPFC_IO_FCP) {
 		lpfc_cmd = (struct lpfc_io_buf *) piocbq->context1;
 		ndlp = lpfc_cmd->rdata->pnode;
 	} else  if ((piocbq->iocb.ulpCommand == CMD_GEN_REQUEST64_CR) &&
-			!(piocbq->iocb_flag & LPFC_IO_LIBDFC)) {
+			!(piocbq->cmd_flag & LPFC_IO_LIBDFC)) {
 		ndlp = piocbq->context_un.ndlp;
-	} else  if (piocbq->iocb_flag & LPFC_IO_LIBDFC) {
-		if (piocbq->iocb_flag & LPFC_IO_LOOPBACK)
+	} else  if (piocbq->cmd_flag & LPFC_IO_LIBDFC) {
+		if (piocbq->cmd_flag & LPFC_IO_LOOPBACK)
 			ndlp = NULL;
 		else
 			ndlp = piocbq->context_un.ndlp;
@@ -1380,7 +1384,7 @@ static void
 __lpfc_sli_release_iocbq_s4(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq)
 {
 	struct lpfc_sglq *sglq;
-	size_t start_clean = offsetof(struct lpfc_iocbq, iocb);
+	size_t start_clean = offsetof(struct lpfc_iocbq, wqe);
 	unsigned long iflag = 0;
 	struct lpfc_sli_ring *pring;
 
@@ -1391,7 +1395,7 @@ __lpfc_sli_release_iocbq_s4(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq)
 
 
 	if (sglq)  {
-		if (iocbq->iocb_flag & LPFC_IO_NVMET) {
+		if (iocbq->cmd_flag & LPFC_IO_NVMET) {
 			spin_lock_irqsave(&phba->sli4_hba.sgl_list_lock,
 					  iflag);
 			sglq->state = SGL_FREED;
@@ -1403,8 +1407,9 @@ __lpfc_sli_release_iocbq_s4(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq)
 			goto out;
 		}
 
-		if ((iocbq->iocb_flag & LPFC_EXCHANGE_BUSY) &&
-			(sglq->state != SGL_XRI_ABORTED)) {
+		if ((iocbq->cmd_flag & LPFC_EXCHANGE_BUSY) &&
+		    (!(unlikely(pci_channel_offline(phba->pcidev)))) &&
+		    sglq->state != SGL_XRI_ABORTED) {
 			spin_lock_irqsave(&phba->sli4_hba.sgl_list_lock,
 					  iflag);
 
@@ -1439,7 +1444,7 @@ out:
 	memset((char *)iocbq + start_clean, 0, sizeof(*iocbq) - start_clean);
 	iocbq->sli4_lxritag = NO_XRI;
 	iocbq->sli4_xritag = NO_XRI;
-	iocbq->iocb_flag &= ~(LPFC_IO_NVME | LPFC_IO_NVMET | LPFC_IO_CMF |
+	iocbq->cmd_flag &= ~(LPFC_IO_NVME | LPFC_IO_NVMET | LPFC_IO_CMF |
 			      LPFC_IO_NVME_LS);
 	list_add_tail(&iocbq->list, &phba->lpfc_iocb_list);
 }
@@ -1529,17 +1534,17 @@ lpfc_sli_cancel_iocbs(struct lpfc_hba *phba, struct list_head *iocblist,
 
 	while (!list_empty(iocblist)) {
 		list_remove_head(iocblist, piocb, struct lpfc_iocbq, list);
-		if (piocb->wqe_cmpl) {
-			if (piocb->iocb_flag & LPFC_IO_NVME)
+		if (piocb->cmd_cmpl) {
+			if (piocb->cmd_flag & LPFC_IO_NVME)
 				lpfc_nvme_cancel_iocb(phba, piocb,
 						      ulpstatus, ulpWord4);
 			else
 				lpfc_sli_release_iocbq(phba, piocb);
 
-		} else if (piocb->iocb_cmpl) {
+		} else if (piocb->cmd_cmpl) {
 			piocb->iocb.ulpStatus = ulpstatus;
 			piocb->iocb.un.ulpWord[4] = ulpWord4;
-			(piocb->iocb_cmpl) (phba, piocb, piocb);
+			(piocb->cmd_cmpl) (phba, piocb, piocb);
 		} else {
 			lpfc_sli_release_iocbq(phba, piocb);
 		}
@@ -1731,7 +1736,7 @@ lpfc_sli_ringtxcmpl_put(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	BUG_ON(!piocb);
 
 	list_add_tail(&piocb->list, &pring->txcmplq);
-	piocb->iocb_flag |= LPFC_IO_ON_TXCMPLQ;
+	piocb->cmd_flag |= LPFC_IO_ON_TXCMPLQ;
 	pring->txcmplq_cnt++;
 
 	if ((unlikely(pring->ringno == LPFC_ELS_RING)) &&
@@ -1772,7 +1777,7 @@ lpfc_sli_ringtx_get(struct lpfc_hba *phba, struct lpfc_sli_ring *pring)
  * lpfc_cmf_sync_cmpl - Process a CMF_SYNC_WQE cmpl
  * @phba: Pointer to HBA context object.
  * @cmdiocb: Pointer to driver command iocb object.
- * @cmf_cmpl: Pointer to completed WCQE.
+ * @rspiocb: Pointer to driver response iocb object.
  *
  * This routine will inform the driver of any BW adjustments we need
  * to make. These changes will be picked up during the next CMF
@@ -1781,10 +1786,11 @@ lpfc_sli_ringtx_get(struct lpfc_hba *phba, struct lpfc_sli_ring *pring)
  **/
 static void
 lpfc_cmf_sync_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
-		   struct lpfc_wcqe_complete *cmf_cmpl)
+		   struct lpfc_iocbq *rspiocb)
 {
 	union lpfc_wqe128 *wqe;
 	uint32_t status, info;
+	struct lpfc_wcqe_complete *wcqe = &rspiocb->wcqe_cmpl;
 	uint64_t bw, bwdif, slop;
 	uint64_t pcent, bwpcent;
 	int asig, afpin, sigcnt, fpincnt;
@@ -1792,22 +1798,22 @@ lpfc_cmf_sync_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	char *s;
 
 	/* First check for error */
-	status = bf_get(lpfc_wcqe_c_status, cmf_cmpl);
+	status = bf_get(lpfc_wcqe_c_status, wcqe);
 	if (status) {
 		lpfc_printf_log(phba, KERN_INFO, LOG_CGN_MGMT,
 				"6211 CMF_SYNC_WQE Error "
 				"req_tag x%x status x%x hwstatus x%x "
 				"tdatap x%x parm x%x\n",
-				bf_get(lpfc_wcqe_c_request_tag, cmf_cmpl),
-				bf_get(lpfc_wcqe_c_status, cmf_cmpl),
-				bf_get(lpfc_wcqe_c_hw_status, cmf_cmpl),
-				cmf_cmpl->total_data_placed,
-				cmf_cmpl->parameter);
+				bf_get(lpfc_wcqe_c_request_tag, wcqe),
+				bf_get(lpfc_wcqe_c_status, wcqe),
+				bf_get(lpfc_wcqe_c_hw_status, wcqe),
+				wcqe->total_data_placed,
+				wcqe->parameter);
 		goto out;
 	}
 
 	/* Gather congestion information on a successful cmpl */
-	info = cmf_cmpl->parameter;
+	info = wcqe->parameter;
 	phba->cmf_active_info = info;
 
 	/* See if firmware info count is valid or has changed */
@@ -1816,15 +1822,15 @@ lpfc_cmf_sync_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	else
 		phba->cmf_info_per_interval = info;
 
-	tdp = bf_get(lpfc_wcqe_c_cmf_bw, cmf_cmpl);
-	cg = bf_get(lpfc_wcqe_c_cmf_cg, cmf_cmpl);
+	tdp = bf_get(lpfc_wcqe_c_cmf_bw, wcqe);
+	cg = bf_get(lpfc_wcqe_c_cmf_cg, wcqe);
 
 	/* Get BW requirement from firmware */
 	bw = (uint64_t)tdp * LPFC_CMF_BLK_SIZE;
 	if (!bw) {
 		lpfc_printf_log(phba, KERN_INFO, LOG_CGN_MGMT,
 				"6212 CMF_SYNC_WQE x%x: NULL bw\n",
-				bf_get(lpfc_wcqe_c_request_tag, cmf_cmpl));
+				bf_get(lpfc_wcqe_c_request_tag, wcqe));
 		goto out;
 	}
 
@@ -1933,7 +1939,7 @@ lpfc_issue_cmf_sync_wqe(struct lpfc_hba *phba, u32 ms, u64 total)
 	sync_buf = __lpfc_sli_get_iocbq(phba);
 	if (!sync_buf) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_CGN_MGMT,
-				"6213 No available WQEs for CMF_SYNC_WQE\n");
+				"6244 No available WQEs for CMF_SYNC_WQE\n");
 		ret_val = ENOMEM;
 		goto out_unlock;
 	}
@@ -1998,19 +2004,20 @@ initpath:
 	bf_set(cmf_sync_cqid, &wqe->cmf_sync, LPFC_WQE_CQ_ID_DEFAULT);
 
 	sync_buf->vport = phba->pport;
-	sync_buf->wqe_cmpl = lpfc_cmf_sync_cmpl;
-	sync_buf->iocb_cmpl = NULL;
+	sync_buf->cmd_cmpl = lpfc_cmf_sync_cmpl;
 	sync_buf->context1 = NULL;
 	sync_buf->context2 = NULL;
 	sync_buf->context3 = NULL;
 	sync_buf->sli4_xritag = NO_XRI;
 
-	sync_buf->iocb_flag |= LPFC_IO_CMF;
+	sync_buf->cmd_flag |= LPFC_IO_CMF;
 	ret_val = lpfc_sli4_issue_wqe(phba, &phba->sli4_hba.hdwq[0], sync_buf);
-	if (ret_val)
+	if (ret_val) {
 		lpfc_printf_log(phba, KERN_INFO, LOG_CGN_MGMT,
 				"6214 Cannot issue CMF_SYNC_WQE: x%x\n",
 				ret_val);
+		__lpfc_sli_release_iocbq(phba, sync_buf);
+	}
 out_unlock:
 	spin_unlock_irqrestore(&phba->hbalock, iflags);
 	return ret_val;
@@ -2172,7 +2179,7 @@ lpfc_sli_submit_iocb(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	/*
 	 * Set up an iotag
 	 */
-	nextiocb->iocb.ulpIoTag = (nextiocb->iocb_cmpl) ? nextiocb->iotag : 0;
+	nextiocb->iocb.ulpIoTag = (nextiocb->cmd_cmpl) ? nextiocb->iotag : 0;
 
 
 	if (pring->ringno == LPFC_ELS_RING) {
@@ -2193,9 +2200,9 @@ lpfc_sli_submit_iocb(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	/*
 	 * If there is no completion routine to call, we can release the
 	 * IOCB buffer back right now. For IOCBs, like QUE_RING_BUF,
-	 * that have no rsp ring completion, iocb_cmpl MUST be NULL.
+	 * that have no rsp ring completion, cmd_cmpl MUST be NULL.
 	 */
-	if (nextiocb->iocb_cmpl)
+	if (nextiocb->cmd_cmpl)
 		lpfc_sli_ringtxcmpl_put(phba, pring, nextiocb);
 	else
 		__lpfc_sli_release_iocbq(phba, nextiocb);
@@ -3549,36 +3556,28 @@ lpfc_sli_iocbq_lookup(struct lpfc_hba *phba,
 		      struct lpfc_iocbq *prspiocb)
 {
 	struct lpfc_iocbq *cmd_iocb = NULL;
-	uint16_t iotag;
-	spinlock_t *temp_lock = NULL;
-	unsigned long iflag = 0;
+	u16 iotag;
 
 	if (phba->sli_rev == LPFC_SLI_REV4)
-		temp_lock = &pring->ring_lock;
+		iotag = get_wqe_reqtag(prspiocb);
 	else
-		temp_lock = &phba->hbalock;
-
-	spin_lock_irqsave(temp_lock, iflag);
-	iotag = prspiocb->iocb.ulpIoTag;
+		iotag = prspiocb->iocb.ulpIoTag;
 
 	if (iotag != 0 && iotag <= phba->sli.last_iotag) {
 		cmd_iocb = phba->sli.iocbq_lookup[iotag];
-		if (cmd_iocb->iocb_flag & LPFC_IO_ON_TXCMPLQ) {
+		if (cmd_iocb->cmd_flag & LPFC_IO_ON_TXCMPLQ) {
 			/* remove from txcmpl queue list */
 			list_del_init(&cmd_iocb->list);
-			cmd_iocb->iocb_flag &= ~LPFC_IO_ON_TXCMPLQ;
+			cmd_iocb->cmd_flag &= ~LPFC_IO_ON_TXCMPLQ;
 			pring->txcmplq_cnt--;
-			spin_unlock_irqrestore(temp_lock, iflag);
 			return cmd_iocb;
 		}
 	}
 
-	spin_unlock_irqrestore(temp_lock, iflag);
 	lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT,
 			"0317 iotag x%x is out of "
-			"range: max iotag x%x wd0 x%x\n",
-			iotag, phba->sli.last_iotag,
-			*(((uint32_t *) &prspiocb->iocb) + 7));
+			"range: max iotag x%x\n",
+			iotag, phba->sli.last_iotag);
 	return NULL;
 }
 
@@ -3599,33 +3598,23 @@ lpfc_sli_iocbq_lookup_by_tag(struct lpfc_hba *phba,
 			     struct lpfc_sli_ring *pring, uint16_t iotag)
 {
 	struct lpfc_iocbq *cmd_iocb = NULL;
-	spinlock_t *temp_lock = NULL;
-	unsigned long iflag = 0;
-
-	if (phba->sli_rev == LPFC_SLI_REV4)
-		temp_lock = &pring->ring_lock;
-	else
-		temp_lock = &phba->hbalock;
 
-	spin_lock_irqsave(temp_lock, iflag);
 	if (iotag != 0 && iotag <= phba->sli.last_iotag) {
 		cmd_iocb = phba->sli.iocbq_lookup[iotag];
-		if (cmd_iocb->iocb_flag & LPFC_IO_ON_TXCMPLQ) {
+		if (cmd_iocb->cmd_flag & LPFC_IO_ON_TXCMPLQ) {
 			/* remove from txcmpl queue list */
 			list_del_init(&cmd_iocb->list);
-			cmd_iocb->iocb_flag &= ~LPFC_IO_ON_TXCMPLQ;
+			cmd_iocb->cmd_flag &= ~LPFC_IO_ON_TXCMPLQ;
 			pring->txcmplq_cnt--;
-			spin_unlock_irqrestore(temp_lock, iflag);
 			return cmd_iocb;
 		}
 	}
 
-	spin_unlock_irqrestore(temp_lock, iflag);
 	lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT,
 			"0372 iotag x%x lookup error: max iotag (x%x) "
-			"iocb_flag x%x\n",
+			"cmd_flag x%x\n",
 			iotag, phba->sli.last_iotag,
-			cmd_iocb ? cmd_iocb->iocb_flag : 0xffff);
+			cmd_iocb ? cmd_iocb->cmd_flag : 0xffff);
 	return NULL;
 }
 
@@ -3653,18 +3642,37 @@ lpfc_sli_process_sol_iocb(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	struct lpfc_iocbq *cmdiocbp;
 	int rc = 1;
 	unsigned long iflag;
+	u32 ulp_command, ulp_status, ulp_word4, ulp_context, iotag;
 
+	if (phba->sli_rev == LPFC_SLI_REV4)
+		spin_lock_irqsave(&pring->ring_lock, iflag);
+	else
+		spin_lock_irqsave(&phba->hbalock, iflag);
 	cmdiocbp = lpfc_sli_iocbq_lookup(phba, pring, saveq);
+	if (phba->sli_rev == LPFC_SLI_REV4)
+		spin_unlock_irqrestore(&pring->ring_lock, iflag);
+	else
+		spin_unlock_irqrestore(&phba->hbalock, iflag);
+
+	ulp_command = get_job_cmnd(phba, saveq);
+	ulp_status = get_job_ulpstatus(phba, saveq);
+	ulp_word4 = get_job_word4(phba, saveq);
+	ulp_context = get_job_ulpcontext(phba, saveq);
+	if (phba->sli_rev == LPFC_SLI_REV4)
+		iotag = get_wqe_reqtag(saveq);
+	else
+		iotag = saveq->iocb.ulpIoTag;
+
 	if (cmdiocbp) {
-		if (cmdiocbp->iocb_cmpl) {
+		ulp_command = get_job_cmnd(phba, cmdiocbp);
+		if (cmdiocbp->cmd_cmpl) {
 			/*
 			 * If an ELS command failed send an event to mgmt
 			 * application.
 			 */
-			if (saveq->iocb.ulpStatus &&
+			if (ulp_status &&
 			     (pring->ringno == LPFC_ELS_RING) &&
-			     (cmdiocbp->iocb.ulpCommand ==
-				CMD_ELS_REQUEST64_CR))
+			     (ulp_command == CMD_ELS_REQUEST64_CR))
 				lpfc_send_els_failure_event(phba,
 					cmdiocbp, saveq);
 
@@ -3674,11 +3682,11 @@ lpfc_sli_process_sol_iocb(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 			 */
 			if (pring->ringno == LPFC_ELS_RING) {
 				if ((phba->sli_rev < LPFC_SLI_REV4) &&
-				    (cmdiocbp->iocb_flag &
+				    (cmdiocbp->cmd_flag &
 							LPFC_DRIVER_ABORTED)) {
 					spin_lock_irqsave(&phba->hbalock,
 							  iflag);
-					cmdiocbp->iocb_flag &=
+					cmdiocbp->cmd_flag &=
 						~LPFC_DRIVER_ABORTED;
 					spin_unlock_irqrestore(&phba->hbalock,
 							       iflag);
@@ -3693,12 +3701,12 @@ lpfc_sli_process_sol_iocb(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 					 */
 					spin_lock_irqsave(&phba->hbalock,
 							  iflag);
-					saveq->iocb_flag |= LPFC_DELAY_MEM_FREE;
+					saveq->cmd_flag |= LPFC_DELAY_MEM_FREE;
 					spin_unlock_irqrestore(&phba->hbalock,
 							       iflag);
 				}
 				if (phba->sli_rev == LPFC_SLI_REV4) {
-					if (saveq->iocb_flag &
+					if (saveq->cmd_flag &
 					    LPFC_EXCHANGE_BUSY) {
 						/* Set cmdiocb flag for the
 						 * exchange busy so sgl (xri)
@@ -3708,12 +3716,12 @@ lpfc_sli_process_sol_iocb(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 						 */
 						spin_lock_irqsave(
 							&phba->hbalock, iflag);
-						cmdiocbp->iocb_flag |=
+						cmdiocbp->cmd_flag |=
 							LPFC_EXCHANGE_BUSY;
 						spin_unlock_irqrestore(
 							&phba->hbalock, iflag);
 					}
-					if (cmdiocbp->iocb_flag &
+					if (cmdiocbp->cmd_flag &
 					    LPFC_DRIVER_ABORTED) {
 						/*
 						 * Clear LPFC_DRIVER_ABORTED
@@ -3722,34 +3730,34 @@ lpfc_sli_process_sol_iocb(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 						 */
 						spin_lock_irqsave(
 							&phba->hbalock, iflag);
-						cmdiocbp->iocb_flag &=
+						cmdiocbp->cmd_flag &=
 							~LPFC_DRIVER_ABORTED;
 						spin_unlock_irqrestore(
 							&phba->hbalock, iflag);
-						cmdiocbp->iocb.ulpStatus =
-							IOSTAT_LOCAL_REJECT;
-						cmdiocbp->iocb.un.ulpWord[4] =
-							IOERR_ABORT_REQUESTED;
+						set_job_ulpstatus(cmdiocbp,
+								  IOSTAT_LOCAL_REJECT);
+						set_job_ulpword4(cmdiocbp,
+								 IOERR_ABORT_REQUESTED);
 						/*
-						 * For SLI4, irsiocb contains
+						 * For SLI4, irspiocb contains
 						 * NO_XRI in sli_xritag, it
 						 * shall not affect releasing
 						 * sgl (xri) process.
 						 */
-						saveq->iocb.ulpStatus =
-							IOSTAT_LOCAL_REJECT;
-						saveq->iocb.un.ulpWord[4] =
-							IOERR_SLI_ABORTED;
+						set_job_ulpstatus(saveq,
+								  IOSTAT_LOCAL_REJECT);
+						set_job_ulpword4(saveq,
+								 IOERR_SLI_ABORTED);
 						spin_lock_irqsave(
 							&phba->hbalock, iflag);
-						saveq->iocb_flag |=
+						saveq->cmd_flag |=
 							LPFC_DELAY_MEM_FREE;
 						spin_unlock_irqrestore(
 							&phba->hbalock, iflag);
 					}
 				}
 			}
-			(cmdiocbp->iocb_cmpl) (phba, cmdiocbp, saveq);
+			cmdiocbp->cmd_cmpl(phba, cmdiocbp, saveq);
 		} else
 			lpfc_sli_release_iocbq(phba, cmdiocbp);
 	} else {
@@ -3767,12 +3775,8 @@ lpfc_sli_process_sol_iocb(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 					 "0322 Ring %d handler: "
 					 "unexpected completion IoTag x%x "
 					 "Data: x%x x%x x%x x%x\n",
-					 pring->ringno,
-					 saveq->iocb.ulpIoTag,
-					 saveq->iocb.ulpStatus,
-					 saveq->iocb.un.ulpWord[4],
-					 saveq->iocb.ulpCommand,
-					 saveq->iocb.ulpContext);
+					 pring->ringno, iotag, ulp_status,
+					 ulp_word4, ulp_command, ulp_context);
 		}
 	}
 
@@ -3985,18 +3989,15 @@ lpfc_sli_handle_fast_ring_event(struct lpfc_hba *phba,
 				break;
 			}
 
-			spin_unlock_irqrestore(&phba->hbalock, iflag);
 			cmdiocbq = lpfc_sli_iocbq_lookup(phba, pring,
 							 &rspiocbq);
-			spin_lock_irqsave(&phba->hbalock, iflag);
 			if (unlikely(!cmdiocbq))
 				break;
-			if (cmdiocbq->iocb_flag & LPFC_DRIVER_ABORTED)
-				cmdiocbq->iocb_flag &= ~LPFC_DRIVER_ABORTED;
-			if (cmdiocbq->iocb_cmpl) {
+			if (cmdiocbq->cmd_flag & LPFC_DRIVER_ABORTED)
+				cmdiocbq->cmd_flag &= ~LPFC_DRIVER_ABORTED;
+			if (cmdiocbq->cmd_cmpl) {
 				spin_unlock_irqrestore(&phba->hbalock, iflag);
-				(cmdiocbq->iocb_cmpl)(phba, cmdiocbq,
-						      &rspiocbq);
+				cmdiocbq->cmd_cmpl(phba, cmdiocbq, &rspiocbq);
 				spin_lock_irqsave(&phba->hbalock, iflag);
 			}
 			break;
@@ -4087,155 +4088,159 @@ lpfc_sli_sp_handle_rspiocb(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 			struct lpfc_iocbq *rspiocbp)
 {
 	struct lpfc_iocbq *saveq;
-	struct lpfc_iocbq *cmdiocbp;
+	struct lpfc_iocbq *cmdiocb;
 	struct lpfc_iocbq *next_iocb;
-	IOCB_t *irsp = NULL;
+	IOCB_t *irsp;
 	uint32_t free_saveq;
-	uint8_t iocb_cmd_type;
+	u8 cmd_type;
 	lpfc_iocb_type type;
 	unsigned long iflag;
+	u32 ulp_status = get_job_ulpstatus(phba, rspiocbp);
+	u32 ulp_word4 = get_job_word4(phba, rspiocbp);
+	u32 ulp_command = get_job_cmnd(phba, rspiocbp);
 	int rc;
 
 	spin_lock_irqsave(&phba->hbalock, iflag);
 	/* First add the response iocb to the countinueq list */
-	list_add_tail(&rspiocbp->list, &(pring->iocb_continueq));
+	list_add_tail(&rspiocbp->list, &pring->iocb_continueq);
 	pring->iocb_continueq_cnt++;
 
-	/* Now, determine whether the list is completed for processing */
-	irsp = &rspiocbp->iocb;
-	if (irsp->ulpLe) {
-		/*
-		 * By default, the driver expects to free all resources
-		 * associated with this iocb completion.
-		 */
-		free_saveq = 1;
-		saveq = list_get_first(&pring->iocb_continueq,
-				       struct lpfc_iocbq, list);
-		irsp = &(saveq->iocb);
-		list_del_init(&pring->iocb_continueq);
-		pring->iocb_continueq_cnt = 0;
+	/*
+	 * By default, the driver expects to free all resources
+	 * associated with this iocb completion.
+	 */
+	free_saveq = 1;
+	saveq = list_get_first(&pring->iocb_continueq,
+			       struct lpfc_iocbq, list);
+	list_del_init(&pring->iocb_continueq);
+	pring->iocb_continueq_cnt = 0;
 
-		pring->stats.iocb_rsp++;
+	pring->stats.iocb_rsp++;
 
-		/*
-		 * If resource errors reported from HBA, reduce
-		 * queuedepths of the SCSI device.
-		 */
-		if ((irsp->ulpStatus == IOSTAT_LOCAL_REJECT) &&
-		    ((irsp->un.ulpWord[4] & IOERR_PARAM_MASK) ==
-		     IOERR_NO_RESOURCES)) {
-			spin_unlock_irqrestore(&phba->hbalock, iflag);
-			phba->lpfc_rampdown_queue_depth(phba);
-			spin_lock_irqsave(&phba->hbalock, iflag);
-		}
+	/*
+	 * If resource errors reported from HBA, reduce
+	 * queuedepths of the SCSI device.
+	 */
+	if (ulp_status == IOSTAT_LOCAL_REJECT &&
+	    ((ulp_word4 & IOERR_PARAM_MASK) ==
+	     IOERR_NO_RESOURCES)) {
+		spin_unlock_irqrestore(&phba->hbalock, iflag);
+		phba->lpfc_rampdown_queue_depth(phba);
+		spin_lock_irqsave(&phba->hbalock, iflag);
+	}
 
-		if (irsp->ulpStatus) {
-			/* Rsp ring <ringno> error: IOCB */
+	if (ulp_status) {
+		/* Rsp ring <ringno> error: IOCB */
+		if (phba->sli_rev < LPFC_SLI_REV4) {
+			irsp = &rspiocbp->iocb;
+			lpfc_printf_log(phba, KERN_WARNING, LOG_SLI,
+					"0328 Rsp Ring %d error: ulp_status x%x "
+					"IOCB Data: "
+					"x%08x x%08x x%08x x%08x "
+					"x%08x x%08x x%08x x%08x "
+					"x%08x x%08x x%08x x%08x "
+					"x%08x x%08x x%08x x%08x\n",
+					pring->ringno, ulp_status,
+					get_job_ulpword(rspiocbp, 0),
+					get_job_ulpword(rspiocbp, 1),
+					get_job_ulpword(rspiocbp, 2),
+					get_job_ulpword(rspiocbp, 3),
+					get_job_ulpword(rspiocbp, 4),
+					get_job_ulpword(rspiocbp, 5),
+					*(((uint32_t *)irsp) + 6),
+					*(((uint32_t *)irsp) + 7),
+					*(((uint32_t *)irsp) + 8),
+					*(((uint32_t *)irsp) + 9),
+					*(((uint32_t *)irsp) + 10),
+					*(((uint32_t *)irsp) + 11),
+					*(((uint32_t *)irsp) + 12),
+					*(((uint32_t *)irsp) + 13),
+					*(((uint32_t *)irsp) + 14),
+					*(((uint32_t *)irsp) + 15));
+		} else {
 			lpfc_printf_log(phba, KERN_WARNING, LOG_SLI,
-					"0328 Rsp Ring %d error: "
+					"0321 Rsp Ring %d error: "
 					"IOCB Data: "
-					"x%x x%x x%x x%x "
-					"x%x x%x x%x x%x "
-					"x%x x%x x%x x%x "
 					"x%x x%x x%x x%x\n",
 					pring->ringno,
-					irsp->un.ulpWord[0],
-					irsp->un.ulpWord[1],
-					irsp->un.ulpWord[2],
-					irsp->un.ulpWord[3],
-					irsp->un.ulpWord[4],
-					irsp->un.ulpWord[5],
-					*(((uint32_t *) irsp) + 6),
-					*(((uint32_t *) irsp) + 7),
-					*(((uint32_t *) irsp) + 8),
-					*(((uint32_t *) irsp) + 9),
-					*(((uint32_t *) irsp) + 10),
-					*(((uint32_t *) irsp) + 11),
-					*(((uint32_t *) irsp) + 12),
-					*(((uint32_t *) irsp) + 13),
-					*(((uint32_t *) irsp) + 14),
-					*(((uint32_t *) irsp) + 15));
+					rspiocbp->wcqe_cmpl.word0,
+					rspiocbp->wcqe_cmpl.total_data_placed,
+					rspiocbp->wcqe_cmpl.parameter,
+					rspiocbp->wcqe_cmpl.word3);
 		}
+	}
 
-		/*
-		 * Fetch the IOCB command type and call the correct completion
-		 * routine. Solicited and Unsolicited IOCBs on the ELS ring
-		 * get freed back to the lpfc_iocb_list by the discovery
-		 * kernel thread.
-		 */
-		iocb_cmd_type = irsp->ulpCommand & CMD_IOCB_MASK;
-		type = lpfc_sli_iocb_cmd_type(iocb_cmd_type);
-		switch (type) {
-		case LPFC_SOL_IOCB:
-			spin_unlock_irqrestore(&phba->hbalock, iflag);
-			rc = lpfc_sli_process_sol_iocb(phba, pring, saveq);
-			spin_lock_irqsave(&phba->hbalock, iflag);
-			break;
-
-		case LPFC_UNSOL_IOCB:
-			spin_unlock_irqrestore(&phba->hbalock, iflag);
-			rc = lpfc_sli_process_unsol_iocb(phba, pring, saveq);
-			spin_lock_irqsave(&phba->hbalock, iflag);
-			if (!rc)
-				free_saveq = 0;
-			break;
 
-		case LPFC_ABORT_IOCB:
-			cmdiocbp = NULL;
-			if (irsp->ulpCommand != CMD_XRI_ABORTED_CX) {
+	/*
+	 * Fetch the iocb command type and call the correct completion
+	 * routine. Solicited and Unsolicited IOCBs on the ELS ring
+	 * get freed back to the lpfc_iocb_list by the discovery
+	 * kernel thread.
+	 */
+	cmd_type = ulp_command & CMD_IOCB_MASK;
+	type = lpfc_sli_iocb_cmd_type(cmd_type);
+	switch (type) {
+	case LPFC_SOL_IOCB:
+		spin_unlock_irqrestore(&phba->hbalock, iflag);
+		rc = lpfc_sli_process_sol_iocb(phba, pring, saveq);
+		spin_lock_irqsave(&phba->hbalock, iflag);
+		break;
+	case LPFC_UNSOL_IOCB:
+		spin_unlock_irqrestore(&phba->hbalock, iflag);
+		rc = lpfc_sli_process_unsol_iocb(phba, pring, saveq);
+		spin_lock_irqsave(&phba->hbalock, iflag);
+		if (!rc)
+			free_saveq = 0;
+		break;
+	case LPFC_ABORT_IOCB:
+		cmdiocb = NULL;
+		if (ulp_command != CMD_XRI_ABORTED_CX)
+			cmdiocb = lpfc_sli_iocbq_lookup(phba, pring,
+							saveq);
+		if (cmdiocb) {
+			/* Call the specified completion routine */
+			if (cmdiocb->cmd_cmpl) {
 				spin_unlock_irqrestore(&phba->hbalock, iflag);
-				cmdiocbp = lpfc_sli_iocbq_lookup(phba, pring,
-								 saveq);
+				cmdiocb->cmd_cmpl(phba, cmdiocb, saveq);
 				spin_lock_irqsave(&phba->hbalock, iflag);
-			}
-			if (cmdiocbp) {
-				/* Call the specified completion routine */
-				if (cmdiocbp->iocb_cmpl) {
-					spin_unlock_irqrestore(&phba->hbalock,
-							       iflag);
-					(cmdiocbp->iocb_cmpl)(phba, cmdiocbp,
-							      saveq);
-					spin_lock_irqsave(&phba->hbalock,
-							  iflag);
-				} else
-					__lpfc_sli_release_iocbq(phba,
-								 cmdiocbp);
-			}
-			break;
-
-		case LPFC_UNKNOWN_IOCB:
-			if (irsp->ulpCommand == CMD_ADAPTER_MSG) {
-				char adaptermsg[LPFC_MAX_ADPTMSG];
-				memset(adaptermsg, 0, LPFC_MAX_ADPTMSG);
-				memcpy(&adaptermsg[0], (uint8_t *)irsp,
-				       MAX_MSG_DATA);
-				dev_warn(&((phba->pcidev)->dev),
-					 "lpfc%d: %s\n",
-					 phba->brd_no, adaptermsg);
 			} else {
-				/* Unknown IOCB command */
-				lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT,
-						"0335 Unknown IOCB "
-						"command Data: x%x "
-						"x%x x%x x%x\n",
-						irsp->ulpCommand,
-						irsp->ulpStatus,
-						irsp->ulpIoTag,
-						irsp->ulpContext);
+				__lpfc_sli_release_iocbq(phba, cmdiocb);
 			}
-			break;
 		}
+		break;
+	case LPFC_UNKNOWN_IOCB:
+		if (ulp_command == CMD_ADAPTER_MSG) {
+			char adaptermsg[LPFC_MAX_ADPTMSG];
+
+			memset(adaptermsg, 0, LPFC_MAX_ADPTMSG);
+			memcpy(&adaptermsg[0], (uint8_t *)&rspiocbp->wqe,
+			       MAX_MSG_DATA);
+			dev_warn(&((phba->pcidev)->dev),
+				 "lpfc%d: %s\n",
+				 phba->brd_no, adaptermsg);
+		} else {
+			/* Unknown command */
+			lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT,
+					"0335 Unknown IOCB "
+					"command Data: x%x "
+					"x%x x%x x%x\n",
+					ulp_command,
+					ulp_status,
+					get_wqe_reqtag(rspiocbp),
+					get_job_ulpcontext(phba, rspiocbp));
+		}
+		break;
+	}
 
-		if (free_saveq) {
-			list_for_each_entry_safe(rspiocbp, next_iocb,
-						 &saveq->list, list) {
-				list_del_init(&rspiocbp->list);
-				__lpfc_sli_release_iocbq(phba, rspiocbp);
-			}
-			__lpfc_sli_release_iocbq(phba, saveq);
+	if (free_saveq) {
+		list_for_each_entry_safe(rspiocbp, next_iocb,
+					 &saveq->list, list) {
+			list_del_init(&rspiocbp->list);
+			__lpfc_sli_release_iocbq(phba, rspiocbp);
 		}
-		rspiocbp = NULL;
+		__lpfc_sli_release_iocbq(phba, saveq);
 	}
+	rspiocbp = NULL;
 	spin_unlock_irqrestore(&phba->hbalock, iflag);
 	return rspiocbp;
 }
@@ -4428,8 +4433,8 @@ lpfc_sli_handle_slow_ring_event_s4(struct lpfc_hba *phba,
 			irspiocbq = container_of(cq_event, struct lpfc_iocbq,
 						 cq_event);
 			/* Translate ELS WCQE to response IOCBQ */
-			irspiocbq = lpfc_sli4_els_wcqe_to_rspiocbq(phba,
-								   irspiocbq);
+			irspiocbq = lpfc_sli4_els_preprocess_rspiocbq(phba,
+								      irspiocbq);
 			if (irspiocbq)
 				lpfc_sli_sp_handle_rspiocb(phba, pring,
 							   irspiocbq);
@@ -4572,7 +4577,7 @@ lpfc_sli_flush_io_rings(struct lpfc_hba *phba)
 			list_splice_init(&pring->txq, &txq);
 			list_for_each_entry_safe(piocb, next_iocb,
 						 &pring->txcmplq, list)
-				piocb->iocb_flag &= ~LPFC_IO_ON_TXCMPLQ;
+				piocb->cmd_flag &= ~LPFC_IO_ON_TXCMPLQ;
 			/* Retrieve everything on the txcmplq */
 			list_splice_init(&pring->txcmplq, &txcmplq);
 			pring->txq_cnt = 0;
@@ -4583,10 +4588,12 @@ lpfc_sli_flush_io_rings(struct lpfc_hba *phba)
 			lpfc_sli_cancel_iocbs(phba, &txq,
 					      IOSTAT_LOCAL_REJECT,
 					      IOERR_SLI_DOWN);
-			/* Flush the txcmpq */
+			/* Flush the txcmplq */
 			lpfc_sli_cancel_iocbs(phba, &txcmplq,
 					      IOSTAT_LOCAL_REJECT,
 					      IOERR_SLI_DOWN);
+			if (unlikely(pci_channel_offline(phba->pcidev)))
+				lpfc_sli4_io_xri_aborted(phba, NULL, 0);
 		}
 	} else {
 		pring = &psli->sli3_ring[LPFC_FCP_RING];
@@ -4596,7 +4603,7 @@ lpfc_sli_flush_io_rings(struct lpfc_hba *phba)
 		list_splice_init(&pring->txq, &txq);
 		list_for_each_entry_safe(piocb, next_iocb,
 					 &pring->txcmplq, list)
-			piocb->iocb_flag &= ~LPFC_IO_ON_TXCMPLQ;
+			piocb->cmd_flag &= ~LPFC_IO_ON_TXCMPLQ;
 		/* Retrieve everything on the txcmplq */
 		list_splice_init(&pring->txcmplq, &txcmplq);
 		pring->txq_cnt = 0;
@@ -10112,7 +10119,7 @@ __lpfc_sli_issue_iocb_s3(struct lpfc_hba *phba, uint32_t ring_number,
 
 	lockdep_assert_held(&phba->hbalock);
 
-	if (piocb->iocb_cmpl && (!piocb->vport) &&
+	if (piocb->cmd_cmpl && (!piocb->vport) &&
 	   (piocb->iocb.ulpCommand != CMD_ABORT_XRI_CN) &&
 	   (piocb->iocb.ulpCommand != CMD_CLOSE_XRI_CN)) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT,
@@ -10164,10 +10171,10 @@ __lpfc_sli_issue_iocb_s3(struct lpfc_hba *phba, uint32_t ring_number,
 		case CMD_QUE_RING_BUF64_CN:
 			/*
 			 * For IOCBs, like QUE_RING_BUF, that have no rsp ring
-			 * completion, iocb_cmpl MUST be 0.
+			 * completion, cmd_cmpl MUST be 0.
 			 */
-			if (piocb->iocb_cmpl)
-				piocb->iocb_cmpl = NULL;
+			if (piocb->cmd_cmpl)
+				piocb->cmd_cmpl = NULL;
 			fallthrough;
 		case CMD_CREATE_XRI_CR:
 		case CMD_CLOSE_XRI_CN:
@@ -10358,9 +10365,9 @@ lpfc_sli4_iocb2wqe(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq,
 
 	fip = phba->hba_flag & HBA_FIP_SUPPORT;
 	/* The fcp commands will set command type */
-	if (iocbq->iocb_flag &  LPFC_IO_FCP)
+	if (iocbq->cmd_flag &  LPFC_IO_FCP)
 		command_type = FCP_COMMAND;
-	else if (fip && (iocbq->iocb_flag & LPFC_FIP_ELS_ID_MASK))
+	else if (fip && (iocbq->cmd_flag & LPFC_FIP_ELS_ID_MASK))
 		command_type = ELS_COMMAND_FIP;
 	else
 		command_type = ELS_COMMAND_NON_FIP;
@@ -10405,7 +10412,7 @@ lpfc_sli4_iocb2wqe(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq,
 
 	switch (iocbq->iocb.ulpCommand) {
 	case CMD_ELS_REQUEST64_CR:
-		if (iocbq->iocb_flag & LPFC_IO_LIBDFC)
+		if (iocbq->cmd_flag & LPFC_IO_LIBDFC)
 			ndlp = iocbq->context_un.ndlp;
 		else
 			ndlp = (struct lpfc_nodelist *)iocbq->context1;
@@ -10432,7 +10439,7 @@ lpfc_sli4_iocb2wqe(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq,
 		bf_set(wqe_pu, &wqe->els_req.wqe_com, 0);
 		/* CCP CCPE PV PRI in word10 were set in the memcpy */
 		if (command_type == ELS_COMMAND_FIP)
-			els_id = ((iocbq->iocb_flag & LPFC_FIP_ELS_ID_MASK)
+			els_id = ((iocbq->cmd_flag & LPFC_FIP_ELS_ID_MASK)
 					>> LPFC_FIP_ELS_ID_SHIFT);
 		pcmd = (uint32_t *) (((struct lpfc_dmabuf *)
 					iocbq->context2)->virt);
@@ -10534,7 +10541,7 @@ lpfc_sli4_iocb2wqe(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq,
 		       LPFC_WQE_LENLOC_WORD4);
 		bf_set(wqe_pu, &wqe->fcp_iwrite.wqe_com, iocbq->iocb.ulpPU);
 		bf_set(wqe_dbde, &wqe->fcp_iwrite.wqe_com, 1);
-		if (iocbq->iocb_flag & LPFC_IO_OAS) {
+		if (iocbq->cmd_flag & LPFC_IO_OAS) {
 			bf_set(wqe_oas, &wqe->fcp_iwrite.wqe_com, 1);
 			bf_set(wqe_ccpe, &wqe->fcp_iwrite.wqe_com, 1);
 			if (iocbq->priority) {
@@ -10598,7 +10605,7 @@ lpfc_sli4_iocb2wqe(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq,
 		       LPFC_WQE_LENLOC_WORD4);
 		bf_set(wqe_pu, &wqe->fcp_iread.wqe_com, iocbq->iocb.ulpPU);
 		bf_set(wqe_dbde, &wqe->fcp_iread.wqe_com, 1);
-		if (iocbq->iocb_flag & LPFC_IO_OAS) {
+		if (iocbq->cmd_flag & LPFC_IO_OAS) {
 			bf_set(wqe_oas, &wqe->fcp_iread.wqe_com, 1);
 			bf_set(wqe_ccpe, &wqe->fcp_iread.wqe_com, 1);
 			if (iocbq->priority) {
@@ -10661,7 +10668,7 @@ lpfc_sli4_iocb2wqe(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq,
 		       LPFC_WQE_LENLOC_NONE);
 		bf_set(wqe_erp, &wqe->fcp_icmd.wqe_com,
 		       iocbq->iocb.ulpFCP2Rcvy);
-		if (iocbq->iocb_flag & LPFC_IO_OAS) {
+		if (iocbq->cmd_flag & LPFC_IO_OAS) {
 			bf_set(wqe_oas, &wqe->fcp_icmd.wqe_com, 1);
 			bf_set(wqe_ccpe, &wqe->fcp_icmd.wqe_com, 1);
 			if (iocbq->priority) {
@@ -10795,7 +10802,7 @@ lpfc_sli4_iocb2wqe(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq,
 		abrt_iotag = iocbq->iocb.un.acxri.abortContextTag;
 		if (abrt_iotag != 0 && abrt_iotag <= phba->sli.last_iotag) {
 			abrtiocbq = phba->sli.iocbq_lookup[abrt_iotag];
-			fip = abrtiocbq->iocb_flag & LPFC_FIP_ELS_ID_MASK;
+			fip = abrtiocbq->cmd_flag & LPFC_FIP_ELS_ID_MASK;
 		} else
 			fip = 0;
 
@@ -10904,13 +10911,13 @@ lpfc_sli4_iocb2wqe(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq,
 		return IOCB_ERROR;
 	}
 
-	if (iocbq->iocb_flag & LPFC_IO_DIF_PASS)
+	if (iocbq->cmd_flag & LPFC_IO_DIF_PASS)
 		bf_set(wqe_dif, &wqe->generic.wqe_com, LPFC_WQE_DIF_PASSTHRU);
-	else if (iocbq->iocb_flag & LPFC_IO_DIF_STRIP)
+	else if (iocbq->cmd_flag & LPFC_IO_DIF_STRIP)
 		bf_set(wqe_dif, &wqe->generic.wqe_com, LPFC_WQE_DIF_STRIP);
-	else if (iocbq->iocb_flag & LPFC_IO_DIF_INSERT)
+	else if (iocbq->cmd_flag & LPFC_IO_DIF_INSERT)
 		bf_set(wqe_dif, &wqe->generic.wqe_com, LPFC_WQE_DIF_INSERT);
-	iocbq->iocb_flag &= ~(LPFC_IO_DIF_PASS | LPFC_IO_DIF_STRIP |
+	iocbq->cmd_flag &= ~(LPFC_IO_DIF_PASS | LPFC_IO_DIF_STRIP |
 			      LPFC_IO_DIF_INSERT);
 	bf_set(wqe_xri_tag, &wqe->generic.wqe_com, xritag);
 	bf_set(wqe_reqtag, &wqe->generic.wqe_com, iocbq->iotag);
@@ -10930,7 +10937,7 @@ lpfc_sli4_iocb2wqe(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq,
  * @flag: Flag indicating if this command can be put into txq.
  *
  * __lpfc_sli_issue_fcp_io_s3 is wrapper function to invoke lockless func to
- * send  an iocb command to an HBA with SLI-4 interface spec.
+ * send  an iocb command to an HBA with SLI-3 interface spec.
  *
  * This function takes the hbalock before invoking the lockless version.
  * The function will return success after it successfully submit the wqe to
@@ -10971,7 +10978,17 @@ __lpfc_sli_issue_fcp_io_s4(struct lpfc_hba *phba, uint32_t ring_number,
 	int rc;
 	struct lpfc_io_buf *lpfc_cmd =
 		(struct lpfc_io_buf *)piocb->context1;
-	union lpfc_wqe128 *wqe = &piocb->wqe;
+
+	lpfc_prep_embed_io(phba, lpfc_cmd);
+	rc = lpfc_sli4_issue_wqe(phba, lpfc_cmd->hdwq, piocb);
+	return rc;
+}
+
+void
+lpfc_prep_embed_io(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_cmd)
+{
+	struct lpfc_iocbq *piocb = &lpfc_cmd->cur_iocbq;
+	union lpfc_wqe128 *wqe = &lpfc_cmd->cur_iocbq.wqe;
 	struct sli4_sge *sgl;
 
 	/* 128 byte wqe support here */
@@ -11009,7 +11026,7 @@ __lpfc_sli_issue_fcp_io_s4(struct lpfc_hba *phba, uint32_t ring_number,
 	}
 
 	/* add the VMID tags as per switch response */
-	if (unlikely(piocb->iocb_flag & LPFC_IO_VMID)) {
+	if (unlikely(piocb->cmd_flag & LPFC_IO_VMID)) {
 		if (phba->pport->vmid_priority_tagging) {
 			bf_set(wqe_ccpe, &wqe->fcp_iwrite.wqe_com, 1);
 			bf_set(wqe_ccp, &wqe->fcp_iwrite.wqe_com,
@@ -11020,8 +11037,6 @@ __lpfc_sli_issue_fcp_io_s4(struct lpfc_hba *phba, uint32_t ring_number,
 			wqe->words[31] = piocb->vmid_tag.app_id;
 		}
 	}
-	rc = lpfc_sli4_issue_wqe(phba, lpfc_cmd->hdwq, piocb);
-	return rc;
 }
 
 /**
@@ -11043,13 +11058,14 @@ __lpfc_sli_issue_iocb_s4(struct lpfc_hba *phba, uint32_t ring_number,
 			 struct lpfc_iocbq *piocb, uint32_t flag)
 {
 	struct lpfc_sglq *sglq;
-	union lpfc_wqe128 wqe;
+	union lpfc_wqe128 *wqe;
 	struct lpfc_queue *wq;
 	struct lpfc_sli_ring *pring;
+	u32 ulp_command = get_job_cmnd(phba, piocb);
 
 	/* Get the WQ */
-	if ((piocb->iocb_flag & LPFC_IO_FCP) ||
-	    (piocb->iocb_flag & LPFC_USE_FCPWQIDX)) {
+	if ((piocb->cmd_flag & LPFC_IO_FCP) ||
+	    (piocb->cmd_flag & LPFC_USE_FCPWQIDX)) {
 		wq = phba->sli4_hba.hdwq[piocb->hba_wqidx].io_wq;
 	} else {
 		wq = phba->sli4_hba.els_wq;
@@ -11063,10 +11079,9 @@ __lpfc_sli_issue_iocb_s4(struct lpfc_hba *phba, uint32_t ring_number,
 	 */
 
 	lockdep_assert_held(&pring->ring_lock);
-
+	wqe = &piocb->wqe;
 	if (piocb->sli4_xritag == NO_XRI) {
-		if (piocb->iocb.ulpCommand == CMD_ABORT_XRI_CN ||
-		    piocb->iocb.ulpCommand == CMD_CLOSE_XRI_CN)
+		if (ulp_command == CMD_ABORT_XRI_WQE)
 			sglq = NULL;
 		else {
 			if (!list_empty(&pring->txq)) {
@@ -11090,7 +11105,7 @@ __lpfc_sli_issue_iocb_s4(struct lpfc_hba *phba, uint32_t ring_number,
 				}
 			}
 		}
-	} else if (piocb->iocb_flag &  LPFC_IO_FCP) {
+	} else if (piocb->cmd_flag &  LPFC_IO_FCP) {
 		/* These IO's already have an XRI and a mapped sgl. */
 		sglq = NULL;
 	}
@@ -11107,14 +11122,24 @@ __lpfc_sli_issue_iocb_s4(struct lpfc_hba *phba, uint32_t ring_number,
 	if (sglq) {
 		piocb->sli4_lxritag = sglq->sli4_lxritag;
 		piocb->sli4_xritag = sglq->sli4_xritag;
-		if (NO_XRI == lpfc_sli4_bpl2sgl(phba, piocb, sglq))
+
+		/* ABTS sent by initiator to CT exchange, the
+		 * RX_ID field will be filled with the newly
+		 * allocated responder XRI.
+		 */
+		if (ulp_command == CMD_XMIT_BLS_RSP64_CX &&
+		    piocb->abort_bls == LPFC_ABTS_UNSOL_INT)
+			bf_set(xmit_bls_rsp64_rxid, &wqe->xmit_bls_rsp,
+			       piocb->sli4_xritag);
+
+		bf_set(wqe_xri_tag, &wqe->generic.wqe_com,
+		       piocb->sli4_xritag);
+
+		if (lpfc_wqe_bpl2sgl(phba, piocb, sglq) == NO_XRI)
 			return IOCB_ERROR;
 	}
 
-	if (lpfc_sli4_iocb2wqe(phba, piocb, &wqe))
-		return IOCB_ERROR;
-
-	if (lpfc_sli4_wq_put(wq, &wqe))
+	if (lpfc_sli4_wq_put(wq, wqe))
 		return IOCB_ERROR;
 	lpfc_sli_ringtxcmpl_put(phba, pring, piocb);
 
@@ -11207,14 +11232,14 @@ lpfc_sli4_calc_ring(struct lpfc_hba *phba, struct lpfc_iocbq *piocb)
 {
 	struct lpfc_io_buf *lpfc_cmd;
 
-	if (piocb->iocb_flag & (LPFC_IO_FCP | LPFC_USE_FCPWQIDX)) {
+	if (piocb->cmd_flag & (LPFC_IO_FCP | LPFC_USE_FCPWQIDX)) {
 		if (unlikely(!phba->sli4_hba.hdwq))
 			return NULL;
 		/*
 		 * for abort iocb hba_wqidx should already
 		 * be setup based on what work queue we used.
 		 */
-		if (!(piocb->iocb_flag & LPFC_USE_FCPWQIDX)) {
+		if (!(piocb->cmd_flag & LPFC_USE_FCPWQIDX)) {
 			lpfc_cmd = (struct lpfc_io_buf *)piocb->context1;
 			piocb->hba_wqidx = lpfc_cmd->hdwq_no;
 		}
@@ -12356,14 +12381,14 @@ lpfc_sli_issue_abort_iotag(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	icmd = &cmdiocb->iocb;
 	if (icmd->ulpCommand == CMD_ABORT_XRI_CN ||
 	    icmd->ulpCommand == CMD_CLOSE_XRI_CN ||
-	    cmdiocb->iocb_flag & LPFC_DRIVER_ABORTED)
+	    cmdiocb->cmd_flag & LPFC_DRIVER_ABORTED)
 		return IOCB_ABORTING;
 
 	if (!pring) {
-		if (cmdiocb->iocb_flag & LPFC_IO_FABRIC)
-			cmdiocb->fabric_iocb_cmpl = lpfc_ignore_els_cmpl;
+		if (cmdiocb->cmd_flag & LPFC_IO_FABRIC)
+			cmdiocb->fabric_cmd_cmpl = lpfc_ignore_els_cmpl;
 		else
-			cmdiocb->iocb_cmpl = lpfc_ignore_els_cmpl;
+			cmdiocb->cmd_cmpl = lpfc_ignore_els_cmpl;
 		return retval;
 	}
 
@@ -12373,10 +12398,10 @@ lpfc_sli_issue_abort_iotag(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	 */
 	if ((vport->load_flag & FC_UNLOADING) &&
 	    pring->ringno == LPFC_ELS_RING) {
-		if (cmdiocb->iocb_flag & LPFC_IO_FABRIC)
-			cmdiocb->fabric_iocb_cmpl = lpfc_ignore_els_cmpl;
+		if (cmdiocb->cmd_flag & LPFC_IO_FABRIC)
+			cmdiocb->fabric_cmd_cmpl = lpfc_ignore_els_cmpl;
 		else
-			cmdiocb->iocb_cmpl = lpfc_ignore_els_cmpl;
+			cmdiocb->cmd_cmpl = lpfc_ignore_els_cmpl;
 		return retval;
 	}
 
@@ -12388,7 +12413,7 @@ lpfc_sli_issue_abort_iotag(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	/* This signals the response to set the correct status
 	 * before calling the completion handler
 	 */
-	cmdiocb->iocb_flag |= LPFC_DRIVER_ABORTED;
+	cmdiocb->cmd_flag |= LPFC_DRIVER_ABORTED;
 
 	iabt = &abtsiocbp->iocb;
 	iabt->un.acxri.abortType = ABORT_TYPE_ABTS;
@@ -12409,10 +12434,10 @@ lpfc_sli_issue_abort_iotag(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 
 	/* ABTS WQE must go to the same WQ as the WQE to be aborted */
 	abtsiocbp->hba_wqidx = cmdiocb->hba_wqidx;
-	if (cmdiocb->iocb_flag & LPFC_IO_FCP)
-		abtsiocbp->iocb_flag |= (LPFC_IO_FCP | LPFC_USE_FCPWQIDX);
-	if (cmdiocb->iocb_flag & LPFC_IO_FOF)
-		abtsiocbp->iocb_flag |= LPFC_IO_FOF;
+	if (cmdiocb->cmd_flag & LPFC_IO_FCP)
+		abtsiocbp->cmd_flag |= (LPFC_IO_FCP | LPFC_USE_FCPWQIDX);
+	if (cmdiocb->cmd_flag & LPFC_IO_FOF)
+		abtsiocbp->cmd_flag |= LPFC_IO_FOF;
 
 	if (phba->link_state < LPFC_LINK_UP ||
 	    (phba->sli_rev == LPFC_SLI_REV4 &&
@@ -12422,9 +12447,9 @@ lpfc_sli_issue_abort_iotag(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		iabt->ulpCommand = CMD_ABORT_XRI_CN;
 
 	if (cmpl)
-		abtsiocbp->iocb_cmpl = cmpl;
+		abtsiocbp->cmd_cmpl = cmpl;
 	else
-		abtsiocbp->iocb_cmpl = lpfc_sli_abort_els_cmpl;
+		abtsiocbp->cmd_cmpl = lpfc_sli_abort_els_cmpl;
 	abtsiocbp->vport = vport;
 
 	if (phba->sli_rev == LPFC_SLI_REV4) {
@@ -12451,7 +12476,7 @@ abort_iotag_exit:
 			 abtsiocbp->iotag, retval);
 
 	if (retval) {
-		cmdiocb->iocb_flag &= ~LPFC_DRIVER_ABORTED;
+		cmdiocb->cmd_flag &= ~LPFC_DRIVER_ABORTED;
 		__lpfc_sli_release_iocbq(phba, abtsiocbp);
 	}
 
@@ -12519,9 +12544,9 @@ lpfc_sli_validate_fcp_iocb_for_abort(struct lpfc_iocbq *iocbq,
 	 * can't be premarked as driver aborted, nor be an ABORT iocb itself
 	 */
 	icmd = &iocbq->iocb;
-	if (!(iocbq->iocb_flag & LPFC_IO_FCP) ||
-	    !(iocbq->iocb_flag & LPFC_IO_ON_TXCMPLQ) ||
-	    (iocbq->iocb_flag & LPFC_DRIVER_ABORTED) ||
+	if (!(iocbq->cmd_flag & LPFC_IO_FCP) ||
+	    !(iocbq->cmd_flag & LPFC_IO_ON_TXCMPLQ) ||
+	    (iocbq->cmd_flag & LPFC_DRIVER_ABORTED) ||
 	    (icmd->ulpCommand == CMD_ABORT_XRI_CN ||
 	     icmd->ulpCommand == CMD_CLOSE_XRI_CN))
 		return -EINVAL;
@@ -12625,8 +12650,8 @@ lpfc_sli_sum_iocb(struct lpfc_vport *vport, uint16_t tgt_id, uint64_t lun_id,
 
 		if (!iocbq || iocbq->vport != vport)
 			continue;
-		if (!(iocbq->iocb_flag & LPFC_IO_FCP) ||
-		    !(iocbq->iocb_flag & LPFC_IO_ON_TXCMPLQ))
+		if (!(iocbq->cmd_flag & LPFC_IO_FCP) ||
+		    !(iocbq->cmd_flag & LPFC_IO_ON_TXCMPLQ))
 			continue;
 
 		/* Include counting outstanding aborts */
@@ -12852,8 +12877,8 @@ lpfc_sli_abort_taskmgmt(struct lpfc_vport *vport, struct lpfc_sli_ring *pring,
 		 * If the iocbq is already being aborted, don't take a second
 		 * action, but do count it.
 		 */
-		if ((iocbq->iocb_flag & LPFC_DRIVER_ABORTED) ||
-		    !(iocbq->iocb_flag & LPFC_IO_ON_TXCMPLQ)) {
+		if ((iocbq->cmd_flag & LPFC_DRIVER_ABORTED) ||
+		    !(iocbq->cmd_flag & LPFC_IO_ON_TXCMPLQ)) {
 			if (phba->sli_rev == LPFC_SLI_REV4)
 				spin_unlock(&pring_s4->ring_lock);
 			spin_unlock(&lpfc_cmd->buf_lock);
@@ -12883,10 +12908,10 @@ lpfc_sli_abort_taskmgmt(struct lpfc_vport *vport, struct lpfc_sli_ring *pring,
 
 		/* ABTS WQE must go to the same WQ as the WQE to be aborted */
 		abtsiocbq->hba_wqidx = iocbq->hba_wqidx;
-		if (iocbq->iocb_flag & LPFC_IO_FCP)
-			abtsiocbq->iocb_flag |= LPFC_USE_FCPWQIDX;
-		if (iocbq->iocb_flag & LPFC_IO_FOF)
-			abtsiocbq->iocb_flag |= LPFC_IO_FOF;
+		if (iocbq->cmd_flag & LPFC_IO_FCP)
+			abtsiocbq->cmd_flag |= LPFC_USE_FCPWQIDX;
+		if (iocbq->cmd_flag & LPFC_IO_FOF)
+			abtsiocbq->cmd_flag |= LPFC_IO_FOF;
 
 		ndlp = lpfc_cmd->rdata->pnode;
 
@@ -12897,13 +12922,13 @@ lpfc_sli_abort_taskmgmt(struct lpfc_vport *vport, struct lpfc_sli_ring *pring,
 			abtsiocbq->iocb.ulpCommand = CMD_CLOSE_XRI_CN;
 
 		/* Setup callback routine and issue the command. */
-		abtsiocbq->iocb_cmpl = lpfc_sli_abort_fcp_cmpl;
+		abtsiocbq->cmd_cmpl = lpfc_sli_abort_fcp_cmpl;
 
 		/*
 		 * Indicate the IO is being aborted by the driver and set
 		 * the caller's flag into the aborted IO.
 		 */
-		iocbq->iocb_flag |= LPFC_DRIVER_ABORTED;
+		iocbq->cmd_flag |= LPFC_DRIVER_ABORTED;
 
 		if (phba->sli_rev == LPFC_SLI_REV4) {
 			ret_val = __lpfc_sli_issue_iocb(phba, pring_s4->ringno,
@@ -12950,9 +12975,10 @@ lpfc_sli_wake_iocb_wait(struct lpfc_hba *phba,
 	wait_queue_head_t *pdone_q;
 	unsigned long iflags;
 	struct lpfc_io_buf *lpfc_cmd;
+	size_t offset = offsetof(struct lpfc_iocbq, wqe);
 
 	spin_lock_irqsave(&phba->hbalock, iflags);
-	if (cmdiocbq->iocb_flag & LPFC_IO_WAKE_TMO) {
+	if (cmdiocbq->cmd_flag & LPFC_IO_WAKE_TMO) {
 
 		/*
 		 * A time out has occurred for the iocb.  If a time out
@@ -12961,26 +12987,27 @@ lpfc_sli_wake_iocb_wait(struct lpfc_hba *phba,
 		 */
 
 		spin_unlock_irqrestore(&phba->hbalock, iflags);
-		cmdiocbq->iocb_cmpl = cmdiocbq->wait_iocb_cmpl;
-		cmdiocbq->wait_iocb_cmpl = NULL;
-		if (cmdiocbq->iocb_cmpl)
-			(cmdiocbq->iocb_cmpl)(phba, cmdiocbq, NULL);
+		cmdiocbq->cmd_cmpl = cmdiocbq->wait_cmd_cmpl;
+		cmdiocbq->wait_cmd_cmpl = NULL;
+		if (cmdiocbq->cmd_cmpl)
+			cmdiocbq->cmd_cmpl(phba, cmdiocbq, NULL);
 		else
 			lpfc_sli_release_iocbq(phba, cmdiocbq);
 		return;
 	}
 
-	cmdiocbq->iocb_flag |= LPFC_IO_WAKE;
+	/* Copy the contents of the local rspiocb into the caller's buffer. */
+	cmdiocbq->cmd_flag |= LPFC_IO_WAKE;
 	if (cmdiocbq->context2 && rspiocbq)
-		memcpy(&((struct lpfc_iocbq *)cmdiocbq->context2)->iocb,
-		       &rspiocbq->iocb, sizeof(IOCB_t));
+		memcpy((char *)cmdiocbq->context2 + offset,
+		       (char *)rspiocbq + offset, sizeof(*rspiocbq) - offset);
 
 	/* Set the exchange busy flag for task management commands */
-	if ((cmdiocbq->iocb_flag & LPFC_IO_FCP) &&
-		!(cmdiocbq->iocb_flag & LPFC_IO_LIBDFC)) {
+	if ((cmdiocbq->cmd_flag & LPFC_IO_FCP) &&
+	    !(cmdiocbq->cmd_flag & LPFC_IO_LIBDFC)) {
 		lpfc_cmd = container_of(cmdiocbq, struct lpfc_io_buf,
-			cur_iocbq);
-		if (rspiocbq && (rspiocbq->iocb_flag & LPFC_EXCHANGE_BUSY))
+					cur_iocbq);
+		if (rspiocbq && (rspiocbq->cmd_flag & LPFC_EXCHANGE_BUSY))
 			lpfc_cmd->flags |= LPFC_SBUF_XBUSY;
 		else
 			lpfc_cmd->flags &= ~LPFC_SBUF_XBUSY;
@@ -12999,7 +13026,7 @@ lpfc_sli_wake_iocb_wait(struct lpfc_hba *phba,
  * @piocbq: Pointer to command iocb.
  * @flag: Flag to test.
  *
- * This routine grabs the hbalock and then test the iocb_flag to
+ * This routine grabs the hbalock and then test the cmd_flag to
  * see if the passed in flag is set.
  * Returns:
  * 1 if flag is set.
@@ -13013,7 +13040,7 @@ lpfc_chk_iocb_flg(struct lpfc_hba *phba,
 	int ret;
 
 	spin_lock_irqsave(&phba->hbalock, iflags);
-	ret = piocbq->iocb_flag & flag;
+	ret = piocbq->cmd_flag & flag;
 	spin_unlock_irqrestore(&phba->hbalock, iflags);
 	return ret;
 
@@ -13028,14 +13055,14 @@ lpfc_chk_iocb_flg(struct lpfc_hba *phba,
  * @timeout: Timeout in number of seconds.
  *
  * This function issues the iocb to firmware and waits for the
- * iocb to complete. The iocb_cmpl field of the shall be used
+ * iocb to complete. The cmd_cmpl field of the shall be used
  * to handle iocbs which time out. If the field is NULL, the
  * function shall free the iocbq structure.  If more clean up is
  * needed, the caller is expected to provide a completion function
  * that will provide the needed clean up.  If the iocb command is
  * not completed within timeout seconds, the function will either
- * free the iocbq structure (if iocb_cmpl == NULL) or execute the
- * completion function set in the iocb_cmpl field and then return
+ * free the iocbq structure (if cmd_cmpl == NULL) or execute the
+ * completion function set in the cmd_cmpl field and then return
  * a status of IOCB_TIMEDOUT.  The caller should not free the iocb
  * resources if this function returns IOCB_TIMEDOUT.
  * The function waits for the iocb completion using an
@@ -13047,7 +13074,7 @@ lpfc_chk_iocb_flg(struct lpfc_hba *phba,
  * This function assumes that the iocb completions occur while
  * this function sleep. So, this function cannot be called from
  * the thread which process iocb completion for this ring.
- * This function clears the iocb_flag of the iocb object before
+ * This function clears the cmd_flag of the iocb object before
  * issuing the iocb and the iocb completion handler sets this
  * flag and wakes this thread when the iocb completes.
  * The contents of the response iocb will be copied to prspiocbq
@@ -13087,10 +13114,10 @@ lpfc_sli_issue_iocb_wait(struct lpfc_hba *phba,
 		piocb->context2 = prspiocbq;
 	}
 
-	piocb->wait_iocb_cmpl = piocb->iocb_cmpl;
-	piocb->iocb_cmpl = lpfc_sli_wake_iocb_wait;
+	piocb->wait_cmd_cmpl = piocb->cmd_cmpl;
+	piocb->cmd_cmpl = lpfc_sli_wake_iocb_wait;
 	piocb->context_un.wait_queue = &done_q;
-	piocb->iocb_flag &= ~(LPFC_IO_WAKE | LPFC_IO_WAKE_TMO);
+	piocb->cmd_flag &= ~(LPFC_IO_WAKE | LPFC_IO_WAKE_TMO);
 
 	if (phba->cfg_poll & DISABLE_FCP_RING_INT) {
 		if (lpfc_readl(phba->HCregaddr, &creg_val))
@@ -13108,7 +13135,7 @@ lpfc_sli_issue_iocb_wait(struct lpfc_hba *phba,
 				lpfc_chk_iocb_flg(phba, piocb, LPFC_IO_WAKE),
 				timeout_req);
 		spin_lock_irqsave(&phba->hbalock, iflags);
-		if (!(piocb->iocb_flag & LPFC_IO_WAKE)) {
+		if (!(piocb->cmd_flag & LPFC_IO_WAKE)) {
 
 			/*
 			 * IOCB timed out.  Inform the wake iocb wait
@@ -13116,7 +13143,7 @@ lpfc_sli_issue_iocb_wait(struct lpfc_hba *phba,
 			 */
 
 			iocb_completed = false;
-			piocb->iocb_flag |= LPFC_IO_WAKE_TMO;
+			piocb->cmd_flag |= LPFC_IO_WAKE_TMO;
 		}
 		spin_unlock_irqrestore(&phba->hbalock, iflags);
 		if (iocb_completed) {
@@ -13171,7 +13198,7 @@ lpfc_sli_issue_iocb_wait(struct lpfc_hba *phba,
 		piocb->context2 = NULL;
 
 	piocb->context_un.wait_queue = NULL;
-	piocb->iocb_cmpl = NULL;
+	piocb->cmd_cmpl = NULL;
 	return retval;
 }
 
@@ -14112,135 +14139,19 @@ void lpfc_sli4_els_xri_abort_event_proc(struct lpfc_hba *phba)
 }
 
 /**
- * lpfc_sli4_iocb_param_transfer - Transfer pIocbOut and cmpl status to pIocbIn
- * @phba: pointer to lpfc hba data structure
- * @pIocbIn: pointer to the rspiocbq
- * @pIocbOut: pointer to the cmdiocbq
- * @wcqe: pointer to the complete wcqe
- *
- * This routine transfers the fields of a command iocbq to a response iocbq
- * by copying all the IOCB fields from command iocbq and transferring the
- * completion status information from the complete wcqe.
- **/
-static void
-lpfc_sli4_iocb_param_transfer(struct lpfc_hba *phba,
-			      struct lpfc_iocbq *pIocbIn,
-			      struct lpfc_iocbq *pIocbOut,
-			      struct lpfc_wcqe_complete *wcqe)
-{
-	int numBdes, i;
-	unsigned long iflags;
-	uint32_t status, max_response;
-	struct lpfc_dmabuf *dmabuf;
-	struct ulp_bde64 *bpl, bde;
-	size_t offset = offsetof(struct lpfc_iocbq, iocb);
-
-	memcpy((char *)pIocbIn + offset, (char *)pIocbOut + offset,
-	       sizeof(struct lpfc_iocbq) - offset);
-	/* Map WCQE parameters into irspiocb parameters */
-	status = bf_get(lpfc_wcqe_c_status, wcqe);
-	pIocbIn->iocb.ulpStatus = (status & LPFC_IOCB_STATUS_MASK);
-	if (pIocbOut->iocb_flag & LPFC_IO_FCP)
-		if (pIocbIn->iocb.ulpStatus == IOSTAT_FCP_RSP_ERROR)
-			pIocbIn->iocb.un.fcpi.fcpi_parm =
-					pIocbOut->iocb.un.fcpi.fcpi_parm -
-					wcqe->total_data_placed;
-		else
-			pIocbIn->iocb.un.ulpWord[4] = wcqe->parameter;
-	else {
-		pIocbIn->iocb.un.ulpWord[4] = wcqe->parameter;
-		switch (pIocbOut->iocb.ulpCommand) {
-		case CMD_ELS_REQUEST64_CR:
-			dmabuf = (struct lpfc_dmabuf *)pIocbOut->context3;
-			bpl  = (struct ulp_bde64 *)dmabuf->virt;
-			bde.tus.w = le32_to_cpu(bpl[1].tus.w);
-			max_response = bde.tus.f.bdeSize;
-			break;
-		case CMD_GEN_REQUEST64_CR:
-			max_response = 0;
-			if (!pIocbOut->context3)
-				break;
-			numBdes = pIocbOut->iocb.un.genreq64.bdl.bdeSize/
-					sizeof(struct ulp_bde64);
-			dmabuf = (struct lpfc_dmabuf *)pIocbOut->context3;
-			bpl = (struct ulp_bde64 *)dmabuf->virt;
-			for (i = 0; i < numBdes; i++) {
-				bde.tus.w = le32_to_cpu(bpl[i].tus.w);
-				if (bde.tus.f.bdeFlags != BUFF_TYPE_BDE_64)
-					max_response += bde.tus.f.bdeSize;
-			}
-			break;
-		default:
-			max_response = wcqe->total_data_placed;
-			break;
-		}
-		if (max_response < wcqe->total_data_placed)
-			pIocbIn->iocb.un.genreq64.bdl.bdeSize = max_response;
-		else
-			pIocbIn->iocb.un.genreq64.bdl.bdeSize =
-				wcqe->total_data_placed;
-	}
-
-	/* Convert BG errors for completion status */
-	if (status == CQE_STATUS_DI_ERROR) {
-		pIocbIn->iocb.ulpStatus = IOSTAT_LOCAL_REJECT;
-
-		if (bf_get(lpfc_wcqe_c_bg_edir, wcqe))
-			pIocbIn->iocb.un.ulpWord[4] = IOERR_RX_DMA_FAILED;
-		else
-			pIocbIn->iocb.un.ulpWord[4] = IOERR_TX_DMA_FAILED;
-
-		pIocbIn->iocb.unsli3.sli3_bg.bgstat = 0;
-		if (bf_get(lpfc_wcqe_c_bg_ge, wcqe)) /* Guard Check failed */
-			pIocbIn->iocb.unsli3.sli3_bg.bgstat |=
-				BGS_GUARD_ERR_MASK;
-		if (bf_get(lpfc_wcqe_c_bg_ae, wcqe)) /* App Tag Check failed */
-			pIocbIn->iocb.unsli3.sli3_bg.bgstat |=
-				BGS_APPTAG_ERR_MASK;
-		if (bf_get(lpfc_wcqe_c_bg_re, wcqe)) /* Ref Tag Check failed */
-			pIocbIn->iocb.unsli3.sli3_bg.bgstat |=
-				BGS_REFTAG_ERR_MASK;
-
-		/* Check to see if there was any good data before the error */
-		if (bf_get(lpfc_wcqe_c_bg_tdpv, wcqe)) {
-			pIocbIn->iocb.unsli3.sli3_bg.bgstat |=
-				BGS_HI_WATER_MARK_PRESENT_MASK;
-			pIocbIn->iocb.unsli3.sli3_bg.bghm =
-				wcqe->total_data_placed;
-		}
-
-		/*
-		* Set ALL the error bits to indicate we don't know what
-		* type of error it is.
-		*/
-		if (!pIocbIn->iocb.unsli3.sli3_bg.bgstat)
-			pIocbIn->iocb.unsli3.sli3_bg.bgstat |=
-				(BGS_REFTAG_ERR_MASK | BGS_APPTAG_ERR_MASK |
-				BGS_GUARD_ERR_MASK);
-	}
-
-	/* Pick up HBA exchange busy condition */
-	if (bf_get(lpfc_wcqe_c_xb, wcqe)) {
-		spin_lock_irqsave(&phba->hbalock, iflags);
-		pIocbIn->iocb_flag |= LPFC_EXCHANGE_BUSY;
-		spin_unlock_irqrestore(&phba->hbalock, iflags);
-	}
-}
-
-/**
- * lpfc_sli4_els_wcqe_to_rspiocbq - Get response iocbq from els wcqe
+ * lpfc_sli4_els_preprocess_rspiocbq - Get response iocbq from els wcqe
  * @phba: Pointer to HBA context object.
  * @irspiocbq: Pointer to work-queue completion queue entry.
  *
  * This routine handles an ELS work-queue completion event and construct
- * a pseudo response ELS IODBQ from the SLI4 ELS WCQE for the common
+ * a pseudo response ELS IOCBQ from the SLI4 ELS WCQE for the common
  * discovery engine to handle.
  *
  * Return: Pointer to the receive IOCBQ, NULL otherwise.
  **/
 static struct lpfc_iocbq *
-lpfc_sli4_els_wcqe_to_rspiocbq(struct lpfc_hba *phba,
-			       struct lpfc_iocbq *irspiocbq)
+lpfc_sli4_els_preprocess_rspiocbq(struct lpfc_hba *phba,
+				  struct lpfc_iocbq *irspiocbq)
 {
 	struct lpfc_sli_ring *pring;
 	struct lpfc_iocbq *cmdiocbq;
@@ -14252,11 +14163,13 @@ lpfc_sli4_els_wcqe_to_rspiocbq(struct lpfc_hba *phba,
 		return NULL;
 
 	wcqe = &irspiocbq->cq_event.cqe.wcqe_cmpl;
+	spin_lock_irqsave(&pring->ring_lock, iflags);
 	pring->stats.iocb_event++;
 	/* Look up the ELS command IOCB and create pseudo response IOCB */
 	cmdiocbq = lpfc_sli_iocbq_lookup_by_tag(phba, pring,
 				bf_get(lpfc_wcqe_c_request_tag, wcqe));
 	if (unlikely(!cmdiocbq)) {
+		spin_unlock_irqrestore(&pring->ring_lock, iflags);
 		lpfc_printf_log(phba, KERN_WARNING, LOG_SLI,
 				"0386 ELS complete with no corresponding "
 				"cmdiocb: 0x%x 0x%x 0x%x 0x%x\n",
@@ -14266,13 +14179,18 @@ lpfc_sli4_els_wcqe_to_rspiocbq(struct lpfc_hba *phba,
 		return NULL;
 	}
 
-	spin_lock_irqsave(&pring->ring_lock, iflags);
+	memcpy(&irspiocbq->wqe, &cmdiocbq->wqe, sizeof(union lpfc_wqe128));
+	memcpy(&irspiocbq->wcqe_cmpl, wcqe, sizeof(*wcqe));
+
 	/* Put the iocb back on the txcmplq */
 	lpfc_sli_ringtxcmpl_put(phba, pring, cmdiocbq);
 	spin_unlock_irqrestore(&pring->ring_lock, iflags);
 
-	/* Fake the irspiocbq and copy necessary response information */
-	lpfc_sli4_iocb_param_transfer(phba, irspiocbq, cmdiocbq, wcqe);
+	if (bf_get(lpfc_wcqe_c_xb, wcqe)) {
+		spin_lock_irqsave(&phba->hbalock, iflags);
+		irspiocbq->cmd_flag |= LPFC_EXCHANGE_BUSY;
+		spin_unlock_irqrestore(&phba->hbalock, iflags);
+	}
 
 	return irspiocbq;
 }
@@ -15073,7 +14991,6 @@ lpfc_sli4_fp_handle_fcp_wcqe(struct lpfc_hba *phba, struct lpfc_queue *cq,
 {
 	struct lpfc_sli_ring *pring = cq->pring;
 	struct lpfc_iocbq *cmdiocbq;
-	struct lpfc_iocbq irspiocbq;
 	unsigned long iflags;
 
 	/* Check for response status */
@@ -15099,9 +15016,9 @@ lpfc_sli4_fp_handle_fcp_wcqe(struct lpfc_hba *phba, struct lpfc_queue *cq,
 	/* Look up the FCP command IOCB and create pseudo response IOCB */
 	spin_lock_irqsave(&pring->ring_lock, iflags);
 	pring->stats.iocb_event++;
-	spin_unlock_irqrestore(&pring->ring_lock, iflags);
 	cmdiocbq = lpfc_sli_iocbq_lookup_by_tag(phba, pring,
 				bf_get(lpfc_wcqe_c_request_tag, wcqe));
+	spin_unlock_irqrestore(&pring->ring_lock, iflags);
 	if (unlikely(!cmdiocbq)) {
 		lpfc_printf_log(phba, KERN_WARNING, LOG_SLI,
 				"0374 FCP complete with no corresponding "
@@ -15112,39 +15029,31 @@ lpfc_sli4_fp_handle_fcp_wcqe(struct lpfc_hba *phba, struct lpfc_queue *cq,
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
 	cmdiocbq->isr_timestamp = cq->isr_timestamp;
 #endif
-	if (cmdiocbq->iocb_cmpl == NULL) {
-		if (cmdiocbq->wqe_cmpl) {
-			/* For FCP the flag is cleared in wqe_cmpl */
-			if (!(cmdiocbq->iocb_flag & LPFC_IO_FCP) &&
-			    cmdiocbq->iocb_flag & LPFC_DRIVER_ABORTED) {
-				spin_lock_irqsave(&phba->hbalock, iflags);
-				cmdiocbq->iocb_flag &= ~LPFC_DRIVER_ABORTED;
-				spin_unlock_irqrestore(&phba->hbalock, iflags);
-			}
+	if (bf_get(lpfc_wcqe_c_xb, wcqe)) {
+		spin_lock_irqsave(&phba->hbalock, iflags);
+		cmdiocbq->cmd_flag |= LPFC_EXCHANGE_BUSY;
+		spin_unlock_irqrestore(&phba->hbalock, iflags);
+	}
 
-			/* Pass the cmd_iocb and the wcqe to the upper layer */
-			(cmdiocbq->wqe_cmpl)(phba, cmdiocbq, wcqe);
-			return;
+	if (cmdiocbq->cmd_cmpl) {
+		/* For FCP the flag is cleared in cmd_cmpl */
+		if (!(cmdiocbq->cmd_flag & LPFC_IO_FCP) &&
+		    cmdiocbq->cmd_flag & LPFC_DRIVER_ABORTED) {
+			spin_lock_irqsave(&phba->hbalock, iflags);
+			cmdiocbq->cmd_flag &= ~LPFC_DRIVER_ABORTED;
+			spin_unlock_irqrestore(&phba->hbalock, iflags);
 		}
+
+		/* Pass the cmd_iocb and the wcqe to the upper layer */
+		memcpy(&cmdiocbq->wcqe_cmpl, wcqe,
+		       sizeof(struct lpfc_wcqe_complete));
+		cmdiocbq->cmd_cmpl(phba, cmdiocbq, cmdiocbq);
+	} else {
 		lpfc_printf_log(phba, KERN_WARNING, LOG_SLI,
 				"0375 FCP cmdiocb not callback function "
 				"iotag: (%d)\n",
 				bf_get(lpfc_wcqe_c_request_tag, wcqe));
-		return;
 	}
-
-	/* Only SLI4 non-IO commands stil use IOCB */
-	/* Fake the irspiocb and copy necessary response information */
-	lpfc_sli4_iocb_param_transfer(phba, &irspiocbq, cmdiocbq, wcqe);
-
-	if (cmdiocbq->iocb_flag & LPFC_DRIVER_ABORTED) {
-		spin_lock_irqsave(&phba->hbalock, iflags);
-		cmdiocbq->iocb_flag &= ~LPFC_DRIVER_ABORTED;
-		spin_unlock_irqrestore(&phba->hbalock, iflags);
-	}
-
-	/* Pass the cmd_iocb and the rsp state to the upper layer */
-	(cmdiocbq->iocb_cmpl)(phba, cmdiocbq, &irspiocbq);
 }
 
 /**
@@ -18966,17 +18875,20 @@ lpfc_sli4_seq_abort_rsp(struct lpfc_vport *vport,
 	}
 
 	ctiocb->vport = phba->pport;
-	ctiocb->iocb_cmpl = lpfc_sli4_seq_abort_rsp_cmpl;
+	ctiocb->cmd_cmpl = lpfc_sli4_seq_abort_rsp_cmpl;
 	ctiocb->sli4_lxritag = NO_XRI;
 	ctiocb->sli4_xritag = NO_XRI;
 
-	if (fctl & FC_FC_EX_CTX)
+	if (fctl & FC_FC_EX_CTX) {
 		/* Exchange responder sent the abort so we
 		 * own the oxid.
 		 */
+		ctiocb->abort_bls = LPFC_ABTS_UNSOL_RSP;
 		xri = oxid;
-	else
+	} else {
+		ctiocb->abort_bls = LPFC_ABTS_UNSOL_INT;
 		xri = rxid;
+	}
 	lxri = lpfc_sli4_xri_inrange(phba, xri);
 	if (lxri != NO_XRI)
 		lpfc_set_rrq_active(phba, ndlp, lxri,
@@ -19299,7 +19211,7 @@ lpfc_sli4_send_seq_to_ulp(struct lpfc_vport *vport,
 
 	/* Free iocb created in lpfc_prep_seq */
 	list_for_each_entry_safe(curr_iocb, next_iocb,
-		&iocbq->list, list) {
+				 &iocbq->list, list) {
 		list_del_init(&curr_iocb->list);
 		lpfc_sli_release_iocbq(phba, curr_iocb);
 	}
@@ -19369,8 +19281,8 @@ lpfc_sli4_handle_mds_loopback(struct lpfc_vport *vport,
 
 	iocbq->context2 = pcmd;
 	iocbq->vport = vport;
-	iocbq->iocb_flag &= ~LPFC_FIP_ELS_ID_MASK;
-	iocbq->iocb_flag |= LPFC_USE_FCPWQIDX;
+	iocbq->cmd_flag &= ~LPFC_FIP_ELS_ID_MASK;
+	iocbq->cmd_flag |= LPFC_USE_FCPWQIDX;
 
 	/*
 	 * Setup rest of the iocb as though it were a WQE
@@ -19388,7 +19300,7 @@ lpfc_sli4_handle_mds_loopback(struct lpfc_vport *vport,
 
 	iocbq->iocb.ulpCommand = CMD_SEND_FRAME;
 	iocbq->iocb.ulpLe = 1;
-	iocbq->iocb_cmpl = lpfc_sli4_mds_loopback_cmpl;
+	iocbq->cmd_cmpl = lpfc_sli4_mds_loopback_cmpl;
 	rc = lpfc_sli_issue_iocb(phba, LPFC_ELS_RING, iocbq, 0);
 	if (rc == IOCB_ERROR)
 		goto exit;
@@ -21230,7 +21142,7 @@ lpfc_wqe_bpl2sgl(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeq,
 	cmd = bf_get(wqe_cmnd, &wqe->generic.wqe_com);
 	if (cmd == CMD_XMIT_BLS_RSP64_WQE)
 		return sglq->sli4_xritag;
-	numBdes = pwqeq->rsvd2;
+	numBdes = pwqeq->num_bdes;
 	if (numBdes) {
 		/* The addrHigh and addrLow fields within the WQE
 		 * have not been byteswapped yet so there is no
@@ -21331,7 +21243,7 @@ lpfc_sli4_issue_wqe(struct lpfc_hba *phba, struct lpfc_sli4_hdw_queue *qp,
 	uint32_t ret = 0;
 
 	/* NVME_LS and NVME_LS ABTS requests. */
-	if (pwqe->iocb_flag & LPFC_IO_NVME_LS) {
+	if (pwqe->cmd_flag & LPFC_IO_NVME_LS) {
 		pring =  phba->sli4_hba.nvmels_wq->pring;
 		lpfc_qp_spin_lock_irqsave(&pring->ring_lock, iflags,
 					  qp, wq_access);
@@ -21362,7 +21274,7 @@ lpfc_sli4_issue_wqe(struct lpfc_hba *phba, struct lpfc_sli4_hdw_queue *qp,
 	}
 
 	/* NVME_FCREQ and NVME_ABTS requests */
-	if (pwqe->iocb_flag & (LPFC_IO_NVME | LPFC_IO_FCP | LPFC_IO_CMF)) {
+	if (pwqe->cmd_flag & (LPFC_IO_NVME | LPFC_IO_FCP | LPFC_IO_CMF)) {
 		/* Get the IO distribution (hba_wqidx) for WQ assignment. */
 		wq = qp->io_wq;
 		pring = wq->pring;
@@ -21384,7 +21296,7 @@ lpfc_sli4_issue_wqe(struct lpfc_hba *phba, struct lpfc_sli4_hdw_queue *qp,
 	}
 
 	/* NVMET requests */
-	if (pwqe->iocb_flag & LPFC_IO_NVMET) {
+	if (pwqe->cmd_flag & LPFC_IO_NVMET) {
 		/* Get the IO distribution (hba_wqidx) for WQ assignment. */
 		wq = qp->io_wq;
 		pring = wq->pring;
@@ -21450,7 +21362,7 @@ lpfc_sli4_issue_abort_iotag(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		return WQE_NORESOURCE;
 
 	/* Indicate the IO is being aborted by the driver. */
-	cmdiocb->iocb_flag |= LPFC_DRIVER_ABORTED;
+	cmdiocb->cmd_flag |= LPFC_DRIVER_ABORTED;
 
 	abtswqe = &abtsiocb->wqe;
 	memset(abtswqe, 0, sizeof(*abtswqe));
@@ -21469,15 +21381,15 @@ lpfc_sli4_issue_abort_iotag(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 
 	/* ABTS WQE must go to the same WQ as the WQE to be aborted */
 	abtsiocb->hba_wqidx = cmdiocb->hba_wqidx;
-	abtsiocb->iocb_flag |= LPFC_USE_FCPWQIDX;
-	if (cmdiocb->iocb_flag & LPFC_IO_FCP)
-		abtsiocb->iocb_flag |= LPFC_IO_FCP;
-	if (cmdiocb->iocb_flag & LPFC_IO_NVME)
-		abtsiocb->iocb_flag |= LPFC_IO_NVME;
-	if (cmdiocb->iocb_flag & LPFC_IO_FOF)
-		abtsiocb->iocb_flag |= LPFC_IO_FOF;
+	abtsiocb->cmd_flag |= LPFC_USE_FCPWQIDX;
+	if (cmdiocb->cmd_flag & LPFC_IO_FCP)
+		abtsiocb->cmd_flag |= LPFC_IO_FCP;
+	if (cmdiocb->cmd_flag & LPFC_IO_NVME)
+		abtsiocb->cmd_flag |= LPFC_IO_NVME;
+	if (cmdiocb->cmd_flag & LPFC_IO_FOF)
+		abtsiocb->cmd_flag |= LPFC_IO_FOF;
 	abtsiocb->vport = vport;
-	abtsiocb->wqe_cmpl = cmpl;
+	abtsiocb->cmd_cmpl = cmpl;
 
 	lpfc_cmd = container_of(cmdiocb, struct lpfc_io_buf, cur_iocbq);
 	retval = lpfc_sli4_issue_wqe(phba, lpfc_cmd->hdwq, abtsiocb);
@@ -21488,7 +21400,7 @@ lpfc_sli4_issue_abort_iotag(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 			 xritag, cmdiocb->iotag, abtsiocb->iotag, retval);
 
 	if (retval) {
-		cmdiocb->iocb_flag &= ~LPFC_DRIVER_ABORTED;
+		cmdiocb->cmd_flag &= ~LPFC_DRIVER_ABORTED;
 		__lpfc_sli_release_iocbq(phba, abtsiocb);
 	}
 
@@ -21850,8 +21762,7 @@ void lpfc_release_io_buf(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_ncmd,
 
 	/* MUST zero fields if buffer is reused by another protocol */
 	lpfc_ncmd->nvmeCmd = NULL;
-	lpfc_ncmd->cur_iocbq.wqe_cmpl = NULL;
-	lpfc_ncmd->cur_iocbq.iocb_cmpl = NULL;
+	lpfc_ncmd->cur_iocbq.cmd_cmpl = NULL;
 
 	if (phba->cfg_xpsgl && !phba->nvmet_support &&
 	    !list_empty(&lpfc_ncmd->dma_sgl_xtra_list))
@@ -22035,8 +21946,26 @@ lpfc_get_io_buf_from_multixri_pools(struct lpfc_hba *phba,
 
 	qp = &phba->sli4_hba.hdwq[hwqid];
 	lpfc_ncmd = NULL;
+	if (!qp) {
+		lpfc_printf_log(phba, KERN_INFO,
+				LOG_SLI | LOG_NVME_ABTS | LOG_FCP,
+				"5556 NULL qp for hwqid  x%x\n", hwqid);
+		return lpfc_ncmd;
+	}
 	multixri_pool = qp->p_multixri_pool;
+	if (!multixri_pool) {
+		lpfc_printf_log(phba, KERN_INFO,
+				LOG_SLI | LOG_NVME_ABTS | LOG_FCP,
+				"5557 NULL multixri for hwqid  x%x\n", hwqid);
+		return lpfc_ncmd;
+	}
 	pvt_pool = &multixri_pool->pvt_pool;
+	if (!pvt_pool) {
+		lpfc_printf_log(phba, KERN_INFO,
+				LOG_SLI | LOG_NVME_ABTS | LOG_FCP,
+				"5558 NULL pvt_pool for hwqid  x%x\n", hwqid);
+		return lpfc_ncmd;
+	}
 	multixri_pool->io_req_count++;
 
 	/* If pvt_pool is empty, move some XRIs from public to private pool */
@@ -22112,6 +22041,12 @@ struct lpfc_io_buf *lpfc_get_io_buf(struct lpfc_hba *phba,
 
 	qp = &phba->sli4_hba.hdwq[hwqid];
 	lpfc_cmd = NULL;
+	if (!qp) {
+		lpfc_printf_log(phba, KERN_WARNING,
+				LOG_SLI | LOG_NVME_ABTS | LOG_FCP,
+				"5555 NULL qp for hwqid  x%x\n", hwqid);
+		return lpfc_cmd;
+	}
 
 	if (phba->cfg_xri_rebalancing)
 		lpfc_cmd = lpfc_get_io_buf_from_multixri_pools(
diff --git a/drivers/scsi/lpfc/lpfc_sli.h b/drivers/scsi/lpfc/lpfc_sli.h
index 5161ccacea3e..06682ad8bbe1 100644
--- a/drivers/scsi/lpfc/lpfc_sli.h
+++ b/drivers/scsi/lpfc/lpfc_sli.h
@@ -35,7 +35,7 @@ typedef enum _lpfc_ctx_cmd {
 	LPFC_CTX_HOST
 } lpfc_ctx_cmd;
 
-union lpfc_vmid_iocb_tag {
+union lpfc_vmid_tag {
 	uint32_t app_id;
 	uint8_t cs_ctl_vmid;
 	struct lpfc_vmid_context *vmid_context;	/* UVEM context information */
@@ -69,16 +69,18 @@ struct lpfc_iocbq {
 	uint16_t sli4_xritag;   /* pre-assigned XRI, (OXID) tag. */
 	uint16_t hba_wqidx;     /* index to HBA work queue */
 	struct lpfc_cq_event cq_event;
-	struct lpfc_wcqe_complete wcqe_cmpl;	/* WQE cmpl */
 	uint64_t isr_timestamp;
 
 	union lpfc_wqe128 wqe;	/* SLI-4 */
 	IOCB_t iocb;		/* SLI-3 */
+	struct lpfc_wcqe_complete wcqe_cmpl;	/* WQE cmpl */
+
+	uint8_t num_bdes;
+	uint8_t abort_bls;	/* ABTS by initiator or responder */
 
-	uint8_t rsvd2;
 	uint8_t priority;	/* OAS priority */
 	uint8_t retry;		/* retry counter for IOCB cmd - if needed */
-	uint32_t iocb_flag;
+	u32 cmd_flag;
 #define LPFC_IO_LIBDFC		1	/* libdfc iocb */
 #define LPFC_IO_WAKE		2	/* Synchronous I/O completed */
 #define LPFC_IO_WAKE_TMO	LPFC_IO_WAKE /* Synchronous I/O timed out */
@@ -123,15 +125,13 @@ struct lpfc_iocbq {
 		struct lpfc_node_rrq *rrq;
 	} context_un;
 
-	union lpfc_vmid_iocb_tag vmid_tag;
-	void (*fabric_iocb_cmpl)(struct lpfc_hba *, struct lpfc_iocbq *,
-			   struct lpfc_iocbq *);
-	void (*wait_iocb_cmpl)(struct lpfc_hba *, struct lpfc_iocbq *,
-			   struct lpfc_iocbq *);
-	void (*iocb_cmpl)(struct lpfc_hba *, struct lpfc_iocbq *,
-			   struct lpfc_iocbq *);
-	void (*wqe_cmpl)(struct lpfc_hba *, struct lpfc_iocbq *,
-			  struct lpfc_wcqe_complete *);
+	union lpfc_vmid_tag vmid_tag;
+	void (*fabric_cmd_cmpl)(struct lpfc_hba *phba, struct lpfc_iocbq *cmd,
+				struct lpfc_iocbq *rsp);
+	void (*wait_cmd_cmpl)(struct lpfc_hba *phba, struct lpfc_iocbq *cmd,
+			      struct lpfc_iocbq *rsp);
+	void (*cmd_cmpl)(struct lpfc_hba *phba, struct lpfc_iocbq *cmd,
+			 struct lpfc_iocbq *rsp);
 };
 
 #define SLI_IOCB_RET_IOCB      1	/* Return IOCB if cmd ring full */
diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h
index 99c5d1e4da5e..5962cf508842 100644
--- a/drivers/scsi/lpfc/lpfc_sli4.h
+++ b/drivers/scsi/lpfc/lpfc_sli4.h
@@ -1116,6 +1116,8 @@ void lpfc_sli4_fcf_redisc_event_proc(struct lpfc_hba *);
 int lpfc_sli4_resume_rpi(struct lpfc_nodelist *,
 			void (*)(struct lpfc_hba *, LPFC_MBOXQ_t *), void *);
 void lpfc_sli4_els_xri_abort_event_proc(struct lpfc_hba *phba);
+void lpfc_sli4_nvme_pci_offline_aborted(struct lpfc_hba *phba,
+					struct lpfc_io_buf *lpfc_ncmd);
 void lpfc_sli4_nvme_xri_aborted(struct lpfc_hba *phba,
 				struct sli4_wcqe_xri_aborted *axri,
 				struct lpfc_io_buf *lpfc_ncmd);
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index bb3f78013a13..88e164e3d2ea 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -3196,6 +3196,9 @@ static int megasas_map_queues(struct Scsi_Host *shost)
 	qoff += map->nr_queues;
 	offset += map->nr_queues;
 
+	/* we never use READ queue, so can't cheat blk-mq */
+	shost->tag_set.map[HCTX_TYPE_READ].nr_queues = 0;
+
 	/* Setup Poll hctx */
 	map = &shost->tag_set.map[HCTX_TYPE_POLL];
 	map->nr_queues = instance->iopoll_q_count;
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index eb5ceb75a15e..056837849ead 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -5279,7 +5279,6 @@ megasas_alloc_fusion_context(struct megasas_instance *instance)
 		if (!fusion->log_to_span) {
 			dev_err(&instance->pdev->dev, "Failed from %s %d\n",
 				__func__, __LINE__);
-			kfree(instance->ctrl_context);
 			return -ENOMEM;
 		}
 	}
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index af275ac42795..9eb3d0b4891d 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -3670,6 +3670,7 @@ static struct fw_event_work *dequeue_next_fw_event(struct MPT3SAS_ADAPTER *ioc)
 		fw_event = list_first_entry(&ioc->fw_event_list,
 				struct fw_event_work, list);
 		list_del_init(&fw_event->list);
+		fw_event_work_put(fw_event);
 	}
 	spin_unlock_irqrestore(&ioc->fw_event_lock, flags);
 
@@ -3751,7 +3752,6 @@ _scsih_fw_event_cleanup_queue(struct MPT3SAS_ADAPTER *ioc)
 		if (cancel_work_sync(&fw_event->work))
 			fw_event_work_put(fw_event);
 
-		fw_event_work_put(fw_event);
 	}
 	ioc->fw_events_cleanup = 0;
 }
@@ -11386,6 +11386,7 @@ scsih_shutdown(struct pci_dev *pdev)
 	_scsih_ir_shutdown(ioc);
 	_scsih_nvme_shutdown(ioc);
 	mpt3sas_base_mask_interrupts(ioc);
+	mpt3sas_base_stop_watchdog(ioc);
 	ioc->shost_recovery = 1;
 	mpt3sas_base_make_ioc_ready(ioc, SOFT_RESET);
 	ioc->shost_recovery = 0;
diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c
index e6dc0b495a82..a117d11f2b07 100644
--- a/drivers/scsi/qedi/qedi_main.c
+++ b/drivers/scsi/qedi/qedi_main.c
@@ -2417,9 +2417,12 @@ static void __qedi_remove(struct pci_dev *pdev, int mode)
 	int rval;
 	u16 retry = 10;
 
-	if (mode == QEDI_MODE_NORMAL || mode == QEDI_MODE_SHUTDOWN) {
-		iscsi_host_remove(qedi->shost);
+	if (mode == QEDI_MODE_NORMAL)
+		iscsi_host_remove(qedi->shost, false);
+	else if (mode == QEDI_MODE_SHUTDOWN)
+		iscsi_host_remove(qedi->shost, true);
 
+	if (mode == QEDI_MODE_NORMAL || mode == QEDI_MODE_SHUTDOWN) {
 		if (qedi->tmf_thread) {
 			flush_workqueue(qedi->tmf_thread);
 			destroy_workqueue(qedi->tmf_thread);
@@ -2796,7 +2799,7 @@ remove_host:
 #ifdef CONFIG_DEBUG_FS
 	qedi_dbg_host_exit(&qedi->dbg_ctx);
 #endif
-	iscsi_host_remove(qedi->shost);
+	iscsi_host_remove(qedi->shost, false);
 stop_iscsi_func:
 	qedi_ops->stop(qedi->cdev);
 stop_slowpath:
diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index d3534e7f2d21..a302ed8b610f 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -2705,17 +2705,24 @@ qla2x00_dev_loss_tmo_callbk(struct fc_rport *rport)
 	if (!fcport)
 		return;
 
-	/* Now that the rport has been deleted, set the fcport state to
-	   FCS_DEVICE_DEAD */
-	qla2x00_set_fcport_state(fcport, FCS_DEVICE_DEAD);
+
+	/*
+	 * Now that the rport has been deleted, set the fcport state to
+	 * FCS_DEVICE_DEAD, if the fcport is still lost.
+	 */
+	if (fcport->scan_state != QLA_FCPORT_FOUND)
+		qla2x00_set_fcport_state(fcport, FCS_DEVICE_DEAD);
 
 	/*
 	 * Transport has effectively 'deleted' the rport, clear
 	 * all local references.
 	 */
 	spin_lock_irqsave(host->host_lock, flags);
-	fcport->rport = fcport->drport = NULL;
-	*((fc_port_t **)rport->dd_data) = NULL;
+	/* Confirm port has not reappeared before clearing pointers. */
+	if (rport->port_state != FC_PORTSTATE_ONLINE) {
+		fcport->rport = fcport->drport = NULL;
+		*((fc_port_t **)rport->dd_data) = NULL;
+	}
 	spin_unlock_irqrestore(host->host_lock, flags);
 
 	if (test_bit(ABORT_ISP_ACTIVE, &fcport->vha->dpc_flags))
@@ -2748,14 +2755,22 @@ qla2x00_terminate_rport_io(struct fc_rport *rport)
 	/*
 	 * At this point all fcport's software-states are cleared.  Perform any
 	 * final cleanup of firmware resources (PCBs and XCBs).
+	 *
+	 * Attempt to cleanup only lost devices.
 	 */
 	if (fcport->loop_id != FC_NO_LOOP_ID) {
-		if (IS_FWI2_CAPABLE(fcport->vha->hw)) {
+		if (IS_FWI2_CAPABLE(fcport->vha->hw) &&
+		    fcport->scan_state != QLA_FCPORT_FOUND) {
 			if (fcport->loop_id != FC_NO_LOOP_ID)
 				fcport->logout_on_delete = 1;
 
-			qlt_schedule_sess_for_deletion(fcport);
-		} else {
+			if (!EDIF_NEGOTIATION_PENDING(fcport)) {
+				ql_dbg(ql_dbg_disc, fcport->vha, 0x911e,
+				       "%s %d schedule session deletion\n", __func__,
+				       __LINE__);
+				qlt_schedule_sess_for_deletion(fcport);
+			}
+		} else if (!IS_FWI2_CAPABLE(fcport->vha->hw)) {
 			qla2x00_port_logout(fcport->vha, fcport);
 		}
 	}
diff --git a/drivers/scsi/qla2xxx/qla_bsg.c b/drivers/scsi/qla2xxx/qla_bsg.c
index c636165be52b..3650f16cab6c 100644
--- a/drivers/scsi/qla2xxx/qla_bsg.c
+++ b/drivers/scsi/qla2xxx/qla_bsg.c
@@ -2972,6 +2972,13 @@ qla24xx_bsg_timeout(struct bsg_job *bsg_job)
 
 	ql_log(ql_log_info, vha, 0x708b, "%s CMD timeout. bsg ptr %p.\n",
 	    __func__, bsg_job);
+
+	if (qla2x00_isp_reg_stat(ha)) {
+		ql_log(ql_log_info, vha, 0x9007,
+		    "PCI/Register disconnect.\n");
+		qla_pci_set_eeh_busy(vha);
+	}
+
 	/* find the bsg job from the active list of commands */
 	spin_lock_irqsave(&ha->hardware_lock, flags);
 	for (que = 0; que < ha->max_req_queues; que++) {
@@ -2989,7 +2996,8 @@ qla24xx_bsg_timeout(struct bsg_job *bsg_job)
 			    sp->u.bsg_job == bsg_job) {
 				req->outstanding_cmds[cnt] = NULL;
 				spin_unlock_irqrestore(&ha->hardware_lock, flags);
-				if (ha->isp_ops->abort_command(sp)) {
+
+				if (!ha->flags.eeh_busy && ha->isp_ops->abort_command(sp)) {
 					ql_log(ql_log_warn, vha, 0x7089,
 					    "mbx abort_command failed.\n");
 					bsg_reply->result = -EIO;
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 2ea35e47ea44..51c7ce5f9792 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -2158,6 +2158,11 @@ typedef struct {
 #define CS_IOCB_ERROR		0x31	/* Generic error for IOCB request
 					   failure */
 #define CS_REJECT_RECEIVED	0x4E	/* Reject received */
+#define CS_EDIF_AUTH_ERROR	0x63	/* decrypt error */
+#define CS_EDIF_PAD_LEN_ERROR	0x65	/* pad > frame size, not 4byte align */
+#define CS_EDIF_INV_REQ		0x66	/* invalid request */
+#define CS_EDIF_SPI_ERROR	0x67	/* rx frame unable to locate sa */
+#define CS_EDIF_HDR_ERROR	0x69	/* data frame != expected len */
 #define CS_BAD_PAYLOAD		0x80	/* Driver defined */
 #define CS_UNKNOWN		0x81	/* Driver defined */
 #define CS_RETRY		0x82	/* Driver defined */
@@ -3201,6 +3206,8 @@ struct ct_sns_rsp {
 #define GFF_NVME_OFFSET		23 /* type = 28h */
 		struct {
 			uint8_t fc4_features[128];
+#define FC4_FF_TARGET    BIT_0
+#define FC4_FF_INITIATOR BIT_1
 		} gff_id;
 		struct {
 			uint8_t reserved;
@@ -3759,6 +3766,7 @@ struct qla_qpair {
 	struct qla_fw_resources fwres ____cacheline_aligned;
 	u32	cmd_cnt;
 	u32	cmd_completion_cnt;
+	u32	prev_completion_cnt;
 };
 
 /* Place holder for FW buffer parameters */
@@ -3971,6 +3979,7 @@ struct qla_hw_data {
 	/* SRB cache. */
 #define SRB_MIN_REQ     128
 	mempool_t       *srb_mempool;
+	u8 port_name[WWN_SIZE];
 
 	volatile struct {
 		uint32_t	mbox_int		:1;
@@ -4036,6 +4045,9 @@ struct qla_hw_data {
 		uint32_t	n2n_fw_acc_sec:1;
 		uint32_t	plogi_template_valid:1;
 		uint32_t	port_isolated:1;
+		uint32_t	eeh_flush:2;
+#define EEH_FLUSH_RDY  1
+#define EEH_FLUSH_DONE 2
 	} flags;
 
 	uint16_t max_exchg;
@@ -4070,6 +4082,7 @@ struct qla_hw_data {
 	uint32_t		rsp_que_len;
 	uint32_t		req_que_off;
 	uint32_t		rsp_que_off;
+	unsigned long		eeh_jif;
 
 	/* Multi queue data structs */
 	device_reg_t *mqiobase;
@@ -4252,8 +4265,8 @@ struct qla_hw_data {
 #define IS_OEM_001(ha)          ((ha)->device_type & DT_OEM_001)
 #define HAS_EXTENDED_IDS(ha)    ((ha)->device_type & DT_EXTENDED_IDS)
 #define IS_CT6_SUPPORTED(ha)	((ha)->device_type & DT_CT6_SUPPORTED)
-#define IS_MQUE_CAPABLE(ha)	((ha)->mqenable || IS_QLA83XX(ha) || \
-				IS_QLA27XX(ha) || IS_QLA28XX(ha))
+#define IS_MQUE_CAPABLE(ha)	(IS_QLA83XX(ha) || IS_QLA27XX(ha) || \
+				 IS_QLA28XX(ha))
 #define IS_BIDI_CAPABLE(ha) \
     (IS_QLA25XX(ha) || IS_QLA2031(ha) || IS_QLA27XX(ha) || IS_QLA28XX(ha))
 /* Bit 21 of fw_attributes decides the MCTP capabilities */
@@ -4618,7 +4631,9 @@ struct qla_hw_data {
 	struct qla_chip_state_84xx *cs84xx;
 	struct isp_operations *isp_ops;
 	struct workqueue_struct *wq;
+	struct work_struct heartbeat_work;
 	struct qlfc_fw fw_buf;
+	unsigned long last_heartbeat_run_jiffies;
 
 	/* FCP_CMND priority support */
 	struct qla_fcp_prio_cfg *fcp_prio_cfg;
@@ -4719,7 +4734,6 @@ struct qla_hw_data {
 
 	struct qla_hw_data_stat stat;
 	pci_error_state_t pci_error_state;
-	u64 prev_cmd_cnt;
 	struct dma_pool *purex_dma_pool;
 	struct btree_head32 host_map;
 
@@ -4865,7 +4879,6 @@ typedef struct scsi_qla_host {
 #define SET_ZIO_THRESHOLD_NEEDED 32
 #define ISP_ABORT_TO_ROM	33
 #define VPORT_DELETE		34
-#define HEARTBEAT_CHK		38
 
 #define PROCESS_PUREX_IOCB	63
 
diff --git a/drivers/scsi/qla2xxx/qla_edif.c b/drivers/scsi/qla2xxx/qla_edif.c
index a00fe88c6021..8e9237434e8b 100644
--- a/drivers/scsi/qla2xxx/qla_edif.c
+++ b/drivers/scsi/qla2xxx/qla_edif.c
@@ -218,7 +218,7 @@ fc_port_t *fcport)
 		    "%s edif not enabled\n", __func__);
 		goto done;
 	}
-	if (vha->e_dbell.db_flags != EDB_ACTIVE) {
+	if (DBELL_INACTIVE(vha)) {
 		ql_dbg(ql_dbg_edif, vha, 0x09102,
 		    "%s doorbell not enabled\n", __func__);
 		goto done;
@@ -482,15 +482,17 @@ qla_edif_app_start(scsi_qla_host_t *vha, struct bsg_job *bsg_job)
 	ql_dbg(ql_dbg_edif, vha, 0x911d, "%s app_vid=%x app_start_flags %x\n",
 	     __func__, appstart.app_info.app_vid, appstart.app_start_flags);
 
-	if (vha->e_dbell.db_flags != EDB_ACTIVE) {
+	if (DBELL_INACTIVE(vha)) {
 		/* mark doorbell as active since an app is now present */
-		vha->e_dbell.db_flags = EDB_ACTIVE;
+		vha->e_dbell.db_flags |= EDB_ACTIVE;
 	} else {
-		ql_dbg(ql_dbg_edif, vha, 0x911e, "%s doorbell already active\n",
-		     __func__);
+		goto out;
 	}
 
 	if (N2N_TOPO(vha->hw)) {
+		list_for_each_entry_safe(fcport, tf, &vha->vp_fcports, list)
+			fcport->n2n_link_reset_cnt = 0;
+
 		if (vha->hw->flags.n2n_fw_acc_sec)
 			set_bit(N2N_LINK_RESET, &vha->dpc_flags);
 		else
@@ -517,19 +519,32 @@ qla_edif_app_start(scsi_qla_host_t *vha, struct bsg_job *bsg_job)
 			if (atomic_read(&vha->loop_state) == LOOP_DOWN)
 				break;
 
-			fcport->edif.app_started = 1;
 			fcport->login_retry = vha->hw->login_retry_count;
 
-			/* no activity */
 			fcport->edif.app_stop = 0;
+			fcport->edif.app_sess_online = 0;
+			fcport->edif.app_started = 1;
+
+			if (fcport->scan_state != QLA_FCPORT_FOUND)
+				continue;
+
+			if (fcport->port_type == FCT_UNKNOWN &&
+			    !fcport->fc4_features)
+				rval = qla24xx_async_gffid(vha, fcport, true);
+
+			if (!rval && !(fcport->fc4_features & FC4_FF_TARGET ||
+			    fcport->port_type & (FCT_TARGET|FCT_NVME_TARGET)))
+				continue;
+
+			rval = 0;
 
 			ql_dbg(ql_dbg_edif, vha, 0x911e,
 			       "%s wwpn %8phC calling qla_edif_reset_auth_wait\n",
 			       __func__, fcport->port_name);
-			fcport->edif.app_sess_online = 0;
 			qlt_schedule_sess_for_deletion(fcport);
 			qla_edif_sa_ctl_init(vha, fcport);
 		}
+		set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
 	}
 
 	if (vha->pur_cinfo.enode_flags != ENODE_ACTIVE) {
@@ -540,6 +555,7 @@ qla_edif_app_start(scsi_qla_host_t *vha, struct bsg_job *bsg_job)
 		     __func__);
 	}
 
+out:
 	appreply.host_support_edif = vha->hw->flags.edif_enabled;
 	appreply.edif_enode_active = vha->pur_cinfo.enode_flags;
 	appreply.edif_edb_active = vha->e_dbell.db_flags;
@@ -884,6 +900,20 @@ qla_edif_app_getfcinfo(scsi_qla_host_t *vha, struct bsg_job *bsg_job)
 			app_reply->ports[pcnt].rekey_count =
 				fcport->edif.rekey_cnt;
 
+			if (fcport->scan_state != QLA_FCPORT_FOUND)
+				continue;
+
+			if (fcport->port_type == FCT_UNKNOWN && !fcport->fc4_features)
+				rval = qla24xx_async_gffid(vha, fcport, true);
+
+			if (!rval &&
+			    !(fcport->fc4_features & FC4_FF_TARGET ||
+			      fcport->port_type &
+			      (FCT_TARGET | FCT_NVME_TARGET)))
+				continue;
+
+			rval = 0;
+
 			app_reply->ports[pcnt].remote_type =
 				VND_CMD_RTYPE_UNKNOWN;
 			if (fcport->port_type & (FCT_NVME_TARGET | FCT_TARGET))
@@ -1248,6 +1278,8 @@ qla24xx_check_sadb_avail_slot(struct bsg_job *bsg_job, fc_port_t *fcport,
 
 #define QLA_SA_UPDATE_FLAGS_RX_KEY      0x0
 #define QLA_SA_UPDATE_FLAGS_TX_KEY      0x2
+#define EDIF_MSLEEP_INTERVAL 100
+#define EDIF_RETRY_COUNT  50
 
 int
 qla24xx_sadb_update(struct bsg_job *bsg_job)
@@ -1260,7 +1292,7 @@ qla24xx_sadb_update(struct bsg_job *bsg_job)
 	struct edif_list_entry *edif_entry = NULL;
 	int			found = 0;
 	int			rval = 0;
-	int result = 0;
+	int result = 0, cnt;
 	struct qla_sa_update_frame sa_frame;
 	struct srb_iocb *iocb_cmd;
 	port_id_t portid;
@@ -1280,7 +1312,7 @@ qla24xx_sadb_update(struct bsg_job *bsg_job)
 		goto done;
 	}
 
-	if (vha->e_dbell.db_flags != EDB_ACTIVE) {
+	if (DBELL_INACTIVE(vha)) {
 		ql_log(ql_log_warn, vha, 0x70a1, "App not started\n");
 		rval = -EIO;
 		SET_DID_STATUS(bsg_reply->result, DID_ERROR);
@@ -1501,11 +1533,23 @@ force_rx_delete:
 	sp->done = qla2x00_bsg_job_done;
 	iocb_cmd = &sp->u.iocb_cmd;
 	iocb_cmd->u.sa_update.sa_frame  = sa_frame;
-
+	cnt = 0;
+retry:
 	rval = qla2x00_start_sp(sp);
-	if (rval != QLA_SUCCESS) {
+	switch (rval) {
+	case QLA_SUCCESS:
+		break;
+	case EAGAIN:
+		msleep(EDIF_MSLEEP_INTERVAL);
+		cnt++;
+		if (cnt < EDIF_RETRY_COUNT)
+			goto retry;
+
+		fallthrough;
+	default:
 		ql_log(ql_dbg_edif, vha, 0x70e3,
-		    "qla2x00_start_sp failed=%d.\n", rval);
+		       "%s qla2x00_start_sp failed=%d.\n",
+		       __func__, rval);
 
 		qla2x00_rel_sp(sp);
 		rval = -EIO;
@@ -1684,41 +1728,25 @@ static struct enode *
 qla_enode_find(scsi_qla_host_t *vha, uint32_t ntype, uint32_t p1, uint32_t p2)
 {
 	struct enode		*node_rtn = NULL;
-	struct enode		*list_node = NULL;
+	struct enode		*list_node, *q;
 	unsigned long		flags;
-	struct list_head	*pos, *q;
 	uint32_t		sid;
-	uint32_t		rw_flag;
 	struct purexevent	*purex;
 
 	/* secure the list from moving under us */
 	spin_lock_irqsave(&vha->pur_cinfo.pur_lock, flags);
 
-	list_for_each_safe(pos, q, &vha->pur_cinfo.head) {
-		list_node = list_entry(pos, struct enode, list);
+	list_for_each_entry_safe(list_node, q, &vha->pur_cinfo.head, list) {
 
 		/* node type determines what p1 and p2 are */
 		purex = &list_node->u.purexinfo;
 		sid = p1;
-		rw_flag = p2;
 
 		if (purex->pur_info.pur_sid.b24 == sid) {
-			if (purex->pur_info.pur_pend == 1 &&
-			    rw_flag == PUR_GET) {
-				/*
-				 * if the receive is in progress
-				 * and its a read/get then can't
-				 * transfer yet
-				 */
-				ql_dbg(ql_dbg_edif, vha, 0x9106,
-				    "%s purex xfer in progress for sid=%x\n",
-				    __func__, sid);
-			} else {
-				/* found it and its complete */
-				node_rtn = list_node;
-				list_del(pos);
-				break;
-			}
+			/* found it and its complete */
+			node_rtn = list_node;
+			list_del(&list_node->list);
+			break;
 		}
 	}
 
@@ -1803,7 +1831,7 @@ qla_els_reject_iocb(scsi_qla_host_t *vha, struct qla_qpair *qp,
 void
 qla_edb_init(scsi_qla_host_t *vha)
 {
-	if (vha->e_dbell.db_flags == EDB_ACTIVE) {
+	if (DBELL_ACTIVE(vha)) {
 		/* list already init'd - error */
 		ql_dbg(ql_dbg_edif, vha, 0x09102,
 		    "edif db already initialized, cannot reinit\n");
@@ -1846,7 +1874,7 @@ static void qla_edb_clear(scsi_qla_host_t *vha, port_id_t portid)
 	port_id_t sid;
 	LIST_HEAD(edb_list);
 
-	if (vha->e_dbell.db_flags != EDB_ACTIVE) {
+	if (DBELL_INACTIVE(vha)) {
 		/* doorbell list not enabled */
 		ql_dbg(ql_dbg_edif, vha, 0x09102,
 		       "%s doorbell not enabled\n", __func__);
@@ -1898,7 +1926,7 @@ qla_edb_stop(scsi_qla_host_t *vha)
 	unsigned long flags;
 	struct edb_node *node, *q;
 
-	if (vha->e_dbell.db_flags != EDB_ACTIVE) {
+	if (DBELL_INACTIVE(vha)) {
 		/* doorbell list not enabled */
 		ql_dbg(ql_dbg_edif, vha, 0x09102,
 		    "%s doorbell not enabled\n", __func__);
@@ -1949,7 +1977,7 @@ qla_edb_node_add(scsi_qla_host_t *vha, struct edb_node *ptr)
 {
 	unsigned long		flags;
 
-	if (vha->e_dbell.db_flags != EDB_ACTIVE) {
+	if (DBELL_INACTIVE(vha)) {
 		/* doorbell list not enabled */
 		ql_dbg(ql_dbg_edif, vha, 0x09102,
 		    "%s doorbell not enabled\n", __func__);
@@ -1980,7 +2008,7 @@ qla_edb_eventcreate(scsi_qla_host_t *vha, uint32_t dbtype,
 		return;
 	}
 
-	if (vha->e_dbell.db_flags != EDB_ACTIVE) {
+	if (DBELL_INACTIVE(vha)) {
 		if (fcport)
 			fcport->edif.auth_state = dbtype;
 		/* doorbell list not enabled */
@@ -2075,7 +2103,7 @@ qla_edif_timer(scsi_qla_host_t *vha)
 	struct qla_hw_data *ha = vha->hw;
 
 	if (!vha->vp_idx && N2N_TOPO(ha) && ha->flags.n2n_fw_acc_sec) {
-		if (vha->e_dbell.db_flags != EDB_ACTIVE &&
+		if (DBELL_INACTIVE(vha) &&
 		    ha->edif_post_stop_cnt_down) {
 			ha->edif_post_stop_cnt_down--;
 
@@ -2113,7 +2141,7 @@ edif_doorbell_show(struct device *dev, struct device_attribute *attr,
 	sz = 256;
 
 	/* stop new threads from waiting if we're not init'd */
-	if (vha->e_dbell.db_flags != EDB_ACTIVE) {
+	if (DBELL_INACTIVE(vha)) {
 		ql_dbg(ql_dbg_edif + ql_dbg_verbose, vha, 0x09122,
 		    "%s error - edif db not enabled\n", __func__);
 		return 0;
@@ -2177,6 +2205,7 @@ edif_doorbell_show(struct device *dev, struct device_attribute *attr,
 
 static void qla_noop_sp_done(srb_t *sp, int res)
 {
+	sp->fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE);
 	/* ref: INIT */
 	kref_put(&sp->cmd_kref, qla2x00_sp_release);
 }
@@ -2201,7 +2230,8 @@ qla24xx_issue_sa_replace_iocb(scsi_qla_host_t *vha, struct qla_work_evt *e)
 	if (!sa_ctl) {
 		ql_dbg(ql_dbg_edif, vha, 0x70e6,
 		    "sa_ctl allocation failed\n");
-		return -ENOMEM;
+		rval =  -ENOMEM;
+		goto done;
 	}
 
 	fcport = sa_ctl->fcport;
@@ -2211,7 +2241,8 @@ qla24xx_issue_sa_replace_iocb(scsi_qla_host_t *vha, struct qla_work_evt *e)
 	if (!sp) {
 		ql_dbg(ql_dbg_edif, vha, 0x70e6,
 		 "SRB allocation failed\n");
-		return -ENOMEM;
+		rval = -ENOMEM;
+		goto done;
 	}
 
 	fcport->flags |= FCF_ASYNC_SENT;
@@ -2240,10 +2271,17 @@ qla24xx_issue_sa_replace_iocb(scsi_qla_host_t *vha, struct qla_work_evt *e)
 
 	rval = qla2x00_start_sp(sp);
 
-	if (rval != QLA_SUCCESS)
-		rval = QLA_FUNCTION_FAILED;
+	if (rval != QLA_SUCCESS) {
+		goto done_free_sp;
+	}
 
 	return rval;
+done_free_sp:
+	kref_put(&sp->cmd_kref, qla2x00_sp_release);
+	fcport->flags &= ~FCF_ASYNC_SENT;
+done:
+	fcport->flags &= ~FCF_ASYNC_ACTIVE;
+	return rval;
 }
 
 void qla24xx_sa_update_iocb(srb_t *sp, struct sa_update_28xx *sa_update_iocb)
@@ -2428,7 +2466,6 @@ void qla24xx_auth_els(scsi_qla_host_t *vha, void **pkt, struct rsp_que **rsp)
 
 	purex = &ptr->u.purexinfo;
 	purex->pur_info.pur_sid = a.did;
-	purex->pur_info.pur_pend = 0;
 	purex->pur_info.pur_bytes_rcvd = totlen;
 	purex->pur_info.pur_rx_xchg_address = le32_to_cpu(p->rx_xchg_addr);
 	purex->pur_info.pur_nphdl = le16_to_cpu(p->nport_handle);
@@ -2460,8 +2497,7 @@ void qla24xx_auth_els(scsi_qla_host_t *vha, void **pkt, struct rsp_que **rsp)
 
 	fcport = qla2x00_find_fcport_by_pid(host, &purex->pur_info.pur_sid);
 
-	if (host->e_dbell.db_flags != EDB_ACTIVE ||
-	    (fcport && EDIF_SESSION_DOWN(fcport))) {
+	if (DBELL_INACTIVE(vha)) {
 		ql_dbg(ql_dbg_edif, host, 0x0910c, "%s e_dbell.db_flags =%x %06x\n",
 		    __func__, host->e_dbell.db_flags,
 		    fcport ? fcport->d_id.b24 : 0);
@@ -2471,6 +2507,22 @@ void qla24xx_auth_els(scsi_qla_host_t *vha, void **pkt, struct rsp_que **rsp)
 		return;
 	}
 
+	if (fcport && EDIF_SESSION_DOWN(fcport)) {
+		ql_dbg(ql_dbg_edif, host, 0x13b6,
+		    "%s terminate exchange. Send logo to 0x%x\n",
+		    __func__, a.did.b24);
+
+		a.tx_byte_count = a.tx_len = 0;
+		a.tx_addr = 0;
+		a.control_flags = EPD_RX_XCHG;  /* EPD_RX_XCHG = terminate cmd */
+		qla_els_reject_iocb(host, (*rsp)->qpair, &a);
+		qla_enode_free(host, ptr);
+		/* send logo to let remote port knows to tear down session */
+		fcport->send_els_logo = 1;
+		qlt_schedule_sess_for_deletion(fcport);
+		return;
+	}
+
 	/* add the local enode to the list */
 	qla_enode_add(host, ptr);
 
@@ -3180,18 +3232,14 @@ static uint16_t qla_edif_sadb_get_sa_index(fc_port_t *fcport,
 /* release any sadb entries -- only done at teardown */
 void qla_edif_sadb_release(struct qla_hw_data *ha)
 {
-	struct list_head *pos;
-	struct list_head *tmp;
-	struct edif_sa_index_entry *entry;
+	struct edif_sa_index_entry *entry, *tmp;
 
-	list_for_each_safe(pos, tmp, &ha->sadb_rx_index_list) {
-		entry = list_entry(pos, struct edif_sa_index_entry, next);
+	list_for_each_entry_safe(entry, tmp, &ha->sadb_rx_index_list, next) {
 		list_del(&entry->next);
 		kfree(entry);
 	}
 
-	list_for_each_safe(pos, tmp, &ha->sadb_tx_index_list) {
-		entry = list_entry(pos, struct edif_sa_index_entry, next);
+	list_for_each_entry_safe(entry, tmp, &ha->sadb_tx_index_list, next) {
 		list_del(&entry->next);
 		kfree(entry);
 	}
@@ -3367,7 +3415,7 @@ int qla_edif_process_els(scsi_qla_host_t *vha, struct bsg_job *bsg_job)
 	fc_port_t *fcport = NULL;
 	struct qla_hw_data *ha = vha->hw;
 	srb_t *sp;
-	int rval =  (DID_ERROR << 16);
+	int rval =  (DID_ERROR << 16), cnt;
 	port_id_t d_id;
 	struct qla_bsg_auth_els_request *p =
 	    (struct qla_bsg_auth_els_request *)bsg_job->request;
@@ -3389,7 +3437,7 @@ int qla_edif_process_els(scsi_qla_host_t *vha, struct bsg_job *bsg_job)
 	if (qla_bsg_check(vha, bsg_job, fcport))
 		return 0;
 
-	if (fcport->loop_id == FC_NO_LOOP_ID) {
+	if (EDIF_SESS_DELETE(fcport)) {
 		ql_dbg(ql_dbg_edif, vha, 0x910d,
 		    "%s ELS code %x, no loop id.\n", __func__,
 		    bsg_request->rqst_data.r_els.els_code);
@@ -3458,17 +3506,26 @@ int qla_edif_process_els(scsi_qla_host_t *vha, struct bsg_job *bsg_job)
 	sp->free = qla2x00_bsg_sp_free;
 	sp->done = qla2x00_bsg_job_done;
 
+	cnt = 0;
+retry:
 	rval = qla2x00_start_sp(sp);
-
-	ql_dbg(ql_dbg_edif, vha, 0x700a,
-	    "%s %s %8phN xchg %x ctlflag %x hdl %x reqlen %xh bsg ptr %p\n",
-	    __func__, sc_to_str(p->e.sub_cmd), fcport->port_name,
-	    p->e.extra_rx_xchg_address, p->e.extra_control_flags,
-	    sp->handle, sp->remap.req.len, bsg_job);
-
-	if (rval != QLA_SUCCESS) {
+	switch (rval) {
+	case QLA_SUCCESS:
+		ql_dbg(ql_dbg_edif, vha, 0x700a,
+		       "%s %s %8phN xchg %x ctlflag %x hdl %x reqlen %xh bsg ptr %p\n",
+		       __func__, sc_to_str(p->e.sub_cmd), fcport->port_name,
+		       p->e.extra_rx_xchg_address, p->e.extra_control_flags,
+		       sp->handle, sp->remap.req.len, bsg_job);
+		break;
+	case EAGAIN:
+		msleep(EDIF_MSLEEP_INTERVAL);
+		cnt++;
+		if (cnt < EDIF_RETRY_COUNT)
+			goto retry;
+		fallthrough;
+	default:
 		ql_log(ql_log_warn, vha, 0x700e,
-		    "qla2x00_start_sp failed = %d\n", rval);
+		    "%s qla2x00_start_sp failed = %d\n", __func__, rval);
 		SET_DID_STATUS(bsg_reply->result, DID_IMM_RETRY);
 		rval = -EIO;
 		goto done_free_remap_rsp;
@@ -3490,7 +3547,7 @@ done:
 
 void qla_edif_sess_down(struct scsi_qla_host *vha, struct fc_port *sess)
 {
-	if (sess->edif.app_sess_online && vha->e_dbell.db_flags & EDB_ACTIVE) {
+	if (sess->edif.app_sess_online && DBELL_ACTIVE(vha)) {
 		ql_dbg(ql_dbg_disc, vha, 0xf09c,
 			"%s: sess %8phN send port_offline event\n",
 			__func__, sess->port_name);
diff --git a/drivers/scsi/qla2xxx/qla_edif.h b/drivers/scsi/qla2xxx/qla_edif.h
index 45cf87e33778..b9cedf6defd9 100644
--- a/drivers/scsi/qla2xxx/qla_edif.h
+++ b/drivers/scsi/qla2xxx/qla_edif.h
@@ -41,9 +41,12 @@ struct pur_core {
 };
 
 enum db_flags_t {
-	EDB_ACTIVE = 0x1,
+	EDB_ACTIVE = BIT_0,
 };
 
+#define DBELL_ACTIVE(_v) (_v->e_dbell.db_flags & EDB_ACTIVE)
+#define DBELL_INACTIVE(_v) (!(_v->e_dbell.db_flags & EDB_ACTIVE))
+
 struct edif_dbell {
 	enum db_flags_t		db_flags;
 	spinlock_t		db_lock;
@@ -101,7 +104,6 @@ struct dinfo {
 };
 
 struct pur_ninfo {
-	unsigned int	pur_pend:1;
 	port_id_t       pur_sid;
 	port_id_t	pur_did;
 	uint8_t		vp_idx;
@@ -134,4 +136,12 @@ struct enode {
 	 _s->disc_state == DSC_DELETED || \
 	 !_s->edif.app_sess_online))
 
+#define EDIF_NEGOTIATION_PENDING(_fcport) \
+	(DBELL_ACTIVE(_fcport->vha) && \
+	 (_fcport->disc_state == DSC_LOGIN_AUTH_PEND))
+
+#define EDIF_SESS_DELETE(_s) \
+	(qla_ini_mode_enabled(_s->vha) && (_s->disc_state == DSC_DELETE_PEND || \
+	 _s->disc_state == DSC_DELETED))
+
 #endif	/* __QLA_EDIF_H */
diff --git a/drivers/scsi/qla2xxx/qla_edif_bsg.h b/drivers/scsi/qla2xxx/qla_edif_bsg.h
index 53026d82ebff..af9f1ffb1e4a 100644
--- a/drivers/scsi/qla2xxx/qla_edif_bsg.h
+++ b/drivers/scsi/qla2xxx/qla_edif_bsg.h
@@ -217,4 +217,6 @@ struct auth_complete_cmd {
 
 #define RX_DELAY_DELETE_TIMEOUT 20
 
+#define FCH_EVT_VENDOR_UNIQUE_VPORT_DOWN  1
+
 #endif	/* QLA_EDIF_BSG_H */
diff --git a/drivers/scsi/qla2xxx/qla_fw.h b/drivers/scsi/qla2xxx/qla_fw.h
index 073d06e88c58..6faf7533958f 100644
--- a/drivers/scsi/qla2xxx/qla_fw.h
+++ b/drivers/scsi/qla2xxx/qla_fw.h
@@ -807,7 +807,7 @@ struct els_entry_24xx {
 #define EPD_ELS_COMMAND		(0 << 13)
 #define EPD_ELS_ACC		(1 << 13)
 #define EPD_ELS_RJT		(2 << 13)
-#define EPD_RX_XCHG		(3 << 13)
+#define EPD_RX_XCHG		(3 << 13)  /* terminate exchange */
 #define ECF_CLR_PASSTHRU_PEND	BIT_12
 #define ECF_INCL_FRAME_HDR	BIT_11
 #define ECF_SEC_LOGIN		BIT_3
diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h
index 83912787fa2e..f82e4a348330 100644
--- a/drivers/scsi/qla2xxx/qla_gbl.h
+++ b/drivers/scsi/qla2xxx/qla_gbl.h
@@ -192,6 +192,8 @@ extern int ql2xfulldump_on_mpifail;
 extern int ql2xsecenable;
 extern int ql2xenforce_iocb_limit;
 extern int ql2xabts_wait_nvme;
+extern int ql2xrspq_follow_inptr;
+extern int ql2xrspq_follow_inptr_legacy;
 
 extern int qla2x00_loop_reset(scsi_qla_host_t *);
 extern void qla2x00_abort_all_cmds(scsi_qla_host_t *, int);
@@ -334,6 +336,7 @@ extern int qla24xx_configure_prot_mode(srb_t *, uint16_t *);
 extern int qla24xx_issue_sa_replace_iocb(scsi_qla_host_t *vha,
 	struct qla_work_evt *e);
 void qla2x00_sp_release(struct kref *kref);
+void qla2x00_els_dcmd2_iocb_timeout(void *data);
 
 /*
  * Global Function Prototypes in qla_mbx.c source file.
@@ -432,7 +435,8 @@ extern int
 qla2x00_get_resource_cnts(scsi_qla_host_t *);
 
 extern int
-qla2x00_get_fcal_position_map(scsi_qla_host_t *ha, char *pos_map);
+qla2x00_get_fcal_position_map(scsi_qla_host_t *ha, char *pos_map,
+		u8 *num_entries);
 
 extern int
 qla2x00_get_link_status(scsi_qla_host_t *, uint16_t, struct link_statistics *,
@@ -722,7 +726,7 @@ int qla24xx_async_gpsc(scsi_qla_host_t *, fc_port_t *);
 void qla24xx_handle_gpsc_event(scsi_qla_host_t *, struct event_arg *);
 int qla2x00_mgmt_svr_login(scsi_qla_host_t *);
 void qla24xx_handle_gffid_event(scsi_qla_host_t *vha, struct event_arg *ea);
-int qla24xx_async_gffid(scsi_qla_host_t *vha, fc_port_t *fcport);
+int qla24xx_async_gffid(scsi_qla_host_t *vha, fc_port_t *fcport, bool);
 int qla24xx_async_gpnft(scsi_qla_host_t *, u8, srb_t *);
 void qla24xx_async_gpnft_done(scsi_qla_host_t *, srb_t *);
 void qla24xx_async_gnnft_done(scsi_qla_host_t *, srb_t *);
diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c
index da7080c4bd00..d3742a83d2fd 100644
--- a/drivers/scsi/qla2xxx/qla_gs.c
+++ b/drivers/scsi/qla2xxx/qla_gs.c
@@ -1595,7 +1595,6 @@ qla2x00_hba_attributes(scsi_qla_host_t *vha, void *entries,
 	unsigned int callopt)
 {
 	struct qla_hw_data *ha = vha->hw;
-	struct init_cb_24xx *icb24 = (void *)ha->init_cb;
 	struct new_utsname *p_sysid = utsname();
 	struct ct_fdmi_hba_attr *eiter;
 	uint16_t alen;
@@ -1757,8 +1756,8 @@ qla2x00_hba_attributes(scsi_qla_host_t *vha, void *entries,
 	/* MAX CT Payload Length */
 	eiter = entries + size;
 	eiter->type = cpu_to_be16(FDMI_HBA_MAXIMUM_CT_PAYLOAD_LENGTH);
-	eiter->a.max_ct_len = cpu_to_be32(le16_to_cpu(IS_FWI2_CAPABLE(ha) ?
-		icb24->frame_payload_size : ha->init_cb->frame_payload_size));
+	eiter->a.max_ct_len = cpu_to_be32(ha->frame_payload_size >> 2);
+
 	alen = sizeof(eiter->a.max_ct_len);
 	alen += FDMI_ATTR_TYPELEN(eiter);
 	eiter->len = cpu_to_be16(alen);
@@ -1850,7 +1849,6 @@ qla2x00_port_attributes(scsi_qla_host_t *vha, void *entries,
 	unsigned int callopt)
 {
 	struct qla_hw_data *ha = vha->hw;
-	struct init_cb_24xx *icb24 = (void *)ha->init_cb;
 	struct new_utsname *p_sysid = utsname();
 	char *hostname = p_sysid ?
 		p_sysid->nodename : fc_host_system_hostname(vha->host);
@@ -1902,8 +1900,7 @@ qla2x00_port_attributes(scsi_qla_host_t *vha, void *entries,
 	/* Max frame size. */
 	eiter = entries + size;
 	eiter->type = cpu_to_be16(FDMI_PORT_MAX_FRAME_SIZE);
-	eiter->a.max_frame_size = cpu_to_be32(le16_to_cpu(IS_FWI2_CAPABLE(ha) ?
-		icb24->frame_payload_size : ha->init_cb->frame_payload_size));
+	eiter->a.max_frame_size = cpu_to_be32(ha->frame_payload_size);
 	alen = sizeof(eiter->a.max_frame_size);
 	alen += FDMI_ATTR_TYPELEN(eiter);
 	eiter->len = cpu_to_be16(alen);
@@ -3279,19 +3276,12 @@ done:
 	return rval;
 }
 
-void qla24xx_handle_gffid_event(scsi_qla_host_t *vha, struct event_arg *ea)
-{
-	fc_port_t *fcport = ea->fcport;
-
-	qla24xx_post_gnl_work(vha, fcport);
-}
 
 void qla24xx_async_gffid_sp_done(srb_t *sp, int res)
 {
 	struct scsi_qla_host *vha = sp->vha;
 	fc_port_t *fcport = sp->fcport;
 	struct ct_sns_rsp *ct_rsp;
-	struct event_arg ea;
 	uint8_t fc4_scsi_feat;
 	uint8_t fc4_nvme_feat;
 
@@ -3299,10 +3289,10 @@ void qla24xx_async_gffid_sp_done(srb_t *sp, int res)
 	       "Async done-%s res %x ID %x. %8phC\n",
 	       sp->name, res, fcport->d_id.b24, fcport->port_name);
 
-	fcport->flags &= ~FCF_ASYNC_SENT;
-	ct_rsp = &fcport->ct_desc.ct_sns->p.rsp;
+	ct_rsp = sp->u.iocb_cmd.u.ctarg.rsp;
 	fc4_scsi_feat = ct_rsp->rsp.gff_id.fc4_features[GFF_FCP_SCSI_OFFSET];
 	fc4_nvme_feat = ct_rsp->rsp.gff_id.fc4_features[GFF_NVME_OFFSET];
+	sp->rc = res;
 
 	/*
 	 * FC-GS-7, 5.2.3.12 FC-4 Features - format
@@ -3323,24 +3313,42 @@ void qla24xx_async_gffid_sp_done(srb_t *sp, int res)
 		}
 	}
 
-	memset(&ea, 0, sizeof(ea));
-	ea.sp = sp;
-	ea.fcport = sp->fcport;
-	ea.rc = res;
+	if (sp->flags & SRB_WAKEUP_ON_COMP) {
+		complete(sp->comp);
+	} else  {
+		if (sp->u.iocb_cmd.u.ctarg.req) {
+			dma_free_coherent(&vha->hw->pdev->dev,
+				sp->u.iocb_cmd.u.ctarg.req_allocated_size,
+				sp->u.iocb_cmd.u.ctarg.req,
+				sp->u.iocb_cmd.u.ctarg.req_dma);
+			sp->u.iocb_cmd.u.ctarg.req = NULL;
+		}
 
-	qla24xx_handle_gffid_event(vha, &ea);
-	/* ref: INIT */
-	kref_put(&sp->cmd_kref, qla2x00_sp_release);
+		if (sp->u.iocb_cmd.u.ctarg.rsp) {
+			dma_free_coherent(&vha->hw->pdev->dev,
+				sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
+				sp->u.iocb_cmd.u.ctarg.rsp,
+				sp->u.iocb_cmd.u.ctarg.rsp_dma);
+			sp->u.iocb_cmd.u.ctarg.rsp = NULL;
+		}
+
+		/* ref: INIT */
+		kref_put(&sp->cmd_kref, qla2x00_sp_release);
+		/* we should not be here */
+		dump_stack();
+	}
 }
 
 /* Get FC4 Feature with Nport ID. */
-int qla24xx_async_gffid(scsi_qla_host_t *vha, fc_port_t *fcport)
+int qla24xx_async_gffid(scsi_qla_host_t *vha, fc_port_t *fcport, bool wait)
 {
 	int rval = QLA_FUNCTION_FAILED;
 	struct ct_sns_req       *ct_req;
 	srb_t *sp;
+	DECLARE_COMPLETION_ONSTACK(comp);
 
-	if (!vha->flags.online || (fcport->flags & FCF_ASYNC_SENT))
+	/* this routine does not have handling for no wait */
+	if (!vha->flags.online || !wait)
 		return rval;
 
 	/* ref: INIT */
@@ -3348,43 +3356,86 @@ int qla24xx_async_gffid(scsi_qla_host_t *vha, fc_port_t *fcport)
 	if (!sp)
 		return rval;
 
-	fcport->flags |= FCF_ASYNC_SENT;
 	sp->type = SRB_CT_PTHRU_CMD;
 	sp->name = "gffid";
 	sp->gen1 = fcport->rscn_gen;
 	sp->gen2 = fcport->login_gen;
 	qla2x00_init_async_sp(sp, qla2x00_get_async_timeout(vha) + 2,
 			      qla24xx_async_gffid_sp_done);
+	sp->comp = &comp;
+	sp->u.iocb_cmd.timeout = qla2x00_els_dcmd2_iocb_timeout;
+
+	if (wait)
+		sp->flags = SRB_WAKEUP_ON_COMP;
+
+	sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt);
+	sp->u.iocb_cmd.u.ctarg.req = dma_alloc_coherent(&vha->hw->pdev->dev,
+				sp->u.iocb_cmd.u.ctarg.req_allocated_size,
+				&sp->u.iocb_cmd.u.ctarg.req_dma,
+	    GFP_KERNEL);
+	if (!sp->u.iocb_cmd.u.ctarg.req) {
+		ql_log(ql_log_warn, vha, 0xd041,
+		       "%s: Failed to allocate ct_sns request.\n",
+		       __func__);
+		goto done_free_sp;
+	}
+
+	sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt);
+	sp->u.iocb_cmd.u.ctarg.rsp = dma_alloc_coherent(&vha->hw->pdev->dev,
+				sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
+				&sp->u.iocb_cmd.u.ctarg.rsp_dma,
+	    GFP_KERNEL);
+	if (!sp->u.iocb_cmd.u.ctarg.rsp) {
+		ql_log(ql_log_warn, vha, 0xd041,
+		       "%s: Failed to allocate ct_sns response.\n",
+		       __func__);
+		goto done_free_sp;
+	}
 
 	/* CT_IU preamble  */
-	ct_req = qla2x00_prep_ct_req(fcport->ct_desc.ct_sns, GFF_ID_CMD,
-	    GFF_ID_RSP_SIZE);
+	ct_req = qla2x00_prep_ct_req(sp->u.iocb_cmd.u.ctarg.req, GFF_ID_CMD, GFF_ID_RSP_SIZE);
 
 	ct_req->req.gff_id.port_id[0] = fcport->d_id.b.domain;
 	ct_req->req.gff_id.port_id[1] = fcport->d_id.b.area;
 	ct_req->req.gff_id.port_id[2] = fcport->d_id.b.al_pa;
 
-	sp->u.iocb_cmd.u.ctarg.req = fcport->ct_desc.ct_sns;
-	sp->u.iocb_cmd.u.ctarg.req_dma = fcport->ct_desc.ct_sns_dma;
-	sp->u.iocb_cmd.u.ctarg.rsp = fcport->ct_desc.ct_sns;
-	sp->u.iocb_cmd.u.ctarg.rsp_dma = fcport->ct_desc.ct_sns_dma;
 	sp->u.iocb_cmd.u.ctarg.req_size = GFF_ID_REQ_SIZE;
 	sp->u.iocb_cmd.u.ctarg.rsp_size = GFF_ID_RSP_SIZE;
 	sp->u.iocb_cmd.u.ctarg.nport_handle = NPH_SNS;
 
-	ql_dbg(ql_dbg_disc, vha, 0x2132,
-	    "Async-%s hdl=%x  %8phC.\n", sp->name,
-	    sp->handle, fcport->port_name);
-
 	rval = qla2x00_start_sp(sp);
-	if (rval != QLA_SUCCESS)
+
+	if (rval != QLA_SUCCESS) {
+		rval = QLA_FUNCTION_FAILED;
 		goto done_free_sp;
+	} else {
+		ql_dbg(ql_dbg_disc, vha, 0x3074,
+		       "Async-%s hdl=%x portid %06x\n",
+		       sp->name, sp->handle, fcport->d_id.b24);
+	}
+
+	wait_for_completion(sp->comp);
+	rval = sp->rc;
 
-	return rval;
 done_free_sp:
+	if (sp->u.iocb_cmd.u.ctarg.req) {
+		dma_free_coherent(&vha->hw->pdev->dev,
+				  sp->u.iocb_cmd.u.ctarg.req_allocated_size,
+				  sp->u.iocb_cmd.u.ctarg.req,
+				  sp->u.iocb_cmd.u.ctarg.req_dma);
+		sp->u.iocb_cmd.u.ctarg.req = NULL;
+	}
+
+	if (sp->u.iocb_cmd.u.ctarg.rsp) {
+		dma_free_coherent(&vha->hw->pdev->dev,
+				  sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
+				  sp->u.iocb_cmd.u.ctarg.rsp,
+				  sp->u.iocb_cmd.u.ctarg.rsp_dma);
+		sp->u.iocb_cmd.u.ctarg.rsp = NULL;
+	}
+
 	/* ref: INIT */
 	kref_put(&sp->cmd_kref, qla2x00_sp_release);
-	fcport->flags &= ~FCF_ASYNC_SENT;
 	return rval;
 }
 
@@ -3577,7 +3628,7 @@ login_logout:
 				do_delete) {
 				if (fcport->loop_id != FC_NO_LOOP_ID) {
 					if (fcport->flags & FCF_FCP2_DEVICE)
-						fcport->logout_on_delete = 0;
+						continue;
 
 					ql_log(ql_log_warn, vha, 0x20f0,
 					       "%s %d %8phC post del sess\n",
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index af8df5a800c6..b81797a3ab61 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -47,6 +47,7 @@ qla2x00_sp_timeout(struct timer_list *t)
 {
 	srb_t *sp = from_timer(sp, t, u.iocb_cmd.timer);
 	struct srb_iocb *iocb;
+	scsi_qla_host_t *vha = sp->vha;
 
 	WARN_ON(irqs_disabled());
 	iocb = &sp->u.iocb_cmd;
@@ -54,6 +55,12 @@ qla2x00_sp_timeout(struct timer_list *t)
 
 	/* ref: TMR */
 	kref_put(&sp->cmd_kref, qla2x00_sp_release);
+
+	if (vha && qla2x00_isp_reg_stat(vha->hw)) {
+		ql_log(ql_log_info, vha, 0x9008,
+		    "PCI/Register disconnect.\n");
+		qla_pci_set_eeh_busy(vha);
+	}
 }
 
 void qla2x00_sp_free(srb_t *sp)
@@ -161,6 +168,7 @@ int qla24xx_async_abort_cmd(srb_t *cmd_sp, bool wait)
 	struct srb_iocb *abt_iocb;
 	srb_t *sp;
 	int rval = QLA_FUNCTION_FAILED;
+	uint8_t bail;
 
 	/* ref: INIT for ABTS command */
 	sp = qla2xxx_get_qpair_sp(cmd_sp->vha, cmd_sp->qpair, cmd_sp->fcport,
@@ -168,6 +176,7 @@ int qla24xx_async_abort_cmd(srb_t *cmd_sp, bool wait)
 	if (!sp)
 		return QLA_MEMORY_ALLOC_FAILED;
 
+	QLA_VHA_MARK_BUSY(vha, bail);
 	abt_iocb = &sp->u.iocb_cmd;
 	sp->type = SRB_ABT_CMD;
 	sp->name = "abort";
@@ -341,7 +350,7 @@ qla2x00_async_login(struct scsi_qla_host *vha, fc_port_t *fcport,
 		lio->u.logio.flags |= SRB_LOGIN_PRLI_ONLY;
 	} else {
 		if (vha->hw->flags.edif_enabled &&
-		    vha->e_dbell.db_flags & EDB_ACTIVE) {
+		    DBELL_ACTIVE(vha)) {
 			lio->u.logio.flags |=
 				(SRB_LOGIN_FCSP | SRB_LOGIN_SKIP_PRLI);
 			ql_dbg(ql_dbg_disc, vha, 0x2072,
@@ -881,7 +890,7 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha,
 				break;
 			case DSC_LS_PLOGI_COMP:
 				if (vha->hw->flags.edif_enabled &&
-				    vha->e_dbell.db_flags & EDB_ACTIVE) {
+				    DBELL_ACTIVE(vha)) {
 					/* check to see if App support secure or not */
 					qla24xx_post_gpdb_work(vha, fcport, 0);
 					break;
@@ -1477,7 +1486,7 @@ static int	qla_chk_secure_login(scsi_qla_host_t	*vha, fc_port_t *fcport,
 			qla2x00_post_aen_work(vha, FCH_EVT_PORT_ONLINE,
 			    fcport->d_id.b24);
 
-			if (vha->e_dbell.db_flags ==  EDB_ACTIVE) {
+			if (DBELL_ACTIVE(vha)) {
 				ql_dbg(ql_dbg_disc, vha, 0x20ef,
 				    "%s %d %8phC EDIF: post DB_AUTH: AUTH needed\n",
 				    __func__, __LINE__, fcport->port_name);
@@ -1764,8 +1773,16 @@ int qla24xx_fcport_handle_login(struct scsi_qla_host *vha, fc_port_t *fcport)
 		break;
 
 	case DSC_LOGIN_PEND:
-		if (fcport->fw_login_state == DSC_LS_PLOGI_COMP)
+		if (vha->hw->flags.edif_enabled)
+			break;
+
+		if (fcport->fw_login_state == DSC_LS_PLOGI_COMP) {
+			ql_dbg(ql_dbg_disc, vha, 0x2118,
+			       "%s %d %8phC post %s PRLI\n",
+			       __func__, __LINE__, fcport->port_name,
+			       NVME_TARGET(vha->hw, fcport) ? "NVME" : "FC");
 			qla24xx_post_prli_work(vha, fcport);
+		}
 		break;
 
 	case DSC_UPD_FCPORT:
@@ -1819,19 +1836,41 @@ void qla2x00_handle_rscn(scsi_qla_host_t *vha, struct event_arg *ea)
 	case RSCN_PORT_ADDR:
 		fcport = qla2x00_find_fcport_by_nportid(vha, &ea->id, 1);
 		if (fcport) {
-			if (fcport->flags & FCF_FCP2_DEVICE) {
+			if (fcport->flags & FCF_FCP2_DEVICE &&
+			    atomic_read(&fcport->state) == FCS_ONLINE) {
 				ql_dbg(ql_dbg_disc, vha, 0x2115,
 				       "Delaying session delete for FCP2 portid=%06x %8phC ",
 					fcport->d_id.b24, fcport->port_name);
 				return;
 			}
-			fcport->scan_needed = 1;
-			fcport->rscn_gen++;
+
+			if (vha->hw->flags.edif_enabled && DBELL_ACTIVE(vha)) {
+				/*
+				 * On ipsec start by remote port, Target port
+				 * may use RSCN to trigger initiator to
+				 * relogin. If driver is already in the
+				 * process of a relogin, then ignore the RSCN
+				 * and allow the current relogin to continue.
+				 * This reduces thrashing of the connection.
+				 */
+				if (atomic_read(&fcport->state) == FCS_ONLINE) {
+					/*
+					 * If state = online, then set scan_needed=1 to do relogin.
+					 * Otherwise we're already in the middle of a relogin
+					 */
+					fcport->scan_needed = 1;
+					fcport->rscn_gen++;
+				}
+			} else {
+				fcport->scan_needed = 1;
+				fcport->rscn_gen++;
+			}
 		}
 		break;
 	case RSCN_AREA_ADDR:
 		list_for_each_entry(fcport, &vha->vp_fcports, list) {
-			if (fcport->flags & FCF_FCP2_DEVICE)
+			if (fcport->flags & FCF_FCP2_DEVICE &&
+			    atomic_read(&fcport->state) == FCS_ONLINE)
 				continue;
 
 			if ((ea->id.b24 & 0xffff00) == (fcport->d_id.b24 & 0xffff00)) {
@@ -1842,7 +1881,8 @@ void qla2x00_handle_rscn(scsi_qla_host_t *vha, struct event_arg *ea)
 		break;
 	case RSCN_DOM_ADDR:
 		list_for_each_entry(fcport, &vha->vp_fcports, list) {
-			if (fcport->flags & FCF_FCP2_DEVICE)
+			if (fcport->flags & FCF_FCP2_DEVICE &&
+			    atomic_read(&fcport->state) == FCS_ONLINE)
 				continue;
 
 			if ((ea->id.b24 & 0xff0000) == (fcport->d_id.b24 & 0xff0000)) {
@@ -1854,7 +1894,8 @@ void qla2x00_handle_rscn(scsi_qla_host_t *vha, struct event_arg *ea)
 	case RSCN_FAB_ADDR:
 	default:
 		list_for_each_entry(fcport, &vha->vp_fcports, list) {
-			if (fcport->flags & FCF_FCP2_DEVICE)
+			if (fcport->flags & FCF_FCP2_DEVICE &&
+			    atomic_read(&fcport->state) == FCS_ONLINE)
 				continue;
 
 			fcport->scan_needed = 1;
@@ -1981,12 +2022,14 @@ qla2x00_async_tm_cmd(fc_port_t *fcport, uint32_t flags, uint32_t lun,
 	struct srb_iocb *tm_iocb;
 	srb_t *sp;
 	int rval = QLA_FUNCTION_FAILED;
+	uint8_t bail;
 
 	/* ref: INIT */
 	sp = qla2x00_get_sp(vha, fcport, GFP_KERNEL);
 	if (!sp)
 		goto done;
 
+	QLA_VHA_MARK_BUSY(vha, bail);
 	sp->type = SRB_TM_CMD;
 	sp->name = "tmf";
 	qla2x00_init_async_sp(sp, qla2x00_get_async_timeout(vha),
@@ -2105,6 +2148,13 @@ qla24xx_handle_prli_done_event(struct scsi_qla_host *vha, struct event_arg *ea)
 		}
 
 		if (N2N_TOPO(vha->hw)) {
+			if (ea->fcport->n2n_link_reset_cnt ==
+			    vha->hw->login_retry_count &&
+			    ea->fcport->flags & FCF_FCSP_DEVICE) {
+				/* remote authentication app just started */
+				ea->fcport->n2n_link_reset_cnt = 0;
+			}
+
 			if (ea->fcport->n2n_link_reset_cnt <
 			    vha->hw->login_retry_count) {
 				ea->fcport->n2n_link_reset_cnt++;
@@ -4246,7 +4296,7 @@ qla24xx_update_fw_options(scsi_qla_host_t *vha)
 		 * fw shal not send PRLI after PLOGI Acc
 		 */
 		if (ha->flags.edif_enabled &&
-		    vha->e_dbell.db_flags & EDB_ACTIVE) {
+		    DBELL_ACTIVE(vha)) {
 			ha->fw_options[3] |= BIT_15;
 			ha->flags.n2n_fw_acc_sec = 1;
 		} else {
@@ -4490,6 +4540,8 @@ qla2x00_init_rings(scsi_qla_host_t *vha)
 			 BIT_6) != 0;
 		ql_dbg(ql_dbg_init, vha, 0x00bc, "FA-WWPN Support: %s.\n",
 		    (ha->flags.fawwpn_enabled) ? "enabled" : "disabled");
+		/* Init_cb will be reused for other command(s).  Save a backup copy of port_name */
+		memcpy(ha->port_name, ha->init_cb->port_name, WWN_SIZE);
 	}
 
 	/* ELS pass through payload is limit by frame size. */
@@ -5402,8 +5454,7 @@ qla2x00_configure_loop(scsi_qla_host_t *vha)
 			 * use link up to wake up app to get ready for
 			 * authentication.
 			 */
-			if (ha->flags.edif_enabled &&
-			    !(vha->e_dbell.db_flags & EDB_ACTIVE))
+			if (ha->flags.edif_enabled && DBELL_INACTIVE(vha))
 				qla2x00_post_aen_work(vha, FCH_EVT_LINKUP,
 						      ha->link_data_rate);
 
@@ -5470,6 +5521,22 @@ static int qla2x00_configure_n2n_loop(scsi_qla_host_t *vha)
 	return QLA_FUNCTION_FAILED;
 }
 
+static void
+qla_reinitialize_link(scsi_qla_host_t *vha)
+{
+	int rval;
+
+	atomic_set(&vha->loop_state, LOOP_DOWN);
+	atomic_set(&vha->loop_down_timer, LOOP_DOWN_TIME);
+	rval = qla2x00_full_login_lip(vha);
+	if (rval == QLA_SUCCESS) {
+		ql_dbg(ql_dbg_disc, vha, 0xd050, "Link reinitialized\n");
+	} else {
+		ql_dbg(ql_dbg_disc, vha, 0xd051,
+			"Link reinitialization failed (%d)\n", rval);
+	}
+}
+
 /*
  * qla2x00_configure_local_loop
  *	Updates Fibre Channel Device Database with local loop devices.
@@ -5521,6 +5588,19 @@ qla2x00_configure_local_loop(scsi_qla_host_t *vha)
 		spin_unlock_irqrestore(&vha->work_lock, flags);
 
 		if (vha->scan.scan_retry < MAX_SCAN_RETRIES) {
+			u8 loop_map_entries = 0;
+			int rc;
+
+			rc = qla2x00_get_fcal_position_map(vha, NULL,
+						&loop_map_entries);
+			if (rc == QLA_SUCCESS && loop_map_entries > 1) {
+				/*
+				 * There are devices that are still not logged
+				 * in. Reinitialize to give them a chance.
+				 */
+				qla_reinitialize_link(vha);
+				return QLA_FUNCTION_FAILED;
+			}
 			set_bit(LOCAL_LOOP_UPDATE, &vha->dpc_flags);
 			set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags);
 		}
@@ -5749,8 +5829,6 @@ qla2x00_reg_remote_port(scsi_qla_host_t *vha, fc_port_t *fcport)
 	if (atomic_read(&fcport->state) == FCS_ONLINE)
 		return;
 
-	qla2x00_set_fcport_state(fcport, FCS_ONLINE);
-
 	rport_ids.node_name = wwn_to_u64(fcport->node_name);
 	rport_ids.port_name = wwn_to_u64(fcport->port_name);
 	rport_ids.port_id = fcport->d_id.b.domain << 16 |
@@ -5858,7 +5936,6 @@ qla2x00_update_fcport(scsi_qla_host_t *vha, fc_port_t *fcport)
 		qla2x00_reg_remote_port(vha, fcport);
 		break;
 	case MODE_TARGET:
-		qla2x00_set_fcport_state(fcport, FCS_ONLINE);
 		if (!vha->vha_tgt.qla_tgt->tgt_stop &&
 			!vha->vha_tgt.qla_tgt->tgt_stopped)
 			qlt_fc_port_added(vha, fcport);
@@ -5873,6 +5950,8 @@ qla2x00_update_fcport(scsi_qla_host_t *vha, fc_port_t *fcport)
 		break;
 	}
 
+	qla2x00_set_fcport_state(fcport, FCS_ONLINE);
+
 	if (IS_IIDMA_CAPABLE(vha->hw) && vha->hw->flags.gpsc_supported) {
 		if (fcport->id_changed) {
 			fcport->id_changed = 0;
@@ -7096,12 +7175,14 @@ qla2x00_abort_isp_cleanup(scsi_qla_host_t *vha)
 	ha->chip_reset++;
 	ha->base_qpair->chip_reset = ha->chip_reset;
 	ha->base_qpair->cmd_cnt = ha->base_qpair->cmd_completion_cnt = 0;
+	ha->base_qpair->prev_completion_cnt = 0;
 	for (i = 0; i < ha->max_qpairs; i++) {
 		if (ha->queue_pair_map[i]) {
 			ha->queue_pair_map[i]->chip_reset =
 				ha->base_qpair->chip_reset;
 			ha->queue_pair_map[i]->cmd_cnt =
 			    ha->queue_pair_map[i]->cmd_completion_cnt = 0;
+			ha->base_qpair->prev_completion_cnt = 0;
 		}
 	}
 
@@ -9661,6 +9742,12 @@ int qla2xxx_disable_port(struct Scsi_Host *host)
 
 	vha->hw->flags.port_isolated = 1;
 
+	if (qla2x00_isp_reg_stat(vha->hw)) {
+		ql_log(ql_log_info, vha, 0x9006,
+		    "PCI/Register disconnect, exiting.\n");
+		qla_pci_set_eeh_busy(vha);
+		return FAILED;
+	}
 	if (qla2x00_chip_is_down(vha))
 		return 0;
 
@@ -9676,6 +9763,13 @@ int qla2xxx_enable_port(struct Scsi_Host *host)
 {
 	scsi_qla_host_t *vha = shost_priv(host);
 
+	if (qla2x00_isp_reg_stat(vha->hw)) {
+		ql_log(ql_log_info, vha, 0x9001,
+		    "PCI/Register disconnect, exiting.\n");
+		qla_pci_set_eeh_busy(vha);
+		return FAILED;
+	}
+
 	vha->hw->flags.port_isolated = 0;
 	/* Set the flag to 1, so that isp_abort can proceed */
 	vha->flags.online = 1;
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index 606228f4a8b5..42ce4e1fe744 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -2819,7 +2819,7 @@ qla24xx_els_logo_iocb(srb_t *sp, struct els_entry_24xx *els_iocb)
 	sp->vha->qla_stats.control_requests++;
 }
 
-static void
+void
 qla2x00_els_dcmd2_iocb_timeout(void *data)
 {
 	srb_t *sp = data;
@@ -2882,6 +2882,9 @@ static void qla2x00_els_dcmd2_sp_done(srb_t *sp, int res)
 	    sp->name, res, sp->handle, fcport->d_id.b24, fcport->port_name);
 
 	fcport->flags &= ~(FCF_ASYNC_SENT|FCF_ASYNC_ACTIVE);
+	/* For edif, set logout on delete to ensure any residual key from FW is flushed.*/
+	fcport->logout_on_delete = 1;
+	fcport->chip_reset = vha->hw->base_qpair->chip_reset;
 
 	if (sp->flags & SRB_WAKEUP_ON_COMP)
 		complete(&lio->u.els_plogi.comp);
@@ -3065,8 +3068,7 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode,
 	elsio->u.els_plogi.els_cmd = els_opcode;
 	elsio->u.els_plogi.els_plogi_pyld->opcode = els_opcode;
 
-	if (els_opcode == ELS_DCMD_PLOGI && vha->hw->flags.edif_enabled &&
-	    vha->e_dbell.db_flags & EDB_ACTIVE) {
+	if (els_opcode == ELS_DCMD_PLOGI && DBELL_ACTIVE(vha)) {
 		struct fc_els_flogi *p = ptr;
 
 		p->fl_csp.sp_features |= cpu_to_be16(FC_SP_FT_SEC);
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 62d2f14848e7..59f5918dca95 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -1354,9 +1354,7 @@ skip_rio:
 			if (!vha->vp_idx) {
 				if (ha->flags.fawwpn_enabled &&
 				    (ha->current_topology == ISP_CFG_F)) {
-					void *wwpn = ha->init_cb->port_name;
-
-					memcpy(vha->port_name, wwpn, WWN_SIZE);
+					memcpy(vha->port_name, ha->port_name, WWN_SIZE);
 					fc_host_port_name(vha->host) =
 					    wwn_to_u64(vha->port_name);
 					ql_dbg(ql_dbg_init + ql_dbg_verbose,
@@ -2635,7 +2633,7 @@ static void qla24xx_nvme_iocb_entry(scsi_qla_host_t *vha, struct req_que *req,
 	}
 
 	if (unlikely(logit))
-		ql_log(ql_dbg_io, fcport->vha, 0x5060,
+		ql_dbg(ql_dbg_io, fcport->vha, 0x5060,
 		   "NVME-%s ERR Handling - hdl=%x status(%x) tr_len:%x resid=%x  ox_id=%x\n",
 		   sp->name, sp->handle, comp_status,
 		   fd->transferred_length, le32_to_cpu(sts->residual_len),
@@ -3422,6 +3420,7 @@ check_scsi_status:
 	case CS_PORT_UNAVAILABLE:
 	case CS_TIMEOUT:
 	case CS_RESET:
+	case CS_EDIF_INV_REQ:
 
 		/*
 		 * We are going to have the fc class block the rport
@@ -3492,7 +3491,7 @@ check_scsi_status:
 
 out:
 	if (logit)
-		ql_log(ql_dbg_io, fcport->vha, 0x3022,
+		ql_dbg(ql_dbg_io, fcport->vha, 0x3022,
 		       "FCP command status: 0x%x-0x%x (0x%x) nexus=%ld:%d:%llu portid=%02x%02x%02x oxid=0x%x cdb=%10phN len=0x%x rsp_info=0x%x resid=0x%x fw_resid=0x%x sp=%p cp=%p.\n",
 		       comp_status, scsi_status, res, vha->host_no,
 		       cp->device->id, cp->device->lun, fcport->d_id.b.domain,
@@ -3708,12 +3707,11 @@ void qla24xx_nvme_ls4_iocb(struct scsi_qla_host *vha,
  * Return: 0 all iocbs has arrived, xx- all iocbs have not arrived.
  */
 static int qla_chk_cont_iocb_avail(struct scsi_qla_host *vha,
-	struct rsp_que *rsp, response_t *pkt)
+	struct rsp_que *rsp, response_t *pkt, u32 rsp_q_in)
 {
-	int start_pkt_ring_index, end_pkt_ring_index, n_ring_index;
-	response_t *end_pkt;
+	int start_pkt_ring_index;
+	u32 iocb_cnt = 0;
 	int rc = 0;
-	u32 rsp_q_in;
 
 	if (pkt->entry_count == 1)
 		return rc;
@@ -3724,34 +3722,18 @@ static int qla_chk_cont_iocb_avail(struct scsi_qla_host *vha,
 	else
 		start_pkt_ring_index = rsp->ring_index - 1;
 
-	if ((start_pkt_ring_index + pkt->entry_count) >= rsp->length)
-		end_pkt_ring_index = start_pkt_ring_index + pkt->entry_count -
-			rsp->length - 1;
+	if (rsp_q_in < start_pkt_ring_index)
+		/* q in ptr is wrapped */
+		iocb_cnt = rsp->length - start_pkt_ring_index + rsp_q_in;
 	else
-		end_pkt_ring_index = start_pkt_ring_index + pkt->entry_count - 1;
-
-	end_pkt = rsp->ring + end_pkt_ring_index;
-
-	/*  next pkt = end_pkt + 1 */
-	n_ring_index = end_pkt_ring_index + 1;
-	if (n_ring_index >= rsp->length)
-		n_ring_index = 0;
+		iocb_cnt = rsp_q_in - start_pkt_ring_index;
 
-	rsp_q_in = rsp->qpair->use_shadow_reg ? *rsp->in_ptr :
-		rd_reg_dword(rsp->rsp_q_in);
-
-	/* rsp_q_in is either wrapped or pointing beyond endpkt */
-	if ((rsp_q_in < start_pkt_ring_index && rsp_q_in < n_ring_index) ||
-			rsp_q_in >= n_ring_index)
-		/* all IOCBs arrived. */
-		rc = 0;
-	else
+	if (iocb_cnt < pkt->entry_count)
 		rc = -EIO;
 
-	ql_dbg(ql_dbg_init + ql_dbg_verbose, vha, 0x5091,
-	    "%s - ring %p pkt %p end pkt %p entry count %#x rsp_q_in %d rc %d\n",
-	    __func__, rsp->ring, pkt, end_pkt, pkt->entry_count,
-	    rsp_q_in, rc);
+	ql_dbg(ql_dbg_init, vha, 0x5091,
+	       "%s - ring %p pkt %p entry count %d iocb_cnt %d rsp_q_in %d rc %d\n",
+	       __func__, rsp->ring, pkt, pkt->entry_count, iocb_cnt, rsp_q_in, rc);
 
 	return rc;
 }
@@ -3768,6 +3750,8 @@ void qla24xx_process_response_queue(struct scsi_qla_host *vha,
 	struct qla_hw_data *ha = vha->hw;
 	struct purex_entry_24xx *purex_entry;
 	struct purex_item *pure_item;
+	u16 rsp_in = 0, cur_ring_index;
+	int follow_inptr, is_shadow_hba;
 
 	if (!ha->flags.fw_started)
 		return;
@@ -3777,8 +3761,27 @@ void qla24xx_process_response_queue(struct scsi_qla_host *vha,
 		qla_cpu_update(rsp->qpair, smp_processor_id());
 	}
 
-	while (rsp->ring_ptr->signature != RESPONSE_PROCESSED) {
+#define __update_rsp_in(_update, _is_shadow_hba, _rsp, _rsp_in)		\
+	do {								\
+		if (_update) {						\
+			_rsp_in = _is_shadow_hba ? *(_rsp)->in_ptr :	\
+				rd_reg_dword_relaxed((_rsp)->rsp_q_in);	\
+		}							\
+	} while (0)
+
+	is_shadow_hba = IS_SHADOW_REG_CAPABLE(ha);
+	follow_inptr = is_shadow_hba ? ql2xrspq_follow_inptr :
+				ql2xrspq_follow_inptr_legacy;
+
+	__update_rsp_in(follow_inptr, is_shadow_hba, rsp, rsp_in);
+
+	while ((likely(follow_inptr &&
+		       rsp->ring_index != rsp_in &&
+		       rsp->ring_ptr->signature != RESPONSE_PROCESSED)) ||
+		       (!follow_inptr &&
+			rsp->ring_ptr->signature != RESPONSE_PROCESSED)) {
 		pkt = (struct sts_entry_24xx *)rsp->ring_ptr;
+		cur_ring_index = rsp->ring_index;
 
 		rsp->ring_index++;
 		if (rsp->ring_index == rsp->length) {
@@ -3890,6 +3893,8 @@ process_err:
 				}
 				pure_item = qla27xx_copy_fpin_pkt(vha,
 							  (void **)&pkt, &rsp);
+				__update_rsp_in(follow_inptr, is_shadow_hba,
+						rsp, rsp_in);
 				if (!pure_item)
 					break;
 				qla24xx_queue_purex_item(vha, pure_item,
@@ -3897,7 +3902,17 @@ process_err:
 				break;
 
 			case ELS_AUTH_ELS:
-				if (qla_chk_cont_iocb_avail(vha, rsp, (response_t *)pkt)) {
+				if (qla_chk_cont_iocb_avail(vha, rsp, (response_t *)pkt, rsp_in)) {
+					/*
+					 * ring_ptr and ring_index were
+					 * pre-incremented above. Reset them
+					 * back to current. Wait for next
+					 * interrupt with all IOCBs to arrive
+					 * and re-process.
+					 */
+					rsp->ring_ptr = (response_t *)pkt;
+					rsp->ring_index = cur_ring_index;
+
 					ql_dbg(ql_dbg_init, vha, 0x5091,
 					    "Defer processing ELS opcode %#x...\n",
 					    purex_entry->els_frame_payload[3]);
@@ -4416,16 +4431,12 @@ msix_register_fail:
 	}
 
 	/* Enable MSI-X vector for response queue update for queue 0 */
-	if (IS_QLA83XX(ha) || IS_QLA27XX(ha) || IS_QLA28XX(ha)) {
-		if (ha->msixbase && ha->mqiobase &&
-		    (ha->max_rsp_queues > 1 || ha->max_req_queues > 1 ||
-		     ql2xmqsupport))
-			ha->mqenable = 1;
-	} else
-		if (ha->mqiobase &&
-		    (ha->max_rsp_queues > 1 || ha->max_req_queues > 1 ||
-		     ql2xmqsupport))
-			ha->mqenable = 1;
+	if (IS_MQUE_CAPABLE(ha) &&
+	    (ha->msixbase && ha->mqiobase && ha->max_qpairs))
+		ha->mqenable = 1;
+	else
+		ha->mqenable = 0;
+
 	ql_dbg(ql_dbg_multiq, vha, 0xc005,
 	    "mqiobase=%p, max_rsp_queues=%d, max_req_queues=%d.\n",
 	    ha->mqiobase, ha->max_rsp_queues, ha->max_req_queues);
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 950c5903e799..5bcb8da4360f 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -238,6 +238,8 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 			ql_dbg(ql_dbg_mbx, vha, 0x1112,
 			    "mbox[%d]<-0x%04x\n", cnt, *iptr);
 			wrt_reg_word(optr, *iptr);
+		} else {
+			wrt_reg_word(optr, 0);
 		}
 
 		mboxes >>= 1;
@@ -274,6 +276,12 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 		atomic_inc(&ha->num_pend_mbx_stage3);
 		if (!wait_for_completion_timeout(&ha->mbx_intr_comp,
 		    mcp->tov * HZ)) {
+			ql_dbg(ql_dbg_mbx, vha, 0x117a,
+			    "cmd=%x Timeout.\n", command);
+			spin_lock_irqsave(&ha->hardware_lock, flags);
+			clear_bit(MBX_INTR_WAIT, &ha->mbx_cmd_flags);
+			spin_unlock_irqrestore(&ha->hardware_lock, flags);
+
 			if (chip_reset != ha->chip_reset) {
 				eeh_delay = ha->flags.eeh_busy ? 1 : 0;
 
@@ -286,12 +294,6 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 				rval = QLA_ABORTED;
 				goto premature_exit;
 			}
-			ql_dbg(ql_dbg_mbx, vha, 0x117a,
-			    "cmd=%x Timeout.\n", command);
-			spin_lock_irqsave(&ha->hardware_lock, flags);
-			clear_bit(MBX_INTR_WAIT, &ha->mbx_cmd_flags);
-			spin_unlock_irqrestore(&ha->hardware_lock, flags);
-
 		} else if (ha->flags.purge_mbox ||
 		    chip_reset != ha->chip_reset) {
 			eeh_delay = ha->flags.eeh_busy ? 1 : 0;
@@ -3060,7 +3062,8 @@ qla2x00_get_resource_cnts(scsi_qla_host_t *vha)
  *	Kernel context.
  */
 int
-qla2x00_get_fcal_position_map(scsi_qla_host_t *vha, char *pos_map)
+qla2x00_get_fcal_position_map(scsi_qla_host_t *vha, char *pos_map,
+		u8 *num_entries)
 {
 	int rval;
 	mbx_cmd_t mc;
@@ -3100,6 +3103,8 @@ qla2x00_get_fcal_position_map(scsi_qla_host_t *vha, char *pos_map)
 
 		if (pos_map)
 			memcpy(pos_map, pmap, FCAL_MAP_SIZE);
+		if (num_entries)
+			*num_entries = pmap[0];
 	}
 	dma_pool_free(ha->s_dma_pool, pmap, pmap_dma);
 
diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c
index e6b5c4ccce97..eb43a5f1b399 100644
--- a/drivers/scsi/qla2xxx/qla_mid.c
+++ b/drivers/scsi/qla2xxx/qla_mid.c
@@ -166,9 +166,13 @@ qla24xx_disable_vp(scsi_qla_host_t *vha)
 	int ret = QLA_SUCCESS;
 	fc_port_t *fcport;
 
-	if (vha->hw->flags.edif_enabled)
+	if (vha->hw->flags.edif_enabled) {
+		if (DBELL_ACTIVE(vha))
+			qla2x00_post_aen_work(vha, FCH_EVT_VENDOR_UNIQUE,
+			    FCH_EVT_VENDOR_UNIQUE_VPORT_DOWN);
 		/* delete sessions and flush sa_indexes */
 		qla2x00_wait_for_sess_deletion(vha);
+	}
 
 	if (vha->hw->flags.fw_started)
 		ret = qla24xx_control_vp(vha, VCE_COMMAND_DISABLE_VPS_LOGO_ALL);
diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c
index 42b29f4fd937..3e167dc4eec7 100644
--- a/drivers/scsi/qla2xxx/qla_nvme.c
+++ b/drivers/scsi/qla2xxx/qla_nvme.c
@@ -35,11 +35,6 @@ int qla_nvme_register_remote(struct scsi_qla_host *vha, struct fc_port *fcport)
 		(fcport->nvme_flag & NVME_FLAG_REGISTERED))
 		return 0;
 
-	if (atomic_read(&fcport->state) == FCS_ONLINE)
-		return 0;
-
-	qla2x00_set_fcport_state(fcport, FCS_ONLINE);
-
 	fcport->nvme_flag &= ~NVME_FLAG_RESETTING;
 
 	memset(&req, 0, sizeof(struct nvme_fc_port_info));
@@ -775,7 +770,6 @@ int qla_nvme_register_hba(struct scsi_qla_host *vha)
 	ha = vha->hw;
 	tmpl = &qla_nvme_fc_transport;
 
-	WARN_ON(vha->nvme_local_port);
 
 	qla_nvme_fc_transport.max_hw_queues =
 	    min((uint8_t)(qla_nvme_fc_transport.max_hw_queues),
@@ -786,13 +780,25 @@ int qla_nvme_register_hba(struct scsi_qla_host *vha)
 	pinfo.port_role = FC_PORT_ROLE_NVME_INITIATOR;
 	pinfo.port_id = vha->d_id.b24;
 
-	ql_log(ql_log_info, vha, 0xffff,
-	    "register_localport: host-traddr=nn-0x%llx:pn-0x%llx on portID:%x\n",
-	    pinfo.node_name, pinfo.port_name, pinfo.port_id);
-	qla_nvme_fc_transport.dma_boundary = vha->host->dma_boundary;
-
-	ret = nvme_fc_register_localport(&pinfo, tmpl,
-	    get_device(&ha->pdev->dev), &vha->nvme_local_port);
+	mutex_lock(&ha->vport_lock);
+	/*
+	 * Check again for nvme_local_port to see if any other thread raced
+	 * with this one and finished registration.
+	 */
+	if (!vha->nvme_local_port) {
+		ql_log(ql_log_info, vha, 0xffff,
+		    "register_localport: host-traddr=nn-0x%llx:pn-0x%llx on portID:%x\n",
+		    pinfo.node_name, pinfo.port_name, pinfo.port_id);
+		qla_nvme_fc_transport.dma_boundary = vha->host->dma_boundary;
+
+		ret = nvme_fc_register_localport(&pinfo, tmpl,
+						 get_device(&ha->pdev->dev),
+						 &vha->nvme_local_port);
+		mutex_unlock(&ha->vport_lock);
+	} else {
+		mutex_unlock(&ha->vport_lock);
+		return 0;
+	}
 	if (ret) {
 		ql_log(ql_log_warn, vha, 0xffff,
 		    "register_localport failed: ret=%x\n", ret);
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 77c0bf06f162..00e97f0a07eb 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -333,6 +333,21 @@ MODULE_PARM_DESC(ql2xabts_wait_nvme,
 		 "To wait for ABTS response on I/O timeouts for NVMe. (default: 1)");
 
 
+u32 ql2xdelay_before_pci_error_handling = 5;
+module_param(ql2xdelay_before_pci_error_handling, uint, 0644);
+MODULE_PARM_DESC(ql2xdelay_before_pci_error_handling,
+	"Number of seconds delayed before qla begin PCI error self-handling (default: 5).\n");
+
+int ql2xrspq_follow_inptr = 1;
+module_param(ql2xrspq_follow_inptr, int, 0644);
+MODULE_PARM_DESC(ql2xrspq_follow_inptr,
+		 "Follow RSP IN pointer for RSP updates for HBAs 27xx and newer (default: 1).");
+
+int ql2xrspq_follow_inptr_legacy = 1;
+module_param(ql2xrspq_follow_inptr_legacy, int, 0644);
+MODULE_PARM_DESC(ql2xrspq_follow_inptr_legacy,
+		 "Follow RSP IN pointer for RSP updates for HBAs older than 27XX. (default: 1).");
+
 static void qla2x00_clear_drv_active(struct qla_hw_data *);
 static void qla2x00_free_device(scsi_qla_host_t *);
 static int qla2xxx_map_queues(struct Scsi_Host *shost);
@@ -1333,21 +1348,20 @@ qla2xxx_eh_abort(struct scsi_cmnd *cmd)
 /*
  * Returns: QLA_SUCCESS or QLA_FUNCTION_FAILED.
  */
-int
-qla2x00_eh_wait_for_pending_commands(scsi_qla_host_t *vha, unsigned int t,
-	uint64_t l, enum nexus_wait_type type)
+static int
+__qla2x00_eh_wait_for_pending_commands(struct qla_qpair *qpair, unsigned int t,
+				       uint64_t l, enum nexus_wait_type type)
 {
 	int cnt, match, status;
 	unsigned long flags;
-	struct qla_hw_data *ha = vha->hw;
-	struct req_que *req;
+	scsi_qla_host_t *vha = qpair->vha;
+	struct req_que *req = qpair->req;
 	srb_t *sp;
 	struct scsi_cmnd *cmd;
 
 	status = QLA_SUCCESS;
 
-	spin_lock_irqsave(&ha->hardware_lock, flags);
-	req = vha->req;
+	spin_lock_irqsave(qpair->qp_lock_ptr, flags);
 	for (cnt = 1; status == QLA_SUCCESS &&
 		cnt < req->num_outstanding_cmds; cnt++) {
 		sp = req->outstanding_cmds[cnt];
@@ -1374,15 +1388,35 @@ qla2x00_eh_wait_for_pending_commands(scsi_qla_host_t *vha, unsigned int t,
 		if (!match)
 			continue;
 
-		spin_unlock_irqrestore(&ha->hardware_lock, flags);
+		spin_unlock_irqrestore(qpair->qp_lock_ptr, flags);
 		status = qla2x00_eh_wait_on_command(cmd);
-		spin_lock_irqsave(&ha->hardware_lock, flags);
+		spin_lock_irqsave(qpair->qp_lock_ptr, flags);
 	}
-	spin_unlock_irqrestore(&ha->hardware_lock, flags);
+	spin_unlock_irqrestore(qpair->qp_lock_ptr, flags);
 
 	return status;
 }
 
+int
+qla2x00_eh_wait_for_pending_commands(scsi_qla_host_t *vha, unsigned int t,
+				     uint64_t l, enum nexus_wait_type type)
+{
+	struct qla_qpair *qpair;
+	struct qla_hw_data *ha = vha->hw;
+	int i, status = QLA_SUCCESS;
+
+	status = __qla2x00_eh_wait_for_pending_commands(ha->base_qpair, t, l,
+							type);
+	for (i = 0; status == QLA_SUCCESS && i < ha->max_qpairs; i++) {
+		qpair = ha->queue_pair_map[i];
+		if (!qpair)
+			continue;
+		status = __qla2x00_eh_wait_for_pending_commands(qpair, t, l,
+								type);
+	}
+	return status;
+}
+
 static char *reset_errors[] = {
 	"HBA not online",
 	"HBA not ready",
@@ -1416,7 +1450,7 @@ qla2xxx_eh_device_reset(struct scsi_cmnd *cmd)
 		return err;
 
 	if (fcport->deleted)
-		return SUCCESS;
+		return FAILED;
 
 	ql_log(ql_log_info, vha, 0x8009,
 	    "DEVICE RESET ISSUED nexus=%ld:%d:%llu cmd=%p.\n", vha->host_no,
@@ -1484,7 +1518,7 @@ qla2xxx_eh_target_reset(struct scsi_cmnd *cmd)
 		return err;
 
 	if (fcport->deleted)
-		return SUCCESS;
+		return FAILED;
 
 	ql_log(ql_log_info, vha, 0x8009,
 	    "TARGET RESET ISSUED nexus=%ld:%d cmd=%p.\n", vha->host_no,
@@ -2779,6 +2813,16 @@ qla2xxx_scan_finished(struct Scsi_Host *shost, unsigned long time)
 	return atomic_read(&vha->loop_state) == LOOP_READY;
 }
 
+static void qla_heartbeat_work_fn(struct work_struct *work)
+{
+	struct qla_hw_data *ha = container_of(work,
+		struct qla_hw_data, heartbeat_work);
+	struct scsi_qla_host *base_vha = pci_get_drvdata(ha->pdev);
+
+	if (!ha->flags.mbox_busy && base_vha->flags.init_done)
+		qla_no_op_mb(base_vha);
+}
+
 static void qla2x00_iocb_work_fn(struct work_struct *work)
 {
 	struct scsi_qla_host *vha = container_of(work,
@@ -3217,6 +3261,7 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	    host->transportt, sht->vendor_id);
 
 	INIT_WORK(&base_vha->iocb_work, qla2x00_iocb_work_fn);
+	INIT_WORK(&ha->heartbeat_work, qla_heartbeat_work_fn);
 
 	/* Set up the irqs */
 	ret = qla2x00_request_irqs(ha, rsp);
@@ -3875,13 +3920,15 @@ qla2x00_remove_one(struct pci_dev *pdev)
 static inline void
 qla24xx_free_purex_list(struct purex_list *list)
 {
-	struct list_head *item, *next;
+	struct purex_item *item, *next;
 	ulong flags;
 
 	spin_lock_irqsave(&list->lock, flags);
-	list_for_each_safe(item, next, &list->head) {
-		list_del(item);
-		kfree(list_entry(item, struct purex_item, list));
+	list_for_each_entry_safe(item, next, &list->head, list) {
+		list_del(&item->list);
+		if (item == &item->vha->default_item)
+			continue;
+		kfree(item);
 	}
 	spin_unlock_irqrestore(&list->lock, flags);
 }
@@ -5453,7 +5500,7 @@ qla2x00_do_work(struct scsi_qla_host *vha)
 			    e->u.fcport.fcport, false);
 			break;
 		case QLA_EVT_SA_REPLACE:
-			qla24xx_issue_sa_replace_iocb(vha, e);
+			rc = qla24xx_issue_sa_replace_iocb(vha, e);
 			break;
 		}
 
@@ -7103,17 +7150,6 @@ intr_on_check:
 			qla2x00_lip_reset(base_vha);
 		}
 
-		if (test_bit(HEARTBEAT_CHK, &base_vha->dpc_flags)) {
-			/*
-			 * if there is a mb in progress then that's
-			 * enough of a check to see if fw is still ticking.
-			 */
-			if (!ha->flags.mbox_busy && base_vha->flags.init_done)
-				qla_no_op_mb(base_vha);
-
-			clear_bit(HEARTBEAT_CHK, &base_vha->dpc_flags);
-		}
-
 		ha->dpc_active = 0;
 end_loop:
 		set_current_state(TASK_INTERRUPTIBLE);
@@ -7172,56 +7208,99 @@ qla2x00_rst_aen(scsi_qla_host_t *vha)
 
 static bool qla_do_heartbeat(struct scsi_qla_host *vha)
 {
-	u64 cmd_cnt, prev_cmd_cnt;
-	bool do_hb = false;
 	struct qla_hw_data *ha = vha->hw;
-	int i;
+	u32 cmpl_cnt;
+	u16 i;
+	bool do_heartbeat = false;
 
-	/* if cmds are still pending down in fw, then do hb */
-	if (ha->base_qpair->cmd_cnt != ha->base_qpair->cmd_completion_cnt) {
-		do_hb = true;
+	/*
+	 * Allow do_heartbeat only if we don’t have any active interrupts,
+	 * but there are still IOs outstanding with firmware.
+	 */
+	cmpl_cnt = ha->base_qpair->cmd_completion_cnt;
+	if (cmpl_cnt == ha->base_qpair->prev_completion_cnt &&
+	    cmpl_cnt != ha->base_qpair->cmd_cnt) {
+		do_heartbeat = true;
 		goto skip;
 	}
+	ha->base_qpair->prev_completion_cnt = cmpl_cnt;
 
 	for (i = 0; i < ha->max_qpairs; i++) {
-		if (ha->queue_pair_map[i] &&
-		    ha->queue_pair_map[i]->cmd_cnt !=
-		    ha->queue_pair_map[i]->cmd_completion_cnt) {
-			do_hb = true;
-			break;
+		if (ha->queue_pair_map[i]) {
+			cmpl_cnt = ha->queue_pair_map[i]->cmd_completion_cnt;
+			if (cmpl_cnt == ha->queue_pair_map[i]->prev_completion_cnt &&
+			    cmpl_cnt != ha->queue_pair_map[i]->cmd_cnt) {
+				do_heartbeat = true;
+				break;
+			}
+			ha->queue_pair_map[i]->prev_completion_cnt = cmpl_cnt;
 		}
 	}
 
 skip:
-	prev_cmd_cnt = ha->prev_cmd_cnt;
-	cmd_cnt = ha->base_qpair->cmd_cnt;
-	for (i = 0; i < ha->max_qpairs; i++) {
-		if (ha->queue_pair_map[i])
-			cmd_cnt += ha->queue_pair_map[i]->cmd_cnt;
-	}
-	ha->prev_cmd_cnt = cmd_cnt;
-
-	if (!do_hb && ((cmd_cnt - prev_cmd_cnt) > 50))
-		/*
-		 * IOs are completing before periodic hb check.
-		 * IOs seems to be running, do hb for sanity check.
-		 */
-		do_hb = true;
-
-	return do_hb;
+	return do_heartbeat;
 }
 
-static void qla_heart_beat(struct scsi_qla_host *vha)
+static void qla_heart_beat(struct scsi_qla_host *vha, u16 dpc_started)
 {
+	struct qla_hw_data *ha = vha->hw;
+
 	if (vha->vp_idx)
 		return;
 
 	if (vha->hw->flags.eeh_busy || qla2x00_chip_is_down(vha))
 		return;
 
+	/*
+	 * dpc thread cannot run if heartbeat is running at the same time.
+	 * We also do not want to starve heartbeat task. Therefore, do
+	 * heartbeat task at least once every 5 seconds.
+	 */
+	if (dpc_started &&
+	    time_before(jiffies, ha->last_heartbeat_run_jiffies + 5 * HZ))
+		return;
+
 	if (qla_do_heartbeat(vha)) {
-		set_bit(HEARTBEAT_CHK, &vha->dpc_flags);
-		qla2xxx_wake_dpc(vha);
+		ha->last_heartbeat_run_jiffies = jiffies;
+		queue_work(ha->wq, &ha->heartbeat_work);
+	}
+}
+
+static void qla_wind_down_chip(scsi_qla_host_t *vha)
+{
+	struct qla_hw_data *ha = vha->hw;
+
+	if (!ha->flags.eeh_busy)
+		return;
+	if (ha->pci_error_state)
+		/* system is trying to recover */
+		return;
+
+	/*
+	 * Current system is not handling PCIE error.  At this point, this is
+	 * best effort to wind down the adapter.
+	 */
+	if (time_after_eq(jiffies, ha->eeh_jif + ql2xdelay_before_pci_error_handling * HZ) &&
+	    !ha->flags.eeh_flush) {
+		ql_log(ql_log_info, vha, 0x9009,
+		    "PCI Error detected, attempting to reset hardware.\n");
+
+		ha->isp_ops->reset_chip(vha);
+		ha->isp_ops->disable_intrs(ha);
+
+		ha->flags.eeh_flush = EEH_FLUSH_RDY;
+		ha->eeh_jif = jiffies;
+
+	} else if (ha->flags.eeh_flush == EEH_FLUSH_RDY &&
+	    time_after_eq(jiffies, ha->eeh_jif +  5 * HZ)) {
+		pci_clear_master(ha->pdev);
+
+		/* flush all command */
+		qla2x00_abort_isp_cleanup(vha);
+		ha->flags.eeh_flush = EEH_FLUSH_DONE;
+
+		ql_log(ql_log_info, vha, 0x900a,
+		    "PCI Error handling complete, all IOs aborted.\n");
 	}
 }
 
@@ -7248,6 +7327,8 @@ qla2x00_timer(struct timer_list *t)
 	fc_port_t *fcport = NULL;
 
 	if (ha->flags.eeh_busy) {
+		qla_wind_down_chip(vha);
+
 		ql_dbg(ql_dbg_timer, vha, 0x6000,
 		    "EEH = %d, restarting timer.\n",
 		    ha->flags.eeh_busy);
@@ -7413,6 +7494,8 @@ qla2x00_timer(struct timer_list *t)
 		start_dpc++;
 	}
 
+	/* borrowing w to signify dpc will run */
+	w = 0;
 	/* Schedule the DPC routine if needed */
 	if ((test_bit(ISP_ABORT_NEEDED, &vha->dpc_flags) ||
 	    test_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags) ||
@@ -7445,9 +7528,10 @@ qla2x00_timer(struct timer_list *t)
 		    test_bit(RELOGIN_NEEDED, &vha->dpc_flags),
 		    test_bit(PROCESS_PUREX_IOCB, &vha->dpc_flags));
 		qla2xxx_wake_dpc(vha);
+		w = 1;
 	}
 
-	qla_heart_beat(vha);
+	qla_heart_beat(vha, w);
 
 	qla2x00_restart_timer(vha, WATCH_INTERVAL);
 }
@@ -7825,6 +7909,9 @@ void qla_pci_set_eeh_busy(struct scsi_qla_host *vha)
 
 	spin_lock_irqsave(&base_vha->work_lock, flags);
 	if (!ha->flags.eeh_busy) {
+		ha->eeh_jif = jiffies;
+		ha->flags.eeh_flush = 0;
+
 		ha->flags.eeh_busy = 1;
 		do_cleanup = true;
 	}
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index ae5eaa4a9283..b86f6e1f21b5 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -4815,7 +4815,7 @@ static int qlt_handle_login(struct scsi_qla_host *vha,
 	}
 
 	if (vha->hw->flags.edif_enabled) {
-		if (!(vha->e_dbell.db_flags & EDB_ACTIVE)) {
+		if (DBELL_INACTIVE(vha)) {
 			ql_dbg(ql_dbg_disc, vha, 0xffff,
 			       "%s %d Term INOT due to app not started lid=%d, NportID %06X ",
 			       __func__, __LINE__, loop_id, port_id.b24);
@@ -6961,14 +6961,8 @@ qlt_24xx_config_rings(struct scsi_qla_host *vha)
 
 	if (ha->flags.msix_enabled) {
 		if (IS_QLA83XX(ha) || IS_QLA27XX(ha) || IS_QLA28XX(ha)) {
-			if (IS_QLA2071(ha)) {
-				/* 4 ports Baker: Enable Interrupt Handshake */
-				icb->msix_atio = 0;
-				icb->firmware_options_2 |= cpu_to_le32(BIT_26);
-			} else {
-				icb->msix_atio = cpu_to_le16(msix->entry);
-				icb->firmware_options_2 &= cpu_to_le32(~BIT_26);
-			}
+			icb->msix_atio = cpu_to_le16(msix->entry);
+			icb->firmware_options_2 &= cpu_to_le32(~BIT_26);
 			ql_dbg(ql_dbg_init, vha, 0xf072,
 			    "Registering ICB vector 0x%x for atio que.\n",
 			    msix->entry);
diff --git a/drivers/scsi/scsi_ioctl.c b/drivers/scsi/scsi_ioctl.c
index d8f69b204202..5f774b8c12be 100644
--- a/drivers/scsi/scsi_ioctl.c
+++ b/drivers/scsi/scsi_ioctl.c
@@ -471,7 +471,7 @@ static int sg_io(struct scsi_device *sdev, struct gendisk *disk,
 		goto out_free_cdb;
 
 	ret = 0;
-	if (hdr->iovec_count) {
+	if (hdr->iovec_count && hdr->dxfer_len) {
 		struct iov_iter i;
 		struct iovec *iov = NULL;
 
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index 5947b9d5746e..f46ae5391758 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -2283,16 +2283,8 @@ static void iscsi_if_disconnect_bound_ep(struct iscsi_cls_conn *conn,
 	}
 }
 
-static int iscsi_if_stop_conn(struct iscsi_transport *transport,
-			      struct iscsi_uevent *ev)
+static int iscsi_if_stop_conn(struct iscsi_cls_conn *conn, int flag)
 {
-	int flag = ev->u.stop_conn.flag;
-	struct iscsi_cls_conn *conn;
-
-	conn = iscsi_conn_lookup(ev->u.stop_conn.sid, ev->u.stop_conn.cid);
-	if (!conn)
-		return -EINVAL;
-
 	ISCSI_DBG_TRANS_CONN(conn, "iscsi if conn stop.\n");
 	/*
 	 * If this is a termination we have to call stop_conn with that flag
@@ -2368,6 +2360,55 @@ static void iscsi_cleanup_conn_work_fn(struct work_struct *work)
 	ISCSI_DBG_TRANS_CONN(conn, "cleanup done.\n");
 }
 
+static int iscsi_iter_force_destroy_conn_fn(struct device *dev, void *data)
+{
+	struct iscsi_transport *transport;
+	struct iscsi_cls_conn *conn;
+
+	if (!iscsi_is_conn_dev(dev))
+		return 0;
+
+	conn = iscsi_dev_to_conn(dev);
+	transport = conn->transport;
+
+	if (READ_ONCE(conn->state) != ISCSI_CONN_DOWN)
+		iscsi_if_stop_conn(conn, STOP_CONN_TERM);
+
+	transport->destroy_conn(conn);
+	return 0;
+}
+
+/**
+ * iscsi_force_destroy_session - destroy a session from the kernel
+ * @session: session to destroy
+ *
+ * Force the destruction of a session from the kernel. This should only be
+ * used when userspace is no longer running during system shutdown.
+ */
+void iscsi_force_destroy_session(struct iscsi_cls_session *session)
+{
+	struct iscsi_transport *transport = session->transport;
+	unsigned long flags;
+
+	WARN_ON_ONCE(system_state == SYSTEM_RUNNING);
+
+	spin_lock_irqsave(&sesslock, flags);
+	if (list_empty(&session->sess_list)) {
+		spin_unlock_irqrestore(&sesslock, flags);
+		/*
+		 * Conn/ep is already freed. Session is being torn down via
+		 * async path. For shutdown we don't care about it so return.
+		 */
+		return;
+	}
+	spin_unlock_irqrestore(&sesslock, flags);
+
+	device_for_each_child(&session->dev, NULL,
+			      iscsi_iter_force_destroy_conn_fn);
+	transport->destroy_session(session);
+}
+EXPORT_SYMBOL_GPL(iscsi_force_destroy_session);
+
 void iscsi_free_session(struct iscsi_cls_session *session)
 {
 	ISCSI_DBG_TRANS_SESSION(session, "Freeing session\n");
@@ -3739,7 +3780,12 @@ static int iscsi_if_transport_conn(struct iscsi_transport *transport,
 	case ISCSI_UEVENT_DESTROY_CONN:
 		return iscsi_if_destroy_conn(transport, ev);
 	case ISCSI_UEVENT_STOP_CONN:
-		return iscsi_if_stop_conn(transport, ev);
+		conn = iscsi_conn_lookup(ev->u.stop_conn.sid,
+					 ev->u.stop_conn.cid);
+		if (!conn)
+			return -EINVAL;
+
+		return iscsi_if_stop_conn(conn, ev->u.stop_conn.flag);
 	}
 
 	/*
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 3c98f08dc25d..d771a1988f94 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -191,7 +191,7 @@ static void sg_link_reserve(Sg_fd * sfp, Sg_request * srp, int size);
 static void sg_unlink_reserve(Sg_fd * sfp, Sg_request * srp);
 static Sg_fd *sg_add_sfp(Sg_device * sdp);
 static void sg_remove_sfp(struct kref *);
-static Sg_request *sg_get_rq_mark(Sg_fd * sfp, int pack_id);
+static Sg_request *sg_get_rq_mark(Sg_fd * sfp, int pack_id, bool *busy);
 static Sg_request *sg_add_request(Sg_fd * sfp);
 static int sg_remove_request(Sg_fd * sfp, Sg_request * srp);
 static Sg_device *sg_get_dev(int dev);
@@ -445,6 +445,7 @@ sg_read(struct file *filp, char __user *buf, size_t count, loff_t * ppos)
 	Sg_fd *sfp;
 	Sg_request *srp;
 	int req_pack_id = -1;
+	bool busy;
 	sg_io_hdr_t *hp;
 	struct sg_header *old_hdr;
 	int retval;
@@ -467,20 +468,16 @@ sg_read(struct file *filp, char __user *buf, size_t count, loff_t * ppos)
 	if (retval)
 		return retval;
 
-	srp = sg_get_rq_mark(sfp, req_pack_id);
+	srp = sg_get_rq_mark(sfp, req_pack_id, &busy);
 	if (!srp) {		/* now wait on packet to arrive */
-		if (atomic_read(&sdp->detaching))
-			return -ENODEV;
 		if (filp->f_flags & O_NONBLOCK)
 			return -EAGAIN;
 		retval = wait_event_interruptible(sfp->read_wait,
-			(atomic_read(&sdp->detaching) ||
-			(srp = sg_get_rq_mark(sfp, req_pack_id))));
-		if (atomic_read(&sdp->detaching))
-			return -ENODEV;
-		if (retval)
-			/* -ERESTARTSYS as signal hit process */
-			return retval;
+			((srp = sg_get_rq_mark(sfp, req_pack_id, &busy)) ||
+			(!busy && atomic_read(&sdp->detaching))));
+		if (!srp)
+			/* signal or detaching */
+			return retval ? retval : -ENODEV;
 	}
 	if (srp->header.interface_id != '\0')
 		return sg_new_read(sfp, buf, count, srp);
@@ -941,9 +938,7 @@ sg_ioctl_common(struct file *filp, Sg_device *sdp, Sg_fd *sfp,
 		if (result < 0)
 			return result;
 		result = wait_event_interruptible(sfp->read_wait,
-			(srp_done(sfp, srp) || atomic_read(&sdp->detaching)));
-		if (atomic_read(&sdp->detaching))
-			return -ENODEV;
+			srp_done(sfp, srp));
 		write_lock_irq(&sfp->rq_list_lock);
 		if (srp->done) {
 			srp->done = 2;
@@ -2056,19 +2051,28 @@ sg_unlink_reserve(Sg_fd * sfp, Sg_request * srp)
 }
 
 static Sg_request *
-sg_get_rq_mark(Sg_fd * sfp, int pack_id)
+sg_get_rq_mark(Sg_fd * sfp, int pack_id, bool *busy)
 {
 	Sg_request *resp;
 	unsigned long iflags;
 
+	*busy = false;
 	write_lock_irqsave(&sfp->rq_list_lock, iflags);
 	list_for_each_entry(resp, &sfp->rq_list, entry) {
-		/* look for requests that are ready + not SG_IO owned */
-		if ((1 == resp->done) && (!resp->sg_io_owned) &&
+		/* look for requests that are not SG_IO owned */
+		if ((!resp->sg_io_owned) &&
 		    ((-1 == pack_id) || (resp->header.pack_id == pack_id))) {
-			resp->done = 2;	/* guard against other readers */
-			write_unlock_irqrestore(&sfp->rq_list_lock, iflags);
-			return resp;
+			switch (resp->done) {
+			case 0: /* request active */
+				*busy = true;
+				break;
+			case 1: /* request done; response ready to return */
+				resp->done = 2;	/* guard against other readers */
+				write_unlock_irqrestore(&sfp->rq_list_lock, iflags);
+				return resp;
+			case 2: /* response already being returned */
+				break;
+			}
 		}
 	}
 	write_unlock_irqrestore(&sfp->rq_list_lock, iflags);
@@ -2122,6 +2126,15 @@ sg_remove_request(Sg_fd * sfp, Sg_request * srp)
 		res = 1;
 	}
 	write_unlock_irqrestore(&sfp->rq_list_lock, iflags);
+
+	/*
+	 * If the device is detaching, wakeup any readers in case we just
+	 * removed the last response, which would leave nothing for them to
+	 * return other than -ENODEV.
+	 */
+	if (unlikely(atomic_read(&sfp->parentdp->detaching)))
+		wake_up_interruptible_all(&sfp->read_wait);
+
 	return res;
 }
 
diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index 2e690d8a3444..e3d8de1159b5 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -5310,10 +5310,10 @@ static int pqi_raid_submit_scsi_cmd_with_io_request(
 	}
 
 	switch (scmd->sc_data_direction) {
-	case DMA_TO_DEVICE:
+	case DMA_FROM_DEVICE:
 		request->data_direction = SOP_READ_FLAG;
 		break;
-	case DMA_FROM_DEVICE:
+	case DMA_TO_DEVICE:
 		request->data_direction = SOP_WRITE_FLAG;
 		break;
 	case DMA_NONE:
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 71c7f7b435c4..3d03e1ca5820 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -2093,7 +2093,7 @@ static int storvsc_probe(struct hv_device *device,
 	 */
 	host_dev->handle_error_wq =
 			alloc_ordered_workqueue("storvsc_error_wq_%d",
-						WQ_MEM_RECLAIM,
+						0,
 						host->host_no);
 	if (!host_dev->handle_error_wq) {
 		ret = -ENOMEM;
diff --git a/drivers/scsi/ufs/ufs-mediatek.c b/drivers/scsi/ufs/ufs-mediatek.c
index 4e53857605de..a9ddb50d593c 100644
--- a/drivers/scsi/ufs/ufs-mediatek.c
+++ b/drivers/scsi/ufs/ufs-mediatek.c
@@ -949,7 +949,6 @@ static int ufs_mtk_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 		 * ufshcd_suspend() re-enabling regulators while vreg is still
 		 * in low-power mode.
 		 */
-		ufs_mtk_vreg_set_lpm(hba, true);
 		err = ufs_mtk_mphy_power_on(hba, false);
 		if (err)
 			goto fail;
@@ -973,12 +972,13 @@ static int ufs_mtk_resume(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 {
 	int err;
 
+	if (hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL)
+		ufs_mtk_vreg_set_lpm(hba, false);
+
 	err = ufs_mtk_mphy_power_on(hba, true);
 	if (err)
 		goto fail;
 
-	ufs_mtk_vreg_set_lpm(hba, false);
-
 	if (ufshcd_is_link_hibern8(hba)) {
 		err = ufs_mtk_link_set_hpm(hba);
 		if (err)
@@ -1139,9 +1139,59 @@ static int ufs_mtk_remove(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+int ufs_mtk_system_suspend(struct device *dev)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+	int ret;
+
+	ret = ufshcd_system_suspend(dev);
+	if (ret)
+		return ret;
+
+	ufs_mtk_vreg_set_lpm(hba, true);
+
+	return 0;
+}
+
+int ufs_mtk_system_resume(struct device *dev)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+
+	ufs_mtk_vreg_set_lpm(hba, false);
+
+	return ufshcd_system_resume(dev);
+}
+#endif
+
+int ufs_mtk_runtime_suspend(struct device *dev)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+	int ret = 0;
+
+	ret = ufshcd_runtime_suspend(dev);
+	if (ret)
+		return ret;
+
+	ufs_mtk_vreg_set_lpm(hba, true);
+
+	return 0;
+}
+
+int ufs_mtk_runtime_resume(struct device *dev)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+
+	ufs_mtk_vreg_set_lpm(hba, false);
+
+	return ufshcd_runtime_resume(dev);
+}
+
 static const struct dev_pm_ops ufs_mtk_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(ufshcd_system_suspend, ufshcd_system_resume)
-	SET_RUNTIME_PM_OPS(ufshcd_runtime_suspend, ufshcd_runtime_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(ufs_mtk_system_suspend,
+				ufs_mtk_system_resume)
+	SET_RUNTIME_PM_OPS(ufs_mtk_runtime_suspend,
+			   ufs_mtk_runtime_resume, NULL)
 	.prepare	 = ufshcd_suspend_prepare,
 	.complete	 = ufshcd_resume_complete,
 };
diff --git a/drivers/scsi/ufs/ufshcd-pltfrm.c b/drivers/scsi/ufs/ufshcd-pltfrm.c
index 87975d1a21c8..adc302b1a57a 100644
--- a/drivers/scsi/ufs/ufshcd-pltfrm.c
+++ b/drivers/scsi/ufs/ufshcd-pltfrm.c
@@ -107,9 +107,20 @@ out:
 	return ret;
 }
 
+static bool phandle_exists(const struct device_node *np,
+			   const char *phandle_name, int index)
+{
+	struct device_node *parse_np = of_parse_phandle(np, phandle_name, index);
+
+	if (parse_np)
+		of_node_put(parse_np);
+
+	return parse_np != NULL;
+}
+
 #define MAX_PROP_SIZE 32
 static int ufshcd_populate_vreg(struct device *dev, const char *name,
-		struct ufs_vreg **out_vreg)
+				struct ufs_vreg **out_vreg)
 {
 	char prop_name[MAX_PROP_SIZE];
 	struct ufs_vreg *vreg = NULL;
@@ -121,7 +132,7 @@ static int ufshcd_populate_vreg(struct device *dev, const char *name,
 	}
 
 	snprintf(prop_name, MAX_PROP_SIZE, "%s-supply", name);
-	if (!of_parse_phandle(np, prop_name, 0)) {
+	if (!phandle_exists(np, prop_name, 0)) {
 		dev_info(dev, "%s: Unable to find %s regulator, assuming enabled\n",
 				__func__, prop_name);
 		goto out;
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 5c9a31f18b7f..dae1a85f1512 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -5638,7 +5638,7 @@ int ufshcd_wb_toggle(struct ufs_hba *hba, bool enable)
 	}
 
 	hba->dev_info.wb_enabled = enable;
-	dev_info(hba->dev, "%s Write Booster %s\n",
+	dev_dbg(hba->dev, "%s Write Booster %s\n",
 			__func__, enable ? "enabled" : "disabled");
 
 	return ret;
@@ -8476,6 +8476,8 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba,
 	struct scsi_device *sdp;
 	unsigned long flags;
 	int ret, retries;
+	unsigned long deadline;
+	int32_t remaining;
 
 	spin_lock_irqsave(hba->host->host_lock, flags);
 	sdp = hba->sdev_ufs_device;
@@ -8508,9 +8510,14 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba,
 	 * callbacks hence set the RQF_PM flag so that it doesn't resume the
 	 * already suspended childs.
 	 */
+	deadline = jiffies + 10 * HZ;
 	for (retries = 3; retries > 0; --retries) {
+		ret = -ETIMEDOUT;
+		remaining = deadline - jiffies;
+		if (remaining <= 0)
+			break;
 		ret = scsi_execute(sdp, cmd, DMA_NONE, NULL, 0, NULL, &sshdr,
-				START_STOP_TIMEOUT, 0, 0, RQF_PM, NULL);
+				   remaining / HZ, 0, 0, RQF_PM, NULL);
 		if (!scsi_status_is_check_condition(ret) ||
 				!scsi_sense_valid(&sshdr) ||
 				sshdr.sense_key != UNIT_ATTENTION)
@@ -9239,12 +9246,8 @@ EXPORT_SYMBOL(ufshcd_runtime_resume);
 int ufshcd_shutdown(struct ufs_hba *hba)
 {
 	if (ufshcd_is_ufs_dev_poweroff(hba) && ufshcd_is_link_off(hba))
-		goto out;
+		ufshcd_suspend(hba);
 
-	pm_runtime_get_sync(hba->dev);
-
-	ufshcd_suspend(hba);
-out:
 	hba->is_powered = false;
 	/* allow force shutdown even in case of errors */
 	return 0;
diff --git a/drivers/scsi/ufs/ufshci.h b/drivers/scsi/ufs/ufshci.h
index 3ed60068c4ea..8dbe9866ea6c 100644
--- a/drivers/scsi/ufs/ufshci.h
+++ b/drivers/scsi/ufs/ufshci.h
@@ -133,11 +133,7 @@ static inline u32 ufshci_version(u32 major, u32 minor)
 
 #define UFSHCD_UIC_MASK		(UIC_COMMAND_COMPL | UFSHCD_UIC_PWR_MASK)
 
-#define UFSHCD_ERROR_MASK	(UIC_ERROR |\
-				DEVICE_FATAL_ERROR |\
-				CONTROLLER_FATAL_ERROR |\
-				SYSTEM_BUS_FATAL_ERROR |\
-				CRYPTO_ENGINE_FATAL_ERROR)
+#define UFSHCD_ERROR_MASK	(UIC_ERROR | INT_FATAL_ERRORS)
 
 #define INT_FATAL_ERRORS	(DEVICE_FATAL_ERROR |\
 				CONTROLLER_FATAL_ERROR |\
diff --git a/drivers/soc/amlogic/meson-mx-socinfo.c b/drivers/soc/amlogic/meson-mx-socinfo.c
index 78f0f1aeca57..92125dd65f33 100644
--- a/drivers/soc/amlogic/meson-mx-socinfo.c
+++ b/drivers/soc/amlogic/meson-mx-socinfo.c
@@ -126,6 +126,7 @@ static int __init meson_mx_socinfo_init(void)
 	np = of_find_matching_node(NULL, meson_mx_socinfo_analog_top_ids);
 	if (np) {
 		analog_top_regmap = syscon_node_to_regmap(np);
+		of_node_put(np);
 		if (IS_ERR(analog_top_regmap))
 			return PTR_ERR(analog_top_regmap);
 
diff --git a/drivers/soc/amlogic/meson-secure-pwrc.c b/drivers/soc/amlogic/meson-secure-pwrc.c
index 59bd195fa9c9..2eeea5e1b3b7 100644
--- a/drivers/soc/amlogic/meson-secure-pwrc.c
+++ b/drivers/soc/amlogic/meson-secure-pwrc.c
@@ -139,8 +139,10 @@ static int meson_secure_pwrc_probe(struct platform_device *pdev)
 	}
 
 	pwrc = devm_kzalloc(&pdev->dev, sizeof(*pwrc), GFP_KERNEL);
-	if (!pwrc)
+	if (!pwrc) {
+		of_node_put(sm_np);
 		return -ENOMEM;
+	}
 
 	pwrc->fw = meson_sm_get(sm_np);
 	of_node_put(sm_np);
diff --git a/drivers/soc/atmel/soc.c b/drivers/soc/atmel/soc.c
index a490ad7e090f..9e3d37011447 100644
--- a/drivers/soc/atmel/soc.c
+++ b/drivers/soc/atmel/soc.c
@@ -91,14 +91,14 @@ static const struct at91_soc socs[] __initconst = {
 	AT91_SOC(SAM9X60_CIDR_MATCH, AT91_CIDR_MATCH_MASK,
 		 AT91_CIDR_VERSION_MASK, SAM9X60_EXID_MATCH,
 		 "sam9x60", "sam9x60"),
-	AT91_SOC(SAM9X60_CIDR_MATCH, SAM9X60_D5M_EXID_MATCH,
-		 AT91_CIDR_VERSION_MASK, SAM9X60_EXID_MATCH,
+	AT91_SOC(SAM9X60_CIDR_MATCH, AT91_CIDR_MATCH_MASK,
+		 AT91_CIDR_VERSION_MASK, SAM9X60_D5M_EXID_MATCH,
 		 "sam9x60 64MiB DDR2 SiP", "sam9x60"),
-	AT91_SOC(SAM9X60_CIDR_MATCH, SAM9X60_D1G_EXID_MATCH,
-		 AT91_CIDR_VERSION_MASK, SAM9X60_EXID_MATCH,
+	AT91_SOC(SAM9X60_CIDR_MATCH, AT91_CIDR_MATCH_MASK,
+		 AT91_CIDR_VERSION_MASK, SAM9X60_D1G_EXID_MATCH,
 		 "sam9x60 128MiB DDR2 SiP", "sam9x60"),
-	AT91_SOC(SAM9X60_CIDR_MATCH, SAM9X60_D6K_EXID_MATCH,
-		 AT91_CIDR_VERSION_MASK, SAM9X60_EXID_MATCH,
+	AT91_SOC(SAM9X60_CIDR_MATCH, AT91_CIDR_MATCH_MASK,
+		 AT91_CIDR_VERSION_MASK, SAM9X60_D6K_EXID_MATCH,
 		 "sam9x60 8MiB SDRAM SiP", "sam9x60"),
 #endif
 #ifdef CONFIG_SOC_SAMA5
diff --git a/drivers/soc/bcm/brcmstb/pm/pm-arm.c b/drivers/soc/bcm/brcmstb/pm/pm-arm.c
index 70ad0f3dce28..286f5d57c0ca 100644
--- a/drivers/soc/bcm/brcmstb/pm/pm-arm.c
+++ b/drivers/soc/bcm/brcmstb/pm/pm-arm.c
@@ -684,13 +684,14 @@ static int brcmstb_pm_probe(struct platform_device *pdev)
 	const struct of_device_id *of_id = NULL;
 	struct device_node *dn;
 	void __iomem *base;
-	int ret, i;
+	int ret, i, s;
 
 	/* AON ctrl registers */
 	base = brcmstb_ioremap_match(aon_ctrl_dt_ids, 0, NULL);
 	if (IS_ERR(base)) {
 		pr_err("error mapping AON_CTRL\n");
-		return PTR_ERR(base);
+		ret = PTR_ERR(base);
+		goto aon_err;
 	}
 	ctrl.aon_ctrl_base = base;
 
@@ -700,8 +701,10 @@ static int brcmstb_pm_probe(struct platform_device *pdev)
 		/* Assume standard offset */
 		ctrl.aon_sram = ctrl.aon_ctrl_base +
 				     AON_CTRL_SYSTEM_DATA_RAM_OFS;
+		s = 0;
 	} else {
 		ctrl.aon_sram = base;
+		s = 1;
 	}
 
 	writel_relaxed(0, ctrl.aon_sram + AON_REG_PANIC);
@@ -711,7 +714,8 @@ static int brcmstb_pm_probe(struct platform_device *pdev)
 				     (const void **)&ddr_phy_data);
 	if (IS_ERR(base)) {
 		pr_err("error mapping DDR PHY\n");
-		return PTR_ERR(base);
+		ret = PTR_ERR(base);
+		goto ddr_phy_err;
 	}
 	ctrl.support_warm_boot = ddr_phy_data->supports_warm_boot;
 	ctrl.pll_status_offset = ddr_phy_data->pll_status_offset;
@@ -731,17 +735,20 @@ static int brcmstb_pm_probe(struct platform_device *pdev)
 	for_each_matching_node(dn, ddr_shimphy_dt_ids) {
 		i = ctrl.num_memc;
 		if (i >= MAX_NUM_MEMC) {
+			of_node_put(dn);
 			pr_warn("too many MEMCs (max %d)\n", MAX_NUM_MEMC);
 			break;
 		}
 
 		base = of_io_request_and_map(dn, 0, dn->full_name);
 		if (IS_ERR(base)) {
+			of_node_put(dn);
 			if (!ctrl.support_warm_boot)
 				break;
 
 			pr_err("error mapping DDR SHIMPHY %d\n", i);
-			return PTR_ERR(base);
+			ret = PTR_ERR(base);
+			goto ddr_shimphy_err;
 		}
 		ctrl.memcs[i].ddr_shimphy_base = base;
 		ctrl.num_memc++;
@@ -752,14 +759,18 @@ static int brcmstb_pm_probe(struct platform_device *pdev)
 	for_each_matching_node(dn, brcmstb_memc_of_match) {
 		base = of_iomap(dn, 0);
 		if (!base) {
+			of_node_put(dn);
 			pr_err("error mapping DDR Sequencer %d\n", i);
-			return -ENOMEM;
+			ret = -ENOMEM;
+			goto brcmstb_memc_err;
 		}
 
 		of_id = of_match_node(brcmstb_memc_of_match, dn);
 		if (!of_id) {
 			iounmap(base);
-			return -EINVAL;
+			of_node_put(dn);
+			ret = -EINVAL;
+			goto brcmstb_memc_err;
 		}
 
 		ddr_seq_data = of_id->data;
@@ -779,21 +790,24 @@ static int brcmstb_pm_probe(struct platform_device *pdev)
 	dn = of_find_matching_node(NULL, sram_dt_ids);
 	if (!dn) {
 		pr_err("SRAM not found\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto brcmstb_memc_err;
 	}
 
 	ret = brcmstb_init_sram(dn);
 	of_node_put(dn);
 	if (ret) {
 		pr_err("error setting up SRAM for PM\n");
-		return ret;
+		goto brcmstb_memc_err;
 	}
 
 	ctrl.pdev = pdev;
 
 	ctrl.s3_params = kmalloc(sizeof(*ctrl.s3_params), GFP_KERNEL);
-	if (!ctrl.s3_params)
-		return -ENOMEM;
+	if (!ctrl.s3_params) {
+		ret = -ENOMEM;
+		goto s3_params_err;
+	}
 	ctrl.s3_params_pa = dma_map_single(&pdev->dev, ctrl.s3_params,
 					   sizeof(*ctrl.s3_params),
 					   DMA_TO_DEVICE);
@@ -813,7 +827,21 @@ static int brcmstb_pm_probe(struct platform_device *pdev)
 
 out:
 	kfree(ctrl.s3_params);
-
+s3_params_err:
+	iounmap(ctrl.boot_sram);
+brcmstb_memc_err:
+	for (i--; i >= 0; i--)
+		iounmap(ctrl.memcs[i].ddr_ctrl);
+ddr_shimphy_err:
+	for (i = 0; i < ctrl.num_memc; i++)
+		iounmap(ctrl.memcs[i].ddr_shimphy_base);
+
+	iounmap(ctrl.memcs[0].ddr_phy_base);
+ddr_phy_err:
+	iounmap(ctrl.aon_ctrl_base);
+	if (s)
+		iounmap(ctrl.aon_sram);
+aon_err:
 	pr_warn("PM: initialization failed with code %d\n", ret);
 
 	return ret;
diff --git a/drivers/soc/fsl/Kconfig b/drivers/soc/fsl/Kconfig
index 7c962720d7d3..f760e03a2887 100644
--- a/drivers/soc/fsl/Kconfig
+++ b/drivers/soc/fsl/Kconfig
@@ -25,6 +25,7 @@ config FSL_MC_DPIO
         depends on FSL_MC_BUS
         select SOC_BUS
         select DIMLIB
+        select FSL_GUTS
         help
 	  Driver for the DPAA2 DPIO object.  A DPIO provides queue and
 	  buffer management facilities for software to interact with
diff --git a/drivers/soc/fsl/guts.c b/drivers/soc/fsl/guts.c
index 75eabfb916cb..0b2c7fdbaa5b 100644
--- a/drivers/soc/fsl/guts.c
+++ b/drivers/soc/fsl/guts.c
@@ -141,7 +141,7 @@ static int fsl_guts_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct resource *res;
 	const struct fsl_soc_die_attr *soc_die;
-	const char *machine;
+	const char *machine = NULL;
 	u32 svr;
 
 	/* Initialize guts */
diff --git a/drivers/soc/ixp4xx/ixp4xx-npe.c b/drivers/soc/ixp4xx/ixp4xx-npe.c
index f490c4ca51f5..a0159805d061 100644
--- a/drivers/soc/ixp4xx/ixp4xx-npe.c
+++ b/drivers/soc/ixp4xx/ixp4xx-npe.c
@@ -743,7 +743,7 @@ static const struct of_device_id ixp4xx_npe_of_match[] = {
 static struct platform_driver ixp4xx_npe_driver = {
 	.driver = {
 		.name           = "ixp4xx-npe",
-		.of_match_table = of_match_ptr(ixp4xx_npe_of_match),
+		.of_match_table = ixp4xx_npe_of_match,
 	},
 	.probe = ixp4xx_npe_probe,
 	.remove = ixp4xx_npe_remove,
diff --git a/drivers/soc/qcom/Kconfig b/drivers/soc/qcom/Kconfig
index 79b568f82a1c..499718e131d7 100644
--- a/drivers/soc/qcom/Kconfig
+++ b/drivers/soc/qcom/Kconfig
@@ -129,6 +129,7 @@ config QCOM_RPMHPD
 
 config QCOM_RPMPD
 	tristate "Qualcomm RPM Power domain driver"
+	depends on PM
 	depends on QCOM_SMD_RPM
 	help
 	  QCOM RPM Power domain driver to support power-domains with
diff --git a/drivers/soc/qcom/ocmem.c b/drivers/soc/qcom/ocmem.c
index 85f82e195ef8..1dfdd0b9ba24 100644
--- a/drivers/soc/qcom/ocmem.c
+++ b/drivers/soc/qcom/ocmem.c
@@ -194,14 +194,17 @@ struct ocmem *of_get_ocmem(struct device *dev)
 	devnode = of_parse_phandle(dev->of_node, "sram", 0);
 	if (!devnode || !devnode->parent) {
 		dev_err(dev, "Cannot look up sram phandle\n");
+		of_node_put(devnode);
 		return ERR_PTR(-ENODEV);
 	}
 
 	pdev = of_find_device_by_node(devnode->parent);
 	if (!pdev) {
 		dev_err(dev, "Cannot find device node %s\n", devnode->name);
+		of_node_put(devnode);
 		return ERR_PTR(-EPROBE_DEFER);
 	}
+	of_node_put(devnode);
 
 	ocmem = platform_get_drvdata(pdev);
 	if (!ocmem) {
diff --git a/drivers/soc/qcom/qcom_aoss.c b/drivers/soc/qcom/qcom_aoss.c
index 8583c1e558ae..3973accdc982 100644
--- a/drivers/soc/qcom/qcom_aoss.c
+++ b/drivers/soc/qcom/qcom_aoss.c
@@ -499,8 +499,10 @@ static int qmp_cooling_devices_register(struct qmp *qmp)
 			continue;
 		ret = qmp_cooling_device_add(qmp, &qmp->cooling_devs[count++],
 					     child);
-		if (ret)
+		if (ret) {
+			of_node_put(child);
 			goto unroll;
+		}
 	}
 
 	if (!count)
diff --git a/drivers/soc/renesas/r8a779a0-sysc.c b/drivers/soc/renesas/r8a779a0-sysc.c
index 7410b9fa9846..7e1aba9abce2 100644
--- a/drivers/soc/renesas/r8a779a0-sysc.c
+++ b/drivers/soc/renesas/r8a779a0-sysc.c
@@ -83,11 +83,11 @@ static struct r8a779a0_sysc_area r8a779a0_areas[] __initdata = {
 	{ "a2cv6",	R8A779A0_PD_A2CV6, R8A779A0_PD_A3IR },
 	{ "a2cn2",	R8A779A0_PD_A2CN2, R8A779A0_PD_A3IR },
 	{ "a2imp23",	R8A779A0_PD_A2IMP23, R8A779A0_PD_A3IR },
-	{ "a2dp1",	R8A779A0_PD_A2DP0, R8A779A0_PD_A3IR },
-	{ "a2cv2",	R8A779A0_PD_A2CV0, R8A779A0_PD_A3IR },
-	{ "a2cv3",	R8A779A0_PD_A2CV1, R8A779A0_PD_A3IR },
-	{ "a2cv5",	R8A779A0_PD_A2CV4, R8A779A0_PD_A3IR },
-	{ "a2cv7",	R8A779A0_PD_A2CV6, R8A779A0_PD_A3IR },
+	{ "a2dp1",	R8A779A0_PD_A2DP1, R8A779A0_PD_A3IR },
+	{ "a2cv2",	R8A779A0_PD_A2CV2, R8A779A0_PD_A3IR },
+	{ "a2cv3",	R8A779A0_PD_A2CV3, R8A779A0_PD_A3IR },
+	{ "a2cv5",	R8A779A0_PD_A2CV5, R8A779A0_PD_A3IR },
+	{ "a2cv7",	R8A779A0_PD_A2CV7, R8A779A0_PD_A3IR },
 	{ "a2cn1",	R8A779A0_PD_A2CN1, R8A779A0_PD_A3IR },
 	{ "a1cnn0",	R8A779A0_PD_A1CNN0, R8A779A0_PD_A2CN0 },
 	{ "a1cnn2",	R8A779A0_PD_A1CNN2, R8A779A0_PD_A2CN2 },
diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c
index 67369e941d0d..b7cdfa65157c 100644
--- a/drivers/soundwire/bus.c
+++ b/drivers/soundwire/bus.c
@@ -7,6 +7,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/soundwire/sdw_registers.h>
 #include <linux/soundwire/sdw.h>
+#include <linux/soundwire/sdw_type.h>
 #include "bus.h"
 #include "sysfs_local.h"
 
@@ -846,15 +847,21 @@ static int sdw_slave_clk_stop_callback(struct sdw_slave *slave,
 				       enum sdw_clk_stop_mode mode,
 				       enum sdw_clk_stop_type type)
 {
-	int ret;
+	int ret = 0;
 
-	if (slave->ops && slave->ops->clk_stop) {
-		ret = slave->ops->clk_stop(slave, mode, type);
-		if (ret < 0)
-			return ret;
+	mutex_lock(&slave->sdw_dev_lock);
+
+	if (slave->probed)  {
+		struct device *dev = &slave->dev;
+		struct sdw_driver *drv = drv_to_sdw_driver(dev->driver);
+
+		if (drv->ops && drv->ops->clk_stop)
+			ret = drv->ops->clk_stop(slave, mode, type);
 	}
 
-	return 0;
+	mutex_unlock(&slave->sdw_dev_lock);
+
+	return ret;
 }
 
 static int sdw_slave_clk_stop_prepare(struct sdw_slave *slave,
@@ -1616,14 +1623,24 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave)
 		}
 
 		/* Update the Slave driver */
-		if (slave_notify && slave->ops &&
-		    slave->ops->interrupt_callback) {
-			slave_intr.sdca_cascade = sdca_cascade;
-			slave_intr.control_port = clear;
-			memcpy(slave_intr.port, &port_status,
-			       sizeof(slave_intr.port));
-
-			slave->ops->interrupt_callback(slave, &slave_intr);
+		if (slave_notify) {
+			mutex_lock(&slave->sdw_dev_lock);
+
+			if (slave->probed) {
+				struct device *dev = &slave->dev;
+				struct sdw_driver *drv = drv_to_sdw_driver(dev->driver);
+
+				if (drv->ops && drv->ops->interrupt_callback) {
+					slave_intr.sdca_cascade = sdca_cascade;
+					slave_intr.control_port = clear;
+					memcpy(slave_intr.port, &port_status,
+					       sizeof(slave_intr.port));
+
+					drv->ops->interrupt_callback(slave, &slave_intr);
+				}
+			}
+
+			mutex_unlock(&slave->sdw_dev_lock);
 		}
 
 		/* Ack interrupt */
@@ -1697,29 +1714,21 @@ io_err:
 static int sdw_update_slave_status(struct sdw_slave *slave,
 				   enum sdw_slave_status status)
 {
-	unsigned long time;
+	int ret = 0;
 
-	if (!slave->probed) {
-		/*
-		 * the slave status update is typically handled in an
-		 * interrupt thread, which can race with the driver
-		 * probe, e.g. when a module needs to be loaded.
-		 *
-		 * make sure the probe is complete before updating
-		 * status.
-		 */
-		time = wait_for_completion_timeout(&slave->probe_complete,
-				msecs_to_jiffies(DEFAULT_PROBE_TIMEOUT));
-		if (!time) {
-			dev_err(&slave->dev, "Probe not complete, timed out\n");
-			return -ETIMEDOUT;
-		}
+	mutex_lock(&slave->sdw_dev_lock);
+
+	if (slave->probed) {
+		struct device *dev = &slave->dev;
+		struct sdw_driver *drv = drv_to_sdw_driver(dev->driver);
+
+		if (drv->ops && drv->ops->update_status)
+			ret = drv->ops->update_status(slave, status);
 	}
 
-	if (!slave->ops || !slave->ops->update_status)
-		return 0;
+	mutex_unlock(&slave->sdw_dev_lock);
 
-	return slave->ops->update_status(slave, status);
+	return ret;
 }
 
 /**
diff --git a/drivers/soundwire/bus_type.c b/drivers/soundwire/bus_type.c
index 893296f3fe39..04b3529f8929 100644
--- a/drivers/soundwire/bus_type.c
+++ b/drivers/soundwire/bus_type.c
@@ -98,8 +98,6 @@ static int sdw_drv_probe(struct device *dev)
 	if (!id)
 		return -ENODEV;
 
-	slave->ops = drv->ops;
-
 	/*
 	 * attach to power domain but don't turn on (last arg)
 	 */
@@ -107,19 +105,23 @@ static int sdw_drv_probe(struct device *dev)
 	if (ret)
 		return ret;
 
+	mutex_lock(&slave->sdw_dev_lock);
+
 	ret = drv->probe(slave, id);
 	if (ret) {
 		name = drv->name;
 		if (!name)
 			name = drv->driver.name;
+		mutex_unlock(&slave->sdw_dev_lock);
+
 		dev_err(dev, "Probe of %s failed: %d\n", name, ret);
 		dev_pm_domain_detach(dev, false);
 		return ret;
 	}
 
 	/* device is probed so let's read the properties now */
-	if (slave->ops && slave->ops->read_prop)
-		slave->ops->read_prop(slave);
+	if (drv->ops && drv->ops->read_prop)
+		drv->ops->read_prop(slave);
 
 	/* init the sysfs as we have properties now */
 	ret = sdw_slave_sysfs_init(slave);
@@ -139,7 +141,19 @@ static int sdw_drv_probe(struct device *dev)
 					     slave->prop.clk_stop_timeout);
 
 	slave->probed = true;
-	complete(&slave->probe_complete);
+
+	/*
+	 * if the probe happened after the bus was started, notify the codec driver
+	 * of the current hardware status to e.g. start the initialization.
+	 * Errors are only logged as warnings to avoid failing the probe.
+	 */
+	if (drv->ops && drv->ops->update_status) {
+		ret = drv->ops->update_status(slave, slave->status);
+		if (ret < 0)
+			dev_warn(dev, "%s: update_status failed with status %d\n", __func__, ret);
+	}
+
+	mutex_unlock(&slave->sdw_dev_lock);
 
 	dev_dbg(dev, "probe complete\n");
 
@@ -152,9 +166,15 @@ static int sdw_drv_remove(struct device *dev)
 	struct sdw_driver *drv = drv_to_sdw_driver(dev->driver);
 	int ret = 0;
 
+	mutex_lock(&slave->sdw_dev_lock);
+
+	slave->probed = false;
+
 	if (drv->remove)
 		ret = drv->remove(slave);
 
+	mutex_unlock(&slave->sdw_dev_lock);
+
 	dev_pm_domain_detach(dev, false);
 
 	return ret;
@@ -193,12 +213,8 @@ int __sdw_register_driver(struct sdw_driver *drv, struct module *owner)
 
 	drv->driver.owner = owner;
 	drv->driver.probe = sdw_drv_probe;
-
-	if (drv->remove)
-		drv->driver.remove = sdw_drv_remove;
-
-	if (drv->shutdown)
-		drv->driver.shutdown = sdw_drv_shutdown;
+	drv->driver.remove = sdw_drv_remove;
+	drv->driver.shutdown = sdw_drv_shutdown;
 
 	return driver_register(&drv->driver);
 }
diff --git a/drivers/soundwire/qcom.c b/drivers/soundwire/qcom.c
index f5955826b152..1ce6f948e9a4 100644
--- a/drivers/soundwire/qcom.c
+++ b/drivers/soundwire/qcom.c
@@ -148,7 +148,7 @@ struct qcom_swrm_ctrl {
 	u8 wcmd_id;
 	struct qcom_swrm_port_config pconfig[QCOM_SDW_MAX_PORTS];
 	struct sdw_stream_runtime *sruntime[SWRM_MAX_DAIS];
-	enum sdw_slave_status status[SDW_MAX_DEVICES];
+	enum sdw_slave_status status[SDW_MAX_DEVICES + 1];
 	int (*reg_read)(struct qcom_swrm_ctrl *ctrl, int reg, u32 *val);
 	int (*reg_write)(struct qcom_swrm_ctrl *ctrl, int reg, int val);
 	u32 slave_status;
@@ -391,7 +391,7 @@ static int qcom_swrm_get_alert_slave_dev_num(struct qcom_swrm_ctrl *ctrl)
 
 	ctrl->reg_read(ctrl, SWRM_MCP_SLV_STATUS, &val);
 
-	for (dev_num = 0; dev_num < SDW_MAX_DEVICES; dev_num++) {
+	for (dev_num = 0; dev_num <= SDW_MAX_DEVICES; dev_num++) {
 		status = (val >> (dev_num * SWRM_MCP_SLV_STATUS_SZ));
 
 		if ((status & SWRM_MCP_SLV_STATUS_MASK) == SDW_SLAVE_ALERT) {
@@ -411,7 +411,7 @@ static void qcom_swrm_get_device_status(struct qcom_swrm_ctrl *ctrl)
 	ctrl->reg_read(ctrl, SWRM_MCP_SLV_STATUS, &val);
 	ctrl->slave_status = val;
 
-	for (i = 0; i < SDW_MAX_DEVICES; i++) {
+	for (i = 0; i <= SDW_MAX_DEVICES; i++) {
 		u32 s;
 
 		s = (val >> (i * 2));
@@ -451,6 +451,10 @@ static int qcom_swrm_enumerate(struct sdw_bus *bus)
 	char *buf1 = (char *)&val1, *buf2 = (char *)&val2;
 
 	for (i = 1; i <= SDW_MAX_DEVICES; i++) {
+		/* do not continue if the status is Not Present  */
+		if (!ctrl->status[i])
+			continue;
+
 		/*SCP_Devid5 - Devid 4*/
 		ctrl->reg_read(ctrl, SWRM_ENUMERATOR_SLAVE_DEV_ID_1(i), &val1);
 
diff --git a/drivers/soundwire/slave.c b/drivers/soundwire/slave.c
index 669d7573320b..25e76b5d4a1a 100644
--- a/drivers/soundwire/slave.c
+++ b/drivers/soundwire/slave.c
@@ -12,6 +12,7 @@ static void sdw_slave_release(struct device *dev)
 {
 	struct sdw_slave *slave = dev_to_sdw_dev(dev);
 
+	mutex_destroy(&slave->sdw_dev_lock);
 	kfree(slave);
 }
 
@@ -58,9 +59,9 @@ int sdw_slave_add(struct sdw_bus *bus,
 	init_completion(&slave->enumeration_complete);
 	init_completion(&slave->initialization_complete);
 	slave->dev_num = 0;
-	init_completion(&slave->probe_complete);
 	slave->probed = false;
 	slave->first_interrupt_done = false;
+	mutex_init(&slave->sdw_dev_lock);
 
 	for (i = 0; i < SDW_MAX_PORTS; i++)
 		init_completion(&slave->port_ready[i]);
diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c
index 5d4f6b308ef7..ebbe138a5626 100644
--- a/drivers/soundwire/stream.c
+++ b/drivers/soundwire/stream.c
@@ -13,6 +13,7 @@
 #include <linux/slab.h>
 #include <linux/soundwire/sdw_registers.h>
 #include <linux/soundwire/sdw.h>
+#include <linux/soundwire/sdw_type.h>
 #include <sound/soc.h>
 #include "bus.h"
 
@@ -401,20 +402,26 @@ static int sdw_do_port_prep(struct sdw_slave_runtime *s_rt,
 			    struct sdw_prepare_ch prep_ch,
 			    enum sdw_port_prep_ops cmd)
 {
-	const struct sdw_slave_ops *ops = s_rt->slave->ops;
-	int ret;
+	int ret = 0;
+	struct sdw_slave *slave = s_rt->slave;
 
-	if (ops->port_prep) {
-		ret = ops->port_prep(s_rt->slave, &prep_ch, cmd);
-		if (ret < 0) {
-			dev_err(&s_rt->slave->dev,
-				"Slave Port Prep cmd %d failed: %d\n",
-				cmd, ret);
-			return ret;
+	mutex_lock(&slave->sdw_dev_lock);
+
+	if (slave->probed) {
+		struct device *dev = &slave->dev;
+		struct sdw_driver *drv = drv_to_sdw_driver(dev->driver);
+
+		if (drv->ops && drv->ops->port_prep) {
+			ret = drv->ops->port_prep(slave, &prep_ch, cmd);
+			if (ret < 0)
+				dev_err(dev, "Slave Port Prep cmd %d failed: %d\n",
+					cmd, ret);
 		}
 	}
 
-	return 0;
+	mutex_unlock(&slave->sdw_dev_lock);
+
+	return ret;
 }
 
 static int sdw_prep_deprep_slave_ports(struct sdw_bus *bus,
@@ -578,7 +585,7 @@ static int sdw_notify_config(struct sdw_master_runtime *m_rt)
 	struct sdw_slave_runtime *s_rt;
 	struct sdw_bus *bus = m_rt->bus;
 	struct sdw_slave *slave;
-	int ret = 0;
+	int ret;
 
 	if (bus->ops->set_bus_conf) {
 		ret = bus->ops->set_bus_conf(bus, &bus->params);
@@ -589,17 +596,27 @@ static int sdw_notify_config(struct sdw_master_runtime *m_rt)
 	list_for_each_entry(s_rt, &m_rt->slave_rt_list, m_rt_node) {
 		slave = s_rt->slave;
 
-		if (slave->ops->bus_config) {
-			ret = slave->ops->bus_config(slave, &bus->params);
-			if (ret < 0) {
-				dev_err(bus->dev, "Notify Slave: %d failed\n",
-					slave->dev_num);
-				return ret;
+		mutex_lock(&slave->sdw_dev_lock);
+
+		if (slave->probed) {
+			struct device *dev = &slave->dev;
+			struct sdw_driver *drv = drv_to_sdw_driver(dev->driver);
+
+			if (drv->ops && drv->ops->bus_config) {
+				ret = drv->ops->bus_config(slave, &bus->params);
+				if (ret < 0) {
+					dev_err(dev, "Notify Slave: %d failed\n",
+						slave->dev_num);
+					mutex_unlock(&slave->sdw_dev_lock);
+					return ret;
+				}
 			}
 		}
+
+		mutex_unlock(&slave->sdw_dev_lock);
 	}
 
-	return ret;
+	return 0;
 }
 
 /**
diff --git a/drivers/spi/spi-altera-dfl.c b/drivers/spi/spi-altera-dfl.c
index ca40923258af..596e181ae136 100644
--- a/drivers/spi/spi-altera-dfl.c
+++ b/drivers/spi/spi-altera-dfl.c
@@ -128,9 +128,9 @@ static int dfl_spi_altera_probe(struct dfl_device *dfl_dev)
 	struct spi_master *master;
 	struct altera_spi *hw;
 	void __iomem *base;
-	int err = -ENODEV;
+	int err;
 
-	master = spi_alloc_master(dev, sizeof(struct altera_spi));
+	master = devm_spi_alloc_master(dev, sizeof(struct altera_spi));
 	if (!master)
 		return -ENOMEM;
 
@@ -159,10 +159,9 @@ static int dfl_spi_altera_probe(struct dfl_device *dfl_dev)
 	altera_spi_init_master(master);
 
 	err = devm_spi_register_master(dev, master);
-	if (err) {
-		dev_err(dev, "%s failed to register spi master %d\n", __func__, err);
-		goto exit;
-	}
+	if (err)
+		return dev_err_probe(dev, err, "%s failed to register spi master\n",
+				     __func__);
 
 	if (dfl_dev->revision == FME_FEATURE_REV_MAX10_SPI_N5010)
 		strscpy(board_info.modalias, "m10-n5010", SPI_NAME_SIZE);
@@ -179,9 +178,6 @@ static int dfl_spi_altera_probe(struct dfl_device *dfl_dev)
 	}
 
 	return 0;
-exit:
-	spi_master_put(master);
-	return err;
 }
 
 static const struct dfl_device_id dfl_spi_altera_ids[] = {
diff --git a/drivers/spi/spi-amd.c b/drivers/spi/spi-amd.c
index 3cf76096a76d..39dbe9903da2 100644
--- a/drivers/spi/spi-amd.c
+++ b/drivers/spi/spi-amd.c
@@ -28,6 +28,7 @@
 #define AMD_SPI_RX_COUNT_REG	0x4B
 #define AMD_SPI_STATUS_REG	0x4C
 
+#define AMD_SPI_FIFO_SIZE	70
 #define AMD_SPI_MEM_SIZE	200
 
 /* M_CMD OP codes for SPI */
@@ -245,6 +246,11 @@ static int amd_spi_master_transfer(struct spi_master *master,
 	return 0;
 }
 
+static size_t amd_spi_max_transfer_size(struct spi_device *spi)
+{
+	return AMD_SPI_FIFO_SIZE;
+}
+
 static int amd_spi_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -275,6 +281,8 @@ static int amd_spi_probe(struct platform_device *pdev)
 	master->flags = SPI_MASTER_HALF_DUPLEX;
 	master->setup = amd_spi_master_setup;
 	master->transfer_one_message = amd_spi_master_transfer;
+	master->max_transfer_size = amd_spi_max_transfer_size;
+	master->max_message_size = amd_spi_max_transfer_size;
 
 	/* Register the controller with SPI framework */
 	err = devm_spi_register_master(dev, master);
diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c
index 775c0bf2f923..0933948d7df3 100644
--- a/drivers/spi/spi-bcm2835.c
+++ b/drivers/spi/spi-bcm2835.c
@@ -1138,10 +1138,14 @@ static void bcm2835_spi_handle_err(struct spi_controller *ctlr,
 	struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr);
 
 	/* if an error occurred and we have an active dma, then terminate */
-	dmaengine_terminate_sync(ctlr->dma_tx);
-	bs->tx_dma_active = false;
-	dmaengine_terminate_sync(ctlr->dma_rx);
-	bs->rx_dma_active = false;
+	if (ctlr->dma_tx) {
+		dmaengine_terminate_sync(ctlr->dma_tx);
+		bs->tx_dma_active = false;
+	}
+	if (ctlr->dma_rx) {
+		dmaengine_terminate_sync(ctlr->dma_rx);
+		bs->rx_dma_active = false;
+	}
 	bcm2835_spi_undo_prologue(bs);
 
 	/* and reset */
diff --git a/drivers/spi/spi-meson-spicc.c b/drivers/spi/spi-meson-spicc.c
index 0bc7daa7afc8..e4cb52e1fe26 100644
--- a/drivers/spi/spi-meson-spicc.c
+++ b/drivers/spi/spi-meson-spicc.c
@@ -156,6 +156,7 @@ struct meson_spicc_device {
 	void __iomem			*base;
 	struct clk			*core;
 	struct clk			*pclk;
+	struct clk_divider		pow2_div;
 	struct clk			*clk;
 	struct spi_message		*message;
 	struct spi_transfer		*xfer;
@@ -168,6 +169,8 @@ struct meson_spicc_device {
 	unsigned long			xfer_remain;
 };
 
+#define pow2_clk_to_spicc(_div) container_of(_div, struct meson_spicc_device, pow2_div)
+
 static void meson_spicc_oen_enable(struct meson_spicc_device *spicc)
 {
 	u32 conf;
@@ -421,7 +424,7 @@ static int meson_spicc_prepare_message(struct spi_master *master,
 {
 	struct meson_spicc_device *spicc = spi_master_get_devdata(master);
 	struct spi_device *spi = message->spi;
-	u32 conf = 0;
+	u32 conf = readl_relaxed(spicc->base + SPICC_CONREG) & SPICC_DATARATE_MASK;
 
 	/* Store current message */
 	spicc->message = message;
@@ -458,8 +461,6 @@ static int meson_spicc_prepare_message(struct spi_master *master,
 	/* Select CS */
 	conf |= FIELD_PREP(SPICC_CS_MASK, spi->chip_select);
 
-	/* Default Clock rate core/4 */
-
 	/* Default 8bit word */
 	conf |= FIELD_PREP(SPICC_BITLENGTH_MASK, 8 - 1);
 
@@ -476,12 +477,16 @@ static int meson_spicc_prepare_message(struct spi_master *master,
 static int meson_spicc_unprepare_transfer(struct spi_master *master)
 {
 	struct meson_spicc_device *spicc = spi_master_get_devdata(master);
+	u32 conf = readl_relaxed(spicc->base + SPICC_CONREG) & SPICC_DATARATE_MASK;
 
 	/* Disable all IRQs */
 	writel(0, spicc->base + SPICC_INTREG);
 
 	device_reset_optional(&spicc->pdev->dev);
 
+	/* Set default configuration, keeping datarate field */
+	writel_relaxed(conf, spicc->base + SPICC_CONREG);
+
 	return 0;
 }
 
@@ -518,14 +523,60 @@ static void meson_spicc_cleanup(struct spi_device *spi)
  * Clk path for G12A series:
  *    pclk -> pow2 fixed div -> pow2 div -> mux -> out
  *    pclk -> enh fixed div -> enh div -> mux -> out
+ *
+ * The pow2 divider is tied to the controller HW state, and the
+ * divider is only valid when the controller is initialized.
+ *
+ * A set of clock ops is added to make sure we don't read/set this
+ * clock rate while the controller is in an unknown state.
  */
 
-static int meson_spicc_clk_init(struct meson_spicc_device *spicc)
+static unsigned long meson_spicc_pow2_recalc_rate(struct clk_hw *hw,
+						  unsigned long parent_rate)
+{
+	struct clk_divider *divider = to_clk_divider(hw);
+	struct meson_spicc_device *spicc = pow2_clk_to_spicc(divider);
+
+	if (!spicc->master->cur_msg || !spicc->master->busy)
+		return 0;
+
+	return clk_divider_ops.recalc_rate(hw, parent_rate);
+}
+
+static int meson_spicc_pow2_determine_rate(struct clk_hw *hw,
+					   struct clk_rate_request *req)
+{
+	struct clk_divider *divider = to_clk_divider(hw);
+	struct meson_spicc_device *spicc = pow2_clk_to_spicc(divider);
+
+	if (!spicc->master->cur_msg || !spicc->master->busy)
+		return -EINVAL;
+
+	return clk_divider_ops.determine_rate(hw, req);
+}
+
+static int meson_spicc_pow2_set_rate(struct clk_hw *hw, unsigned long rate,
+				     unsigned long parent_rate)
+{
+	struct clk_divider *divider = to_clk_divider(hw);
+	struct meson_spicc_device *spicc = pow2_clk_to_spicc(divider);
+
+	if (!spicc->master->cur_msg || !spicc->master->busy)
+		return -EINVAL;
+
+	return clk_divider_ops.set_rate(hw, rate, parent_rate);
+}
+
+const struct clk_ops meson_spicc_pow2_clk_ops = {
+	.recalc_rate = meson_spicc_pow2_recalc_rate,
+	.determine_rate = meson_spicc_pow2_determine_rate,
+	.set_rate = meson_spicc_pow2_set_rate,
+};
+
+static int meson_spicc_pow2_clk_init(struct meson_spicc_device *spicc)
 {
 	struct device *dev = &spicc->pdev->dev;
-	struct clk_fixed_factor *pow2_fixed_div, *enh_fixed_div;
-	struct clk_divider *pow2_div, *enh_div;
-	struct clk_mux *mux;
+	struct clk_fixed_factor *pow2_fixed_div;
 	struct clk_init_data init;
 	struct clk *clk;
 	struct clk_parent_data parent_data[2];
@@ -560,31 +611,45 @@ static int meson_spicc_clk_init(struct meson_spicc_device *spicc)
 	if (WARN_ON(IS_ERR(clk)))
 		return PTR_ERR(clk);
 
-	pow2_div = devm_kzalloc(dev, sizeof(*pow2_div), GFP_KERNEL);
-	if (!pow2_div)
-		return -ENOMEM;
-
 	snprintf(name, sizeof(name), "%s#pow2_div", dev_name(dev));
 	init.name = name;
-	init.ops = &clk_divider_ops;
-	init.flags = CLK_SET_RATE_PARENT;
+	init.ops = &meson_spicc_pow2_clk_ops;
+	/*
+	 * Set NOCACHE here to make sure we read the actual HW value
+	 * since we reset the HW after each transfer.
+	 */
+	init.flags = CLK_SET_RATE_PARENT | CLK_GET_RATE_NOCACHE;
 	parent_data[0].hw = &pow2_fixed_div->hw;
 	init.num_parents = 1;
 
-	pow2_div->shift = 16,
-	pow2_div->width = 3,
-	pow2_div->flags = CLK_DIVIDER_POWER_OF_TWO,
-	pow2_div->reg = spicc->base + SPICC_CONREG;
-	pow2_div->hw.init = &init;
+	spicc->pow2_div.shift = 16,
+	spicc->pow2_div.width = 3,
+	spicc->pow2_div.flags = CLK_DIVIDER_POWER_OF_TWO,
+	spicc->pow2_div.reg = spicc->base + SPICC_CONREG;
+	spicc->pow2_div.hw.init = &init;
 
-	clk = devm_clk_register(dev, &pow2_div->hw);
-	if (WARN_ON(IS_ERR(clk)))
-		return PTR_ERR(clk);
+	spicc->clk = devm_clk_register(dev, &spicc->pow2_div.hw);
+	if (WARN_ON(IS_ERR(spicc->clk)))
+		return PTR_ERR(spicc->clk);
 
-	if (!spicc->data->has_enhance_clk_div) {
-		spicc->clk = clk;
-		return 0;
-	}
+	return 0;
+}
+
+static int meson_spicc_enh_clk_init(struct meson_spicc_device *spicc)
+{
+	struct device *dev = &spicc->pdev->dev;
+	struct clk_fixed_factor *enh_fixed_div;
+	struct clk_divider *enh_div;
+	struct clk_mux *mux;
+	struct clk_init_data init;
+	struct clk *clk;
+	struct clk_parent_data parent_data[2];
+	char name[64];
+
+	memset(&init, 0, sizeof(init));
+	memset(&parent_data, 0, sizeof(parent_data));
+
+	init.parent_data = parent_data;
 
 	/* algorithm for enh div: rate = freq / 2 / (N + 1) */
 
@@ -637,7 +702,7 @@ static int meson_spicc_clk_init(struct meson_spicc_device *spicc)
 	snprintf(name, sizeof(name), "%s#sel", dev_name(dev));
 	init.name = name;
 	init.ops = &clk_mux_ops;
-	parent_data[0].hw = &pow2_div->hw;
+	parent_data[0].hw = &spicc->pow2_div.hw;
 	parent_data[1].hw = &enh_div->hw;
 	init.num_parents = 2;
 	init.flags = CLK_SET_RATE_PARENT;
@@ -754,12 +819,20 @@ static int meson_spicc_probe(struct platform_device *pdev)
 
 	meson_spicc_oen_enable(spicc);
 
-	ret = meson_spicc_clk_init(spicc);
+	ret = meson_spicc_pow2_clk_init(spicc);
 	if (ret) {
-		dev_err(&pdev->dev, "clock registration failed\n");
+		dev_err(&pdev->dev, "pow2 clock registration failed\n");
 		goto out_clk;
 	}
 
+	if (spicc->data->has_enhance_clk_div) {
+		ret = meson_spicc_enh_clk_init(spicc);
+		if (ret) {
+			dev_err(&pdev->dev, "clock registration failed\n");
+			goto out_clk;
+		}
+	}
+
 	ret = devm_spi_register_master(&pdev->dev, master);
 	if (ret) {
 		dev_err(&pdev->dev, "spi master registration failed\n");
diff --git a/drivers/spi/spi-rspi.c b/drivers/spi/spi-rspi.c
index d575c935e9f0..f634a405382c 100644
--- a/drivers/spi/spi-rspi.c
+++ b/drivers/spi/spi-rspi.c
@@ -612,6 +612,10 @@ static int rspi_dma_transfer(struct rspi_data *rspi, struct sg_table *tx,
 					       rspi->dma_callbacked, HZ);
 	if (ret > 0 && rspi->dma_callbacked) {
 		ret = 0;
+		if (tx)
+			dmaengine_synchronize(rspi->ctlr->dma_tx);
+		if (rx)
+			dmaengine_synchronize(rspi->ctlr->dma_rx);
 	} else {
 		if (!ret) {
 			dev_err(&rspi->ctlr->dev, "DMA timeout\n");
diff --git a/drivers/spi/spi-synquacer.c b/drivers/spi/spi-synquacer.c
index ea706d9629cb..47cbe73137c2 100644
--- a/drivers/spi/spi-synquacer.c
+++ b/drivers/spi/spi-synquacer.c
@@ -783,6 +783,7 @@ static int __maybe_unused synquacer_spi_resume(struct device *dev)
 
 		ret = synquacer_spi_enable(master);
 		if (ret) {
+			clk_disable_unprepare(sspi->clk);
 			dev_err(dev, "failed to enable spi (%d)\n", ret);
 			return ret;
 		}
diff --git a/drivers/spi/spi-tegra20-slink.c b/drivers/spi/spi-tegra20-slink.c
index 3b44ca455049..cf61bf302a05 100644
--- a/drivers/spi/spi-tegra20-slink.c
+++ b/drivers/spi/spi-tegra20-slink.c
@@ -1130,7 +1130,7 @@ exit_free_master:
 
 static int tegra_slink_remove(struct platform_device *pdev)
 {
-	struct spi_master *master = platform_get_drvdata(pdev);
+	struct spi_master *master = spi_master_get(platform_get_drvdata(pdev));
 	struct tegra_slink_data	*tspi = spi_master_get_devdata(master);
 
 	spi_unregister_master(master);
@@ -1145,6 +1145,7 @@ static int tegra_slink_remove(struct platform_device *pdev)
 	if (tspi->rx_dma_chan)
 		tegra_slink_deinit_dma_param(tspi, true);
 
+	spi_master_put(master);
 	return 0;
 }
 
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index d0bbf8f9414d..556d65af5e23 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -2949,9 +2949,9 @@ free_bus_id:
 }
 EXPORT_SYMBOL_GPL(spi_register_controller);
 
-static void devm_spi_unregister(void *ctlr)
+static void devm_spi_unregister(struct device *dev, void *res)
 {
-	spi_unregister_controller(ctlr);
+	spi_unregister_controller(*(struct spi_controller **)res);
 }
 
 /**
@@ -2970,13 +2970,22 @@ static void devm_spi_unregister(void *ctlr)
 int devm_spi_register_controller(struct device *dev,
 				 struct spi_controller *ctlr)
 {
+	struct spi_controller **ptr;
 	int ret;
 
+	ptr = devres_alloc(devm_spi_unregister, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return -ENOMEM;
+
 	ret = spi_register_controller(ctlr);
-	if (ret)
-		return ret;
+	if (!ret) {
+		*ptr = ctlr;
+		devres_add(dev, ptr);
+	} else {
+		devres_free(ptr);
+	}
 
-	return devm_add_action_or_reset(dev, devm_spi_unregister, ctlr);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(devm_spi_register_controller);
 
diff --git a/drivers/staging/media/atomisp/pci/atomisp_cmd.c b/drivers/staging/media/atomisp/pci/atomisp_cmd.c
index ef0b0963cf93..88db9818e083 100644
--- a/drivers/staging/media/atomisp/pci/atomisp_cmd.c
+++ b/drivers/staging/media/atomisp/pci/atomisp_cmd.c
@@ -899,9 +899,9 @@ void atomisp_buf_done(struct atomisp_sub_device *asd, int error,
 	int err;
 	unsigned long irqflags;
 	struct ia_css_frame *frame = NULL;
-	struct atomisp_s3a_buf *s3a_buf = NULL, *_s3a_buf_tmp;
-	struct atomisp_dis_buf *dis_buf = NULL, *_dis_buf_tmp;
-	struct atomisp_metadata_buf *md_buf = NULL, *_md_buf_tmp;
+	struct atomisp_s3a_buf *s3a_buf = NULL, *_s3a_buf_tmp, *s3a_iter;
+	struct atomisp_dis_buf *dis_buf = NULL, *_dis_buf_tmp, *dis_iter;
+	struct atomisp_metadata_buf *md_buf = NULL, *_md_buf_tmp, *md_iter;
 	enum atomisp_metadata_type md_type;
 	struct atomisp_device *isp = asd->isp;
 	struct v4l2_control ctrl;
@@ -940,60 +940,75 @@ void atomisp_buf_done(struct atomisp_sub_device *asd, int error,
 
 	switch (buf_type) {
 	case IA_CSS_BUFFER_TYPE_3A_STATISTICS:
-		list_for_each_entry_safe(s3a_buf, _s3a_buf_tmp,
+		list_for_each_entry_safe(s3a_iter, _s3a_buf_tmp,
 					 &asd->s3a_stats_in_css, list) {
-			if (s3a_buf->s3a_data ==
+			if (s3a_iter->s3a_data ==
 			    buffer.css_buffer.data.stats_3a) {
-				list_del_init(&s3a_buf->list);
-				list_add_tail(&s3a_buf->list,
+				list_del_init(&s3a_iter->list);
+				list_add_tail(&s3a_iter->list,
 					      &asd->s3a_stats_ready);
+				s3a_buf = s3a_iter;
 				break;
 			}
 		}
 
 		asd->s3a_bufs_in_css[css_pipe_id]--;
 		atomisp_3a_stats_ready_event(asd, buffer.css_buffer.exp_id);
-		dev_dbg(isp->dev, "%s: s3a stat with exp_id %d is ready\n",
-			__func__, s3a_buf->s3a_data->exp_id);
+		if (s3a_buf)
+			dev_dbg(isp->dev, "%s: s3a stat with exp_id %d is ready\n",
+				__func__, s3a_buf->s3a_data->exp_id);
+		else
+			dev_dbg(isp->dev, "%s: s3a stat is ready with no exp_id found\n",
+				__func__);
 		break;
 	case IA_CSS_BUFFER_TYPE_METADATA:
 		if (error)
 			break;
 
 		md_type = atomisp_get_metadata_type(asd, css_pipe_id);
-		list_for_each_entry_safe(md_buf, _md_buf_tmp,
+		list_for_each_entry_safe(md_iter, _md_buf_tmp,
 					 &asd->metadata_in_css[md_type], list) {
-			if (md_buf->metadata ==
+			if (md_iter->metadata ==
 			    buffer.css_buffer.data.metadata) {
-				list_del_init(&md_buf->list);
-				list_add_tail(&md_buf->list,
+				list_del_init(&md_iter->list);
+				list_add_tail(&md_iter->list,
 					      &asd->metadata_ready[md_type]);
+				md_buf = md_iter;
 				break;
 			}
 		}
 		asd->metadata_bufs_in_css[stream_id][css_pipe_id]--;
 		atomisp_metadata_ready_event(asd, md_type);
-		dev_dbg(isp->dev, "%s: metadata with exp_id %d is ready\n",
-			__func__, md_buf->metadata->exp_id);
+		if (md_buf)
+			dev_dbg(isp->dev, "%s: metadata with exp_id %d is ready\n",
+				__func__, md_buf->metadata->exp_id);
+		else
+			dev_dbg(isp->dev, "%s: metadata is ready with no exp_id found\n",
+				__func__);
 		break;
 	case IA_CSS_BUFFER_TYPE_DIS_STATISTICS:
-		list_for_each_entry_safe(dis_buf, _dis_buf_tmp,
+		list_for_each_entry_safe(dis_iter, _dis_buf_tmp,
 					 &asd->dis_stats_in_css, list) {
-			if (dis_buf->dis_data ==
+			if (dis_iter->dis_data ==
 			    buffer.css_buffer.data.stats_dvs) {
 				spin_lock_irqsave(&asd->dis_stats_lock,
 						  irqflags);
-				list_del_init(&dis_buf->list);
-				list_add(&dis_buf->list, &asd->dis_stats);
+				list_del_init(&dis_iter->list);
+				list_add(&dis_iter->list, &asd->dis_stats);
 				asd->params.dis_proj_data_valid = true;
 				spin_unlock_irqrestore(&asd->dis_stats_lock,
 						       irqflags);
+				dis_buf = dis_iter;
 				break;
 			}
 		}
 		asd->dis_bufs_in_css--;
-		dev_dbg(isp->dev, "%s: dis stat with exp_id %d is ready\n",
-			__func__, dis_buf->dis_data->exp_id);
+		if (dis_buf)
+			dev_dbg(isp->dev, "%s: dis stat with exp_id %d is ready\n",
+				__func__, dis_buf->dis_data->exp_id);
+		else
+			dev_dbg(isp->dev, "%s: dis stat is ready with no exp_id found\n",
+				__func__);
 		break;
 	case IA_CSS_BUFFER_TYPE_VF_OUTPUT_FRAME:
 	case IA_CSS_BUFFER_TYPE_SEC_VF_OUTPUT_FRAME:
diff --git a/drivers/staging/media/hantro/hantro.h b/drivers/staging/media/hantro/hantro.h
index c2e2dca38628..88792c863edc 100644
--- a/drivers/staging/media/hantro/hantro.h
+++ b/drivers/staging/media/hantro/hantro.h
@@ -262,6 +262,7 @@ struct hantro_ctx {
  * @max_depth:	Maximum depth, for bitstream formats
  * @enc_fmt:	Format identifier for encoder registers.
  * @frmsize:	Supported range of frame sizes (only for bitstream formats).
+ * @postprocessed: Indicates if this format needs the post-processor.
  */
 struct hantro_fmt {
 	char *name;
@@ -271,6 +272,7 @@ struct hantro_fmt {
 	int max_depth;
 	enum hantro_enc_fmt enc_fmt;
 	struct v4l2_frmsize_stepwise frmsize;
+	bool postprocessed;
 };
 
 struct hantro_reg {
diff --git a/drivers/staging/media/hantro/hantro_g2_hevc_dec.c b/drivers/staging/media/hantro/hantro_g2_hevc_dec.c
index e63b777d4266..bcdfa359de7f 100644
--- a/drivers/staging/media/hantro/hantro_g2_hevc_dec.c
+++ b/drivers/staging/media/hantro/hantro_g2_hevc_dec.c
@@ -264,24 +264,11 @@ static void set_params(struct hantro_ctx *ctx)
 	hantro_reg_write(vpu, &g2_apf_threshold, 8);
 }
 
-static int find_ref_pic_index(const struct v4l2_hevc_dpb_entry *dpb, int pic_order_cnt)
-{
-	int i;
-
-	for (i = 0; i < V4L2_HEVC_DPB_ENTRIES_NUM_MAX; i++) {
-		if (dpb[i].pic_order_cnt[0] == pic_order_cnt)
-			return i;
-	}
-
-	return 0x0;
-}
-
 static void set_ref_pic_list(struct hantro_ctx *ctx)
 {
 	const struct hantro_hevc_dec_ctrls *ctrls = &ctx->hevc_dec.ctrls;
 	struct hantro_dev *vpu = ctx->dev;
 	const struct v4l2_ctrl_hevc_decode_params *decode_params = ctrls->decode_params;
-	const struct v4l2_hevc_dpb_entry *dpb = decode_params->dpb;
 	u32 list0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX] = {};
 	u32 list1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX] = {};
 	static const struct hantro_reg ref_pic_regs0[] = {
@@ -325,11 +312,11 @@ static void set_ref_pic_list(struct hantro_ctx *ctx)
 	/* List 0 contains: short term before, short term after and long term */
 	j = 0;
 	for (i = 0; i < decode_params->num_poc_st_curr_before && j < ARRAY_SIZE(list0); i++)
-		list0[j++] = find_ref_pic_index(dpb, decode_params->poc_st_curr_before[i]);
+		list0[j++] = decode_params->poc_st_curr_before[i];
 	for (i = 0; i < decode_params->num_poc_st_curr_after && j < ARRAY_SIZE(list0); i++)
-		list0[j++] = find_ref_pic_index(dpb, decode_params->poc_st_curr_after[i]);
+		list0[j++] = decode_params->poc_st_curr_after[i];
 	for (i = 0; i < decode_params->num_poc_lt_curr && j < ARRAY_SIZE(list0); i++)
-		list0[j++] = find_ref_pic_index(dpb, decode_params->poc_lt_curr[i]);
+		list0[j++] = decode_params->poc_lt_curr[i];
 
 	/* Fill the list, copying over and over */
 	i = 0;
@@ -338,11 +325,11 @@ static void set_ref_pic_list(struct hantro_ctx *ctx)
 
 	j = 0;
 	for (i = 0; i < decode_params->num_poc_st_curr_after && j < ARRAY_SIZE(list1); i++)
-		list1[j++] = find_ref_pic_index(dpb, decode_params->poc_st_curr_after[i]);
+		list1[j++] = decode_params->poc_st_curr_after[i];
 	for (i = 0; i < decode_params->num_poc_st_curr_before && j < ARRAY_SIZE(list1); i++)
-		list1[j++] = find_ref_pic_index(dpb, decode_params->poc_st_curr_before[i]);
+		list1[j++] = decode_params->poc_st_curr_before[i];
 	for (i = 0; i < decode_params->num_poc_lt_curr && j < ARRAY_SIZE(list1); i++)
-		list1[j++] = find_ref_pic_index(dpb, decode_params->poc_lt_curr[i]);
+		list1[j++] = decode_params->poc_lt_curr[i];
 
 	i = 0;
 	while (j < ARRAY_SIZE(list1))
@@ -426,7 +413,7 @@ static int set_ref(struct hantro_ctx *ctx)
 
 	set_ref_pic_list(ctx);
 
-	/* We will only keep the references picture that are still used */
+	/* We will only keep the reference pictures that are still used */
 	ctx->hevc_dec.ref_bufs_used = 0;
 
 	/* Set up addresses of DPB buffers */
diff --git a/drivers/staging/media/hantro/hantro_hevc.c b/drivers/staging/media/hantro/hantro_hevc.c
index 5347f5a41c2a..7ce98a2b1655 100644
--- a/drivers/staging/media/hantro/hantro_hevc.c
+++ b/drivers/staging/media/hantro/hantro_hevc.c
@@ -98,7 +98,7 @@ dma_addr_t hantro_hevc_get_ref_buf(struct hantro_ctx *ctx,
 	struct hantro_hevc_dec_hw_ctx *hevc_dec = &ctx->hevc_dec;
 	int i;
 
-	/* Find the reference buffer in already know ones */
+	/* Find the reference buffer in already known ones */
 	for (i = 0;  i < NUM_REF_PICTURES; i++) {
 		if (hevc_dec->ref_bufs_poc[i] == poc) {
 			hevc_dec->ref_bufs_used |= 1 << i;
diff --git a/drivers/staging/media/hantro/hantro_postproc.c b/drivers/staging/media/hantro/hantro_postproc.c
index ed8916c950a4..46434c97317b 100644
--- a/drivers/staging/media/hantro/hantro_postproc.c
+++ b/drivers/staging/media/hantro/hantro_postproc.c
@@ -53,15 +53,9 @@ const struct hantro_postproc_regs hantro_g1_postproc_regs = {
 bool hantro_needs_postproc(const struct hantro_ctx *ctx,
 			   const struct hantro_fmt *fmt)
 {
-	struct hantro_dev *vpu = ctx->dev;
-
 	if (ctx->is_encoder)
 		return false;
-
-	if (!vpu->variant->postproc_fmts)
-		return false;
-
-	return fmt->fourcc != V4L2_PIX_FMT_NV12;
+	return fmt->postprocessed;
 }
 
 void hantro_postproc_enable(struct hantro_ctx *ctx)
@@ -132,9 +126,10 @@ int hantro_postproc_alloc(struct hantro_ctx *ctx)
 	unsigned int num_buffers = cap_queue->num_buffers;
 	unsigned int i, buf_size;
 
-	buf_size = ctx->dst_fmt.plane_fmt[0].sizeimage +
-		   hantro_h264_mv_size(ctx->dst_fmt.width,
-				       ctx->dst_fmt.height);
+	buf_size = ctx->dst_fmt.plane_fmt[0].sizeimage;
+	if (ctx->vpu_src_fmt->fourcc == V4L2_PIX_FMT_H264_SLICE)
+		buf_size += hantro_h264_mv_size(ctx->dst_fmt.width,
+						ctx->dst_fmt.height);
 
 	for (i = 0; i < num_buffers; ++i) {
 		struct hantro_aux_buf *priv = &ctx->postproc.dec_q[i];
diff --git a/drivers/staging/media/hantro/imx8m_vpu_hw.c b/drivers/staging/media/hantro/imx8m_vpu_hw.c
index ea919bfb9891..b692b74b0914 100644
--- a/drivers/staging/media/hantro/imx8m_vpu_hw.c
+++ b/drivers/staging/media/hantro/imx8m_vpu_hw.c
@@ -82,6 +82,7 @@ static const struct hantro_fmt imx8m_vpu_postproc_fmts[] = {
 	{
 		.fourcc = V4L2_PIX_FMT_YUYV,
 		.codec_mode = HANTRO_MODE_NONE,
+		.postprocessed = true,
 	},
 };
 
diff --git a/drivers/staging/media/hantro/rockchip_vpu_hw.c b/drivers/staging/media/hantro/rockchip_vpu_hw.c
index 0c22039162a0..543dc4a5486c 100644
--- a/drivers/staging/media/hantro/rockchip_vpu_hw.c
+++ b/drivers/staging/media/hantro/rockchip_vpu_hw.c
@@ -62,6 +62,7 @@ static const struct hantro_fmt rockchip_vpu1_postproc_fmts[] = {
 	{
 		.fourcc = V4L2_PIX_FMT_YUYV,
 		.codec_mode = HANTRO_MODE_NONE,
+		.postprocessed = true,
 	},
 };
 
diff --git a/drivers/staging/media/hantro/sama5d4_vdec_hw.c b/drivers/staging/media/hantro/sama5d4_vdec_hw.c
index 9c3b8cd0b239..99432008b241 100644
--- a/drivers/staging/media/hantro/sama5d4_vdec_hw.c
+++ b/drivers/staging/media/hantro/sama5d4_vdec_hw.c
@@ -15,6 +15,7 @@ static const struct hantro_fmt sama5d4_vdec_postproc_fmts[] = {
 	{
 		.fourcc = V4L2_PIX_FMT_YUYV,
 		.codec_mode = HANTRO_MODE_NONE,
+		.postprocessed = true,
 	},
 };
 
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_h265.c b/drivers/staging/media/sunxi/cedrus/cedrus_h265.c
index 754942ecf064..830cae03fc6e 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus_h265.c
+++ b/drivers/staging/media/sunxi/cedrus/cedrus_h265.c
@@ -147,6 +147,9 @@ static void cedrus_h265_frame_info_write_dpb(struct cedrus_ctx *ctx,
 			dpb[i].pic_order_cnt[1]
 		};
 
+		if (buffer_index < 0)
+			continue;
+
 		cedrus_h265_frame_info_write_single(ctx, i, dpb[i].field_pic,
 						    pic_order_cnt,
 						    buffer_index);
@@ -495,7 +498,6 @@ static void cedrus_h265_setup(struct cedrus_ctx *ctx,
 
 	reg = VE_DEC_H265_DEC_SLICE_HDR_INFO1_SLICE_TC_OFFSET_DIV2(slice_params->slice_tc_offset_div2) |
 	      VE_DEC_H265_DEC_SLICE_HDR_INFO1_SLICE_BETA_OFFSET_DIV2(slice_params->slice_beta_offset_div2) |
-	      VE_DEC_H265_DEC_SLICE_HDR_INFO1_SLICE_POC_BIGEST_IN_RPS_ST(decode_params->num_poc_st_curr_after == 0) |
 	      VE_DEC_H265_DEC_SLICE_HDR_INFO1_SLICE_CR_QP_OFFSET(slice_params->slice_cr_qp_offset) |
 	      VE_DEC_H265_DEC_SLICE_HDR_INFO1_SLICE_CB_QP_OFFSET(slice_params->slice_cb_qp_offset) |
 	      VE_DEC_H265_DEC_SLICE_HDR_INFO1_SLICE_QP_DELTA(slice_params->slice_qp_delta);
@@ -508,6 +510,9 @@ static void cedrus_h265_setup(struct cedrus_ctx *ctx,
 				V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_LOOP_FILTER_ACROSS_SLICES_ENABLED,
 				slice_params->flags);
 
+	if (decode_params->num_poc_st_curr_after == 0)
+		reg |= VE_DEC_H265_DEC_SLICE_HDR_INFO1_FLAG_SLICE_NOT_LOW_DELAY;
+
 	cedrus_write(dev, VE_DEC_H265_DEC_SLICE_HDR_INFO1, reg);
 
 	chroma_log2_weight_denom = pred_weight_table->luma_log2_weight_denom +
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_regs.h b/drivers/staging/media/sunxi/cedrus/cedrus_regs.h
index 92ace87c1c7d..5f34e3670289 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus_regs.h
+++ b/drivers/staging/media/sunxi/cedrus/cedrus_regs.h
@@ -377,13 +377,12 @@
 
 #define VE_DEC_H265_DEC_SLICE_HDR_INFO1_FLAG_SLICE_DEBLOCKING_FILTER_DISABLED BIT(23)
 #define VE_DEC_H265_DEC_SLICE_HDR_INFO1_FLAG_SLICE_LOOP_FILTER_ACROSS_SLICES_ENABLED BIT(22)
+#define VE_DEC_H265_DEC_SLICE_HDR_INFO1_FLAG_SLICE_NOT_LOW_DELAY BIT(21)
 
 #define VE_DEC_H265_DEC_SLICE_HDR_INFO1_SLICE_TC_OFFSET_DIV2(v) \
 	SHIFT_AND_MASK_BITS(v, 31, 28)
 #define VE_DEC_H265_DEC_SLICE_HDR_INFO1_SLICE_BETA_OFFSET_DIV2(v) \
 	SHIFT_AND_MASK_BITS(v, 27, 24)
-#define VE_DEC_H265_DEC_SLICE_HDR_INFO1_SLICE_POC_BIGEST_IN_RPS_ST(v) \
-	((v) ? BIT(21) : 0)
 #define VE_DEC_H265_DEC_SLICE_HDR_INFO1_SLICE_CR_QP_OFFSET(v) \
 	SHIFT_AND_MASK_BITS(v, 20, 16)
 #define VE_DEC_H265_DEC_SLICE_HDR_INFO1_SLICE_CB_QP_OFFSET(v) \
diff --git a/drivers/staging/r8188eu/os_dep/os_intfs.c b/drivers/staging/r8188eu/os_dep/os_intfs.c
index 8d0158f4a45d..30caa1139c8e 100644
--- a/drivers/staging/r8188eu/os_dep/os_intfs.c
+++ b/drivers/staging/r8188eu/os_dep/os_intfs.c
@@ -17,6 +17,7 @@ MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Realtek Wireless Lan Driver");
 MODULE_AUTHOR("Realtek Semiconductor Corp.");
 MODULE_VERSION(DRIVERVERSION);
+MODULE_FIRMWARE("rtlwifi/rtl8188eufw.bin");
 
 #define CONFIG_BR_EXT_BRNAME "br0"
 #define RTW_NOTCH_FILTER 0 /* 0:Disable, 1:Enable, */
diff --git a/drivers/staging/rtl8192u/r8192U.h b/drivers/staging/rtl8192u/r8192U.h
index 4013107cd93a..a23d6d41de9d 100644
--- a/drivers/staging/rtl8192u/r8192U.h
+++ b/drivers/staging/rtl8192u/r8192U.h
@@ -1013,7 +1013,7 @@ typedef struct r8192_priv {
 	bool		bis_any_nonbepkts;
 	bool		bcurrent_turbo_EDCA;
 	bool		bis_cur_rdlstate;
-	struct timer_list fsync_timer;
+	struct delayed_work fsync_work;
 	bool bfsync_processing;	/* 500ms Fsync timer is active or not */
 	u32	rate_record;
 	u32	rateCountDiffRecord;
diff --git a/drivers/staging/rtl8192u/r8192U_dm.c b/drivers/staging/rtl8192u/r8192U_dm.c
index 725bf5ca9e34..0fcfcaa6500b 100644
--- a/drivers/staging/rtl8192u/r8192U_dm.c
+++ b/drivers/staging/rtl8192u/r8192U_dm.c
@@ -2578,19 +2578,20 @@ static void dm_init_fsync(struct net_device *dev)
 	priv->ieee80211->fsync_seconddiff_ratethreshold = 200;
 	priv->ieee80211->fsync_state = Default_Fsync;
 	priv->framesyncMonitor = 1;	/* current default 0xc38 monitor on */
-	timer_setup(&priv->fsync_timer, dm_fsync_timer_callback, 0);
+	INIT_DELAYED_WORK(&priv->fsync_work, dm_fsync_work_callback);
 }
 
 static void dm_deInit_fsync(struct net_device *dev)
 {
 	struct r8192_priv *priv = ieee80211_priv(dev);
 
-	del_timer_sync(&priv->fsync_timer);
+	cancel_delayed_work_sync(&priv->fsync_work);
 }
 
-void dm_fsync_timer_callback(struct timer_list *t)
+void dm_fsync_work_callback(struct work_struct *work)
 {
-	struct r8192_priv *priv = from_timer(priv, t, fsync_timer);
+	struct r8192_priv *priv =
+	    container_of(work, struct r8192_priv, fsync_work.work);
 	struct net_device *dev = priv->ieee80211->dev;
 	u32 rate_index, rate_count = 0, rate_count_diff = 0;
 	bool		bSwitchFromCountDiff = false;
@@ -2657,17 +2658,16 @@ void dm_fsync_timer_callback(struct timer_list *t)
 			}
 		}
 		if (bDoubleTimeInterval) {
-			if (timer_pending(&priv->fsync_timer))
-				del_timer_sync(&priv->fsync_timer);
-			priv->fsync_timer.expires = jiffies +
-				msecs_to_jiffies(priv->ieee80211->fsync_time_interval*priv->ieee80211->fsync_multiple_timeinterval);
-			add_timer(&priv->fsync_timer);
+			cancel_delayed_work_sync(&priv->fsync_work);
+			schedule_delayed_work(&priv->fsync_work,
+					      msecs_to_jiffies(priv
+					      ->ieee80211->fsync_time_interval *
+					      priv->ieee80211->fsync_multiple_timeinterval));
 		} else {
-			if (timer_pending(&priv->fsync_timer))
-				del_timer_sync(&priv->fsync_timer);
-			priv->fsync_timer.expires = jiffies +
-				msecs_to_jiffies(priv->ieee80211->fsync_time_interval);
-			add_timer(&priv->fsync_timer);
+			cancel_delayed_work_sync(&priv->fsync_work);
+			schedule_delayed_work(&priv->fsync_work,
+					      msecs_to_jiffies(priv
+					      ->ieee80211->fsync_time_interval));
 		}
 	} else {
 		/* Let Register return to default value; */
@@ -2695,7 +2695,7 @@ static void dm_EndSWFsync(struct net_device *dev)
 	struct r8192_priv *priv = ieee80211_priv(dev);
 
 	RT_TRACE(COMP_HALDM, "%s\n", __func__);
-	del_timer_sync(&(priv->fsync_timer));
+	cancel_delayed_work_sync(&priv->fsync_work);
 
 	/* Let Register return to default value; */
 	if (priv->bswitch_fsync) {
@@ -2736,11 +2736,9 @@ static void dm_StartSWFsync(struct net_device *dev)
 		if (priv->ieee80211->fsync_rate_bitmap &  rateBitmap)
 			priv->rate_record += priv->stats.received_rate_histogram[1][rateIndex];
 	}
-	if (timer_pending(&priv->fsync_timer))
-		del_timer_sync(&priv->fsync_timer);
-	priv->fsync_timer.expires = jiffies +
-			msecs_to_jiffies(priv->ieee80211->fsync_time_interval);
-	add_timer(&priv->fsync_timer);
+	cancel_delayed_work_sync(&priv->fsync_work);
+	schedule_delayed_work(&priv->fsync_work,
+			      msecs_to_jiffies(priv->ieee80211->fsync_time_interval));
 
 	write_nic_dword(dev, rOFDM0_RxDetector2, 0x465c12cd);
 }
diff --git a/drivers/staging/rtl8192u/r8192U_dm.h b/drivers/staging/rtl8192u/r8192U_dm.h
index 0b2a1c688597..2159018b4e38 100644
--- a/drivers/staging/rtl8192u/r8192U_dm.h
+++ b/drivers/staging/rtl8192u/r8192U_dm.h
@@ -166,7 +166,7 @@ void dm_force_tx_fw_info(struct net_device *dev,
 void dm_init_edca_turbo(struct net_device *dev);
 void dm_rf_operation_test_callback(unsigned long data);
 void dm_rf_pathcheck_workitemcallback(struct work_struct *work);
-void dm_fsync_timer_callback(struct timer_list *t);
+void dm_fsync_work_callback(struct work_struct *work);
 void dm_cck_txpower_adjust(struct net_device *dev, bool  binch14);
 void dm_shadow_init(struct net_device *dev);
 void dm_initialize_txpower_tracking(struct net_device *dev);
diff --git a/drivers/staging/rtl8712/rtl8712_cmd.c b/drivers/staging/rtl8712/rtl8712_cmd.c
index e9294e1ed06e..eacf5efa3430 100644
--- a/drivers/staging/rtl8712/rtl8712_cmd.c
+++ b/drivers/staging/rtl8712/rtl8712_cmd.c
@@ -117,34 +117,6 @@ static void r871x_internal_cmd_hdl(struct _adapter *padapter, u8 *pbuf)
 	kfree(pdrvcmd->pbuf);
 }
 
-static u8 read_macreg_hdl(struct _adapter *padapter, u8 *pbuf)
-{
-	void (*pcmd_callback)(struct _adapter *dev, struct cmd_obj	*pcmd);
-	struct cmd_obj *pcmd  = (struct cmd_obj *)pbuf;
-
-	/*  invoke cmd->callback function */
-	pcmd_callback = cmd_callback[pcmd->cmdcode].callback;
-	if (!pcmd_callback)
-		r8712_free_cmd_obj(pcmd);
-	else
-		pcmd_callback(padapter, pcmd);
-	return H2C_SUCCESS;
-}
-
-static u8 write_macreg_hdl(struct _adapter *padapter, u8 *pbuf)
-{
-	void (*pcmd_callback)(struct _adapter *dev, struct cmd_obj	*pcmd);
-	struct cmd_obj *pcmd  = (struct cmd_obj *)pbuf;
-
-	/*  invoke cmd->callback function */
-	pcmd_callback = cmd_callback[pcmd->cmdcode].callback;
-	if (!pcmd_callback)
-		r8712_free_cmd_obj(pcmd);
-	else
-		pcmd_callback(padapter, pcmd);
-	return H2C_SUCCESS;
-}
-
 static u8 read_bbreg_hdl(struct _adapter *padapter, u8 *pbuf)
 {
 	struct cmd_obj *pcmd  = (struct cmd_obj *)pbuf;
@@ -213,14 +185,6 @@ static struct cmd_obj *cmd_hdl_filter(struct _adapter *padapter,
 	pcmd_r = NULL;
 
 	switch (pcmd->cmdcode) {
-	case GEN_CMD_CODE(_Read_MACREG):
-		read_macreg_hdl(padapter, (u8 *)pcmd);
-		pcmd_r = pcmd;
-		break;
-	case GEN_CMD_CODE(_Write_MACREG):
-		write_macreg_hdl(padapter, (u8 *)pcmd);
-		pcmd_r = pcmd;
-		break;
 	case GEN_CMD_CODE(_Read_BBREG):
 		read_bbreg_hdl(padapter, (u8 *)pcmd);
 		break;
diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c
index 499fccba3d74..bd96ebb82c8e 100644
--- a/drivers/tee/tee_shm.c
+++ b/drivers/tee/tee_shm.c
@@ -9,6 +9,7 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/tee_drv.h>
+#include <linux/uaccess.h>
 #include <linux/uio.h>
 #include "tee_private.h"
 
@@ -222,6 +223,9 @@ struct tee_shm *tee_shm_register(struct tee_context *ctx, unsigned long addr,
 		goto err;
 	}
 
+	if (!access_ok((void __user *)addr, length))
+		return ERR_PTR(-EFAULT);
+
 	mutex_lock(&teedev->mutex);
 	shm->id = idr_alloc(&teedev->idr, shm, 1, 0, GFP_KERNEL);
 	mutex_unlock(&teedev->mutex);
diff --git a/drivers/thermal/thermal_sysfs.c b/drivers/thermal/thermal_sysfs.c
index 1c4aac8464a7..1e5a78131aba 100644
--- a/drivers/thermal/thermal_sysfs.c
+++ b/drivers/thermal/thermal_sysfs.c
@@ -813,12 +813,13 @@ static const struct attribute_group cooling_device_stats_attr_group = {
 
 static void cooling_device_stats_setup(struct thermal_cooling_device *cdev)
 {
+	const struct attribute_group *stats_attr_group = NULL;
 	struct cooling_dev_stats *stats;
 	unsigned long states;
 	int var;
 
 	if (cdev->ops->get_max_state(cdev, &states))
-		return;
+		goto out;
 
 	states++; /* Total number of states is highest state + 1 */
 
@@ -828,7 +829,7 @@ static void cooling_device_stats_setup(struct thermal_cooling_device *cdev)
 
 	stats = kzalloc(var, GFP_KERNEL);
 	if (!stats)
-		return;
+		goto out;
 
 	stats->time_in_state = (ktime_t *)(stats + 1);
 	stats->trans_table = (unsigned int *)(stats->time_in_state + states);
@@ -838,9 +839,12 @@ static void cooling_device_stats_setup(struct thermal_cooling_device *cdev)
 
 	spin_lock_init(&stats->lock);
 
+	stats_attr_group = &cooling_device_stats_attr_group;
+
+out:
 	/* Fill the empty slot left in cooling_device_attr_groups */
 	var = ARRAY_SIZE(cooling_device_attr_groups) - 2;
-	cooling_device_attr_groups[var] = &cooling_device_stats_attr_group;
+	cooling_device_attr_groups[var] = stats_attr_group;
 }
 
 static void cooling_device_stats_destroy(struct thermal_cooling_device *cdev)
diff --git a/drivers/thunderbolt/ctl.c b/drivers/thunderbolt/ctl.c
index 0fb5e04191e2..409ee1551a7c 100644
--- a/drivers/thunderbolt/ctl.c
+++ b/drivers/thunderbolt/ctl.c
@@ -408,7 +408,7 @@ static void tb_ctl_rx_submit(struct ctl_pkg *pkg)
 
 static int tb_async_error(const struct ctl_pkg *pkg)
 {
-	const struct cfg_error_pkg *error = (const struct cfg_error_pkg *)pkg;
+	const struct cfg_error_pkg *error = pkg->buffer;
 
 	if (pkg->frame.eof != TB_CFG_PKG_ERROR)
 		return false;
diff --git a/drivers/tty/goldfish.c b/drivers/tty/goldfish.c
index 0e32920af10d..7ca3cd8eb574 100644
--- a/drivers/tty/goldfish.c
+++ b/drivers/tty/goldfish.c
@@ -151,7 +151,7 @@ static irqreturn_t goldfish_tty_interrupt(int irq, void *dev_id)
 	address = (unsigned long)(void *)buf;
 	goldfish_tty_rw(qtty, address, count, 0);
 
-	tty_schedule_flip(&qtty->port);
+	tty_flip_buffer_push(&qtty->port);
 	return IRQ_HANDLED;
 }
 
diff --git a/drivers/tty/moxa.c b/drivers/tty/moxa.c
index bf17e90858b8..a29ec5a93839 100644
--- a/drivers/tty/moxa.c
+++ b/drivers/tty/moxa.c
@@ -1383,7 +1383,7 @@ static int moxa_poll_port(struct moxa_port *p, unsigned int handle,
 		if (inited && !tty_throttled(tty) &&
 				MoxaPortRxQueue(p) > 0) { /* RX */
 			MoxaPortReadData(p);
-			tty_schedule_flip(&p->port);
+			tty_flip_buffer_push(&p->port);
 		}
 	} else {
 		clear_bit(EMPTYWAIT, &p->statusflags);
@@ -1408,7 +1408,7 @@ static int moxa_poll_port(struct moxa_port *p, unsigned int handle,
 
 	if (tty && (intr & IntrBreak) && !I_IGNBRK(tty)) { /* BREAK */
 		tty_insert_flip_char(&p->port, 0, TTY_BREAK);
-		tty_schedule_flip(&p->port);
+		tty_flip_buffer_push(&p->port);
 	}
 
 	if (intr & IntrLine)
diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c
index 6734ef22c304..154697be11b0 100644
--- a/drivers/tty/n_gsm.c
+++ b/drivers/tty/n_gsm.c
@@ -137,6 +137,7 @@ struct gsm_dlci {
 	int retries;
 	/* Uplink tty if active */
 	struct tty_port port;	/* The tty bound to this DLCI if there is one */
+#define TX_SIZE		4096    /* Must be power of 2. */
 	struct kfifo fifo;	/* Queue fifo for the DLCI */
 	int adaption;		/* Adaption layer in use */
 	int prev_adaption;
@@ -221,7 +222,6 @@ struct gsm_mux {
 	int encoding;
 	u8 control;
 	u8 fcs;
-	u8 received_fcs;
 	u8 *txframe;			/* TX framing buffer */
 
 	/* Method for the receiver side */
@@ -235,6 +235,7 @@ struct gsm_mux {
 	struct gsm_dlci *dlci[NUM_DLCI];
 	int old_c_iflag;		/* termios c_iflag value before attach */
 	bool constipated;		/* Asked by remote to shut up */
+	bool has_devices;		/* Devices were registered */
 
 	spinlock_t tx_lock;
 	unsigned int tx_bytes;		/* TX data outstanding */
@@ -243,6 +244,7 @@ struct gsm_mux {
 	struct list_head tx_list;	/* Pending data packets */
 
 	/* Control messages */
+	struct timer_list kick_timer;	/* Kick TX queuing on timeout */
 	struct timer_list t2_timer;	/* Retransmit timer for commands */
 	int cretries;			/* Command retry counter */
 	struct gsm_control *pending_cmd;/* Our current pending command */
@@ -274,6 +276,10 @@ static DEFINE_SPINLOCK(gsm_mux_lock);
 
 static struct tty_driver *gsm_tty_driver;
 
+/* Save dlci open address */
+static int addr_open[256] = { 0 };
+/* Save dlci open count */
+static int addr_cnt;
 /*
  *	This section of the driver logic implements the GSM encodings
  *	both the basic and the 'advanced'. Reliable transport is not
@@ -368,6 +374,7 @@ static const u8 gsm_fcs8[256] = {
 #define GOOD_FCS	0xCF
 
 static int gsmld_output(struct gsm_mux *gsm, u8 *data, int len);
+static int gsm_modem_update(struct gsm_dlci *dlci, u8 brk);
 
 /**
  *	gsm_fcs_add	-	update FCS
@@ -419,6 +426,27 @@ static int gsm_read_ea(unsigned int *val, u8 c)
 }
 
 /**
+ *	gsm_read_ea_val	-	read a value until EA
+ *	@val: variable holding value
+ *	@data: buffer of data
+ *	@dlen: length of data
+ *
+ *	Processes an EA value. Updates the passed variable and
+ *	returns the processed data length.
+ */
+static unsigned int gsm_read_ea_val(unsigned int *val, const u8 *data, int dlen)
+{
+	unsigned int len = 0;
+
+	for (; dlen > 0; dlen--) {
+		len++;
+		if (gsm_read_ea(val, *data++))
+			break;
+	}
+	return len;
+}
+
+/**
  *	gsm_encode_modem	-	encode modem data bits
  *	@dlci: DLCI to encode from
  *
@@ -463,10 +491,72 @@ static void gsm_hex_dump_bytes(const char *fname, const u8 *data,
 }
 
 /**
+ *	gsm_register_devices	-	register all tty devices for a given mux index
+ *
+ *	@driver: the tty driver that describes the tty devices
+ *	@index:  the mux number is used to calculate the minor numbers of the
+ *	         ttys for this mux and may differ from the position in the
+ *	         mux array.
+ */
+static int gsm_register_devices(struct tty_driver *driver, unsigned int index)
+{
+	struct device *dev;
+	int i;
+	unsigned int base;
+
+	if (!driver || index >= MAX_MUX)
+		return -EINVAL;
+
+	base = index * NUM_DLCI; /* first minor for this index */
+	for (i = 1; i < NUM_DLCI; i++) {
+		/* Don't register device 0 - this is the control channel
+		 * and not a usable tty interface
+		 */
+		dev = tty_register_device(gsm_tty_driver, base + i, NULL);
+		if (IS_ERR(dev)) {
+			if (debug & 8)
+				pr_info("%s failed to register device minor %u",
+					__func__, base + i);
+			for (i--; i >= 1; i--)
+				tty_unregister_device(gsm_tty_driver, base + i);
+			return PTR_ERR(dev);
+		}
+	}
+
+	return 0;
+}
+
+/**
+ *	gsm_unregister_devices	-	unregister all tty devices for a given mux index
+ *
+ *	@driver: the tty driver that describes the tty devices
+ *	@index:  the mux number is used to calculate the minor numbers of the
+ *	         ttys for this mux and may differ from the position in the
+ *	         mux array.
+ */
+static void gsm_unregister_devices(struct tty_driver *driver,
+				   unsigned int index)
+{
+	int i;
+	unsigned int base;
+
+	if (!driver || index >= MAX_MUX)
+		return;
+
+	base = index * NUM_DLCI; /* first minor for this index */
+	for (i = 1; i < NUM_DLCI; i++) {
+		/* Don't unregister device 0 - this is the control
+		 * channel and not a usable tty interface
+		 */
+		tty_unregister_device(gsm_tty_driver, base + i);
+	}
+}
+
+/**
  *	gsm_print_packet	-	display a frame for debug
  *	@hdr: header to print before decode
  *	@addr: address EA from the frame
- *	@cr: C/R bit from the frame
+ *	@cr: C/R bit seen as initiator
  *	@control: control including PF bit
  *	@data: following data bytes
  *	@dlen: length of data
@@ -566,7 +656,7 @@ static int gsm_stuff_frame(const u8 *input, u8 *output, int len)
  *	gsm_send	-	send a control frame
  *	@gsm: our GSM mux
  *	@addr: address for control frame
- *	@cr: command/response bit
+ *	@cr: command/response bit seen as initiator
  *	@control:  control byte including PF bit
  *
  *	Format up and transmit a control frame. These do not go via the
@@ -581,11 +671,15 @@ static void gsm_send(struct gsm_mux *gsm, int addr, int cr, int control)
 	int len;
 	u8 cbuf[10];
 	u8 ibuf[3];
+	int ocr;
+
+	/* toggle C/R coding if not initiator */
+	ocr = cr ^ (gsm->initiator ? 0 : 1);
 
 	switch (gsm->encoding) {
 	case 0:
 		cbuf[0] = GSM0_SOF;
-		cbuf[1] = (addr << 2) | (cr << 1) | EA;
+		cbuf[1] = (addr << 2) | (ocr << 1) | EA;
 		cbuf[2] = control;
 		cbuf[3] = EA;	/* Length of data = 0 */
 		cbuf[4] = 0xFF - gsm_fcs_add_block(INIT_FCS, cbuf + 1, 3);
@@ -595,7 +689,7 @@ static void gsm_send(struct gsm_mux *gsm, int addr, int cr, int control)
 	case 1:
 	case 2:
 		/* Control frame + packing (but not frame stuffing) in mode 1 */
-		ibuf[0] = (addr << 2) | (cr << 1) | EA;
+		ibuf[0] = (addr << 2) | (ocr << 1) | EA;
 		ibuf[1] = control;
 		ibuf[2] = 0xFF - gsm_fcs_add_block(INIT_FCS, ibuf, 2);
 		/* Stuffing may double the size worst case */
@@ -674,6 +768,37 @@ static struct gsm_msg *gsm_data_alloc(struct gsm_mux *gsm, u8 addr, int len,
 }
 
 /**
+ *	gsm_is_flow_ctrl_msg	-	checks if flow control message
+ *	@msg: message to check
+ *
+ *	Returns true if the given message is a flow control command of the
+ *	control channel. False is returned in any other case.
+ */
+static bool gsm_is_flow_ctrl_msg(struct gsm_msg *msg)
+{
+	unsigned int cmd;
+
+	if (msg->addr > 0)
+		return false;
+
+	switch (msg->ctrl & ~PF) {
+	case UI:
+	case UIH:
+		cmd = 0;
+		if (gsm_read_ea_val(&cmd, msg->data + 2, msg->len - 2) < 1)
+			break;
+		switch (cmd & ~PF) {
+		case CMD_FCOFF:
+		case CMD_FCON:
+			return true;
+		}
+		break;
+	}
+
+	return false;
+}
+
+/**
  *	gsm_data_kick		-	poke the queue
  *	@gsm: GSM Mux
  *	@dlci: DLCI sending the data
@@ -692,7 +817,7 @@ static void gsm_data_kick(struct gsm_mux *gsm, struct gsm_dlci *dlci)
 	int len;
 
 	list_for_each_entry_safe(msg, nmsg, &gsm->tx_list, list) {
-		if (gsm->constipated && msg->addr)
+		if (gsm->constipated && !gsm_is_flow_ctrl_msg(msg))
 			continue;
 		if (gsm->encoding != 0) {
 			gsm->txframe[0] = GSM1_SOF;
@@ -778,6 +903,7 @@ static void __gsm_data_queue(struct gsm_dlci *dlci, struct gsm_msg *msg)
 	list_add_tail(&msg->list, &gsm->tx_list);
 	gsm->tx_bytes += msg->len;
 	gsm_data_kick(gsm, dlci);
+	mod_timer(&gsm->kick_timer, jiffies + 10 * gsm->t1 * HZ / 100);
 }
 
 /**
@@ -814,41 +940,48 @@ static int gsm_dlci_data_output(struct gsm_mux *gsm, struct gsm_dlci *dlci)
 {
 	struct gsm_msg *msg;
 	u8 *dp;
-	int len, total_size, size;
-	int h = dlci->adaption - 1;
+	int h, len, size;
 
-	total_size = 0;
-	while (1) {
-		len = kfifo_len(&dlci->fifo);
-		if (len == 0)
-			return total_size;
-
-		/* MTU/MRU count only the data bits */
-		if (len > gsm->mtu)
-			len = gsm->mtu;
-
-		size = len + h;
-
-		msg = gsm_data_alloc(gsm, dlci->addr, size, gsm->ftype);
-		/* FIXME: need a timer or something to kick this so it can't
-		   get stuck with no work outstanding and no buffer free */
-		if (msg == NULL)
-			return -ENOMEM;
-		dp = msg->data;
-		switch (dlci->adaption) {
-		case 1:	/* Unstructured */
-			break;
-		case 2:	/* Unstructed with modem bits.
-		Always one byte as we never send inline break data */
-			*dp++ = (gsm_encode_modem(dlci) << 1) | EA;
-			break;
-		}
-		WARN_ON(kfifo_out_locked(&dlci->fifo, dp , len, &dlci->lock) != len);
-		__gsm_data_queue(dlci, msg);
-		total_size += size;
+	/* for modem bits without break data */
+	h = ((dlci->adaption == 1) ? 0 : 1);
+
+	len = kfifo_len(&dlci->fifo);
+	if (len == 0)
+		return 0;
+
+	/* MTU/MRU count only the data bits but watch adaption mode */
+	if ((len + h) > gsm->mtu)
+		len = gsm->mtu - h;
+
+	size = len + h;
+
+	msg = gsm_data_alloc(gsm, dlci->addr, size, gsm->ftype);
+	if (!msg)
+		return -ENOMEM;
+	dp = msg->data;
+	switch (dlci->adaption) {
+	case 1: /* Unstructured */
+		break;
+	case 2: /* Unstructured with modem bits.
+		 * Always one byte as we never send inline break data
+		 */
+		*dp++ = (gsm_encode_modem(dlci) << 1) | EA;
+		break;
+	default:
+		pr_err("%s: unsupported adaption %d\n", __func__,
+		       dlci->adaption);
+		break;
 	}
+
+	WARN_ON(len != kfifo_out_locked(&dlci->fifo, dp, len,
+		&dlci->lock));
+
+	/* Notify upper layer about available send space. */
+	tty_port_tty_wakeup(&dlci->port);
+
+	__gsm_data_queue(dlci, msg);
 	/* Bytes of data we used up */
-	return total_size;
+	return size;
 }
 
 /**
@@ -899,9 +1032,6 @@ static int gsm_dlci_data_output_framed(struct gsm_mux *gsm,
 
 	size = len + overhead;
 	msg = gsm_data_alloc(gsm, dlci->addr, size, gsm->ftype);
-
-	/* FIXME: need a timer or something to kick this so it can't
-	   get stuck with no work outstanding and no buffer free */
 	if (msg == NULL) {
 		skb_queue_tail(&dlci->skb_list, dlci->skb);
 		dlci->skb = NULL;
@@ -925,6 +1055,66 @@ static int gsm_dlci_data_output_framed(struct gsm_mux *gsm,
 }
 
 /**
+ *	gsm_dlci_modem_output	-	try and push modem status out of a DLCI
+ *	@gsm: mux
+ *	@dlci: the DLCI to pull modem status from
+ *	@brk: break signal
+ *
+ *	Push an empty frame in to the transmit queue to update the modem status
+ *	bits and to transmit an optional break.
+ *
+ *	Caller must hold the tx_lock of the mux.
+ */
+
+static int gsm_dlci_modem_output(struct gsm_mux *gsm, struct gsm_dlci *dlci,
+				 u8 brk)
+{
+	u8 *dp = NULL;
+	struct gsm_msg *msg;
+	int size = 0;
+
+	/* for modem bits without break data */
+	switch (dlci->adaption) {
+	case 1: /* Unstructured */
+		break;
+	case 2: /* Unstructured with modem bits. */
+		size++;
+		if (brk > 0)
+			size++;
+		break;
+	default:
+		pr_err("%s: unsupported adaption %d\n", __func__,
+		       dlci->adaption);
+		return -EINVAL;
+	}
+
+	msg = gsm_data_alloc(gsm, dlci->addr, size, gsm->ftype);
+	if (!msg) {
+		pr_err("%s: gsm_data_alloc error", __func__);
+		return -ENOMEM;
+	}
+	dp = msg->data;
+	switch (dlci->adaption) {
+	case 1: /* Unstructured */
+		break;
+	case 2: /* Unstructured with modem bits. */
+		if (brk == 0) {
+			*dp++ = (gsm_encode_modem(dlci) << 1) | EA;
+		} else {
+			*dp++ = gsm_encode_modem(dlci) << 1;
+			*dp++ = (brk << 4) | 2 | EA; /* Length, Break, EA */
+		}
+		break;
+	default:
+		/* Handled above */
+		break;
+	}
+
+	__gsm_data_queue(dlci, msg);
+	return size;
+}
+
+/**
  *	gsm_dlci_data_sweep		-	look for data to send
  *	@gsm: the GSM mux
  *
@@ -937,9 +1127,9 @@ static int gsm_dlci_data_output_framed(struct gsm_mux *gsm,
  *	renegotiate DLCI priorities with optional stuff. Needs optimising.
  */
 
-static void gsm_dlci_data_sweep(struct gsm_mux *gsm)
+static int gsm_dlci_data_sweep(struct gsm_mux *gsm)
 {
-	int len;
+	int len, ret = 0;
 	/* Priority ordering: We should do priority with RR of the groups */
 	int i = 1;
 
@@ -962,7 +1152,11 @@ static void gsm_dlci_data_sweep(struct gsm_mux *gsm)
 		/* DLCI empty - try the next */
 		if (len == 0)
 			i++;
+		else
+			ret++;
 	}
+
+	return ret;
 }
 
 /**
@@ -1191,6 +1385,7 @@ static void gsm_control_rls(struct gsm_mux *gsm, const u8 *data, int clen)
 }
 
 static void gsm_dlci_begin_close(struct gsm_dlci *dlci);
+static void gsm_dlci_close(struct gsm_dlci *dlci);
 
 /**
  *	gsm_control_message	-	DLCI 0 control processing
@@ -1209,15 +1404,28 @@ static void gsm_control_message(struct gsm_mux *gsm, unsigned int command,
 {
 	u8 buf[1];
 	unsigned long flags;
+	struct gsm_dlci *dlci;
+	int i;
+	int address;
 
 	switch (command) {
 	case CMD_CLD: {
-		struct gsm_dlci *dlci = gsm->dlci[0];
+		if (addr_cnt > 0) {
+			for (i = 0; i < addr_cnt; i++) {
+				address = addr_open[i];
+				dlci = gsm->dlci[address];
+				gsm_dlci_close(dlci);
+				addr_open[i] = 0;
+			}
+		}
 		/* Modem wishes to close down */
+		dlci = gsm->dlci[0];
 		if (dlci) {
 			dlci->dead = true;
 			gsm->dead = true;
-			gsm_dlci_begin_close(dlci);
+			gsm_dlci_close(dlci);
+			addr_cnt = 0;
+			gsm_response(gsm, 0, UA|PF);
 		}
 		}
 		break;
@@ -1338,7 +1546,7 @@ static void gsm_control_retransmit(struct timer_list *t)
 	spin_lock_irqsave(&gsm->control_lock, flags);
 	ctrl = gsm->pending_cmd;
 	if (ctrl) {
-		if (gsm->cretries == 0) {
+		if (gsm->cretries == 0 || !gsm->dlci[0] || gsm->dlci[0]->dead) {
 			gsm->pending_cmd = NULL;
 			ctrl->error = -ETIMEDOUT;
 			ctrl->done = 1;
@@ -1441,6 +1649,8 @@ static void gsm_dlci_close(struct gsm_dlci *dlci)
 	if (debug & 8)
 		pr_debug("DLCI %d goes closed.\n", dlci->addr);
 	dlci->state = DLCI_CLOSED;
+	/* Prevent us from sending data before the link is up again */
+	dlci->constipated = true;
 	if (dlci->addr != 0) {
 		tty_port_tty_hangup(&dlci->port, false);
 		spin_lock_irqsave(&dlci->lock, flags);
@@ -1470,8 +1680,12 @@ static void gsm_dlci_open(struct gsm_dlci *dlci)
 	del_timer(&dlci->t1);
 	/* This will let a tty open continue */
 	dlci->state = DLCI_OPEN;
+	dlci->constipated = false;
 	if (debug & 8)
 		pr_debug("DLCI %d goes open.\n", dlci->addr);
+	/* Send current modem state */
+	if (dlci->addr)
+		gsm_modem_update(dlci, 0);
 	wake_up(&dlci->gsm->event);
 }
 
@@ -1497,8 +1711,8 @@ static void gsm_dlci_t1(struct timer_list *t)
 
 	switch (dlci->state) {
 	case DLCI_OPENING:
-		dlci->retries--;
 		if (dlci->retries) {
+			dlci->retries--;
 			gsm_command(dlci->gsm, dlci->addr, SABM|PF);
 			mod_timer(&dlci->t1, jiffies + gsm->t1 * HZ / 100);
 		} else if (!dlci->addr && gsm->control == (DM | PF)) {
@@ -1513,8 +1727,8 @@ static void gsm_dlci_t1(struct timer_list *t)
 
 		break;
 	case DLCI_CLOSING:
-		dlci->retries--;
 		if (dlci->retries) {
+			dlci->retries--;
 			gsm_command(dlci->gsm, dlci->addr, DISC|PF);
 			mod_timer(&dlci->t1, jiffies + gsm->t1 * HZ / 100);
 		} else
@@ -1548,6 +1762,25 @@ static void gsm_dlci_begin_open(struct gsm_dlci *dlci)
 }
 
 /**
+ *	gsm_dlci_set_opening	-	change state to opening
+ *	@dlci: DLCI to open
+ *
+ *	Change internal state to wait for DLCI open from initiator side.
+ *	We set off timers and responses upon reception of an SABM.
+ */
+static void gsm_dlci_set_opening(struct gsm_dlci *dlci)
+{
+	switch (dlci->state) {
+	case DLCI_CLOSED:
+	case DLCI_CLOSING:
+		dlci->state = DLCI_OPENING;
+		break;
+	default:
+		break;
+	}
+}
+
+/**
  *	gsm_dlci_begin_close	-	start channel open procedure
  *	@dlci: DLCI to open
  *
@@ -1656,6 +1889,30 @@ static void gsm_dlci_command(struct gsm_dlci *dlci, const u8 *data, int len)
 	}
 }
 
+/**
+ *	gsm_kick_timer	-	transmit if possible
+ *	@t: timer contained in our gsm object
+ *
+ *	Transmit data from DLCIs if the queue is empty. We can't rely on
+ *	a tty wakeup except when we filled the pipe so we need to fire off
+ *	new data ourselves in other cases.
+ */
+static void gsm_kick_timer(struct timer_list *t)
+{
+	struct gsm_mux *gsm = from_timer(gsm, t, kick_timer);
+	unsigned long flags;
+	int sent = 0;
+
+	spin_lock_irqsave(&gsm->tx_lock, flags);
+	/* If we have nothing running then we need to fire up */
+	if (gsm->tx_bytes < TX_THRESH_LO)
+		sent = gsm_dlci_data_sweep(gsm);
+	spin_unlock_irqrestore(&gsm->tx_lock, flags);
+
+	if (sent && debug & 4)
+		pr_info("%s TX queue stalled\n", __func__);
+}
+
 /*
  *	Allocate/Free DLCI channels
  */
@@ -1677,7 +1934,7 @@ static struct gsm_dlci *gsm_dlci_alloc(struct gsm_mux *gsm, int addr)
 		return NULL;
 	spin_lock_init(&dlci->lock);
 	mutex_init(&dlci->mutex);
-	if (kfifo_alloc(&dlci->fifo, 4096, GFP_KERNEL) < 0) {
+	if (kfifo_alloc(&dlci->fifo, TX_SIZE, GFP_KERNEL) < 0) {
 		kfree(dlci);
 		return NULL;
 	}
@@ -1690,10 +1947,13 @@ static struct gsm_dlci *gsm_dlci_alloc(struct gsm_mux *gsm, int addr)
 	dlci->addr = addr;
 	dlci->adaption = gsm->adaption;
 	dlci->state = DLCI_CLOSED;
-	if (addr)
+	if (addr) {
 		dlci->data = gsm_dlci_data;
-	else
+		/* Prevent us from sending data before the link is up */
+		dlci->constipated = true;
+	} else {
 		dlci->data = gsm_dlci_command;
+	}
 	gsm->dlci[addr] = dlci;
 	return dlci;
 }
@@ -1780,18 +2040,8 @@ static void gsm_queue(struct gsm_mux *gsm)
 	struct gsm_dlci *dlci;
 	u8 cr;
 	int address;
-	/* We have to sneak a look at the packet body to do the FCS.
-	   A somewhat layering violation in the spec */
+	int i, j, k, address_tmp;
 
-	if ((gsm->control & ~PF) == UI)
-		gsm->fcs = gsm_fcs_add_block(gsm->fcs, gsm->buf, gsm->len);
-	if (gsm->encoding == 0) {
-		/* WARNING: gsm->received_fcs is used for
-		gsm->encoding = 0 only.
-		In this case it contain the last piece of data
-		required to generate final CRC */
-		gsm->fcs = gsm_fcs_add(gsm->fcs, gsm->received_fcs);
-	}
 	if (gsm->fcs != GOOD_FCS) {
 		gsm->bad_fcs++;
 		if (debug & 4)
@@ -1803,10 +2053,10 @@ static void gsm_queue(struct gsm_mux *gsm)
 		goto invalid;
 
 	cr = gsm->address & 1;		/* C/R bit */
+	cr ^= gsm->initiator ? 0 : 1;	/* Flip so 1 always means command */
 
 	gsm_print_packet("<--", address, cr, gsm->control, gsm->buf, gsm->len);
 
-	cr ^= 1 - gsm->initiator;	/* Flip so 1 always means command */
 	dlci = gsm->dlci[address];
 
 	switch (gsm->control) {
@@ -1818,22 +2068,52 @@ static void gsm_queue(struct gsm_mux *gsm)
 		if (dlci == NULL)
 			return;
 		if (dlci->dead)
-			gsm_response(gsm, address, DM);
+			gsm_response(gsm, address, DM|PF);
 		else {
-			gsm_response(gsm, address, UA);
+			gsm_response(gsm, address, UA|PF);
 			gsm_dlci_open(dlci);
+			/* Save dlci open address */
+			if (address) {
+				addr_open[addr_cnt] = address;
+				addr_cnt++;
+			}
 		}
 		break;
 	case DISC|PF:
 		if (cr == 0)
 			goto invalid;
 		if (dlci == NULL || dlci->state == DLCI_CLOSED) {
-			gsm_response(gsm, address, DM);
+			gsm_response(gsm, address, DM|PF);
 			return;
 		}
 		/* Real close complete */
-		gsm_response(gsm, address, UA);
-		gsm_dlci_close(dlci);
+		if (!address) {
+			if (addr_cnt > 0) {
+				for (i = 0; i < addr_cnt; i++) {
+					address = addr_open[i];
+					dlci = gsm->dlci[address];
+					gsm_dlci_close(dlci);
+					addr_open[i] = 0;
+				}
+			}
+			dlci = gsm->dlci[0];
+			gsm_dlci_close(dlci);
+			addr_cnt = 0;
+			gsm_response(gsm, 0, UA|PF);
+		} else {
+			gsm_response(gsm, address, UA|PF);
+			gsm_dlci_close(dlci);
+			/* clear dlci address */
+			for (j = 0; j < addr_cnt; j++) {
+				address_tmp = addr_open[j];
+				if (address_tmp == address) {
+					for (k = j; k < addr_cnt; k++)
+						addr_open[k] = addr_open[k+1];
+				addr_cnt--;
+				break;
+				}
+			}
+		}
 		break;
 	case UA|PF:
 		if (cr == 0 || dlci == NULL)
@@ -1868,7 +2148,7 @@ static void gsm_queue(struct gsm_mux *gsm)
 			goto invalid;
 #endif
 		if (dlci == NULL || dlci->state != DLCI_OPEN) {
-			gsm_command(gsm, address, DM|PF);
+			gsm_response(gsm, address, DM|PF);
 			return;
 		}
 		dlci->data(dlci, gsm->buf, gsm->len);
@@ -1948,19 +2228,25 @@ static void gsm0_receive(struct gsm_mux *gsm, unsigned char c)
 		break;
 	case GSM_DATA:		/* Data */
 		gsm->buf[gsm->count++] = c;
-		if (gsm->count == gsm->len)
+		if (gsm->count == gsm->len) {
+			/* Calculate final FCS for UI frames over all data */
+			if ((gsm->control & ~PF) != UIH) {
+				gsm->fcs = gsm_fcs_add_block(gsm->fcs, gsm->buf,
+							     gsm->count);
+			}
 			gsm->state = GSM_FCS;
+		}
 		break;
 	case GSM_FCS:		/* FCS follows the packet */
-		gsm->received_fcs = c;
-		gsm_queue(gsm);
+		gsm->fcs = gsm_fcs_add(gsm->fcs, c);
 		gsm->state = GSM_SSOF;
 		break;
 	case GSM_SSOF:
-		if (c == GSM0_SOF) {
-			gsm->state = GSM_SEARCH;
-			break;
-		}
+		gsm->state = GSM_SEARCH;
+		if (c == GSM0_SOF)
+			gsm_queue(gsm);
+		else
+			gsm->bad_size++;
 		break;
 	default:
 		pr_debug("%s: unhandled state: %d\n", __func__, gsm->state);
@@ -1989,11 +2275,24 @@ static void gsm1_receive(struct gsm_mux *gsm, unsigned char c)
 		return;
 	}
 	if (c == GSM1_SOF) {
-		/* EOF is only valid in frame if we have got to the data state
-		   and received at least one byte (the FCS) */
-		if (gsm->state == GSM_DATA && gsm->count) {
-			/* Extract the FCS */
+		/* EOF is only valid in frame if we have got to the data state */
+		if (gsm->state == GSM_DATA) {
+			if (gsm->count < 1) {
+				/* Missing FSC */
+				gsm->malformed++;
+				gsm->state = GSM_START;
+				return;
+			}
+			/* Remove the FCS from data */
 			gsm->count--;
+			if ((gsm->control & ~PF) != UIH) {
+				/* Calculate final FCS for UI frames over all
+				 * data but FCS
+				 */
+				gsm->fcs = gsm_fcs_add_block(gsm->fcs, gsm->buf,
+							     gsm->count);
+			}
+			/* Add the FCS itself to test against GOOD_FCS */
 			gsm->fcs = gsm_fcs_add(gsm->fcs, gsm->buf[gsm->count]);
 			gsm->len = gsm->count;
 			gsm_queue(gsm);
@@ -2103,9 +2402,14 @@ static void gsm_cleanup_mux(struct gsm_mux *gsm, bool disc)
 	}
 
 	/* Finish outstanding timers, making sure they are done */
+	del_timer_sync(&gsm->kick_timer);
 	del_timer_sync(&gsm->t2_timer);
 
 	/* Free up any link layer users and finally the control channel */
+	if (gsm->has_devices) {
+		gsm_unregister_devices(gsm_tty_driver, gsm->num);
+		gsm->has_devices = false;
+	}
 	for (i = NUM_DLCI - 1; i >= 0; i--)
 		if (gsm->dlci[i])
 			gsm_dlci_release(gsm->dlci[i]);
@@ -2129,7 +2433,13 @@ static void gsm_cleanup_mux(struct gsm_mux *gsm, bool disc)
 static int gsm_activate_mux(struct gsm_mux *gsm)
 {
 	struct gsm_dlci *dlci;
+	int ret;
+
+	dlci = gsm_dlci_alloc(gsm, 0);
+	if (dlci == NULL)
+		return -ENOMEM;
 
+	timer_setup(&gsm->kick_timer, gsm_kick_timer, 0);
 	timer_setup(&gsm->t2_timer, gsm_control_retransmit, 0);
 	init_waitqueue_head(&gsm->event);
 	spin_lock_init(&gsm->control_lock);
@@ -2140,9 +2450,11 @@ static int gsm_activate_mux(struct gsm_mux *gsm)
 	else
 		gsm->receive = gsm1_receive;
 
-	dlci = gsm_dlci_alloc(gsm, 0);
-	if (dlci == NULL)
-		return -ENOMEM;
+	ret = gsm_register_devices(gsm_tty_driver, gsm->num);
+	if (ret)
+		return ret;
+
+	gsm->has_devices = true;
 	gsm->dead = false;		/* Tty opens are now permissible */
 	return 0;
 }
@@ -2402,39 +2714,14 @@ static int gsmld_output(struct gsm_mux *gsm, u8 *data, int len)
  *	will need moving to an ioctl path.
  */
 
-static int gsmld_attach_gsm(struct tty_struct *tty, struct gsm_mux *gsm)
+static void gsmld_attach_gsm(struct tty_struct *tty, struct gsm_mux *gsm)
 {
-	unsigned int base;
-	int ret, i;
-
 	gsm->tty = tty_kref_get(tty);
 	/* Turn off tty XON/XOFF handling to handle it explicitly. */
 	gsm->old_c_iflag = tty->termios.c_iflag;
 	tty->termios.c_iflag &= (IXON | IXOFF);
-	ret =  gsm_activate_mux(gsm);
-	if (ret != 0)
-		tty_kref_put(gsm->tty);
-	else {
-		/* Don't register device 0 - this is the control channel and not
-		   a usable tty interface */
-		base = mux_num_to_base(gsm); /* Base for this MUX */
-		for (i = 1; i < NUM_DLCI; i++) {
-			struct device *dev;
-
-			dev = tty_register_device(gsm_tty_driver,
-							base + i, NULL);
-			if (IS_ERR(dev)) {
-				for (i--; i >= 1; i--)
-					tty_unregister_device(gsm_tty_driver,
-								base + i);
-				return PTR_ERR(dev);
-			}
-		}
-	}
-	return ret;
 }
 
-
 /**
  *	gsmld_detach_gsm	-	stop doing 0710 mux
  *	@tty: tty attached to the mux
@@ -2445,12 +2732,7 @@ static int gsmld_attach_gsm(struct tty_struct *tty, struct gsm_mux *gsm)
 
 static void gsmld_detach_gsm(struct tty_struct *tty, struct gsm_mux *gsm)
 {
-	unsigned int base = mux_num_to_base(gsm); /* Base for this MUX */
-	int i;
-
 	WARN_ON(tty != gsm->tty);
-	for (i = 1; i < NUM_DLCI; i++)
-		tty_unregister_device(gsm_tty_driver, base + i);
 	/* Restore tty XON/XOFF handling. */
 	gsm->tty->termios.c_iflag = gsm->old_c_iflag;
 	tty_kref_put(gsm->tty);
@@ -2471,7 +2753,8 @@ static void gsmld_receive_buf(struct tty_struct *tty, const unsigned char *cp,
 			flags = *fp++;
 		switch (flags) {
 		case TTY_NORMAL:
-			gsm->receive(gsm, *cp);
+			if (gsm->receive)
+				gsm->receive(gsm, *cp);
 			break;
 		case TTY_OVERRUN:
 		case TTY_BREAK:
@@ -2542,7 +2825,6 @@ static void gsmld_close(struct tty_struct *tty)
 static int gsmld_open(struct tty_struct *tty)
 {
 	struct gsm_mux *gsm;
-	int ret;
 
 	if (tty->ops->write == NULL)
 		return -EINVAL;
@@ -2558,12 +2840,12 @@ static int gsmld_open(struct tty_struct *tty)
 	/* Attach the initial passive connection */
 	gsm->encoding = 1;
 
-	ret = gsmld_attach_gsm(tty, gsm);
-	if (ret != 0) {
-		gsm_cleanup_mux(gsm, false);
-		mux_put(gsm);
-	}
-	return ret;
+	gsmld_attach_gsm(tty, gsm);
+
+	timer_setup(&gsm->kick_timer, gsm_kick_timer, 0);
+	timer_setup(&gsm->t2_timer, gsm_control_retransmit, 0);
+
+	return 0;
 }
 
 /**
@@ -2631,11 +2913,24 @@ static ssize_t gsmld_read(struct tty_struct *tty, struct file *file,
 static ssize_t gsmld_write(struct tty_struct *tty, struct file *file,
 			   const unsigned char *buf, size_t nr)
 {
-	int space = tty_write_room(tty);
+	struct gsm_mux *gsm = tty->disc_data;
+	unsigned long flags;
+	int space;
+	int ret;
+
+	if (!gsm)
+		return -ENODEV;
+
+	ret = -ENOBUFS;
+	spin_lock_irqsave(&gsm->tx_lock, flags);
+	space = tty_write_room(tty);
 	if (space >= nr)
-		return tty->ops->write(tty, buf, nr);
-	set_bit(TTY_DO_WRITE_WAKEUP, &tty->flags);
-	return -ENOBUFS;
+		ret = tty->ops->write(tty, buf, nr);
+	else
+		set_bit(TTY_DO_WRITE_WAKEUP, &tty->flags);
+	spin_unlock_irqrestore(&gsm->tx_lock, flags);
+
+	return ret;
 }
 
 /**
@@ -2660,12 +2955,15 @@ static __poll_t gsmld_poll(struct tty_struct *tty, struct file *file,
 
 	poll_wait(file, &tty->read_wait, wait);
 	poll_wait(file, &tty->write_wait, wait);
+
+	if (gsm->dead)
+		mask |= EPOLLHUP;
 	if (tty_hung_up_p(file))
 		mask |= EPOLLHUP;
+	if (test_bit(TTY_OTHER_CLOSED, &tty->flags))
+		mask |= EPOLLHUP;
 	if (!tty_is_writelocked(tty) && tty_write_room(tty) > 0)
 		mask |= EPOLLOUT | EPOLLWRNORM;
-	if (gsm->dead)
-		mask |= EPOLLHUP;
 	return mask;
 }
 
@@ -2915,14 +3213,43 @@ static struct tty_ldisc_ops tty_ldisc_packet = {
  *	Virtual tty side
  */
 
-#define TX_SIZE		512
+/**
+ *	gsm_modem_upd_via_data	-	send modem bits via convergence layer
+ *	@dlci: channel
+ *	@brk: break signal
+ *
+ *	Send an empty frame to signal mobile state changes and to transmit the
+ *	break signal for adaption 2.
+ */
+
+static void gsm_modem_upd_via_data(struct gsm_dlci *dlci, u8 brk)
+{
+	struct gsm_mux *gsm = dlci->gsm;
+	unsigned long flags;
+
+	if (dlci->state != DLCI_OPEN || dlci->adaption != 2)
+		return;
+
+	spin_lock_irqsave(&gsm->tx_lock, flags);
+	gsm_dlci_modem_output(gsm, dlci, brk);
+	spin_unlock_irqrestore(&gsm->tx_lock, flags);
+}
+
+/**
+ *	gsm_modem_upd_via_msc	-	send modem bits via control frame
+ *	@dlci: channel
+ *	@brk: break signal
+ */
 
-static int gsmtty_modem_update(struct gsm_dlci *dlci, u8 brk)
+static int gsm_modem_upd_via_msc(struct gsm_dlci *dlci, u8 brk)
 {
 	u8 modembits[3];
 	struct gsm_control *ctrl;
 	int len = 2;
 
+	if (dlci->gsm->encoding != 0)
+		return 0;
+
 	modembits[0] = (dlci->addr << 2) | 2 | EA;  /* DLCI, Valid, EA */
 	if (!brk) {
 		modembits[1] = (gsm_encode_modem(dlci) << 1) | EA;
@@ -2937,6 +3264,27 @@ static int gsmtty_modem_update(struct gsm_dlci *dlci, u8 brk)
 	return gsm_control_wait(dlci->gsm, ctrl);
 }
 
+/**
+ *	gsm_modem_update	-	send modem status line state
+ *	@dlci: channel
+ *	@brk: break signal
+ */
+
+static int gsm_modem_update(struct gsm_dlci *dlci, u8 brk)
+{
+	if (dlci->adaption == 2) {
+		/* Send convergence layer type 2 empty data frame. */
+		gsm_modem_upd_via_data(dlci, brk);
+		return 0;
+	} else if (dlci->gsm->encoding == 0) {
+		/* Send as MSC control message. */
+		return gsm_modem_upd_via_msc(dlci, brk);
+	}
+
+	/* Modem status lines are not supported. */
+	return -EPROTONOSUPPORT;
+}
+
 static int gsm_carrier_raised(struct tty_port *port)
 {
 	struct gsm_dlci *dlci = container_of(port, struct gsm_dlci, port);
@@ -2969,7 +3317,7 @@ static void gsm_dtr_rts(struct tty_port *port, int onoff)
 		modem_tx &= ~(TIOCM_DTR | TIOCM_RTS);
 	if (modem_tx != dlci->modem_tx) {
 		dlci->modem_tx = modem_tx;
-		gsmtty_modem_update(dlci, 0);
+		gsm_modem_update(dlci, 0);
 	}
 }
 
@@ -3039,6 +3387,7 @@ static int gsmtty_open(struct tty_struct *tty, struct file *filp)
 {
 	struct gsm_dlci *dlci = tty->driver_data;
 	struct tty_port *port = &dlci->port;
+	struct gsm_mux *gsm = dlci->gsm;
 
 	port->count++;
 	tty_port_tty_set(port, tty);
@@ -3048,7 +3397,10 @@ static int gsmtty_open(struct tty_struct *tty, struct file *filp)
 	   a DM straight back. This is ok as that will have caused a hangup */
 	tty_port_set_initialized(port, 1);
 	/* Start sending off SABM messages */
-	gsm_dlci_begin_open(dlci);
+	if (gsm->initiator)
+		gsm_dlci_begin_open(dlci);
+	else
+		gsm_dlci_set_opening(dlci);
 	/* And wait for virtual carrier */
 	return tty_port_block_til_ready(port, tty, filp);
 }
@@ -3102,7 +3454,7 @@ static unsigned int gsmtty_write_room(struct tty_struct *tty)
 	struct gsm_dlci *dlci = tty->driver_data;
 	if (dlci->state == DLCI_CLOSED)
 		return 0;
-	return TX_SIZE - kfifo_len(&dlci->fifo);
+	return kfifo_avail(&dlci->fifo);
 }
 
 static unsigned int gsmtty_chars_in_buffer(struct tty_struct *tty)
@@ -3158,7 +3510,7 @@ static int gsmtty_tiocmset(struct tty_struct *tty,
 
 	if (modem_tx != dlci->modem_tx) {
 		dlci->modem_tx = modem_tx;
-		return gsmtty_modem_update(dlci, 0);
+		return gsm_modem_update(dlci, 0);
 	}
 	return 0;
 }
@@ -3219,7 +3571,7 @@ static void gsmtty_throttle(struct tty_struct *tty)
 		dlci->modem_tx &= ~TIOCM_RTS;
 	dlci->throttled = true;
 	/* Send an MSC with RTS cleared */
-	gsmtty_modem_update(dlci, 0);
+	gsm_modem_update(dlci, 0);
 }
 
 static void gsmtty_unthrottle(struct tty_struct *tty)
@@ -3231,7 +3583,7 @@ static void gsmtty_unthrottle(struct tty_struct *tty)
 		dlci->modem_tx |= TIOCM_RTS;
 	dlci->throttled = false;
 	/* Send an MSC with RTS set */
-	gsmtty_modem_update(dlci, 0);
+	gsm_modem_update(dlci, 0);
 }
 
 static int gsmtty_break_ctl(struct tty_struct *tty, int state)
@@ -3249,7 +3601,7 @@ static int gsmtty_break_ctl(struct tty_struct *tty, int state)
 		if (encode > 0x0F)
 			encode = 0x0F;	/* Best effort */
 	}
-	return gsmtty_modem_update(dlci, encode);
+	return gsm_modem_update(dlci, encode);
 }
 
 static void gsmtty_cleanup(struct tty_struct *tty)
diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c
index 74bfabe5b453..752dab3356d7 100644
--- a/drivers/tty/pty.c
+++ b/drivers/tty/pty.c
@@ -111,21 +111,11 @@ static void pty_unthrottle(struct tty_struct *tty)
 static int pty_write(struct tty_struct *tty, const unsigned char *buf, int c)
 {
 	struct tty_struct *to = tty->link;
-	unsigned long flags;
 
-	if (tty->flow.stopped)
+	if (tty->flow.stopped || !c)
 		return 0;
 
-	if (c > 0) {
-		spin_lock_irqsave(&to->port->lock, flags);
-		/* Stuff the data into the input queue of the other end */
-		c = tty_insert_flip_string(to->port, buf, c);
-		spin_unlock_irqrestore(&to->port->lock, flags);
-		/* And shovel */
-		if (c)
-			tty_flip_buffer_push(to->port);
-	}
-	return c;
+	return tty_insert_flip_string_and_push_buffer(to->port, buf, c);
 }
 
 /**
diff --git a/drivers/tty/serial/8250/8250.h b/drivers/tty/serial/8250/8250.h
index 6473361525d1..b3abc29aa927 100644
--- a/drivers/tty/serial/8250/8250.h
+++ b/drivers/tty/serial/8250/8250.h
@@ -17,6 +17,8 @@
 struct uart_8250_dma {
 	int (*tx_dma)(struct uart_8250_port *p);
 	int (*rx_dma)(struct uart_8250_port *p);
+	void (*prepare_tx_dma)(struct uart_8250_port *p);
+	void (*prepare_rx_dma)(struct uart_8250_port *p);
 
 	/* Filter function */
 	dma_filter_fn		fn;
@@ -120,6 +122,28 @@ static inline void serial_out(struct uart_8250_port *up, int offset, int value)
 	up->port.serial_out(&up->port, offset, value);
 }
 
+/*
+ * For the 16C950
+ */
+static void serial_icr_write(struct uart_8250_port *up, int offset, int value)
+{
+	serial_out(up, UART_SCR, offset);
+	serial_out(up, UART_ICR, value);
+}
+
+static unsigned int __maybe_unused serial_icr_read(struct uart_8250_port *up,
+						   int offset)
+{
+	unsigned int value;
+
+	serial_icr_write(up, UART_ACR, up->acr | UART_ACR_ICRRD);
+	serial_out(up, UART_SCR, offset);
+	value = serial_in(up, UART_ICR);
+	serial_icr_write(up, UART_ACR, up->acr);
+
+	return value;
+}
+
 void serial8250_clear_and_reinit_fifos(struct uart_8250_port *p);
 
 static inline int serial_dl_read(struct uart_8250_port *up)
@@ -309,6 +333,22 @@ extern int serial8250_rx_dma(struct uart_8250_port *);
 extern void serial8250_rx_dma_flush(struct uart_8250_port *);
 extern int serial8250_request_dma(struct uart_8250_port *);
 extern void serial8250_release_dma(struct uart_8250_port *);
+
+static inline void serial8250_do_prepare_tx_dma(struct uart_8250_port *p)
+{
+	struct uart_8250_dma *dma = p->dma;
+
+	if (dma->prepare_tx_dma)
+		dma->prepare_tx_dma(p);
+}
+
+static inline void serial8250_do_prepare_rx_dma(struct uart_8250_port *p)
+{
+	struct uart_8250_dma *dma = p->dma;
+
+	if (dma->prepare_rx_dma)
+		dma->prepare_rx_dma(p);
+}
 #else
 static inline int serial8250_tx_dma(struct uart_8250_port *p)
 {
diff --git a/drivers/tty/serial/8250/8250_bcm7271.c b/drivers/tty/serial/8250/8250_bcm7271.c
index 0877cf24f7de..711cf30e835a 100644
--- a/drivers/tty/serial/8250/8250_bcm7271.c
+++ b/drivers/tty/serial/8250/8250_bcm7271.c
@@ -1141,16 +1141,19 @@ static int __maybe_unused brcmuart_suspend(struct device *dev)
 	struct brcmuart_priv *priv = dev_get_drvdata(dev);
 	struct uart_8250_port *up = serial8250_get_port(priv->line);
 	struct uart_port *port = &up->port;
-
-	serial8250_suspend_port(priv->line);
-	clk_disable_unprepare(priv->baud_mux_clk);
+	unsigned long flags;
 
 	/*
 	 * This will prevent resume from enabling RTS before the
-	 *  baud rate has been resored.
+	 *  baud rate has been restored.
 	 */
+	spin_lock_irqsave(&port->lock, flags);
 	priv->saved_mctrl = port->mctrl;
-	port->mctrl = 0;
+	port->mctrl &= ~TIOCM_RTS;
+	spin_unlock_irqrestore(&port->lock, flags);
+
+	serial8250_suspend_port(priv->line);
+	clk_disable_unprepare(priv->baud_mux_clk);
 
 	return 0;
 }
@@ -1160,6 +1163,7 @@ static int __maybe_unused brcmuart_resume(struct device *dev)
 	struct brcmuart_priv *priv = dev_get_drvdata(dev);
 	struct uart_8250_port *up = serial8250_get_port(priv->line);
 	struct uart_port *port = &up->port;
+	unsigned long flags;
 	int ret;
 
 	ret = clk_prepare_enable(priv->baud_mux_clk);
@@ -1182,7 +1186,15 @@ static int __maybe_unused brcmuart_resume(struct device *dev)
 		start_rx_dma(serial8250_get_port(priv->line));
 	}
 	serial8250_resume_port(priv->line);
-	port->mctrl = priv->saved_mctrl;
+
+	if (priv->saved_mctrl & TIOCM_RTS) {
+		/* Restore RTS */
+		spin_lock_irqsave(&port->lock, flags);
+		port->mctrl |= TIOCM_RTS;
+		port->ops->set_mctrl(port, port->mctrl);
+		spin_unlock_irqrestore(&port->lock, flags);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index 1ce193daea7f..30b7890645ac 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -23,6 +23,7 @@
 #include <linux/sysrq.h>
 #include <linux/delay.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/tty.h>
 #include <linux/ratelimit.h>
 #include <linux/tty_flip.h>
@@ -561,6 +562,9 @@ serial8250_register_ports(struct uart_driver *drv, struct device *dev)
 
 		up->port.dev = dev;
 
+		if (uart_console_enabled(&up->port))
+			pm_runtime_get_sync(up->port.dev);
+
 		serial8250_apply_quirks(up);
 		uart_add_one_port(drv, &up->port);
 	}
diff --git a/drivers/tty/serial/8250/8250_dma.c b/drivers/tty/serial/8250/8250_dma.c
index b3c3f7e5851a..1bdc8d6432fe 100644
--- a/drivers/tty/serial/8250/8250_dma.c
+++ b/drivers/tty/serial/8250/8250_dma.c
@@ -86,6 +86,8 @@ int serial8250_tx_dma(struct uart_8250_port *p)
 
 	dma->tx_size = CIRC_CNT_TO_END(xmit->head, xmit->tail, UART_XMIT_SIZE);
 
+	serial8250_do_prepare_tx_dma(p);
+
 	desc = dmaengine_prep_slave_single(dma->txchan,
 					   dma->tx_addr + xmit->tail,
 					   dma->tx_size, DMA_MEM_TO_DEV,
@@ -123,6 +125,8 @@ int serial8250_rx_dma(struct uart_8250_port *p)
 	if (dma->rx_running)
 		return 0;
 
+	serial8250_do_prepare_rx_dma(p);
+
 	desc = dmaengine_prep_slave_single(dma->rxchan, dma->rx_addr,
 					   dma->rx_size, DMA_DEV_TO_MEM,
 					   DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c
index 49559731bbcf..ace221afeb03 100644
--- a/drivers/tty/serial/8250/8250_dw.c
+++ b/drivers/tty/serial/8250/8250_dw.c
@@ -124,12 +124,15 @@ static void dw8250_check_lcr(struct uart_port *p, int value)
 /* Returns once the transmitter is empty or we run out of retries */
 static void dw8250_tx_wait_empty(struct uart_port *p)
 {
+	struct uart_8250_port *up = up_to_u8250p(p);
 	unsigned int tries = 20000;
 	unsigned int delay_threshold = tries - 1000;
 	unsigned int lsr;
 
 	while (tries--) {
 		lsr = readb (p->membase + (UART_LSR << p->regshift));
+		up->lsr_saved_flags |= lsr & LSR_SAVE_FLAGS;
+
 		if (lsr & UART_LSR_TEMT)
 			break;
 
diff --git a/drivers/tty/serial/8250/8250_fsl.c b/drivers/tty/serial/8250/8250_fsl.c
index fc65a2293ce9..af74f82ad782 100644
--- a/drivers/tty/serial/8250/8250_fsl.c
+++ b/drivers/tty/serial/8250/8250_fsl.c
@@ -81,7 +81,7 @@ int fsl8250_handle_irq(struct uart_port *port)
 	if ((lsr & UART_LSR_THRE) && (up->ier & UART_IER_THRI))
 		serial8250_tx_chars(up);
 
-	up->lsr_saved_flags = orig_lsr;
+	up->lsr_saved_flags |= orig_lsr & UART_LSR_BI;
 
 	uart_unlock_and_check_sysrq_irqrestore(&up->port, flags);
 
diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index e7b9805903f4..a16743856fc7 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -11,6 +11,7 @@
 #include <linux/pci.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
+#include <linux/math.h>
 #include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/tty.h>
@@ -75,13 +76,12 @@ static int pci_default_setup(struct serial_private*,
 
 static void moan_device(const char *str, struct pci_dev *dev)
 {
-	dev_err(&dev->dev,
-	       "%s: %s\n"
+	pci_err(dev, "%s\n"
 	       "Please send the output of lspci -vv, this\n"
 	       "message (0x%04x,0x%04x,0x%04x,0x%04x), the\n"
 	       "manufacturer and name of serial board or\n"
 	       "modem board to <linux-serial@vger.kernel.org>.\n",
-	       pci_name(dev), str, dev->vendor, dev->device,
+	       str, dev->vendor, dev->device,
 	       dev->subsystem_vendor, dev->subsystem_device);
 }
 
@@ -238,7 +238,7 @@ static int pci_inteli960ni_init(struct pci_dev *dev)
 	/* is firmware started? */
 	pci_read_config_dword(dev, 0x44, &oldval);
 	if (oldval == 0x00001000L) { /* RESET value */
-		dev_dbg(&dev->dev, "Local i960 firmware missing\n");
+		pci_dbg(dev, "Local i960 firmware missing\n");
 		return -ENODEV;
 	}
 	return 0;
@@ -588,9 +588,8 @@ static int pci_timedia_probe(struct pci_dev *dev)
 	 * (0,2,3,5,6: serial only -- 7,8,9: serial + parallel)
 	 */
 	if ((dev->subsystem_device & 0x00f0) >= 0x70) {
-		dev_info(&dev->dev,
-			"ignoring Timedia subdevice %04x for parport_serial\n",
-			dev->subsystem_device);
+		pci_info(dev, "ignoring Timedia subdevice %04x for parport_serial\n",
+			 dev->subsystem_device);
 		return -ENODEV;
 	}
 
@@ -827,8 +826,7 @@ static int pci_netmos_9900_numports(struct pci_dev *dev)
 		if (sub_serports > 0)
 			return sub_serports;
 
-		dev_err(&dev->dev,
-			"NetMos/Mostech serial driver ignoring port on ambiguous config.\n");
+		pci_err(dev, "NetMos/Mostech serial driver ignoring port on ambiguous config.\n");
 		return 0;
 	}
 
@@ -897,18 +895,16 @@ static int pci_netmos_init(struct pci_dev *dev)
 /* enable IO_Space bit */
 #define ITE_887x_POSIO_ENABLE		(1 << 31)
 
+/* inta_addr are the configuration addresses of the ITE */
+static const short inta_addr[] = { 0x2a0, 0x2c0, 0x220, 0x240, 0x1e0, 0x200, 0x280 };
 static int pci_ite887x_init(struct pci_dev *dev)
 {
-	/* inta_addr are the configuration addresses of the ITE */
-	static const short inta_addr[] = { 0x2a0, 0x2c0, 0x220, 0x240, 0x1e0,
-							0x200, 0x280, 0 };
 	int ret, i, type;
 	struct resource *iobase = NULL;
 	u32 miscr, uartbar, ioport;
 
 	/* search for the base-ioport */
-	i = 0;
-	while (inta_addr[i] && iobase == NULL) {
+	for (i = 0; i < ARRAY_SIZE(inta_addr); i++) {
 		iobase = request_region(inta_addr[i], ITE_887x_IOSIZE,
 								"ite887x");
 		if (iobase != NULL) {
@@ -925,13 +921,11 @@ static int pci_ite887x_init(struct pci_dev *dev)
 				break;
 			}
 			release_region(iobase->start, ITE_887x_IOSIZE);
-			iobase = NULL;
 		}
-		i++;
 	}
 
-	if (!inta_addr[i]) {
-		dev_err(&dev->dev, "ite887x: could not find iobase\n");
+	if (i == ARRAY_SIZE(inta_addr)) {
+		pci_err(dev, "could not find iobase\n");
 		return -ENODEV;
 	}
 
@@ -1001,43 +995,29 @@ static void pci_ite887x_exit(struct pci_dev *dev)
 }
 
 /*
- * EndRun Technologies.
- * Determine the number of ports available on the device.
+ * Oxford Semiconductor Inc.
+ * Check if an OxSemi device is part of the Tornado range of devices.
  */
 #define PCI_VENDOR_ID_ENDRUN			0x7401
 #define PCI_DEVICE_ID_ENDRUN_1588	0xe100
 
-static int pci_endrun_init(struct pci_dev *dev)
+static bool pci_oxsemi_tornado_p(struct pci_dev *dev)
 {
-	u8 __iomem *p;
-	unsigned long deviceID;
-	unsigned int  number_uarts = 0;
+	/* OxSemi Tornado devices are all 0xCxxx */
+	if (dev->vendor == PCI_VENDOR_ID_OXSEMI &&
+	    (dev->device & 0xf000) != 0xc000)
+		return false;
 
-	/* EndRun device is all 0xexxx */
+	/* EndRun devices are all 0xExxx */
 	if (dev->vendor == PCI_VENDOR_ID_ENDRUN &&
-		(dev->device & 0xf000) != 0xe000)
-		return 0;
-
-	p = pci_iomap(dev, 0, 5);
-	if (p == NULL)
-		return -ENOMEM;
+	    (dev->device & 0xf000) != 0xe000)
+		return false;
 
-	deviceID = ioread32(p);
-	/* EndRun device */
-	if (deviceID == 0x07000200) {
-		number_uarts = ioread8(p + 4);
-		dev_dbg(&dev->dev,
-			"%d ports detected on EndRun PCI Express device\n",
-			number_uarts);
-	}
-	pci_iounmap(dev, p);
-	return number_uarts;
+	return true;
 }
 
 /*
- * Oxford Semiconductor Inc.
- * Check that device is part of the Tornado range of devices, then determine
- * the number of ports available on the device.
+ * Determine the number of ports available on a Tornado device.
  */
 static int pci_oxsemi_tornado_init(struct pci_dev *dev)
 {
@@ -1045,9 +1025,7 @@ static int pci_oxsemi_tornado_init(struct pci_dev *dev)
 	unsigned long deviceID;
 	unsigned int  number_uarts = 0;
 
-	/* OxSemi Tornado devices are all 0xCxxx */
-	if (dev->vendor == PCI_VENDOR_ID_OXSEMI &&
-	    (dev->device & 0xF000) != 0xC000)
+	if (!pci_oxsemi_tornado_p(dev))
 		return 0;
 
 	p = pci_iomap(dev, 0, 5);
@@ -1058,14 +1036,217 @@ static int pci_oxsemi_tornado_init(struct pci_dev *dev)
 	/* Tornado device */
 	if (deviceID == 0x07000200) {
 		number_uarts = ioread8(p + 4);
-		dev_dbg(&dev->dev,
-			"%d ports detected on Oxford PCI Express device\n",
-			number_uarts);
+		pci_dbg(dev, "%d ports detected on %s PCI Express device\n",
+			number_uarts,
+			dev->vendor == PCI_VENDOR_ID_ENDRUN ?
+			"EndRun" : "Oxford");
 	}
 	pci_iounmap(dev, p);
 	return number_uarts;
 }
 
+/* Tornado-specific constants for the TCR and CPR registers; see below.  */
+#define OXSEMI_TORNADO_TCR_MASK	0xf
+#define OXSEMI_TORNADO_CPR_MASK	0x1ff
+#define OXSEMI_TORNADO_CPR_MIN	0x008
+#define OXSEMI_TORNADO_CPR_DEF	0x10f
+
+/*
+ * Determine the oversampling rate, the clock prescaler, and the clock
+ * divisor for the requested baud rate.  The clock rate is 62.5 MHz,
+ * which is four times the baud base, and the prescaler increments in
+ * steps of 1/8.  Therefore to make calculations on integers we need
+ * to use a scaled clock rate, which is the baud base multiplied by 32
+ * (or our assumed UART clock rate multiplied by 2).
+ *
+ * The allowed oversampling rates are from 4 up to 16 inclusive (values
+ * from 0 to 3 inclusive map to 16).  Likewise the clock prescaler allows
+ * values between 1.000 and 63.875 inclusive (operation for values from
+ * 0.000 to 0.875 has not been specified).  The clock divisor is the usual
+ * unsigned 16-bit integer.
+ *
+ * For the most accurate baud rate we use a table of predetermined
+ * oversampling rates and clock prescalers that records all possible
+ * products of the two parameters in the range from 4 up to 255 inclusive,
+ * and additionally 335 for the 1500000bps rate, with the prescaler scaled
+ * by 8.  The table is sorted by the decreasing value of the oversampling
+ * rate and ties are resolved by sorting by the decreasing value of the
+ * product.  This way preference is given to higher oversampling rates.
+ *
+ * We iterate over the table and choose the product of an oversampling
+ * rate and a clock prescaler that gives the lowest integer division
+ * result deviation, or if an exact integer divider is found we stop
+ * looking for it right away.  We do some fixup if the resulting clock
+ * divisor required would be out of its unsigned 16-bit integer range.
+ *
+ * Finally we abuse the supposed fractional part returned to encode the
+ * 4-bit value of the oversampling rate and the 9-bit value of the clock
+ * prescaler which will end up in the TCR and CPR/CPR2 registers.
+ */
+static unsigned int pci_oxsemi_tornado_get_divisor(struct uart_port *port,
+						   unsigned int baud,
+						   unsigned int *frac)
+{
+	static u8 p[][2] = {
+		{ 16, 14, }, { 16, 13, }, { 16, 12, }, { 16, 11, },
+		{ 16, 10, }, { 16,  9, }, { 16,  8, }, { 15, 17, },
+		{ 15, 16, }, { 15, 15, }, { 15, 14, }, { 15, 13, },
+		{ 15, 12, }, { 15, 11, }, { 15, 10, }, { 15,  9, },
+		{ 15,  8, }, { 14, 18, }, { 14, 17, }, { 14, 14, },
+		{ 14, 13, }, { 14, 12, }, { 14, 11, }, { 14, 10, },
+		{ 14,  9, }, { 14,  8, }, { 13, 19, }, { 13, 18, },
+		{ 13, 17, }, { 13, 13, }, { 13, 12, }, { 13, 11, },
+		{ 13, 10, }, { 13,  9, }, { 13,  8, }, { 12, 19, },
+		{ 12, 18, }, { 12, 17, }, { 12, 11, }, { 12,  9, },
+		{ 12,  8, }, { 11, 23, }, { 11, 22, }, { 11, 21, },
+		{ 11, 20, }, { 11, 19, }, { 11, 18, }, { 11, 17, },
+		{ 11, 11, }, { 11, 10, }, { 11,  9, }, { 11,  8, },
+		{ 10, 25, }, { 10, 23, }, { 10, 20, }, { 10, 19, },
+		{ 10, 17, }, { 10, 10, }, { 10,  9, }, { 10,  8, },
+		{  9, 27, }, {  9, 23, }, {  9, 21, }, {  9, 19, },
+		{  9, 18, }, {  9, 17, }, {  9,  9, }, {  9,  8, },
+		{  8, 31, }, {  8, 29, }, {  8, 23, }, {  8, 19, },
+		{  8, 17, }, {  8,  8, }, {  7, 35, }, {  7, 31, },
+		{  7, 29, }, {  7, 25, }, {  7, 23, }, {  7, 21, },
+		{  7, 19, }, {  7, 17, }, {  7, 15, }, {  7, 14, },
+		{  7, 13, }, {  7, 12, }, {  7, 11, }, {  7, 10, },
+		{  7,  9, }, {  7,  8, }, {  6, 41, }, {  6, 37, },
+		{  6, 31, }, {  6, 29, }, {  6, 23, }, {  6, 19, },
+		{  6, 17, }, {  6, 13, }, {  6, 11, }, {  6, 10, },
+		{  6,  9, }, {  6,  8, }, {  5, 67, }, {  5, 47, },
+		{  5, 43, }, {  5, 41, }, {  5, 37, }, {  5, 31, },
+		{  5, 29, }, {  5, 25, }, {  5, 23, }, {  5, 19, },
+		{  5, 17, }, {  5, 15, }, {  5, 13, }, {  5, 11, },
+		{  5, 10, }, {  5,  9, }, {  5,  8, }, {  4, 61, },
+		{  4, 59, }, {  4, 53, }, {  4, 47, }, {  4, 43, },
+		{  4, 41, }, {  4, 37, }, {  4, 31, }, {  4, 29, },
+		{  4, 23, }, {  4, 19, }, {  4, 17, }, {  4, 13, },
+		{  4,  9, }, {  4,  8, },
+	};
+	/* Scale the quotient for comparison to get the fractional part.  */
+	const unsigned int quot_scale = 65536;
+	unsigned int sclk = port->uartclk * 2;
+	unsigned int sdiv = DIV_ROUND_CLOSEST(sclk, baud);
+	unsigned int best_squot;
+	unsigned int squot;
+	unsigned int quot;
+	u16 cpr;
+	u8 tcr;
+	int i;
+
+	/* Old custom speed handling.  */
+	if (baud == 38400 && (port->flags & UPF_SPD_MASK) == UPF_SPD_CUST) {
+		unsigned int cust_div = port->custom_divisor;
+
+		quot = cust_div & UART_DIV_MAX;
+		tcr = (cust_div >> 16) & OXSEMI_TORNADO_TCR_MASK;
+		cpr = (cust_div >> 20) & OXSEMI_TORNADO_CPR_MASK;
+		if (cpr < OXSEMI_TORNADO_CPR_MIN)
+			cpr = OXSEMI_TORNADO_CPR_DEF;
+	} else {
+		best_squot = quot_scale;
+		for (i = 0; i < ARRAY_SIZE(p); i++) {
+			unsigned int spre;
+			unsigned int srem;
+			u8 cp;
+			u8 tc;
+
+			tc = p[i][0];
+			cp = p[i][1];
+			spre = tc * cp;
+
+			srem = sdiv % spre;
+			if (srem > spre / 2)
+				srem = spre - srem;
+			squot = DIV_ROUND_CLOSEST(srem * quot_scale, spre);
+
+			if (srem == 0) {
+				tcr = tc;
+				cpr = cp;
+				quot = sdiv / spre;
+				break;
+			} else if (squot < best_squot) {
+				best_squot = squot;
+				tcr = tc;
+				cpr = cp;
+				quot = DIV_ROUND_CLOSEST(sdiv, spre);
+			}
+		}
+		while (tcr <= (OXSEMI_TORNADO_TCR_MASK + 1) >> 1 &&
+		       quot % 2 == 0) {
+			quot >>= 1;
+			tcr <<= 1;
+		}
+		while (quot > UART_DIV_MAX) {
+			if (tcr <= (OXSEMI_TORNADO_TCR_MASK + 1) >> 1) {
+				quot >>= 1;
+				tcr <<= 1;
+			} else if (cpr <= OXSEMI_TORNADO_CPR_MASK >> 1) {
+				quot >>= 1;
+				cpr <<= 1;
+			} else {
+				quot = quot * cpr / OXSEMI_TORNADO_CPR_MASK;
+				cpr = OXSEMI_TORNADO_CPR_MASK;
+			}
+		}
+	}
+
+	*frac = (cpr << 8) | (tcr & OXSEMI_TORNADO_TCR_MASK);
+	return quot;
+}
+
+/*
+ * Set the oversampling rate in the transmitter clock cycle register (TCR),
+ * the clock prescaler in the clock prescaler register (CPR and CPR2), and
+ * the clock divisor in the divisor latch (DLL and DLM).  Note that for
+ * backwards compatibility any write to CPR clears CPR2 and therefore CPR
+ * has to be written first, followed by CPR2, which occupies the location
+ * of CKS used with earlier UART designs.
+ */
+static void pci_oxsemi_tornado_set_divisor(struct uart_port *port,
+					   unsigned int baud,
+					   unsigned int quot,
+					   unsigned int quot_frac)
+{
+	struct uart_8250_port *up = up_to_u8250p(port);
+	u8 cpr2 = quot_frac >> 16;
+	u8 cpr = quot_frac >> 8;
+	u8 tcr = quot_frac;
+
+	serial_icr_write(up, UART_TCR, tcr);
+	serial_icr_write(up, UART_CPR, cpr);
+	serial_icr_write(up, UART_CKS, cpr2);
+	serial8250_do_set_divisor(port, baud, quot, 0);
+}
+
+/*
+ * For Tornado devices we force MCR[7] set for the Divide-by-M N/8 baud rate
+ * generator prescaler (CPR and CPR2).  Otherwise no prescaler would be used.
+ */
+static void pci_oxsemi_tornado_set_mctrl(struct uart_port *port,
+					 unsigned int mctrl)
+{
+	struct uart_8250_port *up = up_to_u8250p(port);
+
+	up->mcr |= UART_MCR_CLKSEL;
+	serial8250_do_set_mctrl(port, mctrl);
+}
+
+static int pci_oxsemi_tornado_setup(struct serial_private *priv,
+				    const struct pciserial_board *board,
+				    struct uart_8250_port *up, int idx)
+{
+	struct pci_dev *dev = priv->dev;
+
+	if (pci_oxsemi_tornado_p(dev)) {
+		up->port.get_divisor = pci_oxsemi_tornado_get_divisor;
+		up->port.set_divisor = pci_oxsemi_tornado_set_divisor;
+		up->port.set_mctrl = pci_oxsemi_tornado_set_mctrl;
+	}
+
+	return pci_default_setup(priv, board, up, idx);
+}
+
 static int pci_asix_setup(struct serial_private *priv,
 		  const struct pciserial_board *board,
 		  struct uart_8250_port *port, int idx)
@@ -1120,15 +1301,15 @@ static struct quatech_feature quatech_cards[] = {
 	{ 0, }
 };
 
-static int pci_quatech_amcc(u16 devid)
+static int pci_quatech_amcc(struct pci_dev *dev)
 {
 	struct quatech_feature *qf = &quatech_cards[0];
 	while (qf->devid) {
-		if (qf->devid == devid)
+		if (qf->devid == dev->device)
 			return qf->amcc;
 		qf++;
 	}
-	pr_err("quatech: unknown port type '0x%04X'.\n", devid);
+	pci_err(dev, "unknown port type '0x%04X'.\n", dev->device);
 	return 0;
 };
 
@@ -1291,7 +1472,7 @@ static int pci_quatech_rs422(struct uart_8250_port *port)
 
 static int pci_quatech_init(struct pci_dev *dev)
 {
-	if (pci_quatech_amcc(dev->device)) {
+	if (pci_quatech_amcc(dev)) {
 		unsigned long base = pci_resource_start(dev, 0);
 		if (base) {
 			u32 tmp;
@@ -1315,7 +1496,7 @@ static int pci_quatech_setup(struct serial_private *priv,
 	port->port.uartclk = pci_quatech_clock(port);
 	/* For now just warn about RS422 */
 	if (pci_quatech_rs422(port))
-		pr_warn("quatech: software control of RS422 features not currently supported.\n");
+		pci_warn(priv->dev, "software control of RS422 features not currently supported.\n");
 	return pci_default_setup(priv, board, port, idx);
 }
 
@@ -1529,7 +1710,7 @@ static int pci_fintek_setup(struct serial_private *priv,
 	/* Get the io address from configuration space */
 	pci_read_config_word(pdev, config_base + 4, &iobase);
 
-	dev_dbg(&pdev->dev, "%s: idx=%d iobase=0x%x", __func__, idx, iobase);
+	pci_dbg(pdev, "idx=%d iobase=0x%x", idx, iobase);
 
 	port->port.iotype = UPIO_PORT;
 	port->port.iobase = iobase;
@@ -1693,7 +1874,7 @@ static int skip_tx_en_setup(struct serial_private *priv,
 			struct uart_8250_port *port, int idx)
 {
 	port->port.quirks |= UPQ_NO_TXEN_TEST;
-	dev_dbg(&priv->dev->dev,
+	pci_dbg(priv->dev,
 		"serial8250: skipping TxEn test for device [%04x:%04x] subsystem [%04x:%04x]\n",
 		priv->dev->vendor, priv->dev->device,
 		priv->dev->subsystem_vendor, priv->dev->subsystem_device);
@@ -2517,7 +2698,7 @@ static struct pci_serial_quirk pci_serial_quirks[] = {
 		.device		= PCI_ANY_ID,
 		.subvendor	= PCI_ANY_ID,
 		.subdevice	= PCI_ANY_ID,
-		.init		= pci_endrun_init,
+		.init		= pci_oxsemi_tornado_init,
 		.setup		= pci_default_setup,
 	},
 	/*
@@ -2529,7 +2710,7 @@ static struct pci_serial_quirk pci_serial_quirks[] = {
 		.subvendor	= PCI_ANY_ID,
 		.subdevice	= PCI_ANY_ID,
 		.init		= pci_oxsemi_tornado_init,
-		.setup		= pci_default_setup,
+		.setup		= pci_oxsemi_tornado_setup,
 	},
 	{
 		.vendor		= PCI_VENDOR_ID_MAINPINE,
@@ -2537,7 +2718,7 @@ static struct pci_serial_quirk pci_serial_quirks[] = {
 		.subvendor	= PCI_ANY_ID,
 		.subdevice	= PCI_ANY_ID,
 		.init		= pci_oxsemi_tornado_init,
-		.setup		= pci_default_setup,
+		.setup		= pci_oxsemi_tornado_setup,
 	},
 	{
 		.vendor		= PCI_VENDOR_ID_DIGI,
@@ -2545,7 +2726,7 @@ static struct pci_serial_quirk pci_serial_quirks[] = {
 		.subvendor		= PCI_SUBVENDOR_ID_IBM,
 		.subdevice		= PCI_ANY_ID,
 		.init			= pci_oxsemi_tornado_init,
-		.setup		= pci_default_setup,
+		.setup		= pci_oxsemi_tornado_setup,
 	},
 	{
 		.vendor         = PCI_VENDOR_ID_INTEL,
@@ -2862,7 +3043,7 @@ enum pci_board_num_t {
 	pbn_b0_2_1843200,
 	pbn_b0_4_1843200,
 
-	pbn_b0_1_3906250,
+	pbn_b0_1_15625000,
 
 	pbn_b0_bt_1_115200,
 	pbn_b0_bt_2_115200,
@@ -2940,12 +3121,11 @@ enum pci_board_num_t {
 	pbn_panacom2,
 	pbn_panacom4,
 	pbn_plx_romulus,
-	pbn_endrun_2_3906250,
 	pbn_oxsemi,
-	pbn_oxsemi_1_3906250,
-	pbn_oxsemi_2_3906250,
-	pbn_oxsemi_4_3906250,
-	pbn_oxsemi_8_3906250,
+	pbn_oxsemi_1_15625000,
+	pbn_oxsemi_2_15625000,
+	pbn_oxsemi_4_15625000,
+	pbn_oxsemi_8_15625000,
 	pbn_intel_i960,
 	pbn_sgi_ioc3,
 	pbn_computone_4,
@@ -3092,10 +3272,10 @@ static struct pciserial_board pci_boards[] = {
 		.uart_offset	= 8,
 	},
 
-	[pbn_b0_1_3906250] = {
+	[pbn_b0_1_15625000] = {
 		.flags		= FL_BASE0,
 		.num_ports	= 1,
-		.base_baud	= 3906250,
+		.base_baud	= 15625000,
 		.uart_offset	= 8,
 	},
 
@@ -3467,20 +3647,6 @@ static struct pciserial_board pci_boards[] = {
 	},
 
 	/*
-	 * EndRun Technologies
-	* Uses the size of PCI Base region 0 to
-	* signal now many ports are available
-	* 2 port 952 Uart support
-	*/
-	[pbn_endrun_2_3906250] = {
-		.flags		= FL_BASE0,
-		.num_ports	= 2,
-		.base_baud	= 3906250,
-		.uart_offset	= 0x200,
-		.first_offset	= 0x1000,
-	},
-
-	/*
 	 * This board uses the size of PCI Base region 0 to
 	 * signal now many ports are available
 	 */
@@ -3490,31 +3656,31 @@ static struct pciserial_board pci_boards[] = {
 		.base_baud	= 115200,
 		.uart_offset	= 8,
 	},
-	[pbn_oxsemi_1_3906250] = {
+	[pbn_oxsemi_1_15625000] = {
 		.flags		= FL_BASE0,
 		.num_ports	= 1,
-		.base_baud	= 3906250,
+		.base_baud	= 15625000,
 		.uart_offset	= 0x200,
 		.first_offset	= 0x1000,
 	},
-	[pbn_oxsemi_2_3906250] = {
+	[pbn_oxsemi_2_15625000] = {
 		.flags		= FL_BASE0,
 		.num_ports	= 2,
-		.base_baud	= 3906250,
+		.base_baud	= 15625000,
 		.uart_offset	= 0x200,
 		.first_offset	= 0x1000,
 	},
-	[pbn_oxsemi_4_3906250] = {
+	[pbn_oxsemi_4_15625000] = {
 		.flags		= FL_BASE0,
 		.num_ports	= 4,
-		.base_baud	= 3906250,
+		.base_baud	= 15625000,
 		.uart_offset	= 0x200,
 		.first_offset	= 0x1000,
 	},
-	[pbn_oxsemi_8_3906250] = {
+	[pbn_oxsemi_8_15625000] = {
 		.flags		= FL_BASE0,
 		.num_ports	= 8,
-		.base_baud	= 3906250,
+		.base_baud	= 15625000,
 		.uart_offset	= 0x200,
 		.first_offset	= 0x1000,
 	},
@@ -4011,12 +4177,12 @@ pciserial_init_ports(struct pci_dev *dev, const struct pciserial_board *board)
 		uart.port.irq = 0;
 	} else {
 		if (pci_match_id(pci_use_msi, dev)) {
-			dev_dbg(&dev->dev, "Using MSI(-X) interrupts\n");
+			pci_dbg(dev, "Using MSI(-X) interrupts\n");
 			pci_set_master(dev);
 			uart.port.flags &= ~UPF_SHARE_IRQ;
 			rc = pci_alloc_irq_vectors(dev, 1, 1, PCI_IRQ_ALL_TYPES);
 		} else {
-			dev_dbg(&dev->dev, "Using legacy interrupts\n");
+			pci_dbg(dev, "Using legacy interrupts\n");
 			rc = pci_alloc_irq_vectors(dev, 1, 1, PCI_IRQ_LEGACY);
 		}
 		if (rc < 0) {
@@ -4034,12 +4200,12 @@ pciserial_init_ports(struct pci_dev *dev, const struct pciserial_board *board)
 		if (quirk->setup(priv, board, &uart, i))
 			break;
 
-		dev_dbg(&dev->dev, "Setup PCI port: port %lx, irq %d, type %d\n",
+		pci_dbg(dev, "Setup PCI port: port %lx, irq %d, type %d\n",
 			uart.port.iobase, uart.port.irq, uart.port.iotype);
 
 		priv->line[i] = serial8250_register_8250_port(&uart);
 		if (priv->line[i] < 0) {
-			dev_err(&dev->dev,
+			pci_err(dev,
 				"Couldn't register serial port %lx, irq %d, type %d, error %d\n",
 				uart.port.iobase, uart.port.irq,
 				uart.port.iotype, priv->line[i]);
@@ -4135,8 +4301,7 @@ pciserial_init_one(struct pci_dev *dev, const struct pci_device_id *ent)
 	}
 
 	if (ent->driver_data >= ARRAY_SIZE(pci_boards)) {
-		dev_err(&dev->dev, "invalid driver_data: %ld\n",
-			ent->driver_data);
+		pci_err(dev, "invalid driver_data: %ld\n", ent->driver_data);
 		return -EINVAL;
 	}
 
@@ -4219,7 +4384,7 @@ static int pciserial_resume_one(struct device *dev)
 		err = pci_enable_device(pdev);
 		/* FIXME: We cannot simply error out here */
 		if (err)
-			dev_err(dev, "Unable to re-enable ports, trying to continue.\n");
+			pci_err(pdev, "Unable to re-enable ports, trying to continue.\n");
 		pciserial_resume_ports(priv);
 	}
 	return 0;
@@ -4413,13 +4578,6 @@ static const struct pci_device_id serial_pci_tbl[] = {
 		0x10b5, 0x106a, 0, 0,
 		pbn_plx_romulus },
 	/*
-	* EndRun Technologies. PCI express device range.
-	*    EndRun PTP/1588 has 2 Native UARTs.
-	*/
-	{	PCI_VENDOR_ID_ENDRUN, PCI_DEVICE_ID_ENDRUN_1588,
-		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_endrun_2_3906250 },
-	/*
 	 * Quatech cards. These actually have configurable clocks but for
 	 * now we just use the default.
 	 *
@@ -4528,158 +4686,165 @@ static const struct pci_device_id serial_pci_tbl[] = {
 	 */
 	{	PCI_VENDOR_ID_OXSEMI, 0xc101,    /* OXPCIe952 1 Legacy UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_b0_1_3906250 },
+		pbn_b0_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc105,    /* OXPCIe952 1 Legacy UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_b0_1_3906250 },
+		pbn_b0_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc11b,    /* OXPCIe952 1 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc11f,    /* OXPCIe952 1 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc120,    /* OXPCIe952 1 Legacy UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_b0_1_3906250 },
+		pbn_b0_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc124,    /* OXPCIe952 1 Legacy UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_b0_1_3906250 },
+		pbn_b0_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc138,    /* OXPCIe952 1 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc13d,    /* OXPCIe952 1 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc140,    /* OXPCIe952 1 Legacy UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_b0_1_3906250 },
+		pbn_b0_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc141,    /* OXPCIe952 1 Legacy UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_b0_1_3906250 },
+		pbn_b0_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc144,    /* OXPCIe952 1 Legacy UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_b0_1_3906250 },
+		pbn_b0_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc145,    /* OXPCIe952 1 Legacy UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_b0_1_3906250 },
+		pbn_b0_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc158,    /* OXPCIe952 2 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_2_3906250 },
+		pbn_oxsemi_2_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc15d,    /* OXPCIe952 2 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_2_3906250 },
+		pbn_oxsemi_2_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc208,    /* OXPCIe954 4 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_4_3906250 },
+		pbn_oxsemi_4_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc20d,    /* OXPCIe954 4 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_4_3906250 },
+		pbn_oxsemi_4_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc308,    /* OXPCIe958 8 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_8_3906250 },
+		pbn_oxsemi_8_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc30d,    /* OXPCIe958 8 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_8_3906250 },
+		pbn_oxsemi_8_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc40b,    /* OXPCIe200 1 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc40f,    /* OXPCIe200 1 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc41b,    /* OXPCIe200 1 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc41f,    /* OXPCIe200 1 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc42b,    /* OXPCIe200 1 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc42f,    /* OXPCIe200 1 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc43b,    /* OXPCIe200 1 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc43f,    /* OXPCIe200 1 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc44b,    /* OXPCIe200 1 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc44f,    /* OXPCIe200 1 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc45b,    /* OXPCIe200 1 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc45f,    /* OXPCIe200 1 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc46b,    /* OXPCIe200 1 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc46f,    /* OXPCIe200 1 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc47b,    /* OXPCIe200 1 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc47f,    /* OXPCIe200 1 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc48b,    /* OXPCIe200 1 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc48f,    /* OXPCIe200 1 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc49b,    /* OXPCIe200 1 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc49f,    /* OXPCIe200 1 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc4ab,    /* OXPCIe200 1 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc4af,    /* OXPCIe200 1 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc4bb,    /* OXPCIe200 1 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc4bf,    /* OXPCIe200 1 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc4cb,    /* OXPCIe200 1 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	{	PCI_VENDOR_ID_OXSEMI, 0xc4cf,    /* OXPCIe200 1 Native UART */
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	/*
 	 * Mainpine Inc. IQ Express "Rev3" utilizing OxSemi Tornado
 	 */
 	{	PCI_VENDOR_ID_MAINPINE, 0x4000,	/* IQ Express 1 Port V.34 Super-G3 Fax */
 		PCI_VENDOR_ID_MAINPINE, 0x4001, 0, 0,
-		pbn_oxsemi_1_3906250 },
+		pbn_oxsemi_1_15625000 },
 	{	PCI_VENDOR_ID_MAINPINE, 0x4000,	/* IQ Express 2 Port V.34 Super-G3 Fax */
 		PCI_VENDOR_ID_MAINPINE, 0x4002, 0, 0,
-		pbn_oxsemi_2_3906250 },
+		pbn_oxsemi_2_15625000 },
 	{	PCI_VENDOR_ID_MAINPINE, 0x4000,	/* IQ Express 4 Port V.34 Super-G3 Fax */
 		PCI_VENDOR_ID_MAINPINE, 0x4004, 0, 0,
-		pbn_oxsemi_4_3906250 },
+		pbn_oxsemi_4_15625000 },
 	{	PCI_VENDOR_ID_MAINPINE, 0x4000,	/* IQ Express 8 Port V.34 Super-G3 Fax */
 		PCI_VENDOR_ID_MAINPINE, 0x4008, 0, 0,
-		pbn_oxsemi_8_3906250 },
+		pbn_oxsemi_8_15625000 },
 
 	/*
 	 * Digi/IBM PCIe 2-port Async EIA-232 Adapter utilizing OxSemi Tornado
 	 */
 	{	PCI_VENDOR_ID_DIGI, PCIE_DEVICE_ID_NEO_2_OX_IBM,
 		PCI_SUBVENDOR_ID_IBM, PCI_ANY_ID, 0, 0,
-		pbn_oxsemi_2_3906250 },
+		pbn_oxsemi_2_15625000 },
+	/*
+	 * EndRun Technologies. PCI express device range.
+	 * EndRun PTP/1588 has 2 Native UARTs utilizing OxSemi 952.
+	 */
+	{	PCI_VENDOR_ID_ENDRUN, PCI_DEVICE_ID_ENDRUN_1588,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_2_15625000 },
 
 	/*
 	 * SBS Technologies, Inc. P-Octal and PMC-OCTPRO cards,
@@ -5311,6 +5476,115 @@ static const struct pci_device_id serial_pci_tbl[] = {
 		0, 0,
 		pbn_b2_4_115200 },
 	/*
+	 * Brainboxes PX-101
+	 */
+	{	PCI_VENDOR_ID_INTASHIELD, 0x4005,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_b0_2_115200 },
+	{	PCI_VENDOR_ID_INTASHIELD, 0x4019,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_oxsemi_2_15625000 },
+	/*
+	 * Brainboxes PX-235/246
+	 */
+	{	PCI_VENDOR_ID_INTASHIELD, 0x4004,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_b0_1_115200 },
+	{	PCI_VENDOR_ID_INTASHIELD, 0x4016,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_oxsemi_1_15625000 },
+	/*
+	 * Brainboxes PX-203/PX-257
+	 */
+	{	PCI_VENDOR_ID_INTASHIELD, 0x4006,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_b0_2_115200 },
+	{	PCI_VENDOR_ID_INTASHIELD, 0x4015,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_oxsemi_4_15625000 },
+	/*
+	 * Brainboxes PX-260/PX-701
+	 */
+	{	PCI_VENDOR_ID_INTASHIELD, 0x400A,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_oxsemi_4_15625000 },
+	/*
+	 * Brainboxes PX-310
+	 */
+	{	PCI_VENDOR_ID_INTASHIELD, 0x400E,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_oxsemi_2_15625000 },
+	/*
+	 * Brainboxes PX-313
+	 */
+	{	PCI_VENDOR_ID_INTASHIELD, 0x400C,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_oxsemi_2_15625000 },
+	/*
+	 * Brainboxes PX-320/324/PX-376/PX-387
+	 */
+	{	PCI_VENDOR_ID_INTASHIELD, 0x400B,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_oxsemi_1_15625000 },
+	/*
+	 * Brainboxes PX-335/346
+	 */
+	{	PCI_VENDOR_ID_INTASHIELD, 0x400F,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_oxsemi_4_15625000 },
+	/*
+	 * Brainboxes PX-368
+	 */
+	{       PCI_VENDOR_ID_INTASHIELD, 0x4010,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_oxsemi_4_15625000 },
+	/*
+	 * Brainboxes PX-420
+	 */
+	{	PCI_VENDOR_ID_INTASHIELD, 0x4000,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_b0_4_115200 },
+	{	PCI_VENDOR_ID_INTASHIELD, 0x4011,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_oxsemi_4_15625000 },
+	/*
+	 * Brainboxes PX-803
+	 */
+	{	PCI_VENDOR_ID_INTASHIELD, 0x4009,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_b0_1_115200 },
+	{	PCI_VENDOR_ID_INTASHIELD, 0x401E,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_oxsemi_1_15625000 },
+	/*
+	 * Brainboxes PX-846
+	 */
+	{	PCI_VENDOR_ID_INTASHIELD, 0x4008,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_b0_1_115200 },
+	{	PCI_VENDOR_ID_INTASHIELD, 0x4017,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_oxsemi_1_15625000 },
+
+	/*
 	 * Perle PCI-RAS cards
 	 */
 	{       PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_9030,
diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index df9731f73746..a5496bd1b650 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -538,27 +538,6 @@ serial_port_out_sync(struct uart_port *p, int offset, int value)
 }
 
 /*
- * For the 16C950
- */
-static void serial_icr_write(struct uart_8250_port *up, int offset, int value)
-{
-	serial_out(up, UART_SCR, offset);
-	serial_out(up, UART_ICR, value);
-}
-
-static unsigned int serial_icr_read(struct uart_8250_port *up, int offset)
-{
-	unsigned int value;
-
-	serial_icr_write(up, UART_ACR, up->acr | UART_ACR_ICRRD);
-	serial_out(up, UART_SCR, offset);
-	value = serial_in(up, UART_ICR);
-	serial_icr_write(up, UART_ACR, up->acr);
-
-	return value;
-}
-
-/*
  * FIFO support.
  */
 static void serial8250_clear_fifos(struct uart_8250_port *p)
@@ -2982,8 +2961,10 @@ static int serial8250_request_std_resource(struct uart_8250_port *up)
 	case UPIO_MEM32BE:
 	case UPIO_MEM16:
 	case UPIO_MEM:
-		if (!port->mapbase)
+		if (!port->mapbase) {
+			ret = -EINVAL;
 			break;
+		}
 
 		if (!request_mem_region(port->mapbase, size, "serial")) {
 			ret = -EBUSY;
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index 0e908061b5d7..300a8bbb4b80 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -1372,6 +1372,15 @@ static void pl011_stop_rx(struct uart_port *port)
 	pl011_dma_rx_stop(uap);
 }
 
+static void pl011_throttle_rx(struct uart_port *port)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&port->lock, flags);
+	pl011_stop_rx(port);
+	spin_unlock_irqrestore(&port->lock, flags);
+}
+
 static void pl011_enable_ms(struct uart_port *port)
 {
 	struct uart_amba_port *uap =
@@ -1793,9 +1802,10 @@ static int pl011_allocate_irq(struct uart_amba_port *uap)
  */
 static void pl011_enable_interrupts(struct uart_amba_port *uap)
 {
+	unsigned long flags;
 	unsigned int i;
 
-	spin_lock_irq(&uap->port.lock);
+	spin_lock_irqsave(&uap->port.lock, flags);
 
 	/* Clear out any spuriously appearing RX interrupts */
 	pl011_write(UART011_RTIS | UART011_RXIS, uap, REG_ICR);
@@ -1817,7 +1827,14 @@ static void pl011_enable_interrupts(struct uart_amba_port *uap)
 	if (!pl011_dma_rx_running(uap))
 		uap->im |= UART011_RXIM;
 	pl011_write(uap->im, uap, REG_IMSC);
-	spin_unlock_irq(&uap->port.lock);
+	spin_unlock_irqrestore(&uap->port.lock, flags);
+}
+
+static void pl011_unthrottle_rx(struct uart_port *port)
+{
+	struct uart_amba_port *uap = container_of(port, struct uart_amba_port, port);
+
+	pl011_enable_interrupts(uap);
 }
 
 static int pl011_startup(struct uart_port *port)
@@ -2245,6 +2262,8 @@ static const struct uart_ops amba_pl011_pops = {
 	.stop_tx	= pl011_stop_tx,
 	.start_tx	= pl011_start_tx,
 	.stop_rx	= pl011_stop_rx,
+	.throttle	= pl011_throttle_rx,
+	.unthrottle	= pl011_unthrottle_rx,
 	.enable_ms	= pl011_enable_ms,
 	.break_ctl	= pl011_break_ctl,
 	.startup	= pl011_startup,
diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index dd350c590880..c0a86558ceaa 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -295,20 +295,16 @@ static int atmel_config_rs485(struct uart_port *port,
 
 	mode = atmel_uart_readl(port, ATMEL_US_MR);
 
-	/* Resetting serial mode to RS232 (0x0) */
-	mode &= ~ATMEL_US_USMODE;
-
-	port->rs485 = *rs485conf;
-
 	if (rs485conf->flags & SER_RS485_ENABLED) {
 		dev_dbg(port->dev, "Setting UART to RS485\n");
-		if (port->rs485.flags & SER_RS485_RX_DURING_TX)
+		if (rs485conf->flags & SER_RS485_RX_DURING_TX)
 			atmel_port->tx_done_mask = ATMEL_US_TXRDY;
 		else
 			atmel_port->tx_done_mask = ATMEL_US_TXEMPTY;
 
 		atmel_uart_writel(port, ATMEL_US_TTGR,
 				  rs485conf->delay_rts_after_send);
+		mode &= ~ATMEL_US_USMODE;
 		mode |= ATMEL_US_USMODE_RS485;
 	} else {
 		dev_dbg(port->dev, "Setting UART to RS232\n");
diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c
index ef95abf3342c..dc7ccdb16de8 100644
--- a/drivers/tty/serial/fsl_lpuart.c
+++ b/drivers/tty/serial/fsl_lpuart.c
@@ -1500,9 +1500,9 @@ static int lpuart_config_rs485(struct uart_port *port,
 		 * Note: UART is assumed to be active high.
 		 */
 		if (rs485->flags & SER_RS485_RTS_ON_SEND)
-			modem &= ~UARTMODEM_TXRTSPOL;
-		else if (rs485->flags & SER_RS485_RTS_AFTER_SEND)
 			modem |= UARTMODEM_TXRTSPOL;
+		else if (rs485->flags & SER_RS485_RTS_AFTER_SEND)
+			modem &= ~UARTMODEM_TXRTSPOL;
 	}
 
 	/* Store the new configuration */
diff --git a/drivers/tty/serial/lpc32xx_hs.c b/drivers/tty/serial/lpc32xx_hs.c
index b199d7859961..07c4161eb4cc 100644
--- a/drivers/tty/serial/lpc32xx_hs.c
+++ b/drivers/tty/serial/lpc32xx_hs.c
@@ -341,7 +341,7 @@ static irqreturn_t serial_lpc32xx_interrupt(int irq, void *dev_id)
 		       LPC32XX_HSUART_IIR(port->membase));
 		port->icount.overrun++;
 		tty_insert_flip_char(tport, 0, TTY_OVERRUN);
-		tty_schedule_flip(tport);
+		tty_flip_buffer_push(tport);
 	}
 
 	/* Data received? */
diff --git a/drivers/tty/serial/mvebu-uart.c b/drivers/tty/serial/mvebu-uart.c
index ab226da75f7b..1074a0fdf7a1 100644
--- a/drivers/tty/serial/mvebu-uart.c
+++ b/drivers/tty/serial/mvebu-uart.c
@@ -237,6 +237,7 @@ static void mvebu_uart_rx_chars(struct uart_port *port, unsigned int status)
 	struct tty_port *tport = &port->state->port;
 	unsigned char ch = 0;
 	char flag = 0;
+	int ret;
 
 	do {
 		if (status & STAT_RX_RDY(port)) {
@@ -249,6 +250,16 @@ static void mvebu_uart_rx_chars(struct uart_port *port, unsigned int status)
 				port->icount.parity++;
 		}
 
+		/*
+		 * For UART2, error bits are not cleared on buffer read.
+		 * This causes interrupt loop and system hang.
+		 */
+		if (IS_EXTENDED(port) && (status & STAT_BRK_ERR)) {
+			ret = readl(port->membase + UART_STAT);
+			ret |= STAT_BRK_ERR;
+			writel(ret, port->membase + UART_STAT);
+		}
+
 		if (status & STAT_BRK_DET) {
 			port->icount.brk++;
 			status &= ~(STAT_FRM_ERR | STAT_PAR_ERR);
@@ -442,13 +453,13 @@ static void mvebu_uart_shutdown(struct uart_port *port)
 	}
 }
 
-static int mvebu_uart_baud_rate_set(struct uart_port *port, unsigned int baud)
+static unsigned int mvebu_uart_baud_rate_set(struct uart_port *port, unsigned int baud)
 {
 	unsigned int d_divisor, m_divisor;
 	u32 brdv, osamp;
 
 	if (!port->uartclk)
-		return -EOPNOTSUPP;
+		return 0;
 
 	/*
 	 * The baudrate is derived from the UART clock thanks to two divisors:
@@ -472,7 +483,7 @@ static int mvebu_uart_baud_rate_set(struct uart_port *port, unsigned int baud)
 	osamp &= ~OSAMP_DIVISORS_MASK;
 	writel(osamp, port->membase + UART_OSAMP);
 
-	return 0;
+	return DIV_ROUND_CLOSEST(port->uartclk, d_divisor * m_divisor);
 }
 
 static void mvebu_uart_set_termios(struct uart_port *port,
@@ -509,15 +520,11 @@ static void mvebu_uart_set_termios(struct uart_port *port,
 	max_baud = 230400;
 
 	baud = uart_get_baud_rate(port, termios, old, min_baud, max_baud);
-	if (mvebu_uart_baud_rate_set(port, baud)) {
-		/* No clock available, baudrate cannot be changed */
-		if (old)
-			baud = uart_get_baud_rate(port, old, NULL,
-						  min_baud, max_baud);
-	} else {
-		tty_termios_encode_baud_rate(termios, baud, baud);
-		uart_update_timeout(port, termios->c_cflag, baud);
-	}
+	baud = mvebu_uart_baud_rate_set(port, baud);
+
+	/* In case baudrate cannot be changed, report previous old value */
+	if (baud == 0 && old)
+		baud = tty_termios_baud_rate(old);
 
 	/* Only the following flag changes are supported */
 	if (old) {
@@ -528,6 +535,11 @@ static void mvebu_uart_set_termios(struct uart_port *port,
 		termios->c_cflag |= CS8;
 	}
 
+	if (baud != 0) {
+		tty_termios_encode_baud_rate(termios, baud, baud);
+		uart_update_timeout(port, termios->c_cflag, baud);
+	}
+
 	spin_unlock_irqrestore(&port->lock, flags);
 }
 
diff --git a/drivers/tty/serial/samsung_tty.c b/drivers/tty/serial/samsung_tty.c
index 319533b3c32a..f460b47ff6f2 100644
--- a/drivers/tty/serial/samsung_tty.c
+++ b/drivers/tty/serial/samsung_tty.c
@@ -378,8 +378,7 @@ static void enable_tx_dma(struct s3c24xx_uart_port *ourport)
 	/* Enable tx dma mode */
 	ucon = rd_regl(port, S3C2410_UCON);
 	ucon &= ~(S3C64XX_UCON_TXBURST_MASK | S3C64XX_UCON_TXMODE_MASK);
-	ucon |= (dma_get_cache_alignment() >= 16) ?
-		S3C64XX_UCON_TXBURST_16 : S3C64XX_UCON_TXBURST_1;
+	ucon |= S3C64XX_UCON_TXBURST_1;
 	ucon |= S3C64XX_UCON_TXMODE_DMA;
 	wr_regl(port,  S3C2410_UCON, ucon);
 
@@ -675,7 +674,7 @@ static void enable_rx_dma(struct s3c24xx_uart_port *ourport)
 			S3C64XX_UCON_DMASUS_EN |
 			S3C64XX_UCON_TIMEOUT_EN |
 			S3C64XX_UCON_RXMODE_MASK);
-	ucon |= S3C64XX_UCON_RXBURST_16 |
+	ucon |= S3C64XX_UCON_RXBURST_1 |
 			0xf << S3C64XX_UCON_TIMEOUT_SHIFT |
 			S3C64XX_UCON_EMPTYINT_EN |
 			S3C64XX_UCON_TIMEOUT_EN |
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 4d3ad4c6c60f..82ddbb92d07d 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -1912,11 +1912,6 @@ static int uart_proc_show(struct seq_file *m, void *v)
 }
 #endif
 
-static inline bool uart_console_enabled(struct uart_port *port)
-{
-	return uart_console(port) && (port->cons->flags & CON_ENABLED);
-}
-
 static void uart_port_spin_lock_init(struct uart_port *port)
 {
 	spin_lock_init(&port->lock);
diff --git a/drivers/tty/serial/stm32-usart.c b/drivers/tty/serial/stm32-usart.c
index 10e9f983de62..fc166cc2c856 100644
--- a/drivers/tty/serial/stm32-usart.c
+++ b/drivers/tty/serial/stm32-usart.c
@@ -71,6 +71,8 @@ static void stm32_usart_config_reg_rs485(u32 *cr1, u32 *cr3, u32 delay_ADE,
 	*cr3 |= USART_CR3_DEM;
 	over8 = *cr1 & USART_CR1_OVER8;
 
+	*cr1 &= ~(USART_CR1_DEDT_MASK | USART_CR1_DEAT_MASK);
+
 	if (over8)
 		rs485_deat_dedt = delay_ADE * baud * 8;
 	else
diff --git a/drivers/tty/serial/ucc_uart.c b/drivers/tty/serial/ucc_uart.c
index 6000853973c1..3cc9ef08455c 100644
--- a/drivers/tty/serial/ucc_uart.c
+++ b/drivers/tty/serial/ucc_uart.c
@@ -1137,6 +1137,8 @@ static unsigned int soc_info(unsigned int *rev_h, unsigned int *rev_l)
 		/* No compatible property, so try the name. */
 		soc_string = np->name;
 
+	of_node_put(np);
+
 	/* Extract the SOC number from the "PowerPC," string */
 	if ((sscanf(soc_string, "PowerPC,%u", &soc) != 1) || !soc)
 		return 0;
diff --git a/drivers/tty/tty.h b/drivers/tty/tty.h
index b710c5ef89ab..f310a8274df1 100644
--- a/drivers/tty/tty.h
+++ b/drivers/tty/tty.h
@@ -111,4 +111,7 @@ static inline void tty_audit_tiocsti(struct tty_struct *tty, char ch)
 
 ssize_t redirected_tty_write(struct kiocb *, struct iov_iter *);
 
+int tty_insert_flip_string_and_push_buffer(struct tty_port *port,
+		const unsigned char *chars, size_t cnt);
+
 #endif
diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c
index 6127f84b92b1..f3143ae4bf7f 100644
--- a/drivers/tty/tty_buffer.c
+++ b/drivers/tty/tty_buffer.c
@@ -403,27 +403,6 @@ int __tty_insert_flip_char(struct tty_port *port, unsigned char ch, char flag)
 EXPORT_SYMBOL(__tty_insert_flip_char);
 
 /**
- *	tty_schedule_flip	-	push characters to ldisc
- *	@port: tty port to push from
- *
- *	Takes any pending buffers and transfers their ownership to the
- *	ldisc side of the queue. It then schedules those characters for
- *	processing by the line discipline.
- */
-
-void tty_schedule_flip(struct tty_port *port)
-{
-	struct tty_bufhead *buf = &port->buf;
-
-	/* paired w/ acquire in flush_to_ldisc(); ensures
-	 * flush_to_ldisc() sees buffer data.
-	 */
-	smp_store_release(&buf->tail->commit, buf->tail->used);
-	queue_work(system_unbound_wq, &buf->work);
-}
-EXPORT_SYMBOL(tty_schedule_flip);
-
-/**
  *	tty_prepare_flip_string		-	make room for characters
  *	@port: tty port
  *	@chars: return pointer for character write area
@@ -554,6 +533,15 @@ static void flush_to_ldisc(struct work_struct *work)
 
 }
 
+static inline void tty_flip_buffer_commit(struct tty_buffer *tail)
+{
+	/*
+	 * Paired w/ acquire in flush_to_ldisc(); ensures flush_to_ldisc() sees
+	 * buffer data.
+	 */
+	smp_store_release(&tail->commit, tail->used);
+}
+
 /**
  *	tty_flip_buffer_push	-	terminal
  *	@port: tty port to push
@@ -567,11 +555,45 @@ static void flush_to_ldisc(struct work_struct *work)
 
 void tty_flip_buffer_push(struct tty_port *port)
 {
-	tty_schedule_flip(port);
+	struct tty_bufhead *buf = &port->buf;
+
+	tty_flip_buffer_commit(buf->tail);
+	queue_work(system_unbound_wq, &buf->work);
 }
 EXPORT_SYMBOL(tty_flip_buffer_push);
 
 /**
+ * tty_insert_flip_string_and_push_buffer - add characters to the tty buffer and
+ *	push
+ * @port: tty port
+ * @chars: characters
+ * @size: size
+ *
+ * The function combines tty_insert_flip_string() and tty_flip_buffer_push()
+ * with the exception of properly holding the @port->lock.
+ *
+ * To be used only internally (by pty currently).
+ *
+ * Returns: the number added.
+ */
+int tty_insert_flip_string_and_push_buffer(struct tty_port *port,
+		const unsigned char *chars, size_t size)
+{
+	struct tty_bufhead *buf = &port->buf;
+	unsigned long flags;
+
+	spin_lock_irqsave(&port->lock, flags);
+	size = tty_insert_flip_string(port, chars, size);
+	if (size)
+		tty_flip_buffer_commit(buf->tail);
+	spin_unlock_irqrestore(&port->lock, flags);
+
+	queue_work(system_unbound_wq, &buf->work);
+
+	return size;
+}
+
+/**
  *	tty_buffer_init		-	prepare a tty buffer structure
  *	@port: tty port to initialise
  *
diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c
index c7fbbcdcc346..3700cd057f27 100644
--- a/drivers/tty/vt/keyboard.c
+++ b/drivers/tty/vt/keyboard.c
@@ -324,13 +324,13 @@ int kbd_rate(struct kbd_repeat *rpt)
 static void put_queue(struct vc_data *vc, int ch)
 {
 	tty_insert_flip_char(&vc->port, ch, 0);
-	tty_schedule_flip(&vc->port);
+	tty_flip_buffer_push(&vc->port);
 }
 
 static void puts_queue(struct vc_data *vc, const char *cp)
 {
 	tty_insert_flip_string(&vc->port, cp, strlen(cp));
-	tty_schedule_flip(&vc->port);
+	tty_flip_buffer_push(&vc->port);
 }
 
 static void applkey(struct vc_data *vc, int key, char mode)
@@ -584,7 +584,7 @@ static void fn_inc_console(struct vc_data *vc)
 static void fn_send_intr(struct vc_data *vc)
 {
 	tty_insert_flip_char(&vc->port, 0, TTY_BREAK);
-	tty_schedule_flip(&vc->port);
+	tty_flip_buffer_push(&vc->port);
 }
 
 static void fn_scroll_forw(struct vc_data *vc)
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 7359c3e80d63..b8f5bc19416d 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -344,7 +344,7 @@ static struct uni_screen *vc_uniscr_alloc(unsigned int cols, unsigned int rows)
 	/* allocate everything in one go */
 	memsize = cols * rows * sizeof(char32_t);
 	memsize += rows * sizeof(char32_t *);
-	p = vmalloc(memsize);
+	p = vzalloc(memsize);
 	if (!p)
 		return NULL;
 
@@ -855,7 +855,7 @@ static void delete_char(struct vc_data *vc, unsigned int nr)
 	unsigned short *p = (unsigned short *) vc->vc_pos;
 
 	vc_uniscr_delete(vc, nr);
-	scr_memcpyw(p, p + nr, (vc->vc_cols - vc->state.x - nr) * 2);
+	scr_memmovew(p, p + nr, (vc->vc_cols - vc->state.x - nr) * 2);
 	scr_memsetw(p + vc->vc_cols - vc->state.x - nr, vc->vc_video_erase_char,
 			nr * 2);
 	vc->vc_need_wrap = 0;
@@ -1833,7 +1833,7 @@ static void csi_m(struct vc_data *vc)
 static void respond_string(const char *p, size_t len, struct tty_port *port)
 {
 	tty_insert_flip_string(port, p, len);
-	tty_schedule_flip(port);
+	tty_flip_buffer_push(port);
 }
 
 static void cursor_report(struct vc_data *vc, struct tty_struct *tty)
@@ -4662,9 +4662,11 @@ static int con_font_set(struct vc_data *vc, struct console_font_op *op)
 	console_lock();
 	if (vc->vc_mode != KD_TEXT)
 		rc = -EINVAL;
-	else if (vc->vc_sw->con_font_set)
+	else if (vc->vc_sw->con_font_set) {
+		if (vc_is_sel(vc))
+			clear_selection();
 		rc = vc->vc_sw->con_font_set(vc, &font, op->flags);
-	else
+	} else
 		rc = -ENOSYS;
 	console_unlock();
 	kfree(font.data);
@@ -4691,9 +4693,11 @@ static int con_font_default(struct vc_data *vc, struct console_font_op *op)
 		console_unlock();
 		return -EINVAL;
 	}
-	if (vc->vc_sw->con_font_default)
+	if (vc->vc_sw->con_font_default) {
+		if (vc_is_sel(vc))
+			clear_selection();
 		rc = vc->vc_sw->con_font_default(vc, &font, s);
-	else
+	} else
 		rc = -ENOSYS;
 	console_unlock();
 	if (!rc) {
diff --git a/drivers/usb/cdns3/cdns3-gadget.c b/drivers/usb/cdns3/cdns3-gadget.c
index c8d3894a121d..1802f6818e63 100644
--- a/drivers/usb/cdns3/cdns3-gadget.c
+++ b/drivers/usb/cdns3/cdns3-gadget.c
@@ -625,9 +625,9 @@ static void cdns3_wa2_remove_old_request(struct cdns3_endpoint *priv_ep)
 		trace_cdns3_wa2(priv_ep, "removes eldest request");
 
 		kfree(priv_req->request.buf);
+		list_del_init(&priv_req->list);
 		cdns3_gadget_ep_free_request(&priv_ep->endpoint,
 					     &priv_req->request);
-		list_del_init(&priv_req->list);
 		--priv_ep->wa2_counter;
 
 		if (!chain)
@@ -1530,7 +1530,8 @@ static void cdns3_transfer_completed(struct cdns3_device *priv_dev,
 						TRB_LEN(le32_to_cpu(trb->length));
 
 				if (priv_req->num_of_trb > 1 &&
-					le32_to_cpu(trb->control) & TRB_SMM)
+					le32_to_cpu(trb->control) & TRB_SMM &&
+					le32_to_cpu(trb->control) & TRB_CHAIN)
 					transfer_end = true;
 
 				cdns3_ep_inc_deq(priv_ep);
@@ -1690,6 +1691,7 @@ static int cdns3_check_ep_interrupt_proceed(struct cdns3_endpoint *priv_ep)
 				ep_cfg &= ~EP_CFG_ENABLE;
 				writel(ep_cfg, &priv_dev->regs->ep_cfg);
 				priv_ep->flags &= ~EP_QUIRK_ISO_OUT_EN;
+				priv_ep->flags |= EP_UPDATE_EP_TRBADDR;
 			}
 			cdns3_transfer_completed(priv_dev, priv_ep);
 		} else if (!(priv_ep->flags & EP_STALLED) &&
@@ -2280,11 +2282,16 @@ static int cdns3_gadget_ep_enable(struct usb_ep *ep,
 	int ret = 0;
 	int val;
 
+	if (!ep) {
+		pr_debug("usbss: ep not configured?\n");
+		return -EINVAL;
+	}
+
 	priv_ep = ep_to_cdns3_ep(ep);
 	priv_dev = priv_ep->cdns3_dev;
 	comp_desc = priv_ep->endpoint.comp_desc;
 
-	if (!ep || !desc || desc->bDescriptorType != USB_DT_ENDPOINT) {
+	if (!desc || desc->bDescriptorType != USB_DT_ENDPOINT) {
 		dev_dbg(priv_dev->dev, "usbss: invalid parameters\n");
 		return -EINVAL;
 	}
@@ -2596,7 +2603,7 @@ int cdns3_gadget_ep_dequeue(struct usb_ep *ep,
 			    struct usb_request *request)
 {
 	struct cdns3_endpoint *priv_ep = ep_to_cdns3_ep(ep);
-	struct cdns3_device *priv_dev = priv_ep->cdns3_dev;
+	struct cdns3_device *priv_dev;
 	struct usb_request *req, *req_temp;
 	struct cdns3_request *priv_req;
 	struct cdns3_trb *link_trb;
@@ -2607,6 +2614,8 @@ int cdns3_gadget_ep_dequeue(struct usb_ep *ep,
 	if (!ep || !request || !ep->desc)
 		return -EINVAL;
 
+	priv_dev = priv_ep->cdns3_dev;
+
 	spin_lock_irqsave(&priv_dev->lock, flags);
 
 	priv_req = to_cdns3_request(request);
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 7b2e2420ecae..adc154b691d0 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1814,6 +1814,9 @@ static const struct usb_device_id acm_ids[] = {
 	{ USB_DEVICE(0x09d8, 0x0320), /* Elatec GmbH TWN3 */
 	.driver_info = NO_UNION_NORMAL, /* has misplaced union descriptor */
 	},
+	{ USB_DEVICE(0x0c26, 0x0020), /* Icom ICF3400 Serie */
+	.driver_info = NO_UNION_NORMAL, /* reports zero length descriptor */
+	},
 	{ USB_DEVICE(0x0ca6, 0xa050), /* Castles VEGA3000 */
 	.driver_info = NO_UNION_NORMAL, /* reports zero length descriptor */
 	},
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 9e28d715fa3b..6c5934dbe9b3 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -1691,7 +1691,6 @@ static void usb_giveback_urb_bh(struct tasklet_struct *t)
 
 	spin_lock_irq(&bh->lock);
 	bh->running = true;
- restart:
 	list_replace_init(&bh->head, &local_list);
 	spin_unlock_irq(&bh->lock);
 
@@ -1705,10 +1704,17 @@ static void usb_giveback_urb_bh(struct tasklet_struct *t)
 		bh->completing_ep = NULL;
 	}
 
-	/* check if there are new URBs to giveback */
+	/*
+	 * giveback new URBs next time to prevent this function
+	 * from not exiting for a long time.
+	 */
 	spin_lock_irq(&bh->lock);
-	if (!list_empty(&bh->head))
-		goto restart;
+	if (!list_empty(&bh->head)) {
+		if (bh->high_prio)
+			tasklet_hi_schedule(&bh->bh);
+		else
+			tasklet_schedule(&bh->bh);
+	}
 	bh->running = false;
 	spin_unlock_irq(&bh->lock);
 }
@@ -1737,7 +1743,7 @@ static void usb_giveback_urb_bh(struct tasklet_struct *t)
 void usb_hcd_giveback_urb(struct usb_hcd *hcd, struct urb *urb, int status)
 {
 	struct giveback_urb_bh *bh;
-	bool running, high_prio_bh;
+	bool running;
 
 	/* pass status to tasklet via unlinked */
 	if (likely(!urb->unlinked))
@@ -1748,13 +1754,10 @@ void usb_hcd_giveback_urb(struct usb_hcd *hcd, struct urb *urb, int status)
 		return;
 	}
 
-	if (usb_pipeisoc(urb->pipe) || usb_pipeint(urb->pipe)) {
+	if (usb_pipeisoc(urb->pipe) || usb_pipeint(urb->pipe))
 		bh = &hcd->high_prio_bh;
-		high_prio_bh = true;
-	} else {
+	else
 		bh = &hcd->low_prio_bh;
-		high_prio_bh = false;
-	}
 
 	spin_lock(&bh->lock);
 	list_add_tail(&urb->urb_list, &bh->head);
@@ -1763,7 +1766,7 @@ void usb_hcd_giveback_urb(struct usb_hcd *hcd, struct urb *urb, int status)
 
 	if (running)
 		;
-	else if (high_prio_bh)
+	else if (bh->high_prio)
 		tasklet_hi_schedule(&bh->bh);
 	else
 		tasklet_schedule(&bh->bh);
@@ -2959,6 +2962,7 @@ int usb_add_hcd(struct usb_hcd *hcd,
 
 	/* initialize tasklets */
 	init_giveback_urb_bh(&hcd->high_prio_bh);
+	hcd->high_prio_bh.high_prio = true;
 	init_giveback_urb_bh(&hcd->low_prio_bh);
 
 	/* enable irqs just before we start the controller,
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 292013bb35d5..7947147f7612 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -6044,6 +6044,11 @@ re_enumerate_no_bos:
  * the reset is over (using their post_reset method).
  *
  * Return: The same as for usb_reset_and_verify_device().
+ * However, if a reset is already in progress (for instance, if a
+ * driver doesn't have pre_ or post_reset() callbacks, and while
+ * being unbound or re-bound during the ongoing reset its disconnect()
+ * or probe() routine tries to perform a second, nested reset), the
+ * routine returns -EINPROGRESS.
  *
  * Note:
  * The caller must own the device lock.  For example, it's safe to use
@@ -6077,6 +6082,10 @@ int usb_reset_device(struct usb_device *udev)
 		return -EISDIR;
 	}
 
+	if (udev->reset_in_progress)
+		return -EINPROGRESS;
+	udev->reset_in_progress = 1;
+
 	port_dev = hub->ports[udev->portnum - 1];
 
 	/*
@@ -6141,6 +6150,7 @@ int usb_reset_device(struct usb_device *udev)
 
 	usb_autosuspend_device(udev);
 	memalloc_noio_restore(noio_flag);
+	udev->reset_in_progress = 0;
 	return ret;
 }
 EXPORT_SYMBOL_GPL(usb_reset_device);
diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c
index e1cebf581a4a..519bb82b00e8 100644
--- a/drivers/usb/dwc2/gadget.c
+++ b/drivers/usb/dwc2/gadget.c
@@ -3594,7 +3594,8 @@ void dwc2_hsotg_core_disconnect(struct dwc2_hsotg *hsotg)
 void dwc2_hsotg_core_connect(struct dwc2_hsotg *hsotg)
 {
 	/* remove the soft-disconnect and let's go */
-	dwc2_clear_bit(hsotg, DCTL, DCTL_SFTDISCON);
+	if (!hsotg->role_sw || (dwc2_readl(hsotg, GOTGCTL) & GOTGCTL_BSESVLD))
+		dwc2_clear_bit(hsotg, DCTL, DCTL_SFTDISCON);
 }
 
 /**
diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c
index c331a5128c2c..265d437ca0f1 100644
--- a/drivers/usb/dwc2/platform.c
+++ b/drivers/usb/dwc2/platform.c
@@ -154,9 +154,9 @@ static int __dwc2_lowlevel_hw_enable(struct dwc2_hsotg *hsotg)
 	} else if (hsotg->plat && hsotg->plat->phy_init) {
 		ret = hsotg->plat->phy_init(pdev, hsotg->plat->phy_type);
 	} else {
-		ret = phy_power_on(hsotg->phy);
+		ret = phy_init(hsotg->phy);
 		if (ret == 0)
-			ret = phy_init(hsotg->phy);
+			ret = phy_power_on(hsotg->phy);
 	}
 
 	return ret;
@@ -188,9 +188,9 @@ static int __dwc2_lowlevel_hw_disable(struct dwc2_hsotg *hsotg)
 	} else if (hsotg->plat && hsotg->plat->phy_exit) {
 		ret = hsotg->plat->phy_exit(pdev, hsotg->plat->phy_type);
 	} else {
-		ret = phy_exit(hsotg->phy);
+		ret = phy_power_off(hsotg->phy);
 		if (ret == 0)
-			ret = phy_power_off(hsotg->phy);
+			ret = phy_exit(hsotg->phy);
 	}
 	if (ret)
 		return ret;
diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index 6db965e388d0..3f4f46759c86 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -162,8 +162,13 @@ static void __dwc3_set_mode(struct work_struct *work)
 		break;
 	}
 
-	/* For DRD host or device mode only */
-	if (dwc->desired_dr_role != DWC3_GCTL_PRTCAP_OTG) {
+	/*
+	 * When current_dr_role is not set, there's no role switching.
+	 * Only perform GCTL.CoreSoftReset when there's DRD role switching.
+	 */
+	if (dwc->current_dr_role && ((DWC3_IP_IS(DWC3) ||
+			DWC3_VER_IS_PRIOR(DWC31, 190A)) &&
+			dwc->desired_dr_role != DWC3_GCTL_PRTCAP_OTG)) {
 		reg = dwc3_readl(dwc->regs, DWC3_GCTL);
 		reg |= DWC3_GCTL_CORESOFTRESET;
 		dwc3_writel(dwc->regs, DWC3_GCTL, reg);
@@ -789,15 +794,16 @@ static void dwc3_core_exit(struct dwc3 *dwc)
 {
 	dwc3_event_buffers_cleanup(dwc);
 
+	usb_phy_set_suspend(dwc->usb2_phy, 1);
+	usb_phy_set_suspend(dwc->usb3_phy, 1);
+	phy_power_off(dwc->usb2_generic_phy);
+	phy_power_off(dwc->usb3_generic_phy);
+
 	usb_phy_shutdown(dwc->usb2_phy);
 	usb_phy_shutdown(dwc->usb3_phy);
 	phy_exit(dwc->usb2_generic_phy);
 	phy_exit(dwc->usb3_generic_phy);
 
-	usb_phy_set_suspend(dwc->usb2_phy, 1);
-	usb_phy_set_suspend(dwc->usb3_phy, 1);
-	phy_power_off(dwc->usb2_generic_phy);
-	phy_power_off(dwc->usb3_generic_phy);
 	clk_bulk_disable_unprepare(dwc->num_clks, dwc->clks);
 	reset_control_assert(dwc->reset);
 
@@ -1822,16 +1828,16 @@ err5:
 	dwc3_debugfs_exit(dwc);
 	dwc3_event_buffers_cleanup(dwc);
 
-	usb_phy_shutdown(dwc->usb2_phy);
-	usb_phy_shutdown(dwc->usb3_phy);
-	phy_exit(dwc->usb2_generic_phy);
-	phy_exit(dwc->usb3_generic_phy);
-
 	usb_phy_set_suspend(dwc->usb2_phy, 1);
 	usb_phy_set_suspend(dwc->usb3_phy, 1);
 	phy_power_off(dwc->usb2_generic_phy);
 	phy_power_off(dwc->usb3_generic_phy);
 
+	usb_phy_shutdown(dwc->usb2_phy);
+	usb_phy_shutdown(dwc->usb3_phy);
+	phy_exit(dwc->usb2_generic_phy);
+	phy_exit(dwc->usb3_generic_phy);
+
 	dwc3_ulpi_exit(dwc);
 
 err4:
diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c
index 9c8887615701..c52f7b5b5ec0 100644
--- a/drivers/usb/dwc3/dwc3-pci.c
+++ b/drivers/usb/dwc3/dwc3-pci.c
@@ -43,6 +43,7 @@
 #define PCI_DEVICE_ID_INTEL_ADLP		0x51ee
 #define PCI_DEVICE_ID_INTEL_ADLM		0x54ee
 #define PCI_DEVICE_ID_INTEL_ADLS		0x7ae1
+#define PCI_DEVICE_ID_INTEL_RPL			0x460e
 #define PCI_DEVICE_ID_INTEL_RPLS		0x7a61
 #define PCI_DEVICE_ID_INTEL_MTLP		0x7ec1
 #define PCI_DEVICE_ID_INTEL_MTL			0x7e7e
@@ -420,6 +421,9 @@ static const struct pci_device_id dwc3_pci_id_table[] = {
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ADLS),
 	  (kernel_ulong_t) &dwc3_pci_intel_swnode, },
 
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_RPL),
+	  (kernel_ulong_t) &dwc3_pci_intel_swnode, },
+
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_RPLS),
 	  (kernel_ulong_t) &dwc3_pci_intel_swnode, },
 
diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c
index b81a9e1c1315..d0352daab012 100644
--- a/drivers/usb/dwc3/dwc3-qcom.c
+++ b/drivers/usb/dwc3/dwc3-qcom.c
@@ -296,6 +296,14 @@ static void dwc3_qcom_interconnect_exit(struct dwc3_qcom *qcom)
 	icc_put(qcom->icc_path_apps);
 }
 
+/* Only usable in contexts where the role can not change. */
+static bool dwc3_qcom_is_host(struct dwc3_qcom *qcom)
+{
+	struct dwc3 *dwc = platform_get_drvdata(qcom->dwc3);
+
+	return dwc->xhci;
+}
+
 static void dwc3_qcom_disable_interrupts(struct dwc3_qcom *qcom)
 {
 	if (qcom->hs_phy_irq) {
@@ -411,7 +419,11 @@ static irqreturn_t qcom_dwc3_resume_irq(int irq, void *data)
 	if (qcom->pm_suspended)
 		return IRQ_HANDLED;
 
-	if (dwc->xhci)
+	/*
+	 * This is safe as role switching is done from a freezable workqueue
+	 * and the wakeup interrupts are disabled as part of resume.
+	 */
+	if (dwc3_qcom_is_host(qcom))
 		pm_runtime_resume(&dwc->xhci->dev);
 
 	return IRQ_HANDLED;
@@ -443,9 +455,9 @@ static int dwc3_qcom_get_irq(struct platform_device *pdev,
 	int ret;
 
 	if (np)
-		ret = platform_get_irq_byname(pdev_irq, name);
+		ret = platform_get_irq_byname_optional(pdev_irq, name);
 	else
-		ret = platform_get_irq(pdev_irq, num);
+		ret = platform_get_irq_optional(pdev_irq, num);
 
 	return ret;
 }
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 11b3259e02ce..76111102ac77 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -1169,17 +1169,49 @@ static u32 dwc3_calc_trbs_left(struct dwc3_ep *dep)
 	return trbs_left;
 }
 
-static void __dwc3_prepare_one_trb(struct dwc3_ep *dep, struct dwc3_trb *trb,
-		dma_addr_t dma, unsigned int length, unsigned int chain,
-		unsigned int node, unsigned int stream_id,
-		unsigned int short_not_ok, unsigned int no_interrupt,
-		unsigned int is_last, bool must_interrupt)
+/**
+ * dwc3_prepare_one_trb - setup one TRB from one request
+ * @dep: endpoint for which this request is prepared
+ * @req: dwc3_request pointer
+ * @trb_length: buffer size of the TRB
+ * @chain: should this TRB be chained to the next?
+ * @node: only for isochronous endpoints. First TRB needs different type.
+ * @use_bounce_buffer: set to use bounce buffer
+ * @must_interrupt: set to interrupt on TRB completion
+ */
+static void dwc3_prepare_one_trb(struct dwc3_ep *dep,
+		struct dwc3_request *req, unsigned int trb_length,
+		unsigned int chain, unsigned int node, bool use_bounce_buffer,
+		bool must_interrupt)
 {
+	struct dwc3_trb		*trb;
+	dma_addr_t		dma;
+	unsigned int		stream_id = req->request.stream_id;
+	unsigned int		short_not_ok = req->request.short_not_ok;
+	unsigned int		no_interrupt = req->request.no_interrupt;
+	unsigned int		is_last = req->request.is_last;
 	struct dwc3		*dwc = dep->dwc;
 	struct usb_gadget	*gadget = dwc->gadget;
 	enum usb_device_speed	speed = gadget->speed;
 
-	trb->size = DWC3_TRB_SIZE_LENGTH(length);
+	if (use_bounce_buffer)
+		dma = dep->dwc->bounce_addr;
+	else if (req->request.num_sgs > 0)
+		dma = sg_dma_address(req->start_sg);
+	else
+		dma = req->request.dma;
+
+	trb = &dep->trb_pool[dep->trb_enqueue];
+
+	if (!req->trb) {
+		dwc3_gadget_move_started_request(req);
+		req->trb = trb;
+		req->trb_dma = dwc3_trb_dma_offset(dep, trb);
+	}
+
+	req->num_trbs++;
+
+	trb->size = DWC3_TRB_SIZE_LENGTH(trb_length);
 	trb->bpl = lower_32_bits(dma);
 	trb->bph = upper_32_bits(dma);
 
@@ -1219,10 +1251,10 @@ static void __dwc3_prepare_one_trb(struct dwc3_ep *dep, struct dwc3_trb *trb,
 				unsigned int mult = 2;
 				unsigned int maxp = usb_endpoint_maxp(ep->desc);
 
-				if (length <= (2 * maxp))
+				if (req->request.length <= (2 * maxp))
 					mult--;
 
-				if (length <= maxp)
+				if (req->request.length <= maxp)
 					mult--;
 
 				trb->size |= DWC3_TRB_SIZE_PCM1(mult);
@@ -1291,50 +1323,6 @@ static void __dwc3_prepare_one_trb(struct dwc3_ep *dep, struct dwc3_trb *trb,
 	trace_dwc3_prepare_trb(dep, trb);
 }
 
-/**
- * dwc3_prepare_one_trb - setup one TRB from one request
- * @dep: endpoint for which this request is prepared
- * @req: dwc3_request pointer
- * @trb_length: buffer size of the TRB
- * @chain: should this TRB be chained to the next?
- * @node: only for isochronous endpoints. First TRB needs different type.
- * @use_bounce_buffer: set to use bounce buffer
- * @must_interrupt: set to interrupt on TRB completion
- */
-static void dwc3_prepare_one_trb(struct dwc3_ep *dep,
-		struct dwc3_request *req, unsigned int trb_length,
-		unsigned int chain, unsigned int node, bool use_bounce_buffer,
-		bool must_interrupt)
-{
-	struct dwc3_trb		*trb;
-	dma_addr_t		dma;
-	unsigned int		stream_id = req->request.stream_id;
-	unsigned int		short_not_ok = req->request.short_not_ok;
-	unsigned int		no_interrupt = req->request.no_interrupt;
-	unsigned int		is_last = req->request.is_last;
-
-	if (use_bounce_buffer)
-		dma = dep->dwc->bounce_addr;
-	else if (req->request.num_sgs > 0)
-		dma = sg_dma_address(req->start_sg);
-	else
-		dma = req->request.dma;
-
-	trb = &dep->trb_pool[dep->trb_enqueue];
-
-	if (!req->trb) {
-		dwc3_gadget_move_started_request(req);
-		req->trb = trb;
-		req->trb_dma = dwc3_trb_dma_offset(dep, trb);
-	}
-
-	req->num_trbs++;
-
-	__dwc3_prepare_one_trb(dep, trb, dma, trb_length, chain, node,
-			stream_id, short_not_ok, no_interrupt, is_last,
-			must_interrupt);
-}
-
 static bool dwc3_needs_extra_trb(struct dwc3_ep *dep, struct dwc3_request *req)
 {
 	unsigned int maxp = usb_endpoint_maxp(dep->endpoint.desc);
@@ -4149,7 +4137,6 @@ static irqreturn_t dwc3_process_event_buf(struct dwc3_event_buffer *evt)
 	}
 
 	evt->count = 0;
-	evt->flags &= ~DWC3_EVENT_PENDING;
 	ret = IRQ_HANDLED;
 
 	/* Unmask interrupt */
@@ -4162,6 +4149,9 @@ static irqreturn_t dwc3_process_event_buf(struct dwc3_event_buffer *evt)
 		dwc3_writel(dwc->regs, DWC3_DEV_IMOD(0), dwc->imod_interval);
 	}
 
+	/* Keep the clearing of DWC3_EVENT_PENDING at the end */
+	evt->flags &= ~DWC3_EVENT_PENDING;
+
 	return ret;
 }
 
diff --git a/drivers/usb/dwc3/host.c b/drivers/usb/dwc3/host.c
index fddf8bf4037e..abccf84a4808 100644
--- a/drivers/usb/dwc3/host.c
+++ b/drivers/usb/dwc3/host.c
@@ -187,4 +187,5 @@ err:
 void dwc3_host_exit(struct dwc3 *dwc)
 {
 	platform_device_unregister(dwc->xhci);
+	dwc->xhci = NULL;
 }
diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c
index 5226a47b68fd..885a7f593d85 100644
--- a/drivers/usb/gadget/function/f_uac2.c
+++ b/drivers/usb/gadget/function/f_uac2.c
@@ -281,6 +281,12 @@ static struct usb_endpoint_descriptor ss_ep_int_desc = {
 	.bInterval = 4,
 };
 
+static struct usb_ss_ep_comp_descriptor ss_ep_int_desc_comp = {
+	.bLength = sizeof(ss_ep_int_desc_comp),
+	.bDescriptorType = USB_DT_SS_ENDPOINT_COMP,
+	.wBytesPerInterval = cpu_to_le16(6),
+};
+
 /* Audio Streaming OUT Interface - Alt0 */
 static struct usb_interface_descriptor std_as_out_if0_desc = {
 	.bLength = sizeof std_as_out_if0_desc,
@@ -594,7 +600,8 @@ static struct usb_descriptor_header *ss_audio_desc[] = {
 	(struct usb_descriptor_header *)&in_feature_unit_desc,
 	(struct usb_descriptor_header *)&io_out_ot_desc,
 
-  (struct usb_descriptor_header *)&ss_ep_int_desc,
+	(struct usb_descriptor_header *)&ss_ep_int_desc,
+	(struct usb_descriptor_header *)&ss_ep_int_desc_comp,
 
 	(struct usb_descriptor_header *)&std_as_out_if0_desc,
 	(struct usb_descriptor_header *)&std_as_out_if1_desc,
@@ -721,6 +728,7 @@ static void setup_headers(struct f_uac2_opts *opts,
 	struct usb_ss_ep_comp_descriptor *epout_desc_comp = NULL;
 	struct usb_ss_ep_comp_descriptor *epin_desc_comp = NULL;
 	struct usb_ss_ep_comp_descriptor *epin_fback_desc_comp = NULL;
+	struct usb_ss_ep_comp_descriptor *ep_int_desc_comp = NULL;
 	struct usb_endpoint_descriptor *epout_desc;
 	struct usb_endpoint_descriptor *epin_desc;
 	struct usb_endpoint_descriptor *epin_fback_desc;
@@ -748,6 +756,7 @@ static void setup_headers(struct f_uac2_opts *opts,
 		epin_fback_desc = &ss_epin_fback_desc;
 		epin_fback_desc_comp = &ss_epin_fback_desc_comp;
 		ep_int_desc = &ss_ep_int_desc;
+		ep_int_desc_comp = &ss_ep_int_desc_comp;
 	}
 
 	i = 0;
@@ -760,15 +769,15 @@ static void setup_headers(struct f_uac2_opts *opts,
 		headers[i++] = USBDHDR(&out_clk_src_desc);
 		headers[i++] = USBDHDR(&usb_out_it_desc);
 
-    if (FUOUT_EN(opts))
-      headers[i++] = USBDHDR(out_feature_unit_desc);
-  }
+		if (FUOUT_EN(opts))
+			headers[i++] = USBDHDR(out_feature_unit_desc);
+	}
 
 	if (EPIN_EN(opts)) {
 		headers[i++] = USBDHDR(&io_in_it_desc);
 
-    if (FUIN_EN(opts))
-      headers[i++] = USBDHDR(in_feature_unit_desc);
+		if (FUIN_EN(opts))
+			headers[i++] = USBDHDR(in_feature_unit_desc);
 
 		headers[i++] = USBDHDR(&usb_in_ot_desc);
 	}
@@ -776,10 +785,13 @@ static void setup_headers(struct f_uac2_opts *opts,
 	if (EPOUT_EN(opts))
 		headers[i++] = USBDHDR(&io_out_ot_desc);
 
-  if (FUOUT_EN(opts) || FUIN_EN(opts))
-      headers[i++] = USBDHDR(ep_int_desc);
+	if (FUOUT_EN(opts) || FUIN_EN(opts)) {
+		headers[i++] = USBDHDR(ep_int_desc);
+		if (ep_int_desc_comp)
+			headers[i++] = USBDHDR(ep_int_desc_comp);
+	}
 
-  if (EPOUT_EN(opts)) {
+	if (EPOUT_EN(opts)) {
 		headers[i++] = USBDHDR(&std_as_out_if0_desc);
 		headers[i++] = USBDHDR(&std_as_out_if1_desc);
 		headers[i++] = USBDHDR(&as_out_hdr_desc);
diff --git a/drivers/usb/gadget/function/storage_common.c b/drivers/usb/gadget/function/storage_common.c
index b859a158a414..e122050eebaf 100644
--- a/drivers/usb/gadget/function/storage_common.c
+++ b/drivers/usb/gadget/function/storage_common.c
@@ -294,8 +294,10 @@ EXPORT_SYMBOL_GPL(fsg_lun_fsync_sub);
 void store_cdrom_address(u8 *dest, int msf, u32 addr)
 {
 	if (msf) {
-		/* Convert to Minutes-Seconds-Frames */
-		addr >>= 2;		/* Convert to 2048-byte frames */
+		/*
+		 * Convert to Minutes-Seconds-Frames.
+		 * Sector size is already set to 2048 bytes.
+		 */
 		addr += 2*75;		/* Lead-in occupies 2 seconds */
 		dest[3] = addr % 75;	/* Frames */
 		addr /= 75;
diff --git a/drivers/usb/gadget/function/uvc_queue.c b/drivers/usb/gadget/function/uvc_queue.c
index 99dc9adf56ef..a64b842665b9 100644
--- a/drivers/usb/gadget/function/uvc_queue.c
+++ b/drivers/usb/gadget/function/uvc_queue.c
@@ -44,7 +44,8 @@ static int uvc_queue_setup(struct vb2_queue *vq,
 {
 	struct uvc_video_queue *queue = vb2_get_drv_priv(vq);
 	struct uvc_video *video = container_of(queue, struct uvc_video, queue);
-	struct usb_composite_dev *cdev = video->uvc->func.config->cdev;
+	unsigned int req_size;
+	unsigned int nreq;
 
 	if (*nbuffers > UVC_MAX_VIDEO_BUFFERS)
 		*nbuffers = UVC_MAX_VIDEO_BUFFERS;
@@ -53,10 +54,16 @@ static int uvc_queue_setup(struct vb2_queue *vq,
 
 	sizes[0] = video->imagesize;
 
-	if (cdev->gadget->speed < USB_SPEED_SUPER)
-		video->uvc_num_requests = 4;
-	else
-		video->uvc_num_requests = 64;
+	req_size = video->ep->maxpacket
+		 * max_t(unsigned int, video->ep->maxburst, 1)
+		 * (video->ep->mult);
+
+	/* We divide by two, to increase the chance to run
+	 * into fewer requests for smaller framesizes.
+	 */
+	nreq = DIV_ROUND_UP(DIV_ROUND_UP(sizes[0], 2), req_size);
+	nreq = clamp(nreq, 4U, 64U);
+	video->uvc_num_requests = nreq;
 
 	return 0;
 }
diff --git a/drivers/usb/gadget/function/uvc_video.c b/drivers/usb/gadget/function/uvc_video.c
index b4a763e5f70e..e170e88abf3a 100644
--- a/drivers/usb/gadget/function/uvc_video.c
+++ b/drivers/usb/gadget/function/uvc_video.c
@@ -225,7 +225,7 @@ uvc_video_complete(struct usb_ep *ep, struct usb_request *req)
 		break;
 
 	default:
-		uvcg_info(&video->uvc->func,
+		uvcg_warn(&video->uvc->func,
 			  "VS request completed with status %d.\n",
 			  req->status);
 		uvcg_queue_cancel(queue, 0);
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index 3279b4767424..9e8b678f0548 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -362,6 +362,7 @@ ep_io (struct ep_data *epdata, void *buf, unsigned len)
 				spin_unlock_irq (&epdata->dev->lock);
 
 				DBG (epdata->dev, "endpoint gone\n");
+				wait_for_completion(&done);
 				epdata->status = -ENODEV;
 			}
 		}
diff --git a/drivers/usb/gadget/udc/Kconfig b/drivers/usb/gadget/udc/Kconfig
index 69394dc1cdfb..2cdd37be165a 100644
--- a/drivers/usb/gadget/udc/Kconfig
+++ b/drivers/usb/gadget/udc/Kconfig
@@ -311,7 +311,7 @@ source "drivers/usb/gadget/udc/bdc/Kconfig"
 
 config USB_AMD5536UDC
 	tristate "AMD5536 UDC"
-	depends on USB_PCI
+	depends on USB_PCI && HAS_DMA
 	select USB_SNP_CORE
 	help
 	   The AMD5536 UDC is part of the AMD Geode CS5536, an x86 southbridge.
diff --git a/drivers/usb/gadget/udc/aspeed-vhub/hub.c b/drivers/usb/gadget/udc/aspeed-vhub/hub.c
index b9960fdd8a51..16a12d2d492e 100644
--- a/drivers/usb/gadget/udc/aspeed-vhub/hub.c
+++ b/drivers/usb/gadget/udc/aspeed-vhub/hub.c
@@ -1028,8 +1028,10 @@ static int ast_vhub_init_desc(struct ast_vhub *vhub)
 	/* Initialize vhub String Descriptors. */
 	INIT_LIST_HEAD(&vhub->vhub_str_desc);
 	desc_np = of_get_child_by_name(vhub_np, "vhub-strings");
-	if (desc_np)
+	if (desc_np) {
 		ret = ast_vhub_of_parse_str_desc(vhub, desc_np);
+		of_node_put(desc_np);
+	}
 	else
 		ret = ast_vhub_str_alloc_add(vhub, &ast_vhub_strings);
 
diff --git a/drivers/usb/gadget/udc/tegra-xudc.c b/drivers/usb/gadget/udc/tegra-xudc.c
index be76f891b9c5..cb4ddfa52cb0 100644
--- a/drivers/usb/gadget/udc/tegra-xudc.c
+++ b/drivers/usb/gadget/udc/tegra-xudc.c
@@ -3689,15 +3689,15 @@ static int tegra_xudc_powerdomain_init(struct tegra_xudc *xudc)
 	int err;
 
 	xudc->genpd_dev_device = dev_pm_domain_attach_by_name(dev, "dev");
-	if (IS_ERR(xudc->genpd_dev_device)) {
-		err = PTR_ERR(xudc->genpd_dev_device);
+	if (IS_ERR_OR_NULL(xudc->genpd_dev_device)) {
+		err = PTR_ERR(xudc->genpd_dev_device) ? : -ENODATA;
 		dev_err(dev, "failed to get device power domain: %d\n", err);
 		return err;
 	}
 
 	xudc->genpd_dev_ss = dev_pm_domain_attach_by_name(dev, "ss");
-	if (IS_ERR(xudc->genpd_dev_ss)) {
-		err = PTR_ERR(xudc->genpd_dev_ss);
+	if (IS_ERR_OR_NULL(xudc->genpd_dev_ss)) {
+		err = PTR_ERR(xudc->genpd_dev_ss) ? : -ENODATA;
 		dev_err(dev, "failed to get SuperSpeed power domain: %d\n", err);
 		return err;
 	}
diff --git a/drivers/usb/host/ehci-ppc-of.c b/drivers/usb/host/ehci-ppc-of.c
index 6bbaee74f7e7..28a19693c19f 100644
--- a/drivers/usb/host/ehci-ppc-of.c
+++ b/drivers/usb/host/ehci-ppc-of.c
@@ -148,6 +148,7 @@ static int ehci_hcd_ppc_of_probe(struct platform_device *op)
 		} else {
 			ehci->has_amcc_usb23 = 1;
 		}
+		of_node_put(np);
 	}
 
 	if (of_get_property(dn, "big-endian", NULL)) {
diff --git a/drivers/usb/host/ohci-nxp.c b/drivers/usb/host/ohci-nxp.c
index 85878e8ad331..106a6bcefb08 100644
--- a/drivers/usb/host/ohci-nxp.c
+++ b/drivers/usb/host/ohci-nxp.c
@@ -164,6 +164,7 @@ static int ohci_hcd_nxp_probe(struct platform_device *pdev)
 	}
 
 	isp1301_i2c_client = isp1301_get_client(isp1301_node);
+	of_node_put(isp1301_node);
 	if (!isp1301_i2c_client)
 		return -EPROBE_DEFER;
 
diff --git a/drivers/usb/host/ohci-ppc-of.c b/drivers/usb/host/ohci-ppc-of.c
index 45f7cceb6df3..98e46725999e 100644
--- a/drivers/usb/host/ohci-ppc-of.c
+++ b/drivers/usb/host/ohci-ppc-of.c
@@ -169,6 +169,7 @@ static int ohci_hcd_ppc_of_probe(struct platform_device *op)
 				release_mem_region(res.start, 0x4);
 		} else
 			pr_debug("%s: cannot get ehci offset from fdt\n", __FILE__);
+		of_node_put(np);
 	}
 
 	irq_dispose_mapping(irq);
diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c
index ccb0156fcebe..46c8f3c187f7 100644
--- a/drivers/usb/host/xhci-dbgcap.c
+++ b/drivers/usb/host/xhci-dbgcap.c
@@ -914,59 +914,6 @@ static void xhci_dbc_handle_events(struct work_struct *work)
 	mod_delayed_work(system_wq, &dbc->event_work, 1);
 }
 
-static void xhci_do_dbc_exit(struct xhci_hcd *xhci)
-{
-	unsigned long		flags;
-
-	spin_lock_irqsave(&xhci->lock, flags);
-	kfree(xhci->dbc);
-	xhci->dbc = NULL;
-	spin_unlock_irqrestore(&xhci->lock, flags);
-}
-
-static int xhci_do_dbc_init(struct xhci_hcd *xhci)
-{
-	u32			reg;
-	struct xhci_dbc		*dbc;
-	unsigned long		flags;
-	void __iomem		*base;
-	int			dbc_cap_offs;
-
-	base = &xhci->cap_regs->hc_capbase;
-	dbc_cap_offs = xhci_find_next_ext_cap(base, 0, XHCI_EXT_CAPS_DEBUG);
-	if (!dbc_cap_offs)
-		return -ENODEV;
-
-	dbc = kzalloc(sizeof(*dbc), GFP_KERNEL);
-	if (!dbc)
-		return -ENOMEM;
-
-	dbc->regs = base + dbc_cap_offs;
-
-	/* We will avoid using DbC in xhci driver if it's in use. */
-	reg = readl(&dbc->regs->control);
-	if (reg & DBC_CTRL_DBC_ENABLE) {
-		kfree(dbc);
-		return -EBUSY;
-	}
-
-	spin_lock_irqsave(&xhci->lock, flags);
-	if (xhci->dbc) {
-		spin_unlock_irqrestore(&xhci->lock, flags);
-		kfree(dbc);
-		return -EBUSY;
-	}
-	xhci->dbc = dbc;
-	spin_unlock_irqrestore(&xhci->lock, flags);
-
-	dbc->xhci = xhci;
-	dbc->dev = xhci_to_hcd(xhci)->self.sysdev;
-	INIT_DELAYED_WORK(&dbc->event_work, xhci_dbc_handle_events);
-	spin_lock_init(&dbc->lock);
-
-	return 0;
-}
-
 static ssize_t dbc_show(struct device *dev,
 			struct device_attribute *attr,
 			char *buf)
@@ -1026,44 +973,86 @@ static ssize_t dbc_store(struct device *dev,
 
 static DEVICE_ATTR_RW(dbc);
 
-int xhci_dbc_init(struct xhci_hcd *xhci)
+struct xhci_dbc *
+xhci_alloc_dbc(struct device *dev, void __iomem *base, const struct dbc_driver *driver)
 {
+	struct xhci_dbc		*dbc;
 	int			ret;
-	struct device		*dev = xhci_to_hcd(xhci)->self.controller;
 
-	ret = xhci_do_dbc_init(xhci);
-	if (ret)
-		goto init_err3;
+	dbc = kzalloc(sizeof(*dbc), GFP_KERNEL);
+	if (!dbc)
+		return NULL;
 
-	ret = xhci_dbc_tty_probe(xhci);
-	if (ret)
-		goto init_err2;
+	dbc->regs = base;
+	dbc->dev = dev;
+	dbc->driver = driver;
+
+	if (readl(&dbc->regs->control) & DBC_CTRL_DBC_ENABLE)
+		return NULL;
+
+	INIT_DELAYED_WORK(&dbc->event_work, xhci_dbc_handle_events);
+	spin_lock_init(&dbc->lock);
 
 	ret = device_create_file(dev, &dev_attr_dbc);
 	if (ret)
-		goto init_err1;
+		goto err;
 
-	return 0;
+	return dbc;
+err:
+	kfree(dbc);
+	return NULL;
+}
+
+/* undo what xhci_alloc_dbc() did */
+void xhci_dbc_remove(struct xhci_dbc *dbc)
+{
+	if (!dbc)
+		return;
+	/* stop hw, stop wq and call dbc->ops->stop() */
+	xhci_dbc_stop(dbc);
+
+	/* remove sysfs files */
+	device_remove_file(dbc->dev, &dev_attr_dbc);
+
+	kfree(dbc);
+}
+
+
+int xhci_create_dbc_dev(struct xhci_hcd *xhci)
+{
+	struct device		*dev;
+	void __iomem		*base;
+	int			ret;
+	int			dbc_cap_offs;
+
+	/* create all parameters needed resembling a dbc device */
+	dev = xhci_to_hcd(xhci)->self.controller;
+	base = &xhci->cap_regs->hc_capbase;
+
+	dbc_cap_offs = xhci_find_next_ext_cap(base, 0, XHCI_EXT_CAPS_DEBUG);
+	if (!dbc_cap_offs)
+		return -ENODEV;
+
+	/* already allocated and in use */
+	if (xhci->dbc)
+		return -EBUSY;
+
+	ret = xhci_dbc_tty_probe(dev, base + dbc_cap_offs, xhci);
 
-init_err1:
-	xhci_dbc_tty_remove(xhci->dbc);
-init_err2:
-	xhci_do_dbc_exit(xhci);
-init_err3:
 	return ret;
 }
 
-void xhci_dbc_exit(struct xhci_hcd *xhci)
+void xhci_remove_dbc_dev(struct xhci_hcd *xhci)
 {
-	struct device		*dev = xhci_to_hcd(xhci)->self.controller;
+	unsigned long		flags;
 
 	if (!xhci->dbc)
 		return;
 
-	device_remove_file(dev, &dev_attr_dbc);
 	xhci_dbc_tty_remove(xhci->dbc);
-	xhci_dbc_stop(xhci->dbc);
-	xhci_do_dbc_exit(xhci);
+	spin_lock_irqsave(&xhci->lock, flags);
+	xhci->dbc = NULL;
+	spin_unlock_irqrestore(&xhci->lock, flags);
 }
 
 #ifdef CONFIG_PM
diff --git a/drivers/usb/host/xhci-dbgcap.h b/drivers/usb/host/xhci-dbgcap.h
index c70b78d504eb..8b5b363a0719 100644
--- a/drivers/usb/host/xhci-dbgcap.h
+++ b/drivers/usb/host/xhci-dbgcap.h
@@ -194,10 +194,13 @@ static inline struct dbc_ep *get_out_ep(struct xhci_dbc *dbc)
 }
 
 #ifdef CONFIG_USB_XHCI_DBGCAP
-int xhci_dbc_init(struct xhci_hcd *xhci);
-void xhci_dbc_exit(struct xhci_hcd *xhci);
-int xhci_dbc_tty_probe(struct xhci_hcd *xhci);
+int xhci_create_dbc_dev(struct xhci_hcd *xhci);
+void xhci_remove_dbc_dev(struct xhci_hcd *xhci);
+int xhci_dbc_tty_probe(struct device *dev, void __iomem *res, struct xhci_hcd *xhci);
 void xhci_dbc_tty_remove(struct xhci_dbc *dbc);
+struct xhci_dbc *xhci_alloc_dbc(struct device *dev, void __iomem *res,
+				 const struct dbc_driver *driver);
+void xhci_dbc_remove(struct xhci_dbc *dbc);
 struct dbc_request *dbc_alloc_request(struct xhci_dbc *dbc,
 				      unsigned int direction,
 				      gfp_t flags);
@@ -208,12 +211,12 @@ int xhci_dbc_suspend(struct xhci_hcd *xhci);
 int xhci_dbc_resume(struct xhci_hcd *xhci);
 #endif /* CONFIG_PM */
 #else
-static inline int xhci_dbc_init(struct xhci_hcd *xhci)
+static inline int xhci_create_dbc_dev(struct xhci_hcd *xhci)
 {
 	return 0;
 }
 
-static inline void xhci_dbc_exit(struct xhci_hcd *xhci)
+static inline void xhci_remove_dbc_dev(struct xhci_hcd *xhci)
 {
 }
 
diff --git a/drivers/usb/host/xhci-dbgtty.c b/drivers/usb/host/xhci-dbgtty.c
index eb46e642e87a..18bcc96853ae 100644
--- a/drivers/usb/host/xhci-dbgtty.c
+++ b/drivers/usb/host/xhci-dbgtty.c
@@ -468,9 +468,9 @@ static const struct dbc_driver dbc_driver = {
 	.disconnect		= xhci_dbc_tty_unregister_device,
 };
 
-int xhci_dbc_tty_probe(struct xhci_hcd *xhci)
+int xhci_dbc_tty_probe(struct device *dev, void __iomem *base, struct xhci_hcd *xhci)
 {
-	struct xhci_dbc		*dbc = xhci->dbc;
+	struct xhci_dbc		*dbc;
 	struct dbc_port		*port;
 	int			status;
 
@@ -485,13 +485,22 @@ int xhci_dbc_tty_probe(struct xhci_hcd *xhci)
 		goto out;
 	}
 
-	dbc->driver = &dbc_driver;
-	dbc->priv = port;
+	dbc_tty_driver->driver_state = port;
+
+	dbc = xhci_alloc_dbc(dev, base, &dbc_driver);
+	if (!dbc) {
+		status = -ENOMEM;
+		goto out2;
+	}
 
+	dbc->priv = port;
 
-	dbc_tty_driver->driver_state = port;
+	/* get rid of xhci once this is a real driver binding to a device */
+	xhci->dbc = dbc;
 
 	return 0;
+out2:
+	kfree(port);
 out:
 	/* dbc_tty_exit will be called by module_exit() in the future */
 	dbc_tty_exit();
@@ -506,8 +515,7 @@ void xhci_dbc_tty_remove(struct xhci_dbc *dbc)
 {
 	struct dbc_port         *port = dbc_to_port(dbc);
 
-	dbc->driver = NULL;
-	dbc->priv = NULL;
+	xhci_dbc_remove(dbc);
 	kfree(port);
 
 	/* dbc_tty_exit will be called by  module_exit() in the future */
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index 42d37843e269..010819e736c9 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -652,7 +652,7 @@ struct xhci_hub *xhci_get_rhub(struct usb_hcd *hcd)
  * It will release and re-aquire the lock while calling ACPI
  * method.
  */
-void xhci_set_port_power(struct xhci_hcd *xhci, struct usb_hcd *hcd,
+static void xhci_set_port_power(struct xhci_hcd *xhci, struct usb_hcd *hcd,
 				u16 index, bool on, unsigned long *flags)
 	__must_hold(&xhci->lock)
 {
@@ -1657,6 +1657,17 @@ int xhci_hub_status_data(struct usb_hcd *hcd, char *buf)
 
 	status = bus_state->resuming_ports;
 
+	/*
+	 * SS devices are only visible to roothub after link training completes.
+	 * Keep polling roothubs for a grace period after xHC start
+	 */
+	if (xhci->run_graceperiod) {
+		if (time_before(jiffies, xhci->run_graceperiod))
+			status = 1;
+		else
+			xhci->run_graceperiod = 0;
+	}
+
 	mask = PORT_CSC | PORT_PEC | PORT_OCC | PORT_PLC | PORT_WRC | PORT_CEC;
 
 	/* For each port, did anything change?  If so, set that bit in buf. */
diff --git a/drivers/usb/host/xhci-mtk-sch.c b/drivers/usb/host/xhci-mtk-sch.c
index f91a30432056..9d8094afcc8b 100644
--- a/drivers/usb/host/xhci-mtk-sch.c
+++ b/drivers/usb/host/xhci-mtk-sch.c
@@ -476,7 +476,6 @@ static int check_fs_bus_bw(struct mu3h_sch_ep_info *sch_ep, int offset)
 
 static int check_sch_tt(struct mu3h_sch_ep_info *sch_ep, u32 offset)
 {
-	u32 extra_cs_count;
 	u32 start_ss, last_ss;
 	u32 start_cs, last_cs;
 
@@ -512,18 +511,12 @@ static int check_sch_tt(struct mu3h_sch_ep_info *sch_ep, u32 offset)
 		if (last_cs > 7)
 			return -ESCH_CS_OVERFLOW;
 
-		if (sch_ep->ep_type == ISOC_IN_EP)
-			extra_cs_count = (last_cs == 7) ? 1 : 2;
-		else /*  ep_type : INTR IN / INTR OUT */
-			extra_cs_count = 1;
-
-		cs_count += extra_cs_count;
 		if (cs_count > 7)
 			cs_count = 7; /* HW limit */
 
 		sch_ep->cs_count = cs_count;
-		/* one for ss, the other for idle */
-		sch_ep->num_budget_microframes = cs_count + 2;
+		/* ss, idle are ignored */
+		sch_ep->num_budget_microframes = cs_count;
 
 		/*
 		 * if interval=1, maxp >752, num_budge_micoframe is larger
@@ -822,8 +815,8 @@ int xhci_mtk_drop_ep(struct usb_hcd *hcd, struct usb_device *udev,
 	if (ret)
 		return ret;
 
-	if (ep->hcpriv)
-		drop_ep_quirk(hcd, udev, ep);
+	/* needn't check @ep->hcpriv, xhci_endpoint_disable set it NULL */
+	drop_ep_quirk(hcd, udev, ep);
 
 	return 0;
 }
diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c
index 996958a6565c..bdb776553826 100644
--- a/drivers/usb/host/xhci-tegra.c
+++ b/drivers/usb/host/xhci-tegra.c
@@ -1010,15 +1010,15 @@ static int tegra_xusb_powerdomain_init(struct device *dev,
 	int err;
 
 	tegra->genpd_dev_host = dev_pm_domain_attach_by_name(dev, "xusb_host");
-	if (IS_ERR(tegra->genpd_dev_host)) {
-		err = PTR_ERR(tegra->genpd_dev_host);
+	if (IS_ERR_OR_NULL(tegra->genpd_dev_host)) {
+		err = PTR_ERR(tegra->genpd_dev_host) ? : -ENODATA;
 		dev_err(dev, "failed to get host pm-domain: %d\n", err);
 		return err;
 	}
 
 	tegra->genpd_dev_ss = dev_pm_domain_attach_by_name(dev, "xusb_ss");
-	if (IS_ERR(tegra->genpd_dev_ss)) {
-		err = PTR_ERR(tegra->genpd_dev_ss);
+	if (IS_ERR_OR_NULL(tegra->genpd_dev_ss)) {
+		err = PTR_ERR(tegra->genpd_dev_ss) ? : -ENODATA;
 		dev_err(dev, "failed to get superspeed pm-domain: %d\n", err);
 		return err;
 	}
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 24e2823be4fd..ce8423540c1b 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -148,9 +148,11 @@ int xhci_start(struct xhci_hcd *xhci)
 		xhci_err(xhci, "Host took too long to start, "
 				"waited %u microseconds.\n",
 				XHCI_MAX_HALT_USEC);
-	if (!ret)
+	if (!ret) {
 		/* clear state flags. Including dying, halted or removing */
 		xhci->xhc_state = 0;
+		xhci->run_graceperiod = jiffies + msecs_to_jiffies(500);
+	}
 
 	return ret;
 }
@@ -693,7 +695,9 @@ int xhci_run(struct usb_hcd *hcd)
 	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
 			"Finished xhci_run for USB2 roothub");
 
-	xhci_dbc_init(xhci);
+	set_bit(HCD_FLAG_DEFER_RH_REGISTER, &hcd->flags);
+
+	xhci_create_dbc_dev(xhci);
 
 	xhci_debugfs_init(xhci);
 
@@ -723,7 +727,7 @@ static void xhci_stop(struct usb_hcd *hcd)
 		return;
 	}
 
-	xhci_dbc_exit(xhci);
+	xhci_remove_dbc_dev(xhci);
 
 	spin_lock_irq(&xhci->lock);
 	xhci->xhc_state |= XHCI_STATE_HALTED;
@@ -774,8 +778,6 @@ static void xhci_stop(struct usb_hcd *hcd)
 void xhci_shutdown(struct usb_hcd *hcd)
 {
 	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
-	unsigned long flags;
-	int i;
 
 	if (xhci->quirks & XHCI_SPURIOUS_REBOOT)
 		usb_disable_xhci_ports(to_pci_dev(hcd->self.sysdev));
@@ -791,21 +793,12 @@ void xhci_shutdown(struct usb_hcd *hcd)
 		del_timer_sync(&xhci->shared_hcd->rh_timer);
 	}
 
-	spin_lock_irqsave(&xhci->lock, flags);
+	spin_lock_irq(&xhci->lock);
 	xhci_halt(xhci);
-
-	/* Power off USB2 ports*/
-	for (i = 0; i < xhci->usb2_rhub.num_ports; i++)
-		xhci_set_port_power(xhci, xhci->main_hcd, i, false, &flags);
-
-	/* Power off USB3 ports*/
-	for (i = 0; i < xhci->usb3_rhub.num_ports; i++)
-		xhci_set_port_power(xhci, xhci->shared_hcd, i, false, &flags);
-
 	/* Workaround for spurious wakeups at shutdown with HSW */
 	if (xhci->quirks & XHCI_SPURIOUS_WAKEUP)
 		xhci_reset(xhci, XHCI_RESET_SHORT_USEC);
-	spin_unlock_irqrestore(&xhci->lock, flags);
+	spin_unlock_irq(&xhci->lock);
 
 	xhci_cleanup_msix(xhci);
 
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 2af41128b44c..cd4b9aac8c8f 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1830,7 +1830,7 @@ struct xhci_hcd {
 
 	/* Host controller watchdog timer structures */
 	unsigned int		xhc_state;
-
+	unsigned long		run_graceperiod;
 	u32			command;
 	struct s3_save		s3;
 /* Host controller is dying - not responding to commands. "I'm not dead yet!"
@@ -2176,8 +2176,6 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, u16 wIndex,
 int xhci_hub_status_data(struct usb_hcd *hcd, char *buf);
 int xhci_find_raw_port_number(struct usb_hcd *hcd, int port1);
 struct xhci_hub *xhci_get_rhub(struct usb_hcd *hcd);
-void xhci_set_port_power(struct xhci_hcd *xhci, struct usb_hcd *hcd, u16 index,
-			 bool on, unsigned long *flags);
 
 void xhci_hc_died(struct xhci_hcd *xhci);
 #ifdef CONFIG_USB_HCD_TEST_MODE
@@ -2407,7 +2405,7 @@ static inline const char *xhci_decode_trb(char *str, size_t size,
 			field3 & TRB_CYCLE ? 'C' : 'c');
 		break;
 	case TRB_STOP_RING:
-		sprintf(str,
+		snprintf(str, size,
 			"%s: slot %d sp %d ep %d flags %c",
 			xhci_trb_type_string(type),
 			TRB_TO_SLOT_ID(field3),
diff --git a/drivers/usb/musb/Kconfig b/drivers/usb/musb/Kconfig
index 4d61df6a9b5c..70693cae83ef 100644
--- a/drivers/usb/musb/Kconfig
+++ b/drivers/usb/musb/Kconfig
@@ -86,7 +86,7 @@ config USB_MUSB_TUSB6010
 	tristate "TUSB6010"
 	depends on HAS_IOMEM
 	depends on ARCH_OMAP2PLUS || COMPILE_TEST
-	depends on NOP_USB_XCEIV = USB_MUSB_HDRC # both built-in or both modules
+	depends on NOP_USB_XCEIV!=m || USB_MUSB_HDRC=m
 
 config USB_MUSB_OMAP2PLUS
 	tristate "OMAP2430 and onwards"
diff --git a/drivers/usb/renesas_usbhs/rza.c b/drivers/usb/renesas_usbhs/rza.c
index 24de64edb674..2d77edefb4b3 100644
--- a/drivers/usb/renesas_usbhs/rza.c
+++ b/drivers/usb/renesas_usbhs/rza.c
@@ -23,6 +23,10 @@ static int usbhs_rza1_hardware_init(struct platform_device *pdev)
 	extal_clk = of_find_node_by_name(NULL, "extal");
 	of_property_read_u32(usb_x1_clk, "clock-frequency", &freq_usb);
 	of_property_read_u32(extal_clk, "clock-frequency", &freq_extal);
+
+	of_node_put(usb_x1_clk);
+	of_node_put(extal_clk);
+
 	if (freq_usb == 0) {
 		if (freq_extal == 12000000) {
 			/* Select 12MHz XTAL */
diff --git a/drivers/usb/serial/ch341.c b/drivers/usb/serial/ch341.c
index b5a1864e9cfd..752daa952abd 100644
--- a/drivers/usb/serial/ch341.c
+++ b/drivers/usb/serial/ch341.c
@@ -97,7 +97,10 @@ struct ch341_private {
 	u8 mcr;
 	u8 msr;
 	u8 lcr;
+
 	unsigned long quirks;
+	u8 version;
+
 	unsigned long break_end;
 };
 
@@ -256,8 +259,12 @@ static int ch341_set_baudrate_lcr(struct usb_device *dev,
 	/*
 	 * CH341A buffers data until a full endpoint-size packet (32 bytes)
 	 * has been received unless bit 7 is set.
+	 *
+	 * At least one device with version 0x27 appears to have this bit
+	 * inverted.
 	 */
-	val |= BIT(7);
+	if (priv->version > 0x27)
+		val |= BIT(7);
 
 	r = ch341_control_out(dev, CH341_REQ_WRITE_REG,
 			      CH341_REG_DIVISOR << 8 | CH341_REG_PRESCALER,
@@ -271,6 +278,9 @@ static int ch341_set_baudrate_lcr(struct usb_device *dev,
 	 * (stop bits, parity and word length). Version 0x30 and above use
 	 * CH341_REG_LCR only and CH341_REG_LCR2 is always set to zero.
 	 */
+	if (priv->version < 0x30)
+		return 0;
+
 	r = ch341_control_out(dev, CH341_REQ_WRITE_REG,
 			      CH341_REG_LCR2 << 8 | CH341_REG_LCR, lcr);
 	if (r)
@@ -323,7 +333,9 @@ static int ch341_configure(struct usb_device *dev, struct ch341_private *priv)
 	r = ch341_control_in(dev, CH341_REQ_READ_VERSION, 0, 0, buffer, size);
 	if (r < 0)
 		goto out;
-	dev_dbg(&dev->dev, "Chip version: 0x%02x\n", buffer[0]);
+
+	priv->version = buffer[0];
+	dev_dbg(&dev->dev, "Chip version: 0x%02x\n", priv->version);
 
 	r = ch341_control_out(dev, CH341_REQ_SERIAL_INIT, 0, 0);
 	if (r < 0)
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index bd006e1712cc..a2126b07e854 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -130,6 +130,7 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x10C4, 0x83AA) }, /* Mark-10 Digital Force Gauge */
 	{ USB_DEVICE(0x10C4, 0x83D8) }, /* DekTec DTA Plus VHF/UHF Booster/Attenuator */
 	{ USB_DEVICE(0x10C4, 0x8411) }, /* Kyocera GPS Module */
+	{ USB_DEVICE(0x10C4, 0x8414) }, /* Decagon USB Cable Adapter */
 	{ USB_DEVICE(0x10C4, 0x8418) }, /* IRZ Automation Teleport SG-10 GSM/GPRS Modem */
 	{ USB_DEVICE(0x10C4, 0x846E) }, /* BEI USB Sensor Interface (VCP) */
 	{ USB_DEVICE(0x10C4, 0x8470) }, /* Juniper Networks BX Series System Console */
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 7e852561d55c..a2ecb3b5d13e 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -1023,6 +1023,9 @@ static const struct usb_device_id id_table_combined[] = {
 	{ USB_DEVICE(FTDI_VID, CHETCO_SEASMART_DISPLAY_PID) },
 	{ USB_DEVICE(FTDI_VID, CHETCO_SEASMART_LITE_PID) },
 	{ USB_DEVICE(FTDI_VID, CHETCO_SEASMART_ANALOG_PID) },
+	/* Belimo Automation devices */
+	{ USB_DEVICE(FTDI_VID, BELIMO_ZTH_PID) },
+	{ USB_DEVICE(FTDI_VID, BELIMO_ZIP_PID) },
 	/* ICP DAS I-756xU devices */
 	{ USB_DEVICE(ICPDAS_VID, ICPDAS_I7560U_PID) },
 	{ USB_DEVICE(ICPDAS_VID, ICPDAS_I7561U_PID) },
@@ -1042,6 +1045,8 @@ static const struct usb_device_id id_table_combined[] = {
 	/* IDS GmbH devices */
 	{ USB_DEVICE(IDS_VID, IDS_SI31A_PID) },
 	{ USB_DEVICE(IDS_VID, IDS_CM31A_PID) },
+	/* Omron devices */
+	{ USB_DEVICE(OMRON_VID, OMRON_CS1W_CIF31_PID) },
 	/* U-Blox devices */
 	{ USB_DEVICE(UBLOX_VID, UBLOX_C099F9P_ZED_PID) },
 	{ USB_DEVICE(UBLOX_VID, UBLOX_C099F9P_ODIN_PID) },
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index d1a9564697a4..31c8ccabbbb7 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -662,6 +662,12 @@
 #define INFINEON_TRIBOARD_TC2X7_PID	0x0043 /* DAS JTAG TriBoard TC2X7 V1.0 */
 
 /*
+ * Omron corporation (https://www.omron.com)
+ */
+ #define OMRON_VID			0x0590
+ #define OMRON_CS1W_CIF31_PID		0x00b2
+
+/*
  * Acton Research Corp.
  */
 #define ACTON_VID		0x0647	/* Vendor ID */
@@ -1569,6 +1575,12 @@
 #define CHETCO_SEASMART_ANALOG_PID	0xA5AF /* SeaSmart Analog Adapter */
 
 /*
+ * Belimo Automation
+ */
+#define BELIMO_ZTH_PID			0x8050
+#define BELIMO_ZIP_PID			0xC811
+
+/*
  * Unjo AB
  */
 #define UNJO_VID			0x22B7
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index de59fa919540..a5e8374a8d71 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -253,6 +253,7 @@ static void option_instat_callback(struct urb *urb);
 #define QUECTEL_PRODUCT_BG96			0x0296
 #define QUECTEL_PRODUCT_EP06			0x0306
 #define QUECTEL_PRODUCT_EM05G			0x030a
+#define QUECTEL_PRODUCT_EM060K			0x030b
 #define QUECTEL_PRODUCT_EM12			0x0512
 #define QUECTEL_PRODUCT_RM500Q			0x0800
 #define QUECTEL_PRODUCT_EC200S_CN		0x6002
@@ -438,6 +439,8 @@ static void option_instat_callback(struct urb *urb);
 #define CINTERION_PRODUCT_MV31_2_RMNET		0x00b9
 #define CINTERION_PRODUCT_MV32_WA		0x00f1
 #define CINTERION_PRODUCT_MV32_WB		0x00f2
+#define CINTERION_PRODUCT_MV32_WA_RMNET		0x00f3
+#define CINTERION_PRODUCT_MV32_WB_RMNET		0x00f4
 
 /* Olivetti products */
 #define OLIVETTI_VENDOR_ID			0x0b3c
@@ -573,6 +576,10 @@ static void option_instat_callback(struct urb *urb);
 #define WETELECOM_PRODUCT_6802			0x6802
 #define WETELECOM_PRODUCT_WMD300		0x6803
 
+/* OPPO products */
+#define OPPO_VENDOR_ID				0x22d9
+#define OPPO_PRODUCT_R11			0x276c
+
 
 /* Device flags */
 
@@ -1138,6 +1145,9 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0, 0) },
 	{ USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G, 0xff),
 	  .driver_info = RSVD(6) | ZLP },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K, 0xff, 0x00, 0x40) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K, 0xff, 0xff, 0x30) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K, 0xff, 0xff, 0x40) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM12, 0xff, 0xff, 0xff),
 	  .driver_info = RSVD(1) | RSVD(2) | RSVD(3) | RSVD(4) | NUMEP2 },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM12, 0xff, 0, 0) },
@@ -1993,8 +2003,12 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = RSVD(0)},
 	{ USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_MV32_WA, 0xff),
 	  .driver_info = RSVD(3)},
+	{ USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_MV32_WA_RMNET, 0xff),
+	  .driver_info = RSVD(0) },
 	{ USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_MV32_WB, 0xff),
 	  .driver_info = RSVD(3)},
+	{ USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_MV32_WB_RMNET, 0xff),
+	  .driver_info = RSVD(0) },
 	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD100),
 	  .driver_info = RSVD(4) },
 	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD120),
@@ -2155,6 +2169,7 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1404, 0xff) },			/* GosunCn GM500 RNDIS */
 	{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1405, 0xff) },			/* GosunCn GM500 MBIM */
 	{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1406, 0xff) },			/* GosunCn GM500 ECM/NCM */
+	{ USB_DEVICE_AND_INTERFACE_INFO(OPPO_VENDOR_ID, OPPO_PRODUCT_R11, 0xff, 0xff, 0x30) },
 	{ } /* Terminating entry */
 };
 MODULE_DEVICE_TABLE(usb, option_ids);
diff --git a/drivers/usb/serial/sierra.c b/drivers/usb/serial/sierra.c
index 9d56138133a9..ef6a2891f290 100644
--- a/drivers/usb/serial/sierra.c
+++ b/drivers/usb/serial/sierra.c
@@ -737,7 +737,8 @@ static void sierra_close(struct usb_serial_port *port)
 
 	/*
 	 * Need to take susp_lock to make sure port is not already being
-	 * resumed, but no need to hold it due to initialized
+	 * resumed, but no need to hold it due to the tty-port initialized
+	 * flag.
 	 */
 	spin_lock_irq(&intfdata->susp_lock);
 	if (--intfdata->open_ports == 0)
diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c
index 090a78c948f2..255fb9583c0a 100644
--- a/drivers/usb/serial/usb-serial.c
+++ b/drivers/usb/serial/usb-serial.c
@@ -292,7 +292,7 @@ static int serial_open(struct tty_struct *tty, struct file *filp)
  *
  * Shut down a USB serial port. Serialized against activate by the
  * tport mutex and kept to matching open/close pairs
- * of calls by the initialized flag.
+ * of calls by the tty-port initialized flag.
  *
  * Not called if tty is console.
  */
diff --git a/drivers/usb/serial/usb_wwan.c b/drivers/usb/serial/usb_wwan.c
index cb01283d4d15..f21f25a8cf6f 100644
--- a/drivers/usb/serial/usb_wwan.c
+++ b/drivers/usb/serial/usb_wwan.c
@@ -389,7 +389,8 @@ void usb_wwan_close(struct usb_serial_port *port)
 
 	/*
 	 * Need to take susp_lock to make sure port is not already being
-	 * resumed, but no need to hold it due to initialized
+	 * resumed, but no need to hold it due to the tty-port initialized
+	 * flag.
 	 */
 	spin_lock_irq(&intfdata->susp_lock);
 	if (--intfdata->open_ports == 0)
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index 1a05e3dcfec8..4993227ab293 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -2294,6 +2294,13 @@ UNUSUAL_DEV( 0x1e74, 0x4621, 0x0000, 0x0000,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_BULK_IGNORE_TAG | US_FL_MAX_SECTORS_64 ),
 
+/* Reported by Witold Lipieta <witold.lipieta@thaumatec.com> */
+UNUSUAL_DEV( 0x1fc9, 0x0117, 0x0100, 0x0100,
+		"NXP Semiconductors",
+		"PN7462AU",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_IGNORE_RESIDUE ),
+
 /* Supplied with some Castlewood ORB removable drives */
 UNUSUAL_DEV(  0x2027, 0xa001, 0x0000, 0x9999,
 		"Double-H Technology",
diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h
index 4051c8cd0cd8..23ab3b048d9b 100644
--- a/drivers/usb/storage/unusual_uas.h
+++ b/drivers/usb/storage/unusual_uas.h
@@ -62,6 +62,13 @@ UNUSUAL_DEV(0x0984, 0x0301, 0x0128, 0x0128,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_IGNORE_UAS),
 
+/* Reported-by: Tom Hu <huxiaoying@kylinos.cn> */
+UNUSUAL_DEV(0x0b05, 0x1932, 0x0000, 0x9999,
+		"ASUS",
+		"External HDD",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_IGNORE_UAS),
+
 /* Reported-by: David Webb <djw@noc.ac.uk> */
 UNUSUAL_DEV(0x0bc2, 0x331a, 0x0000, 0x9999,
 		"Seagate",
diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c
index b7f094435b00..998c1e3e318e 100644
--- a/drivers/usb/typec/altmodes/displayport.c
+++ b/drivers/usb/typec/altmodes/displayport.c
@@ -88,8 +88,8 @@ static int dp_altmode_configure(struct dp_altmode *dp, u8 con)
 	case DP_STATUS_CON_UFP_D:
 	case DP_STATUS_CON_BOTH: /* NOTE: First acting as DP source */
 		conf |= DP_CONF_UFP_U_AS_UFP_D;
-		pin_assign = DP_CAP_DFP_D_PIN_ASSIGN(dp->alt->vdo) &
-			     DP_CAP_UFP_D_PIN_ASSIGN(dp->port->vdo);
+		pin_assign = DP_CAP_PIN_ASSIGN_UFP_D(dp->alt->vdo) &
+				 DP_CAP_PIN_ASSIGN_DFP_D(dp->port->vdo);
 		break;
 	default:
 		break;
diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c
index aeef453aa658..ff6c14d7b1a8 100644
--- a/drivers/usb/typec/class.c
+++ b/drivers/usb/typec/class.c
@@ -1718,6 +1718,7 @@ void typec_set_pwr_opmode(struct typec_port *port,
 			partner->usb_pd = 1;
 			sysfs_notify(&partner_dev->kobj, NULL,
 				     "supports_usb_power_delivery");
+			kobject_uevent(&partner_dev->kobj, KOBJ_CHANGE);
 		}
 		put_device(partner_dev);
 	}
diff --git a/drivers/usb/typec/mux/intel_pmc_mux.c b/drivers/usb/typec/mux/intel_pmc_mux.c
index 2cdd22130834..5daec9d79e94 100644
--- a/drivers/usb/typec/mux/intel_pmc_mux.c
+++ b/drivers/usb/typec/mux/intel_pmc_mux.c
@@ -554,9 +554,11 @@ err_unregister_switch:
 
 static int is_memory(struct acpi_resource *res, void *data)
 {
-	struct resource r;
+	struct resource_win win = {};
+	struct resource *r = &win.res;
 
-	return !acpi_dev_resource_memory(res, &r);
+	return !(acpi_dev_resource_memory(res, r) ||
+		 acpi_dev_resource_address_space(res, &win));
 }
 
 /* IOM ACPI IDs and IOM_PORT_STATUS_OFFSET */
@@ -566,6 +568,9 @@ static const struct acpi_device_id iom_acpi_ids[] = {
 
 	/* AlderLake */
 	{ "INTC1079", 0x160, },
+
+	/* Meteor Lake */
+	{ "INTC107A", 0x160, },
 	{}
 };
 
diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 34aee53936ba..468b60f0cd72 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -6212,6 +6212,13 @@ static int tcpm_psy_set_prop(struct power_supply *psy,
 	struct tcpm_port *port = power_supply_get_drvdata(psy);
 	int ret = 0;
 
+	/*
+	 * All the properties below are related to USB PD. The check needs to be
+	 * property specific when a non-pd related property is added.
+	 */
+	if (!port->pd_supported)
+		return -EOPNOTSUPP;
+
 	switch (psp) {
 	case POWER_SUPPLY_PROP_ONLINE:
 		ret = tcpm_psy_set_online(port, val);
diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index 8a7e2dd52ad5..1f23eb543d8f 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -76,6 +76,10 @@ static int ucsi_read_error(struct ucsi *ucsi)
 	if (ret)
 		return ret;
 
+	ret = ucsi_acknowledge_command(ucsi);
+	if (ret)
+		return ret;
+
 	switch (error) {
 	case UCSI_ERROR_INCOMPATIBLE_PARTNER:
 		return -EOPNOTSUPP;
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index e4258f40dcd7..e748c00789f0 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -1641,7 +1641,7 @@ static void mlx5_vdpa_kick_vq(struct vdpa_device *vdev, u16 idx)
 		return;
 
 	if (unlikely(is_ctrl_vq_idx(mvdev, idx))) {
-		if (!mvdev->cvq.ready)
+		if (!mvdev->wq || !mvdev->cvq.ready)
 			return;
 
 		queue_work(mvdev->wq, &ndev->cvq_ent.work);
@@ -1698,6 +1698,8 @@ static void mlx5_vdpa_set_vq_cb(struct vdpa_device *vdev, u16 idx, struct vdpa_c
 	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
 
 	ndev->event_cbs[idx] = *cb;
+	if (is_ctrl_vq_idx(mvdev, idx))
+		mvdev->cvq.event_cb = *cb;
 }
 
 static void mlx5_cvq_notify(struct vringh *vring)
@@ -1896,7 +1898,6 @@ static int verify_driver_features(struct mlx5_vdpa_dev *mvdev, u64 features)
 static int setup_virtqueues(struct mlx5_vdpa_dev *mvdev)
 {
 	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
-	struct mlx5_control_vq *cvq = &mvdev->cvq;
 	int err;
 	int i;
 
@@ -1906,16 +1907,6 @@ static int setup_virtqueues(struct mlx5_vdpa_dev *mvdev)
 			goto err_vq;
 	}
 
-	if (mvdev->actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VQ)) {
-		err = vringh_init_iotlb(&cvq->vring, mvdev->actual_features,
-					MLX5_CVQ_MAX_ENT, false,
-					(struct vring_desc *)(uintptr_t)cvq->desc_addr,
-					(struct vring_avail *)(uintptr_t)cvq->driver_addr,
-					(struct vring_used *)(uintptr_t)cvq->device_addr);
-		if (err)
-			goto err_vq;
-	}
-
 	return 0;
 
 err_vq:
@@ -2182,6 +2173,21 @@ static void clear_vqs_ready(struct mlx5_vdpa_net *ndev)
 	ndev->mvdev.cvq.ready = false;
 }
 
+static int setup_cvq_vring(struct mlx5_vdpa_dev *mvdev)
+{
+	struct mlx5_control_vq *cvq = &mvdev->cvq;
+	int err = 0;
+
+	if (mvdev->actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VQ))
+		err = vringh_init_iotlb(&cvq->vring, mvdev->actual_features,
+					MLX5_CVQ_MAX_ENT, false,
+					(struct vring_desc *)(uintptr_t)cvq->desc_addr,
+					(struct vring_avail *)(uintptr_t)cvq->driver_addr,
+					(struct vring_used *)(uintptr_t)cvq->device_addr);
+
+	return err;
+}
+
 static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status)
 {
 	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
@@ -2192,6 +2198,11 @@ static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status)
 
 	if ((status ^ ndev->mvdev.status) & VIRTIO_CONFIG_S_DRIVER_OK) {
 		if (status & VIRTIO_CONFIG_S_DRIVER_OK) {
+			err = setup_cvq_vring(mvdev);
+			if (err) {
+				mlx5_vdpa_warn(mvdev, "failed to setup control VQ vring\n");
+				goto err_setup;
+			}
 			err = setup_driver(mvdev);
 			if (err) {
 				mlx5_vdpa_warn(mvdev, "failed to setup driver\n");
@@ -2624,9 +2635,12 @@ static void mlx5_vdpa_dev_del(struct vdpa_mgmt_dev *v_mdev, struct vdpa_device *
 	struct mlx5_vdpa_mgmtdev *mgtdev = container_of(v_mdev, struct mlx5_vdpa_mgmtdev, mgtdev);
 	struct mlx5_vdpa_dev *mvdev = to_mvdev(dev);
 	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
+	struct workqueue_struct *wq;
 
 	mlx5_notifier_unregister(mvdev->mdev, &ndev->nb);
-	destroy_workqueue(mvdev->wq);
+	wq = mvdev->wq;
+	mvdev->wq = NULL;
+	destroy_workqueue(wq);
 	_vdpa_unregister_device(dev);
 	mgtdev->ndev = NULL;
 }
diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c
index 9270398caf15..73e67fa88972 100644
--- a/drivers/vdpa/vdpa_user/vduse_dev.c
+++ b/drivers/vdpa/vdpa_user/vduse_dev.c
@@ -1466,16 +1466,12 @@ static char *vduse_devnode(struct device *dev, umode_t *mode)
 	return kasprintf(GFP_KERNEL, "vduse/%s", dev_name(dev));
 }
 
-static void vduse_mgmtdev_release(struct device *dev)
-{
-}
-
-static struct device vduse_mgmtdev = {
-	.init_name = "vduse",
-	.release = vduse_mgmtdev_release,
+struct vduse_mgmt_dev {
+	struct vdpa_mgmt_dev mgmt_dev;
+	struct device dev;
 };
 
-static struct vdpa_mgmt_dev mgmt_dev;
+static struct vduse_mgmt_dev *vduse_mgmt;
 
 static int vduse_dev_init_vdpa(struct vduse_dev *dev, const char *name)
 {
@@ -1500,7 +1496,7 @@ static int vduse_dev_init_vdpa(struct vduse_dev *dev, const char *name)
 	}
 	set_dma_ops(&vdev->vdpa.dev, &vduse_dev_dma_ops);
 	vdev->vdpa.dma_dev = &vdev->vdpa.dev;
-	vdev->vdpa.mdev = &mgmt_dev;
+	vdev->vdpa.mdev = &vduse_mgmt->mgmt_dev;
 
 	return 0;
 }
@@ -1545,34 +1541,52 @@ static struct virtio_device_id id_table[] = {
 	{ 0 },
 };
 
-static struct vdpa_mgmt_dev mgmt_dev = {
-	.device = &vduse_mgmtdev,
-	.id_table = id_table,
-	.ops = &vdpa_dev_mgmtdev_ops,
-};
+static void vduse_mgmtdev_release(struct device *dev)
+{
+	struct vduse_mgmt_dev *mgmt_dev;
+
+	mgmt_dev = container_of(dev, struct vduse_mgmt_dev, dev);
+	kfree(mgmt_dev);
+}
 
 static int vduse_mgmtdev_init(void)
 {
 	int ret;
 
-	ret = device_register(&vduse_mgmtdev);
-	if (ret)
+	vduse_mgmt = kzalloc(sizeof(*vduse_mgmt), GFP_KERNEL);
+	if (!vduse_mgmt)
+		return -ENOMEM;
+
+	ret = dev_set_name(&vduse_mgmt->dev, "vduse");
+	if (ret) {
+		kfree(vduse_mgmt);
 		return ret;
+	}
 
-	ret = vdpa_mgmtdev_register(&mgmt_dev);
+	vduse_mgmt->dev.release = vduse_mgmtdev_release;
+
+	ret = device_register(&vduse_mgmt->dev);
 	if (ret)
-		goto err;
+		goto dev_reg_err;
 
-	return 0;
-err:
-	device_unregister(&vduse_mgmtdev);
+	vduse_mgmt->mgmt_dev.id_table = id_table;
+	vduse_mgmt->mgmt_dev.ops = &vdpa_dev_mgmtdev_ops;
+	vduse_mgmt->mgmt_dev.device = &vduse_mgmt->dev;
+	ret = vdpa_mgmtdev_register(&vduse_mgmt->mgmt_dev);
+	if (ret)
+		device_unregister(&vduse_mgmt->dev);
+
+	return ret;
+
+dev_reg_err:
+	put_device(&vduse_mgmt->dev);
 	return ret;
 }
 
 static void vduse_mgmtdev_exit(void)
 {
-	vdpa_mgmtdev_unregister(&mgmt_dev);
-	device_unregister(&vduse_mgmtdev);
+	vdpa_mgmtdev_unregister(&vduse_mgmt->mgmt_dev);
+	device_unregister(&vduse_mgmt->dev);
 }
 
 static int vduse_init(void)
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 3c034fe14ccb..818e47fc0896 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -1850,6 +1850,7 @@ struct vfio_info_cap_header *vfio_info_cap_add(struct vfio_info_cap *caps,
 	buf = krealloc(caps->buf, caps->size + size, GFP_KERNEL);
 	if (!buf) {
 		kfree(caps->buf);
+		caps->buf = NULL;
 		caps->size = 0;
 		return ERR_PTR(-ENOMEM);
 	}
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 0e9217687f5c..852e6c5643e5 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -561,6 +561,18 @@ static int vaddr_get_pfns(struct mm_struct *mm, unsigned long vaddr,
 	ret = pin_user_pages_remote(mm, vaddr, npages, flags | FOLL_LONGTERM,
 				    pages, NULL, NULL);
 	if (ret > 0) {
+		int i;
+
+		/*
+		 * The zero page is always resident, we don't need to pin it
+		 * and it falls into our invalid/reserved test so we don't
+		 * unpin in put_pfn().  Unpin all zero pages in the batch here.
+		 */
+		for (i = 0 ; i < ret; i++) {
+			if (unlikely(is_zero_pfn(page_to_pfn(pages[i]))))
+				unpin_user_page(pages[i]);
+		}
+
 		*pfn = page_to_pfn(pages[0]);
 		goto done;
 	}
diff --git a/drivers/video/fbdev/amba-clcd.c b/drivers/video/fbdev/amba-clcd.c
index 8080116aea84..f65c96d1394d 100644
--- a/drivers/video/fbdev/amba-clcd.c
+++ b/drivers/video/fbdev/amba-clcd.c
@@ -698,16 +698,18 @@ static int clcdfb_of_init_display(struct clcd_fb *fb)
 		return -ENODEV;
 
 	panel = of_graph_get_remote_port_parent(endpoint);
-	if (!panel)
-		return -ENODEV;
+	if (!panel) {
+		err = -ENODEV;
+		goto out_endpoint_put;
+	}
 
 	err = clcdfb_of_get_backlight(&fb->dev->dev, fb->panel);
 	if (err)
-		return err;
+		goto out_panel_put;
 
 	err = clcdfb_of_get_mode(&fb->dev->dev, panel, fb->panel);
 	if (err)
-		return err;
+		goto out_panel_put;
 
 	err = of_property_read_u32(fb->dev->dev.of_node, "max-memory-bandwidth",
 			&max_bandwidth);
@@ -736,11 +738,21 @@ static int clcdfb_of_init_display(struct clcd_fb *fb)
 
 	if (of_property_read_u32_array(endpoint,
 			"arm,pl11x,tft-r0g0b0-pads",
-			tft_r0b0g0, ARRAY_SIZE(tft_r0b0g0)) != 0)
-		return -ENOENT;
+			tft_r0b0g0, ARRAY_SIZE(tft_r0b0g0)) != 0) {
+		err = -ENOENT;
+		goto out_panel_put;
+	}
+
+	of_node_put(panel);
+	of_node_put(endpoint);
 
 	return clcdfb_of_init_tft_panel(fb, tft_r0b0g0[0],
 					tft_r0b0g0[1],  tft_r0b0g0[2]);
+out_panel_put:
+	of_node_put(panel);
+out_endpoint_put:
+	of_node_put(endpoint);
+	return err;
 }
 
 static int clcdfb_of_vram_setup(struct clcd_fb *fb)
diff --git a/drivers/video/fbdev/arkfb.c b/drivers/video/fbdev/arkfb.c
index edf169d0816e..8d092b106470 100644
--- a/drivers/video/fbdev/arkfb.c
+++ b/drivers/video/fbdev/arkfb.c
@@ -778,7 +778,12 @@ static int arkfb_set_par(struct fb_info *info)
 		return -EINVAL;
 	}
 
-	ark_set_pixclock(info, (hdiv * info->var.pixclock) / hmul);
+	value = (hdiv * info->var.pixclock) / hmul;
+	if (!value) {
+		fb_dbg(info, "invalid pixclock\n");
+		value = 1;
+	}
+	ark_set_pixclock(info, value);
 	svga_set_timings(par->state.vgabase, &ark_timing_regs, &(info->var), hmul, hdiv,
 			 (info->var.vmode & FB_VMODE_DOUBLE)     ? 2 : 1,
 			 (info->var.vmode & FB_VMODE_INTERLACED) ? 2 : 1,
@@ -789,6 +794,8 @@ static int arkfb_set_par(struct fb_info *info)
 	value = ((value * hmul / hdiv) / 8) - 5;
 	vga_wcrt(par->state.vgabase, 0x42, (value + 1) / 2);
 
+	if (screen_size > info->screen_size)
+		screen_size = info->screen_size;
 	memset_io(info->screen_base, 0x00, screen_size);
 	/* Device and screen back on */
 	svga_wcrt_mask(par->state.vgabase, 0x17, 0x80, 0x80);
diff --git a/drivers/video/fbdev/chipsfb.c b/drivers/video/fbdev/chipsfb.c
index 393894af26f8..2b00a9d554fc 100644
--- a/drivers/video/fbdev/chipsfb.c
+++ b/drivers/video/fbdev/chipsfb.c
@@ -430,6 +430,7 @@ static int chipsfb_pci_init(struct pci_dev *dp, const struct pci_device_id *ent)
  err_release_fb:
 	framebuffer_release(p);
  err_disable:
+	pci_disable_device(dp);
  err_out:
 	return rc;
 }
diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c
index a25b63b56223..e035a63bbe5b 100644
--- a/drivers/video/fbdev/core/fbcon.c
+++ b/drivers/video/fbdev/core/fbcon.c
@@ -115,8 +115,8 @@ static int logo_lines;
    enums.  */
 static int logo_shown = FBCON_LOGO_CANSHOW;
 /* console mappings */
-static int first_fb_vc;
-static int last_fb_vc = MAX_NR_CONSOLES - 1;
+static unsigned int first_fb_vc;
+static unsigned int last_fb_vc = MAX_NR_CONSOLES - 1;
 static int fbcon_is_default = 1; 
 static int primary_device = -1;
 static int fbcon_has_console_bind;
@@ -464,10 +464,12 @@ static int __init fb_console_setup(char *this_opt)
 			options += 3;
 			if (*options)
 				first_fb_vc = simple_strtoul(options, &options, 10) - 1;
-			if (first_fb_vc < 0)
+			if (first_fb_vc >= MAX_NR_CONSOLES)
 				first_fb_vc = 0;
 			if (*options++ == '-')
 				last_fb_vc = simple_strtoul(options, &options, 10) - 1;
+			if (last_fb_vc < first_fb_vc || last_fb_vc >= MAX_NR_CONSOLES)
+				last_fb_vc = MAX_NR_CONSOLES - 1;
 			fbcon_is_default = 0; 
 			continue;
 		}
@@ -1704,8 +1706,6 @@ static bool fbcon_scroll(struct vc_data *vc, unsigned int t, unsigned int b,
 	case SM_UP:
 		if (count > vc->vc_rows)	/* Maximum realistic size */
 			count = vc->vc_rows;
-		if (logo_shown >= 0)
-			goto redraw_up;
 		switch (fb_scrollmode(p)) {
 		case SCROLL_MOVE:
 			fbcon_redraw_blit(vc, info, p, t, b - t - count,
@@ -1794,8 +1794,6 @@ static bool fbcon_scroll(struct vc_data *vc, unsigned int t, unsigned int b,
 	case SM_DOWN:
 		if (count > vc->vc_rows)	/* Maximum realistic size */
 			count = vc->vc_rows;
-		if (logo_shown >= 0)
-			goto redraw_down;
 		switch (fb_scrollmode(p)) {
 		case SCROLL_MOVE:
 			fbcon_redraw_blit(vc, info, p, b - 1, b - t - count,
@@ -2415,15 +2413,21 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount,
 	struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]];
 	struct fbcon_ops *ops = info->fbcon_par;
 	struct fbcon_display *p = &fb_display[vc->vc_num];
-	int resize;
+	int resize, ret, old_userfont, old_width, old_height, old_charcount;
 	char *old_data = NULL;
 
 	resize = (w != vc->vc_font.width) || (h != vc->vc_font.height);
 	if (p->userfont)
 		old_data = vc->vc_font.data;
 	vc->vc_font.data = (void *)(p->fontdata = data);
+	old_userfont = p->userfont;
 	if ((p->userfont = userfont))
 		REFCOUNT(data)++;
+
+	old_width = vc->vc_font.width;
+	old_height = vc->vc_font.height;
+	old_charcount = vc->vc_font.charcount;
+
 	vc->vc_font.width = w;
 	vc->vc_font.height = h;
 	vc->vc_font.charcount = charcount;
@@ -2439,7 +2443,9 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount,
 		rows = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres);
 		cols /= w;
 		rows /= h;
-		vc_resize(vc, cols, rows);
+		ret = vc_resize(vc, cols, rows);
+		if (ret)
+			goto err_out;
 	} else if (con_is_visible(vc)
 		   && vc->vc_mode == KD_TEXT) {
 		fbcon_clear_margins(vc, 0);
@@ -2449,6 +2455,21 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount,
 	if (old_data && (--REFCOUNT(old_data) == 0))
 		kfree(old_data - FONT_EXTRA_WORDS * sizeof(int));
 	return 0;
+
+err_out:
+	p->fontdata = old_data;
+	vc->vc_font.data = (void *)old_data;
+
+	if (userfont) {
+		p->userfont = old_userfont;
+		REFCOUNT(data)--;
+	}
+
+	vc->vc_font.width = old_width;
+	vc->vc_font.height = old_height;
+	vc->vc_font.charcount = old_charcount;
+
+	return ret;
 }
 
 /*
@@ -2480,6 +2501,11 @@ static int fbcon_set_font(struct vc_data *vc, struct console_font *font,
 	if (charcount != 256 && charcount != 512)
 		return -EINVAL;
 
+	/* font bigger than screen resolution ? */
+	if (w > FBCON_SWAP(info->var.rotate, info->var.xres, info->var.yres) ||
+	    h > FBCON_SWAP(info->var.rotate, info->var.yres, info->var.xres))
+		return -EINVAL;
+
 	/* Make sure drawing engine can handle the font */
 	if (!(info->pixmap.blit_x & (1 << (font->width - 1))) ||
 	    !(info->pixmap.blit_y & (1 << (font->height - 1))))
@@ -2742,6 +2768,34 @@ void fbcon_update_vcs(struct fb_info *info, bool all)
 }
 EXPORT_SYMBOL(fbcon_update_vcs);
 
+/* let fbcon check if it supports a new screen resolution */
+int fbcon_modechange_possible(struct fb_info *info, struct fb_var_screeninfo *var)
+{
+	struct fbcon_ops *ops = info->fbcon_par;
+	struct vc_data *vc;
+	unsigned int i;
+
+	WARN_CONSOLE_UNLOCKED();
+
+	if (!ops)
+		return 0;
+
+	/* prevent setting a screen size which is smaller than font size */
+	for (i = first_fb_vc; i <= last_fb_vc; i++) {
+		vc = vc_cons[i].d;
+		if (!vc || vc->vc_mode != KD_TEXT ||
+			   registered_fb[con2fb_map[i]] != info)
+			continue;
+
+		if (vc->vc_font.width  > FBCON_SWAP(var->rotate, var->xres, var->yres) ||
+		    vc->vc_font.height > FBCON_SWAP(var->rotate, var->yres, var->xres))
+			return -EINVAL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(fbcon_modechange_possible);
+
 int fbcon_mode_deleted(struct fb_info *info,
 		       struct fb_videomode *mode)
 {
diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c
index dedfb363d6bd..4cca10e9576c 100644
--- a/drivers/video/fbdev/core/fbmem.c
+++ b/drivers/video/fbdev/core/fbmem.c
@@ -19,6 +19,7 @@
 #include <linux/kernel.h>
 #include <linux/major.h>
 #include <linux/slab.h>
+#include <linux/sysfb.h>
 #include <linux/mm.h>
 #include <linux/mman.h>
 #include <linux/vt.h>
@@ -514,7 +515,7 @@ static int fb_show_logo_line(struct fb_info *info, int rotate,
 
 		while (n && (n * (logo->width + 8) - 8 > xres))
 			--n;
-		image.dx = (xres - n * (logo->width + 8) - 8) / 2;
+		image.dx = (xres - (n * (logo->width + 8) - 8)) / 2;
 		image.dy = y ?: (yres - logo->height) / 2;
 	} else {
 		image.dx = 0;
@@ -1020,6 +1021,16 @@ fb_set_var(struct fb_info *info, struct fb_var_screeninfo *var)
 	if (ret)
 		return ret;
 
+	/* verify that virtual resolution >= physical resolution */
+	if (var->xres_virtual < var->xres ||
+	    var->yres_virtual < var->yres) {
+		pr_warn("WARNING: fbcon: Driver '%s' missed to adjust virtual screen size (%ux%u vs. %ux%u)\n",
+			info->fix.id,
+			var->xres_virtual, var->yres_virtual,
+			var->xres, var->yres);
+		return -EINVAL;
+	}
+
 	if ((var->activate & FB_ACTIVATE_MASK) != FB_ACTIVATE_NOW)
 		return 0;
 
@@ -1110,7 +1121,9 @@ static long do_fb_ioctl(struct fb_info *info, unsigned int cmd,
 			return -EFAULT;
 		console_lock();
 		lock_fb_info(info);
-		ret = fb_set_var(info, &var);
+		ret = fbcon_modechange_possible(info, &var);
+		if (!ret)
+			ret = fb_set_var(info, &var);
 		if (!ret)
 			fbcon_update_vcs(info, var.activate & FB_ACTIVATE_ALL);
 		unlock_fb_info(info);
@@ -1774,6 +1787,17 @@ int remove_conflicting_framebuffers(struct apertures_struct *a,
 		do_free = true;
 	}
 
+	/*
+	 * If a driver asked to unregister a platform device registered by
+	 * sysfb, then can be assumed that this is a driver for a display
+	 * that is set up by the system firmware and has a generic driver.
+	 *
+	 * Drivers for devices that don't have a generic driver will never
+	 * ask for this, so let's assume that a real driver for the display
+	 * was already probed and prevent sysfb to register devices later.
+	 */
+	sysfb_disable();
+
 	mutex_lock(&registration_lock);
 	do_remove_conflicting_framebuffers(a, name, primary);
 	mutex_unlock(&registration_lock);
diff --git a/drivers/video/fbdev/core/fbsysfs.c b/drivers/video/fbdev/core/fbsysfs.c
index ce699396d6ba..09ee27e7fc25 100644
--- a/drivers/video/fbdev/core/fbsysfs.c
+++ b/drivers/video/fbdev/core/fbsysfs.c
@@ -84,6 +84,10 @@ void framebuffer_release(struct fb_info *info)
 	if (WARN_ON(refcount_read(&info->count)))
 		return;
 
+#if IS_ENABLED(CONFIG_FB_BACKLIGHT)
+	mutex_destroy(&info->bl_curve_mutex);
+#endif
+
 	kfree(info->apertures);
 	kfree(info);
 }
diff --git a/drivers/video/fbdev/i740fb.c b/drivers/video/fbdev/i740fb.c
index 52cce0db8bd3..8fb4e01e1943 100644
--- a/drivers/video/fbdev/i740fb.c
+++ b/drivers/video/fbdev/i740fb.c
@@ -400,7 +400,7 @@ static int i740fb_decode_var(const struct fb_var_screeninfo *var,
 	u32 xres, right, hslen, left, xtotal;
 	u32 yres, lower, vslen, upper, ytotal;
 	u32 vxres, xoffset, vyres, yoffset;
-	u32 bpp, base, dacspeed24, mem;
+	u32 bpp, base, dacspeed24, mem, freq;
 	u8 r7;
 	int i;
 
@@ -643,7 +643,12 @@ static int i740fb_decode_var(const struct fb_var_screeninfo *var,
 	par->atc[VGA_ATC_OVERSCAN] = 0;
 
 	/* Calculate VCLK that most closely matches the requested dot clock */
-	i740_calc_vclk((((u32)1e9) / var->pixclock) * (u32)(1e3), par);
+	freq = (((u32)1e9) / var->pixclock) * (u32)(1e3);
+	if (freq < I740_RFREQ_FIX) {
+		fb_dbg(info, "invalid pixclock\n");
+		freq = I740_RFREQ_FIX;
+	}
+	i740_calc_vclk(freq, par);
 
 	/* Since we program the clocks ourselves, always use VCLK2. */
 	par->misc |= 0x0C;
@@ -657,6 +662,9 @@ static int i740fb_decode_var(const struct fb_var_screeninfo *var,
 
 static int i740fb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
 {
+	if (!var->pixclock)
+		return -EINVAL;
+
 	switch (var->bits_per_pixel) {
 	case 8:
 		var->red.offset	= var->green.offset = var->blue.offset = 0;
diff --git a/drivers/video/fbdev/pm2fb.c b/drivers/video/fbdev/pm2fb.c
index c68725eebee3..cbcf112c88d3 100644
--- a/drivers/video/fbdev/pm2fb.c
+++ b/drivers/video/fbdev/pm2fb.c
@@ -617,6 +617,11 @@ static int pm2fb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
 		return -EINVAL;
 	}
 
+	if (!var->pixclock) {
+		DPRINTK("pixclock is zero\n");
+		return -EINVAL;
+	}
+
 	if (PICOS2KHZ(var->pixclock) > PM2_MAX_PIXCLOCK) {
 		DPRINTK("pixclock too high (%ldKHz)\n",
 			PICOS2KHZ(var->pixclock));
diff --git a/drivers/video/fbdev/pxa3xx-gcu.c b/drivers/video/fbdev/pxa3xx-gcu.c
index 9421d14d0eb0..9e9888e40c57 100644
--- a/drivers/video/fbdev/pxa3xx-gcu.c
+++ b/drivers/video/fbdev/pxa3xx-gcu.c
@@ -381,7 +381,7 @@ pxa3xx_gcu_write(struct file *file, const char *buff,
 	struct pxa3xx_gcu_batch	*buffer;
 	struct pxa3xx_gcu_priv *priv = to_pxa3xx_gcu_priv(file);
 
-	int words = count / 4;
+	size_t words = count / 4;
 
 	/* Does not need to be atomic. There's a lock in user space,
 	 * but anyhow, this is just for statistics. */
diff --git a/drivers/video/fbdev/s3fb.c b/drivers/video/fbdev/s3fb.c
index 5c74253e7b2c..a936455a3df2 100644
--- a/drivers/video/fbdev/s3fb.c
+++ b/drivers/video/fbdev/s3fb.c
@@ -902,6 +902,8 @@ static int s3fb_set_par(struct fb_info *info)
 	value = clamp((htotal + hsstart + 1) / 2 + 2, hsstart + 4, htotal + 1);
 	svga_wcrt_multi(par->state.vgabase, s3_dtpc_regs, value);
 
+	if (screen_size > info->screen_size)
+		screen_size = info->screen_size;
 	memset_io(info->screen_base, 0x00, screen_size);
 	/* Device and screen back on */
 	svga_wcrt_mask(par->state.vgabase, 0x17, 0x80, 0x80);
diff --git a/drivers/video/fbdev/sis/init.c b/drivers/video/fbdev/sis/init.c
index b568c646a76c..2ba91d62af92 100644
--- a/drivers/video/fbdev/sis/init.c
+++ b/drivers/video/fbdev/sis/init.c
@@ -355,12 +355,12 @@ SiS_GetModeID(int VGAEngine, unsigned int VBFlags, int HDisplay, int VDisplay,
 		}
 		break;
 	case 400:
-		if((!(VBFlags & CRT1_LCDA)) || ((LCDwidth >= 800) && (LCDwidth >= 600))) {
+		if((!(VBFlags & CRT1_LCDA)) || ((LCDwidth >= 800) && (LCDheight >= 600))) {
 			if(VDisplay == 300) ModeIndex = ModeIndex_400x300[Depth];
 		}
 		break;
 	case 512:
-		if((!(VBFlags & CRT1_LCDA)) || ((LCDwidth >= 1024) && (LCDwidth >= 768))) {
+		if((!(VBFlags & CRT1_LCDA)) || ((LCDwidth >= 1024) && (LCDheight >= 768))) {
 			if(VDisplay == 384) ModeIndex = ModeIndex_512x384[Depth];
 		}
 		break;
diff --git a/drivers/video/fbdev/vt8623fb.c b/drivers/video/fbdev/vt8623fb.c
index 7a959e5ba90b..c274ec5e965c 100644
--- a/drivers/video/fbdev/vt8623fb.c
+++ b/drivers/video/fbdev/vt8623fb.c
@@ -504,6 +504,8 @@ static int vt8623fb_set_par(struct fb_info *info)
 			 (info->var.vmode & FB_VMODE_DOUBLE) ? 2 : 1, 1,
 			 1, info->node);
 
+	if (screen_size > info->screen_size)
+		screen_size = info->screen_size;
 	memset_io(info->screen_base, 0x00, screen_size);
 
 	/* Device and screen back on */
diff --git a/drivers/virt/vboxguest/vboxguest_linux.c b/drivers/virt/vboxguest/vboxguest_linux.c
index 73eb34849eab..4ccfd30c2a30 100644
--- a/drivers/virt/vboxguest/vboxguest_linux.c
+++ b/drivers/virt/vboxguest/vboxguest_linux.c
@@ -356,8 +356,8 @@ static int vbg_pci_probe(struct pci_dev *pci, const struct pci_device_id *id)
 		goto err_vbg_core_exit;
 	}
 
-	ret = devm_request_irq(dev, pci->irq, vbg_core_isr, IRQF_SHARED,
-			       DEVICE_NAME, gdev);
+	ret = request_irq(pci->irq, vbg_core_isr, IRQF_SHARED, DEVICE_NAME,
+			  gdev);
 	if (ret) {
 		vbg_err("vboxguest: Error requesting irq: %d\n", ret);
 		goto err_vbg_core_exit;
@@ -367,7 +367,7 @@ static int vbg_pci_probe(struct pci_dev *pci, const struct pci_device_id *id)
 	if (ret) {
 		vbg_err("vboxguest: Error misc_register %s failed: %d\n",
 			DEVICE_NAME, ret);
-		goto err_vbg_core_exit;
+		goto err_free_irq;
 	}
 
 	ret = misc_register(&gdev->misc_device_user);
@@ -403,6 +403,8 @@ err_unregister_misc_device_user:
 	misc_deregister(&gdev->misc_device_user);
 err_unregister_misc_device:
 	misc_deregister(&gdev->misc_device);
+err_free_irq:
+	free_irq(pci->irq, gdev);
 err_vbg_core_exit:
 	vbg_core_exit(gdev);
 err_disable_pcidev:
@@ -419,6 +421,7 @@ static void vbg_pci_remove(struct pci_dev *pci)
 	vbg_gdev = NULL;
 	mutex_unlock(&vbg_gdev_mutex);
 
+	free_irq(pci->irq, gdev);
 	device_remove_file(gdev->dev, &dev_attr_host_features);
 	device_remove_file(gdev->dev, &dev_attr_host_version);
 	misc_deregister(&gdev->misc_device_user);
diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index 1dd396d4bebb..fe696aafaed8 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -62,6 +62,7 @@
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/virtio.h>
@@ -543,6 +544,28 @@ static const struct virtio_config_ops virtio_mmio_config_ops = {
 	.get_shm_region = vm_get_shm_region,
 };
 
+#ifdef CONFIG_PM_SLEEP
+static int virtio_mmio_freeze(struct device *dev)
+{
+	struct virtio_mmio_device *vm_dev = dev_get_drvdata(dev);
+
+	return virtio_device_freeze(&vm_dev->vdev);
+}
+
+static int virtio_mmio_restore(struct device *dev)
+{
+	struct virtio_mmio_device *vm_dev = dev_get_drvdata(dev);
+
+	if (vm_dev->version == 1)
+		writel(PAGE_SIZE, vm_dev->base + VIRTIO_MMIO_GUEST_PAGE_SIZE);
+
+	return virtio_device_restore(&vm_dev->vdev);
+}
+
+static const struct dev_pm_ops virtio_mmio_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(virtio_mmio_freeze, virtio_mmio_restore)
+};
+#endif
 
 static void virtio_mmio_release_dev(struct device *_d)
 {
@@ -786,6 +809,9 @@ static struct platform_driver virtio_mmio_driver = {
 		.name	= "virtio-mmio",
 		.of_match_table	= virtio_mmio_match,
 		.acpi_match_table = ACPI_PTR(virtio_mmio_acpi_match),
+#ifdef CONFIG_PM_SLEEP
+		.pm	= &virtio_mmio_pm_ops,
+#endif
 	},
 };
 
diff --git a/drivers/watchdog/armada_37xx_wdt.c b/drivers/watchdog/armada_37xx_wdt.c
index 1635f421ef2c..854b1cc723cb 100644
--- a/drivers/watchdog/armada_37xx_wdt.c
+++ b/drivers/watchdog/armada_37xx_wdt.c
@@ -274,6 +274,8 @@ static int armada_37xx_wdt_probe(struct platform_device *pdev)
 	if (!res)
 		return -ENODEV;
 	dev->reg = devm_ioremap(&pdev->dev, res->start, resource_size(res));
+	if (!dev->reg)
+		return -ENOMEM;
 
 	/* init clock */
 	dev->clk = devm_clk_get(&pdev->dev, NULL);
diff --git a/drivers/watchdog/sp5100_tco.c b/drivers/watchdog/sp5100_tco.c
index 4820af929a82..4afc468d8ed1 100644
--- a/drivers/watchdog/sp5100_tco.c
+++ b/drivers/watchdog/sp5100_tco.c
@@ -394,6 +394,7 @@ out:
 		iounmap(addr);
 
 	release_resource(res);
+	kfree(res);
 
 	return ret;
 }
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index 4b56c39f766d..84b143eef395 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -396,13 +396,15 @@ static void __unmap_grant_pages_done(int result,
 	unsigned int offset = data->unmap_ops - map->unmap_ops;
 
 	for (i = 0; i < data->count; i++) {
-		WARN_ON(map->unmap_ops[offset+i].status);
+		WARN_ON(map->unmap_ops[offset + i].status != GNTST_okay &&
+			map->unmap_ops[offset + i].handle != INVALID_GRANT_HANDLE);
 		pr_debug("unmap handle=%d st=%d\n",
 			map->unmap_ops[offset+i].handle,
 			map->unmap_ops[offset+i].status);
 		map->unmap_ops[offset+i].handle = INVALID_GRANT_HANDLE;
 		if (use_ptemod) {
-			WARN_ON(map->kunmap_ops[offset+i].status);
+			WARN_ON(map->kunmap_ops[offset + i].status != GNTST_okay &&
+				map->kunmap_ops[offset + i].handle != INVALID_GRANT_HANDLE);
 			pr_debug("kunmap handle=%u st=%d\n",
 				 map->kunmap_ops[offset+i].handle,
 				 map->kunmap_ops[offset+i].status);
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index 5c83d41766c8..0a2d24d6ac6f 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -981,6 +981,9 @@ int gnttab_dma_alloc_pages(struct gnttab_dma_alloc_args *args)
 	size_t size;
 	int i, ret;
 
+	if (args->nr_pages < 0 || args->nr_pages > (INT_MAX >> PAGE_SHIFT))
+		return -ENOMEM;
+
 	size = args->nr_pages << PAGE_SHIFT;
 	if (args->coherent)
 		args->vaddr = dma_alloc_coherent(args->dev, size,
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index 3369734108af..e88e8f6f0a33 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -581,27 +581,30 @@ static int lock_pages(
 	struct privcmd_dm_op_buf kbufs[], unsigned int num,
 	struct page *pages[], unsigned int nr_pages, unsigned int *pinned)
 {
-	unsigned int i;
+	unsigned int i, off = 0;
 
-	for (i = 0; i < num; i++) {
+	for (i = 0; i < num; ) {
 		unsigned int requested;
 		int page_count;
 
 		requested = DIV_ROUND_UP(
 			offset_in_page(kbufs[i].uptr) + kbufs[i].size,
-			PAGE_SIZE);
+			PAGE_SIZE) - off;
 		if (requested > nr_pages)
 			return -ENOSPC;
 
 		page_count = pin_user_pages_fast(
-			(unsigned long) kbufs[i].uptr,
+			(unsigned long)kbufs[i].uptr + off * PAGE_SIZE,
 			requested, FOLL_WRITE, pages);
-		if (page_count < 0)
-			return page_count;
+		if (page_count <= 0)
+			return page_count ? : -EFAULT;
 
 		*pinned += page_count;
 		nr_pages -= page_count;
 		pages += page_count;
+
+		off = (requested == page_count) ? 0 : off + page_count;
+		i += !off;
 	}
 
 	return 0;
@@ -677,10 +680,8 @@ static long privcmd_ioctl_dm_op(struct file *file, void __user *udata)
 	}
 
 	rc = lock_pages(kbufs, kdata.num, pages, nr_pages, &pinned);
-	if (rc < 0) {
-		nr_pages = pinned;
+	if (rc < 0)
 		goto out;
-	}
 
 	for (i = 0; i < kdata.num; i++) {
 		set_xen_guest_handle(xbufs[i].h, kbufs[i].uptr);
@@ -692,7 +693,7 @@ static long privcmd_ioctl_dm_op(struct file *file, void __user *udata)
 	xen_preemptible_hcall_end();
 
 out:
-	unlock_pages(pages, nr_pages);
+	unlock_pages(pages, pinned);
 	kfree(xbufs);
 	kfree(pages);
 	kfree(kbufs);
diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c
index 597af455a522..0792fda49a15 100644
--- a/drivers/xen/xenbus/xenbus_dev_frontend.c
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -128,7 +128,7 @@ static ssize_t xenbus_file_read(struct file *filp,
 {
 	struct xenbus_file_priv *u = filp->private_data;
 	struct read_buffer *rb;
-	unsigned i;
+	ssize_t i;
 	int ret;
 
 	mutex_lock(&u->reply_mutex);
@@ -148,7 +148,7 @@ again:
 	rb = list_entry(u->read_buffers.next, struct read_buffer, list);
 	i = 0;
 	while (i < len) {
-		unsigned sz = min((unsigned)len - i, rb->len - rb->cons);
+		size_t sz = min_t(size_t, len - i, rb->len - rb->cons);
 
 		ret = copy_to_user(ubuf + i, &rb->msg[rb->cons], sz);
 
diff --git a/fs/9p/acl.c b/fs/9p/acl.c
index c381499f5416..da22415ed036 100644
--- a/fs/9p/acl.c
+++ b/fs/9p/acl.c
@@ -123,6 +123,7 @@ static int v9fs_set_acl(struct p9_fid *fid, int type, struct posix_acl *acl)
 	char *name;
 	size_t size;
 	void *buffer;
+
 	if (!acl)
 		return 0;
 
diff --git a/fs/9p/acl.h b/fs/9p/acl.h
index d43c8949e807..bc87b36f529e 100644
--- a/fs/9p/acl.h
+++ b/fs/9p/acl.h
@@ -15,14 +15,15 @@
 #define FS_9P_ACL_H
 
 #ifdef CONFIG_9P_FS_POSIX_ACL
-extern int v9fs_get_acl(struct inode *, struct p9_fid *);
-extern struct posix_acl *v9fs_iop_get_acl(struct inode *inode, int type, bool rcu);
-extern int v9fs_acl_chmod(struct inode *, struct p9_fid *);
-extern int v9fs_set_create_acl(struct inode *, struct p9_fid *,
-			       struct posix_acl *, struct posix_acl *);
-extern int v9fs_acl_mode(struct inode *dir, umode_t *modep,
-			 struct posix_acl **dpacl, struct posix_acl **pacl);
-extern void v9fs_put_acl(struct posix_acl *dacl, struct posix_acl *acl);
+int v9fs_get_acl(struct inode *inode, struct p9_fid *fid);
+struct posix_acl *v9fs_iop_get_acl(struct inode *inode, int type,
+				   bool rcu);
+int v9fs_acl_chmod(struct inode *inode, struct p9_fid *fid);
+int v9fs_set_create_acl(struct inode *inode, struct p9_fid *fid,
+			struct posix_acl *dacl, struct posix_acl *acl);
+int v9fs_acl_mode(struct inode *dir, umode_t *modep,
+		  struct posix_acl **dpacl, struct posix_acl **pacl);
+void v9fs_put_acl(struct posix_acl *dacl, struct posix_acl *acl);
 #else
 #define v9fs_iop_get_acl NULL
 static inline int v9fs_get_acl(struct inode *inode, struct p9_fid *fid)
diff --git a/fs/9p/cache.c b/fs/9p/cache.c
index 1769a44f4819..41da71320482 100644
--- a/fs/9p/cache.c
+++ b/fs/9p/cache.c
@@ -19,8 +19,8 @@
 #define CACHETAG_LEN  11
 
 struct fscache_netfs v9fs_cache_netfs = {
-	.name 		= "9p",
-	.version 	= 0,
+	.name		= "9p",
+	.version	= 0,
 };
 
 /*
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index 2e0fa7c932db..141067379f5e 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -190,8 +190,10 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts)
 
 	while ((p = strsep(&options, ",")) != NULL) {
 		int token, r;
+
 		if (!*p)
 			continue;
+
 		token = match_token(p, tokens, args);
 		switch (token) {
 		case Opt_debug:
@@ -659,6 +661,7 @@ static void v9fs_destroy_inode_cache(void)
 static int v9fs_cache_register(void)
 {
 	int ret;
+
 	ret = v9fs_init_inode_cache();
 	if (ret < 0)
 		return ret;
@@ -686,6 +689,7 @@ static void v9fs_cache_unregister(void)
 static int __init init_v9fs(void)
 {
 	int err;
+
 	pr_info("Installing v9fs 9p2000 file system support\n");
 	/* TODO: Setup list of registered trasnport modules */
 
diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h
index d44ade76966a..bc417da7e9c1 100644
--- a/fs/9p/v9fs_vfs.h
+++ b/fs/9p/v9fs_vfs.h
@@ -44,9 +44,10 @@ extern struct kmem_cache *v9fs_inode_cache;
 
 struct inode *v9fs_alloc_inode(struct super_block *sb);
 void v9fs_free_inode(struct inode *inode);
-struct inode *v9fs_get_inode(struct super_block *sb, umode_t mode, dev_t);
+struct inode *v9fs_get_inode(struct super_block *sb, umode_t mode,
+			     dev_t rdev);
 int v9fs_init_inode(struct v9fs_session_info *v9ses,
-		    struct inode *inode, umode_t mode, dev_t);
+		    struct inode *inode, umode_t mode, dev_t rdev);
 void v9fs_evict_inode(struct inode *inode);
 ino_t v9fs_qid2ino(struct p9_qid *qid);
 void v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode,
@@ -59,8 +60,8 @@ void v9fs_inode2stat(struct inode *inode, struct p9_wstat *stat);
 int v9fs_uflags2omode(int uflags, int extended);
 
 void v9fs_blank_wstat(struct p9_wstat *wstat);
-int v9fs_vfs_setattr_dotl(struct user_namespace *, struct dentry *,
-			  struct iattr *);
+int v9fs_vfs_setattr_dotl(struct user_namespace *mnt_userns,
+			  struct dentry *dentry, struct iattr *iattr);
 int v9fs_file_fsync_dotl(struct file *filp, loff_t start, loff_t end,
 			 int datasync);
 int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode);
@@ -68,9 +69,9 @@ int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode);
 static inline void v9fs_invalidate_inode_attr(struct inode *inode)
 {
 	struct v9fs_inode *v9inode;
+
 	v9inode = V9FS_I(inode);
 	v9inode->cache_validity |= V9FS_INO_INVALID_ATTR;
-	return;
 }
 
 int v9fs_open_to_dotl_flags(int flags);
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index 1c4f1b39cc95..606d33ef35c6 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -242,11 +242,13 @@ v9fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	loff_t pos = iocb->ki_pos;
 	ssize_t n;
 	int err = 0;
+
 	if (iov_iter_rw(iter) == WRITE) {
 		n = p9_client_write(file->private_data, pos, iter, &err);
 		if (n) {
 			struct inode *inode = file_inode(file);
 			loff_t i_size = i_size_read(inode);
+
 			if (pos + n > i_size)
 				inode_add_bytes(inode, pos + n - i_size);
 		}
@@ -257,7 +259,7 @@ v9fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 }
 
 static int v9fs_write_begin(struct file *filp, struct address_space *mapping,
-			    loff_t pos, unsigned len, unsigned flags,
+			    loff_t pos, unsigned int len, unsigned int flags,
 			    struct page **pagep, void **fsdata)
 {
 	int retval = 0;
@@ -293,7 +295,7 @@ out:
 }
 
 static int v9fs_write_end(struct file *filp, struct address_space *mapping,
-			  loff_t pos, unsigned len, unsigned copied,
+			  loff_t pos, unsigned int len, unsigned int copied,
 			  struct page *page, void *fsdata)
 {
 	loff_t last_pos = pos + copied;
diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c
index 4b4292123b3d..c2736af97884 100644
--- a/fs/9p/vfs_dentry.c
+++ b/fs/9p/vfs_dentry.c
@@ -52,6 +52,7 @@ static int v9fs_cached_dentry_delete(const struct dentry *dentry)
 static void v9fs_dentry_release(struct dentry *dentry)
 {
 	struct hlist_node *p, *n;
+
 	p9_debug(P9_DEBUG_VFS, " dentry: %pd (%p)\n",
 		 dentry, dentry);
 	hlist_for_each_safe(p, n, (struct hlist_head *)&dentry->d_fsdata)
@@ -76,6 +77,7 @@ static int v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
 	if (v9inode->cache_validity & V9FS_INO_INVALID_ATTR) {
 		int retval;
 		struct v9fs_session_info *v9ses;
+
 		fid = v9fs_fid_lookup(dentry);
 		if (IS_ERR(fid))
 			return PTR_ERR(fid);
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 246235ebdb70..7437b185fa8e 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -408,6 +408,7 @@ v9fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		struct inode *inode = file_inode(file);
 		loff_t i_size;
 		unsigned long pg_start, pg_end;
+
 		pg_start = origin >> PAGE_SHIFT;
 		pg_end = (origin + retval - 1) >> PAGE_SHIFT;
 		if (inode->i_mapping && inode->i_mapping->nrpages)
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 15d9492536cf..0d9b7d453a87 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -49,6 +49,7 @@ static const struct inode_operations v9fs_symlink_inode_operations;
 static u32 unixmode2p9mode(struct v9fs_session_info *v9ses, umode_t mode)
 {
 	int res;
+
 	res = mode & 0777;
 	if (S_ISDIR(mode))
 		res |= P9_DMDIR;
@@ -223,6 +224,7 @@ v9fs_blank_wstat(struct p9_wstat *wstat)
 struct inode *v9fs_alloc_inode(struct super_block *sb)
 {
 	struct v9fs_inode *v9inode;
+
 	v9inode = kmem_cache_alloc(v9fs_inode_cache, GFP_KERNEL);
 	if (!v9inode)
 		return NULL;
@@ -251,7 +253,7 @@ int v9fs_init_inode(struct v9fs_session_info *v9ses,
 {
 	int err = 0;
 
-	inode_init_owner(&init_user_ns,inode,  NULL, mode);
+	inode_init_owner(&init_user_ns, inode, NULL, mode);
 	inode->i_blocks = 0;
 	inode->i_rdev = rdev;
 	inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
@@ -440,7 +442,7 @@ static struct inode *v9fs_qid_iget(struct super_block *sb,
 	unsigned long i_ino;
 	struct inode *inode;
 	struct v9fs_session_info *v9ses = sb->s_fs_info;
-	int (*test)(struct inode *, void *);
+	int (*test)(struct inode *inode, void *data);
 
 	if (new)
 		test = v9fs_test_new_inode;
@@ -499,8 +501,10 @@ v9fs_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid,
 static int v9fs_at_to_dotl_flags(int flags)
 {
 	int rflags = 0;
+
 	if (flags & AT_REMOVEDIR)
 		rflags |= P9_DOTL_AT_REMOVEDIR;
+
 	return rflags;
 }
 
@@ -797,7 +801,7 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
 
 static int
 v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry,
-		     struct file *file, unsigned flags, umode_t mode)
+		     struct file *file, unsigned int flags, umode_t mode)
 {
 	int err;
 	u32 perm;
@@ -1084,7 +1088,7 @@ static int v9fs_vfs_setattr(struct user_namespace *mnt_userns,
 		fid = v9fs_fid_lookup(dentry);
 		use_dentry = 1;
 	}
-	if(IS_ERR(fid))
+	if (IS_ERR(fid))
 		return PTR_ERR(fid);
 
 	v9fs_blank_wstat(&wstat);
@@ -1364,7 +1368,7 @@ v9fs_vfs_mknod(struct user_namespace *mnt_userns, struct inode *dir,
 	char name[2 + U32_MAX_DIGITS + 1 + U32_MAX_DIGITS + 1];
 	u32 perm;
 
-	p9_debug(P9_DEBUG_VFS, " %lu,%pd mode: %hx MAJOR: %u MINOR: %u\n",
+	p9_debug(P9_DEBUG_VFS, " %lu,%pd mode: %x MAJOR: %u MINOR: %u\n",
 		 dir->i_ino, dentry, mode,
 		 MAJOR(rdev), MINOR(rdev));
 
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index 833c638437a7..0f73aa26ddf4 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -107,7 +107,7 @@ static struct inode *v9fs_qid_iget_dotl(struct super_block *sb,
 	unsigned long i_ino;
 	struct inode *inode;
 	struct v9fs_session_info *v9ses = sb->s_fs_info;
-	int (*test)(struct inode *, void *);
+	int (*test)(struct inode *inode, void *data);
 
 	if (new)
 		test = v9fs_test_new_inode_dotl;
@@ -230,7 +230,7 @@ v9fs_vfs_create_dotl(struct user_namespace *mnt_userns, struct inode *dir,
 
 static int
 v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
-			  struct file *file, unsigned flags, umode_t omode)
+			  struct file *file, unsigned int flags, umode_t omode)
 {
 	int err = 0;
 	kgid_t gid;
@@ -261,7 +261,7 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
 	v9ses = v9fs_inode2v9ses(dir);
 
 	name = dentry->d_name.name;
-	p9_debug(P9_DEBUG_VFS, "name:%s flags:0x%x mode:0x%hx\n",
+	p9_debug(P9_DEBUG_VFS, "name:%s flags:0x%x mode:0x%x\n",
 		 name, flags, omode);
 
 	dfid = v9fs_parent_fid(dentry);
@@ -821,6 +821,7 @@ v9fs_vfs_link_dotl(struct dentry *old_dentry, struct inode *dir,
 	if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) {
 		/* Get the latest stat info from server. */
 		struct p9_fid *fid;
+
 		fid = v9fs_fid_lookup(old_dentry);
 		if (IS_ERR(fid))
 			return PTR_ERR(fid);
@@ -857,7 +858,7 @@ v9fs_vfs_mknod_dotl(struct user_namespace *mnt_userns, struct inode *dir,
 	struct p9_qid qid;
 	struct posix_acl *dacl = NULL, *pacl = NULL;
 
-	p9_debug(P9_DEBUG_VFS, " %lu,%pd mode: %hx MAJOR: %u MINOR: %u\n",
+	p9_debug(P9_DEBUG_VFS, " %lu,%pd mode: %x MAJOR: %u MINOR: %u\n",
 		 dir->i_ino, dentry, omode,
 		 MAJOR(rdev), MINOR(rdev));
 
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index 5fce6e30bc5a..7449f7fd47d2 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -113,7 +113,7 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags,
 	struct inode *inode = NULL;
 	struct dentry *root = NULL;
 	struct v9fs_session_info *v9ses = NULL;
-	umode_t mode = S_IRWXUGO | S_ISVTX;
+	umode_t mode = 0777 | S_ISVTX;
 	struct p9_fid *fid;
 	int retval = 0;
 
@@ -157,6 +157,7 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags,
 	sb->s_root = root;
 	if (v9fs_proto_dotl(v9ses)) {
 		struct p9_stat_dotl *st = NULL;
+
 		st = p9_client_getattr_dotl(fid, P9_STATS_BASIC);
 		if (IS_ERR(st)) {
 			retval = PTR_ERR(st);
@@ -167,6 +168,7 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags,
 		kfree(st);
 	} else {
 		struct p9_wstat *st = NULL;
+
 		st = p9_client_stat(fid);
 		if (IS_ERR(st)) {
 			retval = PTR_ERR(st);
@@ -275,12 +277,13 @@ done:
 static int v9fs_drop_inode(struct inode *inode)
 {
 	struct v9fs_session_info *v9ses;
+
 	v9ses = v9fs_inode2v9ses(inode);
 	if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
 		return generic_drop_inode(inode);
 	/*
 	 * in case of non cached mode always drop the
-	 * the inode because we want the inode attribute
+	 * inode because we want the inode attribute
 	 * to always match that on the server.
 	 */
 	return 1;
diff --git a/fs/9p/xattr.h b/fs/9p/xattr.h
index c63c3bea5de5..9b28842c6363 100644
--- a/fs/9p/xattr.h
+++ b/fs/9p/xattr.h
@@ -22,13 +22,14 @@ extern const struct xattr_handler *v9fs_xattr_handlers[];
 extern const struct xattr_handler v9fs_xattr_acl_access_handler;
 extern const struct xattr_handler v9fs_xattr_acl_default_handler;
 
-extern ssize_t v9fs_fid_xattr_get(struct p9_fid *, const char *,
-				  void *, size_t);
-extern ssize_t v9fs_xattr_get(struct dentry *, const char *,
-			      void *, size_t);
-extern int v9fs_fid_xattr_set(struct p9_fid *, const char *,
-			  const void *, size_t, int);
-extern int v9fs_xattr_set(struct dentry *, const char *,
-			  const void *, size_t, int);
-extern ssize_t v9fs_listxattr(struct dentry *, char *, size_t);
+ssize_t v9fs_fid_xattr_get(struct p9_fid *fid, const char *name,
+			   void *buffer, size_t buffer_size);
+ssize_t v9fs_xattr_get(struct dentry *dentry, const char *name,
+		       void *buffer, size_t buffer_size);
+int v9fs_fid_xattr_set(struct p9_fid *fid, const char *name,
+		       const void *value, size_t value_len, int flags);
+int v9fs_xattr_set(struct dentry *dentry, const char *name,
+		   const void *value, size_t value_len, int flags);
+ssize_t v9fs_listxattr(struct dentry *dentry, char *buffer,
+		       size_t buffer_size);
 #endif /* FS_9P_XATTR_H */
diff --git a/fs/afs/flock.c b/fs/afs/flock.c
index c4210a3964d8..bbcc5afd1576 100644
--- a/fs/afs/flock.c
+++ b/fs/afs/flock.c
@@ -76,7 +76,7 @@ void afs_lock_op_done(struct afs_call *call)
 	if (call->error == 0) {
 		spin_lock(&vnode->lock);
 		trace_afs_flock_ev(vnode, NULL, afs_flock_timestamp, 0);
-		vnode->locked_at = call->reply_time;
+		vnode->locked_at = call->issue_time;
 		afs_schedule_lock_extension(vnode);
 		spin_unlock(&vnode->lock);
 	}
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index 4943413d9c5f..7d37f63ef0f0 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -131,7 +131,7 @@ bad:
 
 static time64_t xdr_decode_expiry(struct afs_call *call, u32 expiry)
 {
-	return ktime_divns(call->reply_time, NSEC_PER_SEC) + expiry;
+	return ktime_divns(call->issue_time, NSEC_PER_SEC) + expiry;
 }
 
 static void xdr_decode_AFSCallBack(const __be32 **_bp,
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 0ad97a8fc0d4..567e61b553f5 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -138,7 +138,6 @@ struct afs_call {
 	bool			need_attention;	/* T if RxRPC poked us */
 	bool			async;		/* T if asynchronous */
 	bool			upgrade;	/* T to request service upgrade */
-	bool			have_reply_time; /* T if have got reply_time */
 	bool			intr;		/* T if interruptible */
 	bool			unmarshalling_error; /* T if an unmarshalling error occurred */
 	u16			service_id;	/* Actual service ID (after upgrade) */
@@ -152,7 +151,7 @@ struct afs_call {
 		} __attribute__((packed));
 		__be64		tmp64;
 	};
-	ktime_t			reply_time;	/* Time of first reply packet */
+	ktime_t			issue_time;	/* Time of issue of operation */
 };
 
 struct afs_call_type {
diff --git a/fs/afs/misc.c b/fs/afs/misc.c
index 933e67fcdab1..805328ca5428 100644
--- a/fs/afs/misc.c
+++ b/fs/afs/misc.c
@@ -69,6 +69,7 @@ int afs_abort_to_error(u32 abort_code)
 		/* Unified AFS error table */
 	case UAEPERM:			return -EPERM;
 	case UAENOENT:			return -ENOENT;
+	case UAEAGAIN:			return -EAGAIN;
 	case UAEACCES:			return -EACCES;
 	case UAEBUSY:			return -EBUSY;
 	case UAEEXIST:			return -EEXIST;
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index a5434f3e57c6..e3de7fea3643 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -347,6 +347,7 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp)
 	if (call->max_lifespan)
 		rxrpc_kernel_set_max_life(call->net->socket, rxcall,
 					  call->max_lifespan);
+	call->issue_time = ktime_get_real();
 
 	/* send the request */
 	iov[0].iov_base	= call->request;
@@ -497,12 +498,6 @@ static void afs_deliver_to_call(struct afs_call *call)
 			return;
 		}
 
-		if (!call->have_reply_time &&
-		    rxrpc_kernel_get_reply_time(call->net->socket,
-						call->rxcall,
-						&call->reply_time))
-			call->have_reply_time = true;
-
 		ret = call->type->deliver(call);
 		state = READ_ONCE(call->state);
 		if (ret == 0 && call->unmarshalling_error)
diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c
index 2b35cba8ad62..88ea20e79ae2 100644
--- a/fs/afs/yfsclient.c
+++ b/fs/afs/yfsclient.c
@@ -239,8 +239,7 @@ static void xdr_decode_YFSCallBack(const __be32 **_bp,
 	struct afs_callback *cb = &scb->callback;
 	ktime_t cb_expiry;
 
-	cb_expiry = call->reply_time;
-	cb_expiry = ktime_add(cb_expiry, xdr_to_u64(x->expiration_time) * 100);
+	cb_expiry = ktime_add(call->issue_time, xdr_to_u64(x->expiration_time) * 100);
 	cb->expires_at	= ktime_divns(cb_expiry, NSEC_PER_SEC);
 	scb->have_cb	= true;
 	*_bp += xdr_size(x);
diff --git a/fs/attr.c b/fs/attr.c
index dbe996b0dedf..f581c4d00897 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -184,6 +184,8 @@ EXPORT_SYMBOL(setattr_prepare);
  */
 int inode_newsize_ok(const struct inode *inode, loff_t offset)
 {
+	if (offset < 0)
+		return -EINVAL;
 	if (inode->i_size < offset) {
 		unsigned long limit;
 
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 37418b183b07..474dcc0540a8 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -418,39 +418,26 @@ void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache,
 	btrfs_put_caching_control(caching_ctl);
 }
 
-int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache)
+static int btrfs_caching_ctl_wait_done(struct btrfs_block_group *cache,
+				       struct btrfs_caching_control *caching_ctl)
+{
+	wait_event(caching_ctl->wait, btrfs_block_group_done(cache));
+	return cache->cached == BTRFS_CACHE_ERROR ? -EIO : 0;
+}
+
+static int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache)
 {
 	struct btrfs_caching_control *caching_ctl;
-	int ret = 0;
+	int ret;
 
 	caching_ctl = btrfs_get_caching_control(cache);
 	if (!caching_ctl)
 		return (cache->cached == BTRFS_CACHE_ERROR) ? -EIO : 0;
-
-	wait_event(caching_ctl->wait, btrfs_block_group_done(cache));
-	if (cache->cached == BTRFS_CACHE_ERROR)
-		ret = -EIO;
+	ret = btrfs_caching_ctl_wait_done(cache, caching_ctl);
 	btrfs_put_caching_control(caching_ctl);
 	return ret;
 }
 
-static bool space_cache_v1_done(struct btrfs_block_group *cache)
-{
-	bool ret;
-
-	spin_lock(&cache->lock);
-	ret = cache->cached != BTRFS_CACHE_FAST;
-	spin_unlock(&cache->lock);
-
-	return ret;
-}
-
-void btrfs_wait_space_cache_v1_finished(struct btrfs_block_group *cache,
-				struct btrfs_caching_control *caching_ctl)
-{
-	wait_event(caching_ctl->wait, space_cache_v1_done(cache));
-}
-
 #ifdef CONFIG_BTRFS_DEBUG
 static void fragment_free_space(struct btrfs_block_group *block_group)
 {
@@ -727,9 +714,8 @@ done:
 	btrfs_put_block_group(block_group);
 }
 
-int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only)
+int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait)
 {
-	DEFINE_WAIT(wait);
 	struct btrfs_fs_info *fs_info = cache->fs_info;
 	struct btrfs_caching_control *caching_ctl = NULL;
 	int ret = 0;
@@ -762,10 +748,7 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only
 	}
 	WARN_ON(cache->caching_ctl);
 	cache->caching_ctl = caching_ctl;
-	if (btrfs_test_opt(fs_info, SPACE_CACHE))
-		cache->cached = BTRFS_CACHE_FAST;
-	else
-		cache->cached = BTRFS_CACHE_STARTED;
+	cache->cached = BTRFS_CACHE_STARTED;
 	cache->has_caching_ctl = 1;
 	spin_unlock(&cache->lock);
 
@@ -778,8 +761,8 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only
 
 	btrfs_queue_work(fs_info->caching_workers, &caching_ctl->work);
 out:
-	if (load_cache_only && caching_ctl)
-		btrfs_wait_space_cache_v1_finished(cache, caching_ctl);
+	if (wait && caching_ctl)
+		ret = btrfs_caching_ctl_wait_done(cache, caching_ctl);
 	if (caching_ctl)
 		btrfs_put_caching_control(caching_ctl);
 
@@ -1575,9 +1558,11 @@ void btrfs_reclaim_bgs_work(struct work_struct *work)
 				div64_u64(zone_unusable * 100, bg->length));
 		trace_btrfs_reclaim_block_group(bg);
 		ret = btrfs_relocate_chunk(fs_info, bg->start);
-		if (ret)
+		if (ret) {
+			btrfs_dec_block_group_ro(bg);
 			btrfs_err(fs_info, "error relocating chunk %llu",
 				  bg->start);
+		}
 
 next:
 		btrfs_put_block_group(bg);
@@ -3198,7 +3183,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans,
 		 * space back to the block group, otherwise we will leak space.
 		 */
 		if (!alloc && !btrfs_block_group_done(cache))
-			btrfs_cache_block_group(cache, 1);
+			btrfs_cache_block_group(cache, true);
 
 		byte_in_group = bytenr - cache->start;
 		WARN_ON(byte_in_group > cache->length);
@@ -3400,31 +3385,12 @@ static int do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags)
 	 */
 	check_system_chunk(trans, flags);
 
-	bg = btrfs_alloc_chunk(trans, flags);
+	bg = btrfs_create_chunk(trans, flags);
 	if (IS_ERR(bg)) {
 		ret = PTR_ERR(bg);
 		goto out;
 	}
 
-	/*
-	 * If this is a system chunk allocation then stop right here and do not
-	 * add the chunk item to the chunk btree. This is to prevent a deadlock
-	 * because this system chunk allocation can be triggered while COWing
-	 * some extent buffer of the chunk btree and while holding a lock on a
-	 * parent extent buffer, in which case attempting to insert the chunk
-	 * item (or update the device item) would result in a deadlock on that
-	 * parent extent buffer. In this case defer the chunk btree updates to
-	 * the second phase of chunk allocation and keep our reservation until
-	 * the second phase completes.
-	 *
-	 * This is a rare case and can only be triggered by the very few cases
-	 * we have where we need to touch the chunk btree outside chunk allocation
-	 * and chunk removal. These cases are basically adding a device, removing
-	 * a device or resizing a device.
-	 */
-	if (flags & BTRFS_BLOCK_GROUP_SYSTEM)
-		return 0;
-
 	ret = btrfs_chunk_alloc_add_chunk_item(trans, bg);
 	/*
 	 * Normally we are not expected to fail with -ENOSPC here, since we have
@@ -3461,7 +3427,7 @@ static int do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags)
 		const u64 sys_flags = btrfs_system_alloc_profile(trans->fs_info);
 		struct btrfs_block_group *sys_bg;
 
-		sys_bg = btrfs_alloc_chunk(trans, sys_flags);
+		sys_bg = btrfs_create_chunk(trans, sys_flags);
 		if (IS_ERR(sys_bg)) {
 			ret = PTR_ERR(sys_bg);
 			btrfs_abort_transaction(trans, ret);
@@ -3557,14 +3523,14 @@ out:
  * This has happened before and commit eafa4fd0ad0607 ("btrfs: fix exhaustion of
  * the system chunk array due to concurrent allocations") provides more details.
  *
- * For allocation of system chunks, we defer the updates and insertions into the
- * chunk btree to phase 2. This is to prevent deadlocks on extent buffers because
- * if the chunk allocation is triggered while COWing an extent buffer of the
- * chunk btree, we are holding a lock on the parent of that extent buffer and
- * doing the chunk btree updates and insertions can require locking that parent.
- * This is for the very few and rare cases where we update the chunk btree that
- * are not chunk allocation or chunk removal: adding a device, removing a device
- * or resizing a device.
+ * Allocation of system chunks does not happen through this function. A task that
+ * needs to update the chunk btree (the only btree that uses system chunks), must
+ * preallocate chunk space by calling either check_system_chunk() or
+ * btrfs_reserve_chunk_metadata() - the former is used when allocating a data or
+ * metadata chunk or when removing a chunk, while the later is used before doing
+ * a modification to the chunk btree - use cases for the later are adding,
+ * removing and resizing a device as well as relocation of a system chunk.
+ * See the comment below for more details.
  *
  * The reservation of system space, done through check_system_chunk(), as well
  * as all the updates and insertions into the chunk btree must be done while
@@ -3601,11 +3567,27 @@ int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
 	if (trans->allocating_chunk)
 		return -ENOSPC;
 	/*
-	 * If we are removing a chunk, don't re-enter or we would deadlock.
-	 * System space reservation and system chunk allocation is done by the
-	 * chunk remove operation (btrfs_remove_chunk()).
+	 * Allocation of system chunks can not happen through this path, as we
+	 * could end up in a deadlock if we are allocating a data or metadata
+	 * chunk and there is another task modifying the chunk btree.
+	 *
+	 * This is because while we are holding the chunk mutex, we will attempt
+	 * to add the new chunk item to the chunk btree or update an existing
+	 * device item in the chunk btree, while the other task that is modifying
+	 * the chunk btree is attempting to COW an extent buffer while holding a
+	 * lock on it and on its parent - if the COW operation triggers a system
+	 * chunk allocation, then we can deadlock because we are holding the
+	 * chunk mutex and we may need to access that extent buffer or its parent
+	 * in order to add the chunk item or update a device item.
+	 *
+	 * Tasks that want to modify the chunk tree should reserve system space
+	 * before updating the chunk btree, by calling either
+	 * btrfs_reserve_chunk_metadata() or check_system_chunk().
+	 * It's possible that after a task reserves the space, it still ends up
+	 * here - this happens in the cases described above at do_chunk_alloc().
+	 * The task will have to either retry or fail.
 	 */
-	if (trans->removing_chunk)
+	if (flags & BTRFS_BLOCK_GROUP_SYSTEM)
 		return -ENOSPC;
 
 	space_info = btrfs_find_space_info(fs_info, flags);
@@ -3635,6 +3617,7 @@ int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
 			 * attempt.
 			 */
 			wait_for_alloc = true;
+			force = CHUNK_ALLOC_NO_FORCE;
 			spin_unlock(&space_info->lock);
 			mutex_lock(&fs_info->chunk_mutex);
 			mutex_unlock(&fs_info->chunk_mutex);
@@ -3704,17 +3687,14 @@ static u64 get_profile_num_devs(struct btrfs_fs_info *fs_info, u64 type)
 	return num_dev;
 }
 
-/*
- * Reserve space in the system space for allocating or removing a chunk
- */
-void check_system_chunk(struct btrfs_trans_handle *trans, u64 type)
+static void reserve_chunk_space(struct btrfs_trans_handle *trans,
+				u64 bytes,
+				u64 type)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_space_info *info;
 	u64 left;
-	u64 thresh;
 	int ret = 0;
-	u64 num_devs;
 
 	/*
 	 * Needed because we can end up allocating a system chunk and for an
@@ -3727,19 +3707,13 @@ void check_system_chunk(struct btrfs_trans_handle *trans, u64 type)
 	left = info->total_bytes - btrfs_space_info_used(info, true);
 	spin_unlock(&info->lock);
 
-	num_devs = get_profile_num_devs(fs_info, type);
-
-	/* num_devs device items to update and 1 chunk item to add or remove */
-	thresh = btrfs_calc_metadata_size(fs_info, num_devs) +
-		btrfs_calc_insert_metadata_size(fs_info, 1);
-
-	if (left < thresh && btrfs_test_opt(fs_info, ENOSPC_DEBUG)) {
+	if (left < bytes && btrfs_test_opt(fs_info, ENOSPC_DEBUG)) {
 		btrfs_info(fs_info, "left=%llu, need=%llu, flags=%llu",
-			   left, thresh, type);
+			   left, bytes, type);
 		btrfs_dump_space_info(fs_info, info, 0, 0);
 	}
 
-	if (left < thresh) {
+	if (left < bytes) {
 		u64 flags = btrfs_system_alloc_profile(fs_info);
 		struct btrfs_block_group *bg;
 
@@ -3748,21 +3722,20 @@ void check_system_chunk(struct btrfs_trans_handle *trans, u64 type)
 		 * needing it, as we might not need to COW all nodes/leafs from
 		 * the paths we visit in the chunk tree (they were already COWed
 		 * or created in the current transaction for example).
-		 *
-		 * Also, if our caller is allocating a system chunk, do not
-		 * attempt to insert the chunk item in the chunk btree, as we
-		 * could deadlock on an extent buffer since our caller may be
-		 * COWing an extent buffer from the chunk btree.
 		 */
-		bg = btrfs_alloc_chunk(trans, flags);
+		bg = btrfs_create_chunk(trans, flags);
 		if (IS_ERR(bg)) {
 			ret = PTR_ERR(bg);
-		} else if (!(type & BTRFS_BLOCK_GROUP_SYSTEM)) {
+		} else {
 			/*
 			 * If we fail to add the chunk item here, we end up
 			 * trying again at phase 2 of chunk allocation, at
 			 * btrfs_create_pending_block_groups(). So ignore
-			 * any error here.
+			 * any error here. An ENOSPC here could happen, due to
+			 * the cases described at do_chunk_alloc() - the system
+			 * block group we just created was just turned into RO
+			 * mode by a scrub for example, or a running discard
+			 * temporarily removed its free space entries, etc.
 			 */
 			btrfs_chunk_alloc_add_chunk_item(trans, bg);
 		}
@@ -3771,12 +3744,61 @@ void check_system_chunk(struct btrfs_trans_handle *trans, u64 type)
 	if (!ret) {
 		ret = btrfs_block_rsv_add(fs_info->chunk_root,
 					  &fs_info->chunk_block_rsv,
-					  thresh, BTRFS_RESERVE_NO_FLUSH);
+					  bytes, BTRFS_RESERVE_NO_FLUSH);
 		if (!ret)
-			trans->chunk_bytes_reserved += thresh;
+			trans->chunk_bytes_reserved += bytes;
 	}
 }
 
+/*
+ * Reserve space in the system space for allocating or removing a chunk.
+ * The caller must be holding fs_info->chunk_mutex.
+ */
+void check_system_chunk(struct btrfs_trans_handle *trans, u64 type)
+{
+	struct btrfs_fs_info *fs_info = trans->fs_info;
+	const u64 num_devs = get_profile_num_devs(fs_info, type);
+	u64 bytes;
+
+	/* num_devs device items to update and 1 chunk item to add or remove. */
+	bytes = btrfs_calc_metadata_size(fs_info, num_devs) +
+		btrfs_calc_insert_metadata_size(fs_info, 1);
+
+	reserve_chunk_space(trans, bytes, type);
+}
+
+/*
+ * Reserve space in the system space, if needed, for doing a modification to the
+ * chunk btree.
+ *
+ * @trans:		A transaction handle.
+ * @is_item_insertion:	Indicate if the modification is for inserting a new item
+ *			in the chunk btree or if it's for the deletion or update
+ *			of an existing item.
+ *
+ * This is used in a context where we need to update the chunk btree outside
+ * block group allocation and removal, to avoid a deadlock with a concurrent
+ * task that is allocating a metadata or data block group and therefore needs to
+ * update the chunk btree while holding the chunk mutex. After the update to the
+ * chunk btree is done, btrfs_trans_release_chunk_metadata() should be called.
+ *
+ */
+void btrfs_reserve_chunk_metadata(struct btrfs_trans_handle *trans,
+				  bool is_item_insertion)
+{
+	struct btrfs_fs_info *fs_info = trans->fs_info;
+	u64 bytes;
+
+	if (is_item_insertion)
+		bytes = btrfs_calc_insert_metadata_size(fs_info, 1);
+	else
+		bytes = btrfs_calc_metadata_size(fs_info, 1);
+
+	mutex_lock(&fs_info->chunk_mutex);
+	reserve_chunk_space(trans, bytes, BTRFS_BLOCK_GROUP_SYSTEM);
+	mutex_unlock(&fs_info->chunk_mutex);
+}
+
 void btrfs_put_block_group_cache(struct btrfs_fs_info *info)
 {
 	struct btrfs_block_group *block_group;
diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h
index c72a71efcb18..a15868d607a9 100644
--- a/fs/btrfs/block-group.h
+++ b/fs/btrfs/block-group.h
@@ -98,6 +98,7 @@ struct btrfs_block_group {
 	unsigned int to_copy:1;
 	unsigned int relocating_repair:1;
 	unsigned int chunk_item_inserted:1;
+	unsigned int zoned_data_reloc_ongoing:1;
 
 	int disk_cache_state;
 
@@ -250,9 +251,7 @@ void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr);
 void btrfs_wait_nocow_writers(struct btrfs_block_group *bg);
 void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache,
 				           u64 num_bytes);
-int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache);
-int btrfs_cache_block_group(struct btrfs_block_group *cache,
-			    int load_cache_only);
+int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait);
 void btrfs_put_caching_control(struct btrfs_caching_control *ctl);
 struct btrfs_caching_control *btrfs_get_caching_control(
 		struct btrfs_block_group *cache);
@@ -289,6 +288,8 @@ int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
 		      enum btrfs_chunk_alloc_enum force);
 int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans, u64 type);
 void check_system_chunk(struct btrfs_trans_handle *trans, const u64 type);
+void btrfs_reserve_chunk_metadata(struct btrfs_trans_handle *trans,
+				  bool is_item_insertion);
 u64 btrfs_get_alloc_profile(struct btrfs_fs_info *fs_info, u64 orig_flags);
 void btrfs_put_block_group_cache(struct btrfs_fs_info *info);
 int btrfs_free_block_groups(struct btrfs_fs_info *info);
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 76ee1452c57b..37ceea85b871 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -14,6 +14,13 @@
 #include "delayed-inode.h"
 
 /*
+ * Since we search a directory based on f_pos (struct dir_context::pos) we have
+ * to start at 2 since '.' and '..' have f_pos of 0 and 1 respectively, so
+ * everybody else has to start at 2 (see btrfs_real_readdir() and dir_emit_dots()).
+ */
+#define BTRFS_DIR_START_INDEX 2
+
+/*
  * ordered_data_close is set by truncate when a file that used
  * to have good data has been truncated to zero.  When it is set
  * the btrfs file release call will add this inode to the
@@ -164,8 +171,9 @@ struct btrfs_inode {
 	u64 disk_i_size;
 
 	/*
-	 * if this is a directory then index_cnt is the counter for the index
-	 * number for new files that are created
+	 * If this is a directory then index_cnt is the counter for the index
+	 * number for new files that are created. For an empty directory, this
+	 * must be initialized to BTRFS_DIR_START_INDEX.
 	 */
 	u64 index_cnt;
 
diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index 86816088927f..81b11124b67a 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -1455,7 +1455,7 @@ static int btrfsic_map_block(struct btrfsic_state *state, u64 bytenr, u32 len,
 	struct btrfs_fs_info *fs_info = state->fs_info;
 	int ret;
 	u64 length;
-	struct btrfs_bio *multi = NULL;
+	struct btrfs_io_context *multi = NULL;
 	struct btrfs_device *device;
 
 	length = len;
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 899f85445925..fb7e331b6975 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -462,8 +462,8 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 		BUG_ON(ret < 0);
 		rcu_assign_pointer(root->node, cow);
 
-		btrfs_free_tree_block(trans, root, buf, parent_start,
-				      last_ref);
+		btrfs_free_tree_block(trans, btrfs_root_id(root), buf,
+				      parent_start, last_ref);
 		free_extent_buffer(buf);
 		add_root_to_dirty_list(root);
 	} else {
@@ -484,8 +484,8 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 				return ret;
 			}
 		}
-		btrfs_free_tree_block(trans, root, buf, parent_start,
-				      last_ref);
+		btrfs_free_tree_block(trans, btrfs_root_id(root), buf,
+				      parent_start, last_ref);
 	}
 	if (unlock_orig)
 		btrfs_tree_unlock(buf);
@@ -926,7 +926,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 		free_extent_buffer(mid);
 
 		root_sub_used(root, mid->len);
-		btrfs_free_tree_block(trans, root, mid, 0, 1);
+		btrfs_free_tree_block(trans, btrfs_root_id(root), mid, 0, 1);
 		/* once for the root ptr */
 		free_extent_buffer_stale(mid);
 		return 0;
@@ -985,7 +985,8 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 			btrfs_tree_unlock(right);
 			del_ptr(root, path, level + 1, pslot + 1);
 			root_sub_used(root, right->len);
-			btrfs_free_tree_block(trans, root, right, 0, 1);
+			btrfs_free_tree_block(trans, btrfs_root_id(root), right,
+					      0, 1);
 			free_extent_buffer_stale(right);
 			right = NULL;
 		} else {
@@ -1030,7 +1031,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 		btrfs_tree_unlock(mid);
 		del_ptr(root, path, level + 1, pslot);
 		root_sub_used(root, mid->len);
-		btrfs_free_tree_block(trans, root, mid, 0, 1);
+		btrfs_free_tree_block(trans, btrfs_root_id(root), mid, 0, 1);
 		free_extent_buffer_stale(mid);
 		mid = NULL;
 	} else {
@@ -1937,6 +1938,9 @@ cow_done:
 
 		if (!p->skip_locking) {
 			level = btrfs_header_level(b);
+
+			btrfs_maybe_reset_lockdep_class(root, b);
+
 			if (level <= write_lock_level) {
 				btrfs_tree_lock(b);
 				p->locks[level] = BTRFS_WRITE_LOCK;
@@ -4059,7 +4063,7 @@ static noinline void btrfs_del_leaf(struct btrfs_trans_handle *trans,
 	root_sub_used(root, leaf->len);
 
 	atomic_inc(&leaf->refs);
-	btrfs_free_tree_block(trans, root, leaf, 0, 1);
+	btrfs_free_tree_block(trans, btrfs_root_id(root), leaf, 0, 1);
 	free_extent_buffer_stale(leaf);
 }
 /*
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 21c44846b002..02d3ee6c7d9b 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -105,14 +105,6 @@ struct btrfs_ref;
 #define BTRFS_STAT_CURR		0
 #define BTRFS_STAT_PREV		1
 
-/*
- * Count how many BTRFS_MAX_EXTENT_SIZE cover the @size
- */
-static inline u32 count_max_extents(u64 size)
-{
-	return div_u64(size + BTRFS_MAX_EXTENT_SIZE - 1, BTRFS_MAX_EXTENT_SIZE);
-}
-
 static inline unsigned long btrfs_chunk_item_size(int num_stripes)
 {
 	BUG_ON(num_stripes == 0);
@@ -462,7 +454,6 @@ struct btrfs_free_cluster {
 enum btrfs_caching_type {
 	BTRFS_CACHE_NO,
 	BTRFS_CACHE_STARTED,
-	BTRFS_CACHE_FAST,
 	BTRFS_CACHE_FINISHED,
 	BTRFS_CACHE_ERROR,
 };
@@ -999,6 +990,12 @@ struct btrfs_fs_info {
 	u32 csums_per_leaf;
 	u32 stripesize;
 
+	/*
+	 * Maximum size of an extent. BTRFS_MAX_EXTENT_SIZE on regular
+	 * filesystem, on zoned it depends on the device constraints.
+	 */
+	u64 max_extent_size;
+
 	/* Block groups and devices containing active swapfiles. */
 	spinlock_t swapfile_pins_lock;
 	struct rb_root swapfile_pins;
@@ -1017,6 +1014,8 @@ struct btrfs_fs_info {
 		u64 zoned;
 	};
 
+	/* Max size to emit ZONE_APPEND write command */
+	u64 max_zone_append_size;
 	struct mutex zoned_meta_io_lock;
 	spinlock_t treelog_bg_lock;
 	u64 treelog_bg;
@@ -1027,6 +1026,7 @@ struct btrfs_fs_info {
 	 */
 	spinlock_t relocation_bg_lock;
 	u64 data_reloc_bg;
+	struct mutex zoned_data_reloc_io_lock;
 
 #ifdef CONFIG_BTRFS_FS_REF_VERIFY
 	spinlock_t ref_verify_lock;
@@ -1104,6 +1104,8 @@ enum {
 	BTRFS_ROOT_QGROUP_FLUSHING,
 	/* This root has a drop operation that was started previously. */
 	BTRFS_ROOT_UNFINISHED_DROP,
+	/* This reloc root needs to have its buffers lockdep class reset. */
+	BTRFS_ROOT_RESET_LOCKDEP_CLASS,
 };
 
 static inline void btrfs_wake_unfinished_drop(struct btrfs_fs_info *fs_info)
@@ -2256,6 +2258,11 @@ static inline bool btrfs_root_dead(const struct btrfs_root *root)
 	return (root->root_item.flags & cpu_to_le64(BTRFS_ROOT_SUBVOL_DEAD)) != 0;
 }
 
+static inline u64 btrfs_root_id(const struct btrfs_root *root)
+{
+	return root->root_key.objectid;
+}
+
 /* struct btrfs_root_backup */
 BTRFS_SETGET_STACK_FUNCS(backup_tree_root, struct btrfs_root_backup,
 		   tree_root, 64);
@@ -2718,7 +2725,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 					     u64 empty_size,
 					     enum btrfs_lock_nesting nest);
 void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
-			   struct btrfs_root *root,
+			   u64 root_id,
 			   struct extent_buffer *buf,
 			   u64 parent, int last_ref);
 int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
@@ -3160,7 +3167,6 @@ void __btrfs_del_delalloc_inode(struct btrfs_root *root,
 struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry);
 int btrfs_set_inode_index(struct btrfs_inode *dir, u64 *index);
 int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
-		       struct btrfs_root *root,
 		       struct btrfs_inode *dir, struct btrfs_inode *inode,
 		       const char *name, int name_len);
 int btrfs_add_link(struct btrfs_trans_handle *trans,
@@ -3864,6 +3870,19 @@ static inline bool btrfs_is_zoned(const struct btrfs_fs_info *fs_info)
 	return fs_info->zoned != 0;
 }
 
+/*
+ * Count how many fs_info->max_extent_size cover the @size
+ */
+static inline u32 count_max_extents(struct btrfs_fs_info *fs_info, u64 size)
+{
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+	if (!fs_info)
+		return div_u64(size + BTRFS_MAX_EXTENT_SIZE - 1, BTRFS_MAX_EXTENT_SIZE);
+#endif
+
+	return div_u64(size + fs_info->max_extent_size - 1, fs_info->max_extent_size);
+}
+
 static inline bool btrfs_is_data_reloc_root(const struct btrfs_root *root)
 {
 	return root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID;
diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c
index 40c4d6ba3fb9..b934429c2435 100644
--- a/fs/btrfs/delalloc-space.c
+++ b/fs/btrfs/delalloc-space.c
@@ -273,7 +273,7 @@ static void calc_inode_reservations(struct btrfs_fs_info *fs_info,
 				    u64 num_bytes, u64 *meta_reserve,
 				    u64 *qgroup_reserve)
 {
-	u64 nr_extents = count_max_extents(num_bytes);
+	u64 nr_extents = count_max_extents(fs_info, num_bytes);
 	u64 csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, num_bytes);
 	u64 inode_update = btrfs_calc_metadata_size(fs_info, 1);
 
@@ -347,7 +347,7 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
 	 * needs to free the reservation we just made.
 	 */
 	spin_lock(&inode->lock);
-	nr_extents = count_max_extents(num_bytes);
+	nr_extents = count_max_extents(fs_info, num_bytes);
 	btrfs_mod_outstanding_extents(inode, nr_extents);
 	inode->csum_bytes += num_bytes;
 	btrfs_calculate_inode_block_rsv_size(fs_info, inode);
@@ -410,7 +410,7 @@ void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes)
 	unsigned num_extents;
 
 	spin_lock(&inode->lock);
-	num_extents = count_max_extents(num_bytes);
+	num_extents = count_max_extents(fs_info, num_bytes);
 	btrfs_mod_outstanding_extents(inode, -num_extents);
 	btrfs_calculate_inode_block_rsv_size(fs_info, inode);
 	spin_unlock(&inode->lock);
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index e22fba272e4f..31266ba1d430 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -271,7 +271,7 @@ static inline void btrfs_init_generic_ref(struct btrfs_ref *generic_ref,
 }
 
 static inline void btrfs_init_tree_ref(struct btrfs_ref *generic_ref,
-				int level, u64 root)
+				int level, u64 root, u64 mod_root, bool skip_qgroup)
 {
 	/* If @real_root not set, use @root as fallback */
 	if (!generic_ref->real_root)
@@ -282,7 +282,8 @@ static inline void btrfs_init_tree_ref(struct btrfs_ref *generic_ref,
 }
 
 static inline void btrfs_init_data_ref(struct btrfs_ref *generic_ref,
-				u64 ref_root, u64 ino, u64 offset)
+				u64 ref_root, u64 ino, u64 offset, u64 mod_root,
+				bool skip_qgroup)
 {
 	/* If @real_root not set, use @root as fallback */
 	if (!generic_ref->real_root)
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index bdbc310a8f8c..03d8a2d49bf4 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -70,6 +70,7 @@ static int btrfs_dev_replace_kthread(void *data);
 
 int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info)
 {
+	struct btrfs_dev_lookup_args args = { .devid = BTRFS_DEV_REPLACE_DEVID };
 	struct btrfs_key key;
 	struct btrfs_root *dev_root = fs_info->dev_root;
 	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
@@ -100,8 +101,7 @@ no_valid_dev_replace_entry_found:
 		 * We don't have a replace item or it's corrupted.  If there is
 		 * a replace target, fail the mount.
 		 */
-		if (btrfs_find_device(fs_info->fs_devices,
-				      BTRFS_DEV_REPLACE_DEVID, NULL, NULL)) {
+		if (btrfs_find_device(fs_info->fs_devices, &args)) {
 			btrfs_err(fs_info,
 			"found replace target device without a valid replace item");
 			ret = -EUCLEAN;
@@ -163,10 +163,9 @@ no_valid_dev_replace_entry_found:
 		 * We don't have an active replace item but if there is a
 		 * replace target, fail the mount.
 		 */
-		if (btrfs_find_device(fs_info->fs_devices,
-				      BTRFS_DEV_REPLACE_DEVID, NULL, NULL)) {
+		if (btrfs_find_device(fs_info->fs_devices, &args)) {
 			btrfs_err(fs_info,
-			"replace devid present without an active replace item");
+"replace without active item, run 'device scan --forget' on the target device");
 			ret = -EUCLEAN;
 		} else {
 			dev_replace->srcdev = NULL;
@@ -175,11 +174,10 @@ no_valid_dev_replace_entry_found:
 		break;
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED:
-		dev_replace->srcdev = btrfs_find_device(fs_info->fs_devices,
-						src_devid, NULL, NULL);
-		dev_replace->tgtdev = btrfs_find_device(fs_info->fs_devices,
-							BTRFS_DEV_REPLACE_DEVID,
-							NULL, NULL);
+		dev_replace->tgtdev = btrfs_find_device(fs_info->fs_devices, &args);
+		args.devid = src_devid;
+		dev_replace->srcdev = btrfs_find_device(fs_info->fs_devices, &args);
+
 		/*
 		 * allow 'btrfs dev replace_cancel' if src/tgt device is
 		 * missing
@@ -1153,8 +1151,7 @@ int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info)
 		up_write(&dev_replace->rwsem);
 
 		/* Scrub for replace must not be running in suspended state */
-		ret = btrfs_scrub_cancel(fs_info);
-		ASSERT(ret != -ENOTCONN);
+		btrfs_scrub_cancel(fs_info);
 
 		trans = btrfs_start_transaction(root, 0);
 		if (IS_ERR(trans)) {
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 233d894f6feb..c76c360bece5 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -122,88 +122,6 @@ struct async_submit_bio {
 };
 
 /*
- * Lockdep class keys for extent_buffer->lock's in this root.  For a given
- * eb, the lockdep key is determined by the btrfs_root it belongs to and
- * the level the eb occupies in the tree.
- *
- * Different roots are used for different purposes and may nest inside each
- * other and they require separate keysets.  As lockdep keys should be
- * static, assign keysets according to the purpose of the root as indicated
- * by btrfs_root->root_key.objectid.  This ensures that all special purpose
- * roots have separate keysets.
- *
- * Lock-nesting across peer nodes is always done with the immediate parent
- * node locked thus preventing deadlock.  As lockdep doesn't know this, use
- * subclass to avoid triggering lockdep warning in such cases.
- *
- * The key is set by the readpage_end_io_hook after the buffer has passed
- * csum validation but before the pages are unlocked.  It is also set by
- * btrfs_init_new_buffer on freshly allocated blocks.
- *
- * We also add a check to make sure the highest level of the tree is the
- * same as our lockdep setup here.  If BTRFS_MAX_LEVEL changes, this code
- * needs update as well.
- */
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# if BTRFS_MAX_LEVEL != 8
-#  error
-# endif
-
-#define DEFINE_LEVEL(stem, level)					\
-	.names[level] = "btrfs-" stem "-0" #level,
-
-#define DEFINE_NAME(stem)						\
-	DEFINE_LEVEL(stem, 0)						\
-	DEFINE_LEVEL(stem, 1)						\
-	DEFINE_LEVEL(stem, 2)						\
-	DEFINE_LEVEL(stem, 3)						\
-	DEFINE_LEVEL(stem, 4)						\
-	DEFINE_LEVEL(stem, 5)						\
-	DEFINE_LEVEL(stem, 6)						\
-	DEFINE_LEVEL(stem, 7)
-
-static struct btrfs_lockdep_keyset {
-	u64			id;		/* root objectid */
-	/* Longest entry: btrfs-free-space-00 */
-	char			names[BTRFS_MAX_LEVEL][20];
-	struct lock_class_key	keys[BTRFS_MAX_LEVEL];
-} btrfs_lockdep_keysets[] = {
-	{ .id = BTRFS_ROOT_TREE_OBJECTID,	DEFINE_NAME("root")	},
-	{ .id = BTRFS_EXTENT_TREE_OBJECTID,	DEFINE_NAME("extent")	},
-	{ .id = BTRFS_CHUNK_TREE_OBJECTID,	DEFINE_NAME("chunk")	},
-	{ .id = BTRFS_DEV_TREE_OBJECTID,	DEFINE_NAME("dev")	},
-	{ .id = BTRFS_CSUM_TREE_OBJECTID,	DEFINE_NAME("csum")	},
-	{ .id = BTRFS_QUOTA_TREE_OBJECTID,	DEFINE_NAME("quota")	},
-	{ .id = BTRFS_TREE_LOG_OBJECTID,	DEFINE_NAME("log")	},
-	{ .id = BTRFS_TREE_RELOC_OBJECTID,	DEFINE_NAME("treloc")	},
-	{ .id = BTRFS_DATA_RELOC_TREE_OBJECTID,	DEFINE_NAME("dreloc")	},
-	{ .id = BTRFS_UUID_TREE_OBJECTID,	DEFINE_NAME("uuid")	},
-	{ .id = BTRFS_FREE_SPACE_TREE_OBJECTID,	DEFINE_NAME("free-space") },
-	{ .id = 0,				DEFINE_NAME("tree")	},
-};
-
-#undef DEFINE_LEVEL
-#undef DEFINE_NAME
-
-void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb,
-				    int level)
-{
-	struct btrfs_lockdep_keyset *ks;
-
-	BUG_ON(level >= ARRAY_SIZE(ks->keys));
-
-	/* find the matching keyset, id 0 is the default entry */
-	for (ks = btrfs_lockdep_keysets; ks->id; ks++)
-		if (ks->id == objectid)
-			break;
-
-	lockdep_set_class_and_name(&eb->lock,
-				   &ks->keys[level], ks->names[level]);
-}
-
-#endif
-
-/*
  * Compute the csum of a btree block and store the result to provided buffer.
  */
 static void csum_tree_block(struct extent_buffer *buf, u8 *result)
@@ -2914,6 +2832,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
 	mutex_init(&fs_info->reloc_mutex);
 	mutex_init(&fs_info->delalloc_root_mutex);
 	mutex_init(&fs_info->zoned_meta_io_lock);
+	mutex_init(&fs_info->zoned_data_reloc_io_lock);
 	seqlock_init(&fs_info->profiles_lock);
 
 	INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);
@@ -3005,6 +2924,8 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
 	fs_info->sectorsize_bits = ilog2(4096);
 	fs_info->stripesize = 4096;
 
+	fs_info->max_extent_size = BTRFS_MAX_EXTENT_SIZE;
+
 	spin_lock_init(&fs_info->swapfile_pins_lock);
 	fs_info->swapfile_pins = RB_ROOT;
 
@@ -3336,16 +3257,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 	 */
 	fs_info->compress_type = BTRFS_COMPRESS_ZLIB;
 
-	/*
-	 * Flag our filesystem as having big metadata blocks if they are bigger
-	 * than the page size.
-	 */
-	if (btrfs_super_nodesize(disk_super) > PAGE_SIZE) {
-		if (!(features & BTRFS_FEATURE_INCOMPAT_BIG_METADATA))
-			btrfs_info(fs_info,
-				"flagging fs with big metadata feature");
-		features |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA;
-	}
 
 	/* Set up fs_info before parsing mount options */
 	nodesize = btrfs_super_nodesize(disk_super);
@@ -3387,6 +3298,17 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 		btrfs_info(fs_info, "has skinny extents");
 
 	/*
+	 * Flag our filesystem as having big metadata blocks if they are bigger
+	 * than the page size.
+	 */
+	if (btrfs_super_nodesize(disk_super) > PAGE_SIZE) {
+		if (!(features & BTRFS_FEATURE_INCOMPAT_BIG_METADATA))
+			btrfs_info(fs_info,
+				"flagging fs with big metadata feature");
+		features |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA;
+	}
+
+	/*
 	 * mixed block groups end up with duplicate but slightly offset
 	 * extent buffers for the same range.  It leads to corruptions
 	 */
@@ -3556,6 +3478,20 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 		btrfs_err(fs_info, "failed to init dev_replace: %d", ret);
 		goto fail_block_groups;
 	}
+	/*
+	 * We have unsupported RO compat features, although RO mounted, we
+	 * should not cause any metadata write, including log replay.
+	 * Or we could screw up whatever the new feature requires.
+	 */
+	if (unlikely(features && btrfs_super_log_root(disk_super) &&
+		     !btrfs_test_opt(fs_info, NOLOGREPLAY))) {
+		btrfs_err(fs_info,
+"cannot replay dirty log with unsupported compat_ro features (0x%llx), try rescue=nologreplay",
+			  features);
+		err = -EINVAL;
+		goto fail_alloc;
+	}
+
 
 	ret = btrfs_check_zoned_mode(fs_info);
 	if (ret) {
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index 0e7e9526b6a8..1b8fd3deafc9 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -140,14 +140,4 @@ int btrfs_init_root_free_objectid(struct btrfs_root *root);
 int __init btrfs_end_io_wq_init(void);
 void __cold btrfs_end_io_wq_exit(void);
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-void btrfs_set_buffer_lockdep_class(u64 objectid,
-			            struct extent_buffer *eb, int level);
-#else
-static inline void btrfs_set_buffer_lockdep_class(u64 objectid,
-					struct extent_buffer *eb, int level)
-{
-}
-#endif
-
 #endif
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 514adc83577f..401a425a587c 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1266,7 +1266,7 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len,
 	return ret;
 }
 
-static int do_discard_extent(struct btrfs_bio_stripe *stripe, u64 *bytes)
+static int do_discard_extent(struct btrfs_io_stripe *stripe, u64 *bytes)
 {
 	struct btrfs_device *dev = stripe->dev;
 	struct btrfs_fs_info *fs_info = dev->fs_info;
@@ -1313,22 +1313,21 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
 	u64 discarded_bytes = 0;
 	u64 end = bytenr + num_bytes;
 	u64 cur = bytenr;
-	struct btrfs_bio *bbio = NULL;
-
+	struct btrfs_io_context *bioc = NULL;
 
 	/*
-	 * Avoid races with device replace and make sure our bbio has devices
+	 * Avoid races with device replace and make sure our bioc has devices
 	 * associated to its stripes that don't go away while we are discarding.
 	 */
 	btrfs_bio_counter_inc_blocked(fs_info);
 	while (cur < end) {
-		struct btrfs_bio_stripe *stripe;
+		struct btrfs_io_stripe *stripe;
 		int i;
 
 		num_bytes = end - cur;
 		/* Tell the block device(s) that the sectors can be discarded */
 		ret = btrfs_map_block(fs_info, BTRFS_MAP_DISCARD, cur,
-				      &num_bytes, &bbio, 0);
+				      &num_bytes, &bioc, 0);
 		/*
 		 * Error can be -ENOMEM, -ENOENT (no such chunk mapping) or
 		 * -EOPNOTSUPP. For any such error, @num_bytes is not updated,
@@ -1337,8 +1336,8 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
 		if (ret < 0)
 			goto out;
 
-		stripe = bbio->stripes;
-		for (i = 0; i < bbio->num_stripes; i++, stripe++) {
+		stripe = bioc->stripes;
+		for (i = 0; i < bioc->num_stripes; i++, stripe++) {
 			u64 bytes;
 			struct btrfs_device *device = stripe->dev;
 
@@ -1361,7 +1360,7 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
 				 * And since there are two loops, explicitly
 				 * go to out to avoid confusion.
 				 */
-				btrfs_put_bbio(bbio);
+				btrfs_put_bioc(bioc);
 				goto out;
 			}
 
@@ -1372,7 +1371,7 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
 			 */
 			ret = 0;
 		}
-		btrfs_put_bbio(bbio);
+		btrfs_put_bioc(bioc);
 		cur += num_bytes;
 	}
 out:
@@ -2440,7 +2439,8 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans,
 					       num_bytes, parent);
 			generic_ref.real_root = root->root_key.objectid;
 			btrfs_init_data_ref(&generic_ref, ref_root, key.objectid,
-					    key.offset);
+					    key.offset, root->root_key.objectid,
+					    for_reloc);
 			generic_ref.skip_qgroup = for_reloc;
 			if (inc)
 				ret = btrfs_inc_extent_ref(trans, &generic_ref);
@@ -2454,7 +2454,8 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans,
 			btrfs_init_generic_ref(&generic_ref, action, bytenr,
 					       num_bytes, parent);
 			generic_ref.real_root = root->root_key.objectid;
-			btrfs_init_tree_ref(&generic_ref, level - 1, ref_root);
+			btrfs_init_tree_ref(&generic_ref, level - 1, ref_root,
+					    root->root_key.objectid, for_reloc);
 			generic_ref.skip_qgroup = for_reloc;
 			if (inc)
 				ret = btrfs_inc_extent_ref(trans, &generic_ref);
@@ -2571,17 +2572,10 @@ int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans,
 		return -EINVAL;
 
 	/*
-	 * pull in the free space cache (if any) so that our pin
-	 * removes the free space from the cache.  We have load_only set
-	 * to one because the slow code to read in the free extents does check
-	 * the pinned extents.
-	 */
-	btrfs_cache_block_group(cache, 1);
-	/*
-	 * Make sure we wait until the cache is completely built in case it is
-	 * missing or is invalid and therefore needs to be rebuilt.
+	 * Fully cache the free space first so that our pin removes the free space
+	 * from the cache.
 	 */
-	ret = btrfs_wait_block_group_cache_done(cache);
+	ret = btrfs_cache_block_group(cache, true);
 	if (ret)
 		goto out;
 
@@ -2604,12 +2598,7 @@ static int __exclude_logged_extent(struct btrfs_fs_info *fs_info,
 	if (!block_group)
 		return -EINVAL;
 
-	btrfs_cache_block_group(block_group, 1);
-	/*
-	 * Make sure we wait until the cache is completely built in case it is
-	 * missing or is invalid and therefore needs to be rebuilt.
-	 */
-	ret = btrfs_wait_block_group_cache_done(block_group);
+	ret = btrfs_cache_block_group(block_group, true);
 	if (ret)
 		goto out;
 
@@ -3278,20 +3267,20 @@ out_delayed_unlock:
 }
 
 void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
-			   struct btrfs_root *root,
+			   u64 root_id,
 			   struct extent_buffer *buf,
 			   u64 parent, int last_ref)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_ref generic_ref = { 0 };
 	int ret;
 
 	btrfs_init_generic_ref(&generic_ref, BTRFS_DROP_DELAYED_REF,
 			       buf->start, buf->len, parent);
 	btrfs_init_tree_ref(&generic_ref, btrfs_header_level(buf),
-			    root->root_key.objectid);
+			    root_id, 0, false);
 
-	if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
+	if (root_id != BTRFS_TREE_LOG_OBJECTID) {
 		btrfs_ref_tree_mod(fs_info, &generic_ref);
 		ret = btrfs_add_delayed_tree_ref(trans, &generic_ref, NULL);
 		BUG_ON(ret); /* -ENOMEM */
@@ -3301,7 +3290,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 		struct btrfs_block_group *cache;
 		bool must_pin = false;
 
-		if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
+		if (root_id != BTRFS_TREE_LOG_OBJECTID) {
 			ret = check_ref_cleanup(trans, buf->start);
 			if (!ret) {
 				btrfs_redirty_list_add(trans->transaction, buf);
@@ -3803,7 +3792,7 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group,
 	       block_group->start == fs_info->data_reloc_bg ||
 	       fs_info->data_reloc_bg == 0);
 
-	if (block_group->ro) {
+	if (block_group->ro || block_group->zoned_data_reloc_ongoing) {
 		ret = 1;
 		goto out;
 	}
@@ -3864,8 +3853,24 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group,
 out:
 	if (ret && ffe_ctl->for_treelog)
 		fs_info->treelog_bg = 0;
-	if (ret && ffe_ctl->for_data_reloc)
+	if (ret && ffe_ctl->for_data_reloc &&
+	    fs_info->data_reloc_bg == block_group->start) {
+		/*
+		 * Do not allow further allocations from this block group.
+		 * Compared to increasing the ->ro, setting the
+		 * ->zoned_data_reloc_ongoing flag still allows nocow
+		 *  writers to come in. See btrfs_inc_nocow_writers().
+		 *
+		 * We need to disable an allocation to avoid an allocation of
+		 * regular (non-relocation data) extent. With mix of relocation
+		 * extents and regular extents, we can dispatch WRITE commands
+		 * (for relocation extents) and ZONE APPEND commands (for
+		 * regular extents) at the same time to the same zone, which
+		 * easily break the write pointer.
+		 */
+		block_group->zoned_data_reloc_ongoing = 1;
 		fs_info->data_reloc_bg = 0;
+	}
 	spin_unlock(&fs_info->relocation_bg_lock);
 	spin_unlock(&fs_info->treelog_bg_lock);
 	spin_unlock(&block_group->lock);
@@ -4307,7 +4312,7 @@ have_block_group:
 		ffe_ctl.cached = btrfs_block_group_done(block_group);
 		if (unlikely(!ffe_ctl.cached)) {
 			ffe_ctl.have_caching_bg = true;
-			ret = btrfs_cache_block_group(block_group, 0);
+			ret = btrfs_cache_block_group(block_group, false);
 
 			/*
 			 * If we get ENOMEM here or something else we want to
@@ -4705,7 +4710,8 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
 
 	btrfs_init_generic_ref(&generic_ref, BTRFS_ADD_DELAYED_EXTENT,
 			       ins->objectid, ins->offset, 0);
-	btrfs_init_data_ref(&generic_ref, root->root_key.objectid, owner, offset);
+	btrfs_init_data_ref(&generic_ref, root->root_key.objectid, owner,
+			    offset, 0, false);
 	btrfs_ref_tree_mod(root->fs_info, &generic_ref);
 
 	return btrfs_add_delayed_data_ref(trans, &generic_ref, ram_bytes);
@@ -4763,6 +4769,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct extent_buffer *buf;
+	u64 lockdep_owner = owner;
 
 	buf = btrfs_find_create_tree_block(fs_info, bytenr, owner, level);
 	if (IS_ERR(buf))
@@ -4782,11 +4789,26 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	}
 
 	/*
+	 * The reloc trees are just snapshots, so we need them to appear to be
+	 * just like any other fs tree WRT lockdep.
+	 *
+	 * The exception however is in replace_path() in relocation, where we
+	 * hold the lock on the original fs root and then search for the reloc
+	 * root.  At that point we need to make sure any reloc root buffers are
+	 * set to the BTRFS_TREE_RELOC_OBJECTID lockdep class in order to make
+	 * lockdep happy.
+	 */
+	if (lockdep_owner == BTRFS_TREE_RELOC_OBJECTID &&
+	    !test_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &root->state))
+		lockdep_owner = BTRFS_FS_TREE_OBJECTID;
+
+	/*
 	 * This needs to stay, because we could allocate a freed block from an
 	 * old tree into a new tree, so we need to make sure this new block is
 	 * set to the appropriate level and owner.
 	 */
-	btrfs_set_buffer_lockdep_class(owner, buf, level);
+	btrfs_set_buffer_lockdep_class(lockdep_owner, buf, level);
+
 	__btrfs_tree_lock(buf, nest);
 	btrfs_clean_tree_block(buf);
 	clear_bit(EXTENT_BUFFER_STALE, &buf->bflags);
@@ -4898,7 +4920,8 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 		btrfs_init_generic_ref(&generic_ref, BTRFS_ADD_DELAYED_EXTENT,
 				       ins.objectid, ins.offset, parent);
 		generic_ref.real_root = root->root_key.objectid;
-		btrfs_init_tree_ref(&generic_ref, level, root_objectid);
+		btrfs_init_tree_ref(&generic_ref, level, root_objectid,
+				    root->root_key.objectid, false);
 		btrfs_ref_tree_mod(fs_info, &generic_ref);
 		ret = btrfs_add_delayed_tree_ref(trans, &generic_ref, extent_op);
 		if (ret)
@@ -5315,7 +5338,8 @@ skip:
 
 		btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, bytenr,
 				       fs_info->nodesize, parent);
-		btrfs_init_tree_ref(&ref, level - 1, root->root_key.objectid);
+		btrfs_init_tree_ref(&ref, level - 1, root->root_key.objectid,
+				    0, false);
 		ret = btrfs_free_extent(trans, &ref);
 		if (ret)
 			goto out_unlock;
@@ -5436,7 +5460,8 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
 			goto owner_mismatch;
 	}
 
-	btrfs_free_tree_block(trans, root, eb, parent, wc->refs[level] == 1);
+	btrfs_free_tree_block(trans, btrfs_root_id(root), eb, parent,
+			      wc->refs[level] == 1);
 out:
 	wc->refs[level] = 0;
 	wc->flags[level] = 0;
@@ -6045,13 +6070,7 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
 
 		if (end - start >= range->minlen) {
 			if (!btrfs_block_group_done(cache)) {
-				ret = btrfs_cache_block_group(cache, 0);
-				if (ret) {
-					bg_failed++;
-					bg_ret = ret;
-					continue;
-				}
-				ret = btrfs_wait_block_group_cache_done(cache);
+				ret = btrfs_cache_block_group(cache, true);
 				if (ret) {
 					bg_failed++;
 					bg_ret = ret;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 6dd375ed6e3d..7bd704779a99 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1985,8 +1985,10 @@ noinline_for_stack bool find_lock_delalloc_range(struct inode *inode,
 				    struct page *locked_page, u64 *start,
 				    u64 *end)
 {
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
-	u64 max_bytes = BTRFS_MAX_EXTENT_SIZE;
+	/* The sanity tests may not set a valid fs_info. */
+	u64 max_bytes = fs_info ? fs_info->max_extent_size : BTRFS_MAX_EXTENT_SIZE;
 	u64 delalloc_start;
 	u64 delalloc_end;
 	bool found;
@@ -2290,7 +2292,7 @@ int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
 	struct btrfs_device *dev;
 	u64 map_length = 0;
 	u64 sector;
-	struct btrfs_bio *bbio = NULL;
+	struct btrfs_io_context *bioc = NULL;
 	int ret;
 
 	ASSERT(!(fs_info->sb->s_flags & SB_RDONLY));
@@ -2304,7 +2306,7 @@ int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
 	map_length = length;
 
 	/*
-	 * Avoid races with device replace and make sure our bbio has devices
+	 * Avoid races with device replace and make sure our bioc has devices
 	 * associated to its stripes that don't go away while we are doing the
 	 * read repair operation.
 	 */
@@ -2317,28 +2319,28 @@ int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
 		 * stripe's dev and sector.
 		 */
 		ret = btrfs_map_block(fs_info, BTRFS_MAP_READ, logical,
-				      &map_length, &bbio, 0);
+				      &map_length, &bioc, 0);
 		if (ret) {
 			btrfs_bio_counter_dec(fs_info);
 			bio_put(bio);
 			return -EIO;
 		}
-		ASSERT(bbio->mirror_num == 1);
+		ASSERT(bioc->mirror_num == 1);
 	} else {
 		ret = btrfs_map_block(fs_info, BTRFS_MAP_WRITE, logical,
-				      &map_length, &bbio, mirror_num);
+				      &map_length, &bioc, mirror_num);
 		if (ret) {
 			btrfs_bio_counter_dec(fs_info);
 			bio_put(bio);
 			return -EIO;
 		}
-		BUG_ON(mirror_num != bbio->mirror_num);
+		BUG_ON(mirror_num != bioc->mirror_num);
 	}
 
-	sector = bbio->stripes[bbio->mirror_num - 1].physical >> 9;
+	sector = bioc->stripes[bioc->mirror_num - 1].physical >> 9;
 	bio->bi_iter.bi_sector = sector;
-	dev = bbio->stripes[bbio->mirror_num - 1].dev;
-	btrfs_put_bbio(bbio);
+	dev = bioc->stripes[bioc->mirror_num - 1].dev;
+	btrfs_put_bioc(bioc);
 	if (!dev || !dev->bdev ||
 	    !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) {
 		btrfs_bio_counter_dec(fs_info);
@@ -3778,10 +3780,11 @@ static void update_nr_written(struct writeback_control *wbc,
  */
 static noinline_for_stack int writepage_delalloc(struct btrfs_inode *inode,
 		struct page *page, struct writeback_control *wbc,
-		u64 delalloc_start, unsigned long *nr_written)
+		unsigned long *nr_written)
 {
-	u64 page_end = delalloc_start + PAGE_SIZE - 1;
+	u64 page_end = page_offset(page) + PAGE_SIZE - 1;
 	bool found;
+	u64 delalloc_start = page_offset(page);
 	u64 delalloc_to_write = 0;
 	u64 delalloc_end = 0;
 	int ret;
@@ -4066,8 +4069,8 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 			      struct extent_page_data *epd)
 {
 	struct inode *inode = page->mapping->host;
-	u64 start = page_offset(page);
-	u64 page_end = start + PAGE_SIZE - 1;
+	const u64 page_start = page_offset(page);
+	const u64 page_end = page_start + PAGE_SIZE - 1;
 	int ret;
 	int nr = 0;
 	size_t pg_offset;
@@ -4102,8 +4105,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 	}
 
 	if (!epd->extent_locked) {
-		ret = writepage_delalloc(BTRFS_I(inode), page, wbc, start,
-					 &nr_written);
+		ret = writepage_delalloc(BTRFS_I(inode), page, wbc, &nr_written);
 		if (ret == 1)
 			return 0;
 		if (ret)
@@ -4153,7 +4155,7 @@ done:
 	 * capable of that.
 	 */
 	if (PageError(page))
-		end_extent_writepage(page, ret, start, page_end);
+		end_extent_writepage(page, ret, page_start, page_end);
 	unlock_page(page);
 	ASSERT(ret <= 0);
 	return ret;
@@ -5139,8 +5141,6 @@ int extent_writepages(struct address_space *mapping,
 		      struct writeback_control *wbc)
 {
 	struct inode *inode = mapping->host;
-	const bool data_reloc = btrfs_is_data_reloc_root(BTRFS_I(inode)->root);
-	const bool zoned = btrfs_is_zoned(BTRFS_I(inode)->root->fs_info);
 	int ret = 0;
 	struct extent_page_data epd = {
 		.bio_ctrl = { 0 },
@@ -5152,17 +5152,16 @@ int extent_writepages(struct address_space *mapping,
 	 * Allow only a single thread to do the reloc work in zoned mode to
 	 * protect the write pointer updates.
 	 */
-	if (data_reloc && zoned)
-		btrfs_inode_lock(inode, 0);
+	btrfs_zoned_data_reloc_lock(BTRFS_I(inode));
 	ret = extent_write_cache_pages(mapping, wbc, &epd);
-	if (data_reloc && zoned)
-		btrfs_inode_unlock(inode, 0);
 	ASSERT(ret <= 0);
 	if (ret < 0) {
+		btrfs_zoned_data_reloc_unlock(BTRFS_I(inode));
 		end_write_bio(&epd, ret);
 		return ret;
 	}
 	ret = flush_write_bio(&epd);
+	btrfs_zoned_data_reloc_unlock(BTRFS_I(inode));
 	return ret;
 }
 
@@ -6110,6 +6109,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 	struct extent_buffer *exists = NULL;
 	struct page *p;
 	struct address_space *mapping = fs_info->btree_inode->i_mapping;
+	u64 lockdep_owner = owner_root;
 	int uptodate = 1;
 	int ret;
 
@@ -6144,7 +6144,15 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 	eb = __alloc_extent_buffer(fs_info, start, len);
 	if (!eb)
 		return ERR_PTR(-ENOMEM);
-	btrfs_set_buffer_lockdep_class(owner_root, eb, level);
+
+	/*
+	 * The reloc trees are just snapshots, so we need them to appear to be
+	 * just like any other fs tree WRT lockdep.
+	 */
+	if (lockdep_owner == BTRFS_TREE_RELOC_OBJECTID)
+		lockdep_owner = BTRFS_FS_TREE_OBJECTID;
+
+	btrfs_set_buffer_lockdep_class(lockdep_owner, eb, level);
 
 	num_pages = num_extent_pages(eb);
 	for (i = 0; i < num_pages; i++, index++) {
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 4a8e02f7b6c7..5a36add21305 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -360,7 +360,7 @@ static void extent_map_device_set_bits(struct extent_map *em, unsigned bits)
 	int i;
 
 	for (i = 0; i < map->num_stripes; i++) {
-		struct btrfs_bio_stripe *stripe = &map->stripes[i];
+		struct btrfs_io_stripe *stripe = &map->stripes[i];
 		struct btrfs_device *device = stripe->dev;
 
 		set_extent_bits_nowait(&device->alloc_state, stripe->physical,
@@ -375,7 +375,7 @@ static void extent_map_device_clear_bits(struct extent_map *em, unsigned bits)
 	int i;
 
 	for (i = 0; i < map->num_stripes; i++) {
-		struct btrfs_bio_stripe *stripe = &map->stripes[i];
+		struct btrfs_io_stripe *stripe = &map->stripes[i];
 		struct btrfs_device *device = stripe->dev;
 
 		__clear_extent_bit(&device->alloc_state, stripe->physical,
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index a06c8366a8f4..1c597cd6c024 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -869,7 +869,8 @@ next_slot:
 				btrfs_init_data_ref(&ref,
 						root->root_key.objectid,
 						new_key.objectid,
-						args->start - extent_offset);
+						args->start - extent_offset,
+						0, false);
 				ret = btrfs_inc_extent_ref(trans, &ref);
 				BUG_ON(ret); /* -ENOMEM */
 			}
@@ -955,7 +956,8 @@ delete_extent_item:
 				btrfs_init_data_ref(&ref,
 						root->root_key.objectid,
 						key.objectid,
-						key.offset - extent_offset);
+						key.offset - extent_offset, 0,
+						false);
 				ret = btrfs_free_extent(trans, &ref);
 				BUG_ON(ret); /* -ENOMEM */
 				args->bytes_found += extent_end - key.offset;
@@ -1232,7 +1234,7 @@ again:
 		btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, bytenr,
 				       num_bytes, 0);
 		btrfs_init_data_ref(&ref, root->root_key.objectid, ino,
-				    orig_offset);
+				    orig_offset, 0, false);
 		ret = btrfs_inc_extent_ref(trans, &ref);
 		if (ret) {
 			btrfs_abort_transaction(trans, ret);
@@ -1257,7 +1259,8 @@ again:
 	other_end = 0;
 	btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, bytenr,
 			       num_bytes, 0);
-	btrfs_init_data_ref(&ref, root->root_key.objectid, ino, orig_offset);
+	btrfs_init_data_ref(&ref, root->root_key.objectid, ino, orig_offset,
+			    0, false);
 	if (extent_mergeable(leaf, path->slots[0] + 1,
 			     ino, bytenr, orig_offset,
 			     &other_start, &other_end)) {
@@ -2715,7 +2718,7 @@ static int btrfs_insert_replace_extent(struct btrfs_trans_handle *trans,
 				       extent_info->disk_len, 0);
 		ref_offset = extent_info->file_offset - extent_info->data_offset;
 		btrfs_init_data_ref(&ref, root->root_key.objectid,
-				    btrfs_ino(inode), ref_offset);
+				    btrfs_ino(inode), ref_offset, 0, false);
 		ret = btrfs_inc_extent_ref(trans, &ref);
 	}
 
diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
index a33bca94d133..3abec44c6255 100644
--- a/fs/btrfs/free-space-tree.c
+++ b/fs/btrfs/free-space-tree.c
@@ -1256,8 +1256,8 @@ int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info)
 	btrfs_tree_lock(free_space_root->node);
 	btrfs_clean_tree_block(free_space_root->node);
 	btrfs_tree_unlock(free_space_root->node);
-	btrfs_free_tree_block(trans, free_space_root, free_space_root->node,
-			      0, 1);
+	btrfs_free_tree_block(trans, btrfs_root_id(free_space_root),
+			      free_space_root->node, 0, 1);
 
 	btrfs_put_root(free_space_root);
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 044d584c3467..f8a01964a216 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1053,6 +1053,28 @@ static u64 get_extent_allocation_hint(struct btrfs_inode *inode, u64 start,
  * *page_started is set to one if we unlock locked_page and do everything
  * required to start IO on it.  It may be clean and already done with
  * IO when we return.
+ *
+ * When unlock == 1, we unlock the pages in successfully allocated regions.
+ * When unlock == 0, we leave them locked for writing them out.
+ *
+ * However, we unlock all the pages except @locked_page in case of failure.
+ *
+ * In summary, page locking state will be as follow:
+ *
+ * - page_started == 1 (return value)
+ *     - All the pages are unlocked. IO is started.
+ *     - Note that this can happen only on success
+ * - unlock == 1
+ *     - All the pages except @locked_page are unlocked in any case
+ * - unlock == 0
+ *     - On success, all the pages are locked for writing out them
+ *     - On failure, all the pages except @locked_page are unlocked
+ *
+ * When a failure happens in the second or later iteration of the
+ * while-loop, the ordered extents created in previous iterations are kept
+ * intact. So, the caller must clean them up by calling
+ * btrfs_cleanup_ordered_extents(). See btrfs_run_delalloc_range() for
+ * example.
  */
 static noinline int cow_file_range(struct btrfs_inode *inode,
 				   struct page *locked_page,
@@ -1062,6 +1084,7 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
 	struct btrfs_root *root = inode->root;
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	u64 alloc_hint = 0;
+	u64 orig_start = start;
 	u64 num_bytes;
 	unsigned long ram_size;
 	u64 cur_alloc_size = 0;
@@ -1245,18 +1268,44 @@ out_reserve:
 	btrfs_dec_block_group_reservations(fs_info, ins.objectid);
 	btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, 1);
 out_unlock:
+	/*
+	 * Now, we have three regions to clean up:
+	 *
+	 * |-------(1)----|---(2)---|-------------(3)----------|
+	 * `- orig_start  `- start  `- start + cur_alloc_size  `- end
+	 *
+	 * We process each region below.
+	 */
+
 	clear_bits = EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW |
 		EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV;
 	page_ops = PAGE_UNLOCK | PAGE_START_WRITEBACK | PAGE_END_WRITEBACK;
+
+	/*
+	 * For the range (1). We have already instantiated the ordered extents
+	 * for this region. They are cleaned up by
+	 * btrfs_cleanup_ordered_extents() in e.g,
+	 * btrfs_run_delalloc_range(). EXTENT_LOCKED | EXTENT_DELALLOC are
+	 * already cleared in the above loop. And, EXTENT_DELALLOC_NEW |
+	 * EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV are handled by the cleanup
+	 * function.
+	 *
+	 * However, in case of unlock == 0, we still need to unlock the pages
+	 * (except @locked_page) to ensure all the pages are unlocked.
+	 */
+	if (!unlock && orig_start < start)
+		extent_clear_unlock_delalloc(inode, orig_start, start - 1,
+					     locked_page, 0, page_ops);
+
 	/*
-	 * If we reserved an extent for our delalloc range (or a subrange) and
-	 * failed to create the respective ordered extent, then it means that
-	 * when we reserved the extent we decremented the extent's size from
-	 * the data space_info's bytes_may_use counter and incremented the
-	 * space_info's bytes_reserved counter by the same amount. We must make
-	 * sure extent_clear_unlock_delalloc() does not try to decrement again
-	 * the data space_info's bytes_may_use counter, therefore we do not pass
-	 * it the flag EXTENT_CLEAR_DATA_RESV.
+	 * For the range (2). If we reserved an extent for our delalloc range
+	 * (or a subrange) and failed to create the respective ordered extent,
+	 * then it means that when we reserved the extent we decremented the
+	 * extent's size from the data space_info's bytes_may_use counter and
+	 * incremented the space_info's bytes_reserved counter by the same
+	 * amount. We must make sure extent_clear_unlock_delalloc() does not try
+	 * to decrement again the data space_info's bytes_may_use counter,
+	 * therefore we do not pass it the flag EXTENT_CLEAR_DATA_RESV.
 	 */
 	if (extent_reserved) {
 		extent_clear_unlock_delalloc(inode, start,
@@ -1268,6 +1317,13 @@ out_unlock:
 		if (start >= end)
 			goto out;
 	}
+
+	/*
+	 * For the range (3). We never touched the region. In addition to the
+	 * clear_bits above, we add EXTENT_CLEAR_DATA_RESV to release the data
+	 * space_info's bytes_may_use counter, reserved in
+	 * btrfs_check_data_free_space().
+	 */
 	extent_clear_unlock_delalloc(inode, start, end, locked_page,
 				     clear_bits | EXTENT_CLEAR_DATA_RESV,
 				     page_ops);
@@ -1976,6 +2032,7 @@ int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page
 void btrfs_split_delalloc_extent(struct inode *inode,
 				 struct extent_state *orig, u64 split)
 {
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	u64 size;
 
 	/* not delalloc, ignore it */
@@ -1983,7 +2040,7 @@ void btrfs_split_delalloc_extent(struct inode *inode,
 		return;
 
 	size = orig->end - orig->start + 1;
-	if (size > BTRFS_MAX_EXTENT_SIZE) {
+	if (size > fs_info->max_extent_size) {
 		u32 num_extents;
 		u64 new_size;
 
@@ -1992,10 +2049,10 @@ void btrfs_split_delalloc_extent(struct inode *inode,
 		 * applies here, just in reverse.
 		 */
 		new_size = orig->end - split + 1;
-		num_extents = count_max_extents(new_size);
+		num_extents = count_max_extents(fs_info, new_size);
 		new_size = split - orig->start;
-		num_extents += count_max_extents(new_size);
-		if (count_max_extents(size) >= num_extents)
+		num_extents += count_max_extents(fs_info, new_size);
+		if (count_max_extents(fs_info, size) >= num_extents)
 			return;
 	}
 
@@ -2012,6 +2069,7 @@ void btrfs_split_delalloc_extent(struct inode *inode,
 void btrfs_merge_delalloc_extent(struct inode *inode, struct extent_state *new,
 				 struct extent_state *other)
 {
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	u64 new_size, old_size;
 	u32 num_extents;
 
@@ -2025,7 +2083,7 @@ void btrfs_merge_delalloc_extent(struct inode *inode, struct extent_state *new,
 		new_size = other->end - new->start + 1;
 
 	/* we're not bigger than the max, unreserve the space and go */
-	if (new_size <= BTRFS_MAX_EXTENT_SIZE) {
+	if (new_size <= fs_info->max_extent_size) {
 		spin_lock(&BTRFS_I(inode)->lock);
 		btrfs_mod_outstanding_extents(BTRFS_I(inode), -1);
 		spin_unlock(&BTRFS_I(inode)->lock);
@@ -2051,10 +2109,10 @@ void btrfs_merge_delalloc_extent(struct inode *inode, struct extent_state *new,
 	 * this case.
 	 */
 	old_size = other->end - other->start + 1;
-	num_extents = count_max_extents(old_size);
+	num_extents = count_max_extents(fs_info, old_size);
 	old_size = new->end - new->start + 1;
-	num_extents += count_max_extents(old_size);
-	if (count_max_extents(new_size) >= num_extents)
+	num_extents += count_max_extents(fs_info, old_size);
+	if (count_max_extents(fs_info, new_size) >= num_extents)
 		return;
 
 	spin_lock(&BTRFS_I(inode)->lock);
@@ -2133,7 +2191,7 @@ void btrfs_set_delalloc_extent(struct inode *inode, struct extent_state *state,
 	if (!(state->state & EXTENT_DELALLOC) && (*bits & EXTENT_DELALLOC)) {
 		struct btrfs_root *root = BTRFS_I(inode)->root;
 		u64 len = state->end + 1 - state->start;
-		u32 num_extents = count_max_extents(len);
+		u32 num_extents = count_max_extents(fs_info, len);
 		bool do_list = !btrfs_is_free_space_inode(BTRFS_I(inode));
 
 		spin_lock(&BTRFS_I(inode)->lock);
@@ -2175,7 +2233,7 @@ void btrfs_clear_delalloc_extent(struct inode *vfs_inode,
 	struct btrfs_inode *inode = BTRFS_I(vfs_inode);
 	struct btrfs_fs_info *fs_info = btrfs_sb(vfs_inode->i_sb);
 	u64 len = state->end + 1 - state->start;
-	u32 num_extents = count_max_extents(len);
+	u32 num_extents = count_max_extents(fs_info, len);
 
 	if ((state->state & EXTENT_DEFRAG) && (*bits & EXTENT_DEFRAG)) {
 		spin_lock(&inode->lock);
@@ -3069,6 +3127,8 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 						ordered_extent->file_offset,
 						ordered_extent->file_offset +
 						logical_len);
+		btrfs_zoned_release_data_reloc_bg(fs_info, ordered_extent->disk_bytenr,
+						  ordered_extent->disk_num_bytes);
 	} else {
 		BUG_ON(root == fs_info->tree_root);
 		ret = insert_ordered_extent_file_extent(trans, ordered_extent);
@@ -4037,11 +4097,11 @@ int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans,
  * also drops the back refs in the inode to the directory
  */
 static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans,
-				struct btrfs_root *root,
 				struct btrfs_inode *dir,
 				struct btrfs_inode *inode,
 				const char *name, int name_len)
 {
+	struct btrfs_root *root = dir->root;
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_path *path;
 	int ret = 0;
@@ -4141,15 +4201,14 @@ out:
 }
 
 int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
-		       struct btrfs_root *root,
 		       struct btrfs_inode *dir, struct btrfs_inode *inode,
 		       const char *name, int name_len)
 {
 	int ret;
-	ret = __btrfs_unlink_inode(trans, root, dir, inode, name, name_len);
+	ret = __btrfs_unlink_inode(trans, dir, inode, name, name_len);
 	if (!ret) {
 		drop_nlink(&inode->vfs_inode);
-		ret = btrfs_update_inode(trans, root, inode);
+		ret = btrfs_update_inode(trans, inode->root, inode);
 	}
 	return ret;
 }
@@ -4178,7 +4237,6 @@ static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir)
 
 static int btrfs_unlink(struct inode *dir, struct dentry *dentry)
 {
-	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct btrfs_trans_handle *trans;
 	struct inode *inode = d_inode(dentry);
 	int ret;
@@ -4190,7 +4248,7 @@ static int btrfs_unlink(struct inode *dir, struct dentry *dentry)
 	btrfs_record_unlink_dir(trans, BTRFS_I(dir), BTRFS_I(d_inode(dentry)),
 			0);
 
-	ret = btrfs_unlink_inode(trans, root, BTRFS_I(dir),
+	ret = btrfs_unlink_inode(trans, BTRFS_I(dir),
 			BTRFS_I(d_inode(dentry)), dentry->d_name.name,
 			dentry->d_name.len);
 	if (ret)
@@ -4204,7 +4262,7 @@ static int btrfs_unlink(struct inode *dir, struct dentry *dentry)
 
 out:
 	btrfs_end_transaction(trans);
-	btrfs_btree_balance_dirty(root->fs_info);
+	btrfs_btree_balance_dirty(BTRFS_I(dir)->root->fs_info);
 	return ret;
 }
 
@@ -4562,7 +4620,6 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
 {
 	struct inode *inode = d_inode(dentry);
 	int err = 0;
-	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct btrfs_trans_handle *trans;
 	u64 last_unlink_trans;
 
@@ -4587,7 +4644,7 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
 	last_unlink_trans = BTRFS_I(inode)->last_unlink_trans;
 
 	/* now the directory is empty */
-	err = btrfs_unlink_inode(trans, root, BTRFS_I(dir),
+	err = btrfs_unlink_inode(trans, BTRFS_I(dir),
 			BTRFS_I(d_inode(dentry)), dentry->d_name.name,
 			dentry->d_name.len);
 	if (!err) {
@@ -4608,7 +4665,7 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
 	}
 out:
 	btrfs_end_transaction(trans);
-	btrfs_btree_balance_dirty(root->fs_info);
+	btrfs_btree_balance_dirty(BTRFS_I(dir)->root->fs_info);
 
 	return err;
 }
@@ -4919,7 +4976,8 @@ delete:
 					extent_start, extent_num_bytes, 0);
 			ref.real_root = root->root_key.objectid;
 			btrfs_init_data_ref(&ref, btrfs_header_owner(leaf),
-					ino, extent_offset);
+					ino, extent_offset,
+					root->root_key.objectid, false);
 			ret = btrfs_free_extent(trans, &ref);
 			if (ret) {
 				btrfs_abort_transaction(trans, ret);
@@ -6335,14 +6393,8 @@ static int btrfs_set_inode_index_count(struct btrfs_inode *inode)
 		goto out;
 	ret = 0;
 
-	/*
-	 * MAGIC NUMBER EXPLANATION:
-	 * since we search a directory based on f_pos we have to start at 2
-	 * since '.' and '..' have f_pos of 0 and 1 respectively, so everybody
-	 * else has to start at 2
-	 */
 	if (path->slots[0] == 0) {
-		inode->index_cnt = 2;
+		inode->index_cnt = BTRFS_DIR_START_INDEX;
 		goto out;
 	}
 
@@ -6353,7 +6405,7 @@ static int btrfs_set_inode_index_count(struct btrfs_inode *inode)
 
 	if (found_key.objectid != btrfs_ino(inode) ||
 	    found_key.type != BTRFS_DIR_INDEX_KEY) {
-		inode->index_cnt = 2;
+		inode->index_cnt = BTRFS_DIR_START_INDEX;
 		goto out;
 	}
 
@@ -6897,7 +6949,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 				goto fail;
 		}
 		d_instantiate(dentry, inode);
-		btrfs_log_new_name(trans, BTRFS_I(inode), NULL, parent);
+		btrfs_log_new_name(trans, old_dentry, NULL, parent);
 	}
 
 fail:
@@ -7956,7 +8008,19 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
 	if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags) ||
 	    em->block_start == EXTENT_MAP_INLINE) {
 		free_extent_map(em);
-		ret = -ENOTBLK;
+		/*
+		 * If we are in a NOWAIT context, return -EAGAIN in order to
+		 * fallback to buffered IO. This is not only because we can
+		 * block with buffered IO (no support for NOWAIT semantics at
+		 * the moment) but also to avoid returning short reads to user
+		 * space - this happens if we were able to read some data from
+		 * previous non-compressed extents and then when we fallback to
+		 * buffered IO, at btrfs_file_read_iter() by calling
+		 * filemap_read(), we fail to fault in pages for the read buffer,
+		 * in which case filemap_read() returns a short read (the number
+		 * of bytes previously read is > 0, so it does not return -EFAULT).
+		 */
+		ret = (flags & IOMAP_NOWAIT) ? -EAGAIN : -ENOTBLK;
 		goto unlock_err;
 	}
 
@@ -9504,7 +9568,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 	if (old_ino == BTRFS_FIRST_FREE_OBJECTID) {
 		ret = btrfs_unlink_subvol(trans, old_dir, old_dentry);
 	} else { /* src is an inode */
-		ret = __btrfs_unlink_inode(trans, root, BTRFS_I(old_dir),
+		ret = __btrfs_unlink_inode(trans, BTRFS_I(old_dir),
 					   BTRFS_I(old_dentry->d_inode),
 					   old_dentry->d_name.name,
 					   old_dentry->d_name.len);
@@ -9520,7 +9584,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 	if (new_ino == BTRFS_FIRST_FREE_OBJECTID) {
 		ret = btrfs_unlink_subvol(trans, new_dir, new_dentry);
 	} else { /* dest is an inode */
-		ret = __btrfs_unlink_inode(trans, dest, BTRFS_I(new_dir),
+		ret = __btrfs_unlink_inode(trans, BTRFS_I(new_dir),
 					   BTRFS_I(new_dentry->d_inode),
 					   new_dentry->d_name.name,
 					   new_dentry->d_name.len);
@@ -9554,13 +9618,13 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 		BTRFS_I(new_inode)->dir_index = new_idx;
 
 	if (root_log_pinned) {
-		btrfs_log_new_name(trans, BTRFS_I(old_inode), BTRFS_I(old_dir),
+		btrfs_log_new_name(trans, old_dentry, BTRFS_I(old_dir),
 				   new_dentry->d_parent);
 		btrfs_end_log_trans(root);
 		root_log_pinned = false;
 	}
 	if (dest_log_pinned) {
-		btrfs_log_new_name(trans, BTRFS_I(new_inode), BTRFS_I(new_dir),
+		btrfs_log_new_name(trans, new_dentry, BTRFS_I(new_dir),
 				   old_dentry->d_parent);
 		btrfs_end_log_trans(dest);
 		dest_log_pinned = false;
@@ -9795,7 +9859,7 @@ static int btrfs_rename(struct user_namespace *mnt_userns,
 		 */
 		btrfs_pin_log_trans(root);
 		log_pinned = true;
-		ret = __btrfs_unlink_inode(trans, root, BTRFS_I(old_dir),
+		ret = __btrfs_unlink_inode(trans, BTRFS_I(old_dir),
 					BTRFS_I(d_inode(old_dentry)),
 					old_dentry->d_name.name,
 					old_dentry->d_name.len);
@@ -9815,7 +9879,7 @@ static int btrfs_rename(struct user_namespace *mnt_userns,
 			ret = btrfs_unlink_subvol(trans, new_dir, new_dentry);
 			BUG_ON(new_inode->i_nlink == 0);
 		} else {
-			ret = btrfs_unlink_inode(trans, dest, BTRFS_I(new_dir),
+			ret = btrfs_unlink_inode(trans, BTRFS_I(new_dir),
 						 BTRFS_I(d_inode(new_dentry)),
 						 new_dentry->d_name.name,
 						 new_dentry->d_name.len);
@@ -9841,7 +9905,7 @@ static int btrfs_rename(struct user_namespace *mnt_userns,
 		BTRFS_I(old_inode)->dir_index = index;
 
 	if (log_pinned) {
-		btrfs_log_new_name(trans, BTRFS_I(old_inode), BTRFS_I(old_dir),
+		btrfs_log_new_name(trans, old_dentry, BTRFS_I(old_dir),
 				   new_dentry->d_parent);
 		btrfs_end_log_trans(root);
 		log_pinned = false;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index bf53af8694f8..b9dcaae7c8d5 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -615,11 +615,13 @@ static noinline int create_subvol(struct user_namespace *mnt_userns,
 		 * Since we don't abort the transaction in this case, free the
 		 * tree block so that we don't leak space and leave the
 		 * filesystem in an inconsistent state (an extent item in the
-		 * extent tree without backreferences). Also no need to have
-		 * the tree block locked since it is not in any tree at this
-		 * point, so no other task can find it and use it.
+		 * extent tree with a backreference for a root that does not
+		 * exists).
 		 */
-		btrfs_free_tree_block(trans, root, leaf, 0, 1);
+		btrfs_tree_lock(leaf);
+		btrfs_clean_tree_block(leaf);
+		btrfs_tree_unlock(leaf);
+		btrfs_free_tree_block(trans, objectid, leaf, 0, 1);
 		free_extent_buffer(leaf);
 		goto fail;
 	}
@@ -1655,6 +1657,7 @@ static int exclop_start_or_cancel_reloc(struct btrfs_fs_info *fs_info,
 static noinline int btrfs_ioctl_resize(struct file *file,
 					void __user *arg)
 {
+	BTRFS_DEV_LOOKUP_ARGS(args);
 	struct inode *inode = file_inode(file);
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	u64 new_size;
@@ -1710,7 +1713,8 @@ static noinline int btrfs_ioctl_resize(struct file *file,
 		btrfs_info(fs_info, "resizing devid %llu", devid);
 	}
 
-	device = btrfs_find_device(fs_info->fs_devices, devid, NULL, NULL);
+	args.devid = devid;
+	device = btrfs_find_device(fs_info->fs_devices, &args);
 	if (!device) {
 		btrfs_info(fs_info, "resizer unable to find device %llu",
 			   devid);
@@ -3214,6 +3218,7 @@ out:
 
 static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
 {
+	BTRFS_DEV_LOOKUP_ARGS(args);
 	struct inode *inode = file_inode(file);
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_ioctl_vol_args_v2 *vol_args;
@@ -3225,35 +3230,37 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	ret = mnt_want_write_file(file);
-	if (ret)
-		return ret;
-
 	vol_args = memdup_user(arg, sizeof(*vol_args));
-	if (IS_ERR(vol_args)) {
-		ret = PTR_ERR(vol_args);
-		goto err_drop;
-	}
+	if (IS_ERR(vol_args))
+		return PTR_ERR(vol_args);
 
 	if (vol_args->flags & ~BTRFS_DEVICE_REMOVE_ARGS_MASK) {
 		ret = -EOPNOTSUPP;
 		goto out;
 	}
+
 	vol_args->name[BTRFS_SUBVOL_NAME_MAX] = '\0';
-	if (!(vol_args->flags & BTRFS_DEVICE_SPEC_BY_ID) &&
-	    strcmp("cancel", vol_args->name) == 0)
+	if (vol_args->flags & BTRFS_DEVICE_SPEC_BY_ID) {
+		args.devid = vol_args->devid;
+	} else if (!strcmp("cancel", vol_args->name)) {
 		cancel = true;
+	} else {
+		ret = btrfs_get_dev_args_from_path(fs_info, &args, vol_args->name);
+		if (ret)
+			goto out;
+	}
+
+	ret = mnt_want_write_file(file);
+	if (ret)
+		goto out;
 
 	ret = exclop_start_or_cancel_reloc(fs_info, BTRFS_EXCLOP_DEV_REMOVE,
 					   cancel);
 	if (ret)
-		goto out;
-	/* Exclusive operation is now claimed */
+		goto err_drop;
 
-	if (vol_args->flags & BTRFS_DEVICE_SPEC_BY_ID)
-		ret = btrfs_rm_device(fs_info, NULL, vol_args->devid, &bdev, &mode);
-	else
-		ret = btrfs_rm_device(fs_info, vol_args->name, 0, &bdev, &mode);
+	/* Exclusive operation is now claimed */
+	ret = btrfs_rm_device(fs_info, &args, &bdev, &mode);
 
 	btrfs_exclop_finish(fs_info);
 
@@ -3265,54 +3272,62 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
 			btrfs_info(fs_info, "device deleted: %s",
 					vol_args->name);
 	}
-out:
-	kfree(vol_args);
 err_drop:
 	mnt_drop_write_file(file);
 	if (bdev)
 		blkdev_put(bdev, mode);
+out:
+	btrfs_put_dev_args_from_path(&args);
+	kfree(vol_args);
 	return ret;
 }
 
 static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
 {
+	BTRFS_DEV_LOOKUP_ARGS(args);
 	struct inode *inode = file_inode(file);
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_ioctl_vol_args *vol_args;
 	struct block_device *bdev = NULL;
 	fmode_t mode;
 	int ret;
-	bool cancel;
+	bool cancel = false;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	ret = mnt_want_write_file(file);
-	if (ret)
-		return ret;
-
 	vol_args = memdup_user(arg, sizeof(*vol_args));
-	if (IS_ERR(vol_args)) {
-		ret = PTR_ERR(vol_args);
-		goto out_drop_write;
-	}
+	if (IS_ERR(vol_args))
+		return PTR_ERR(vol_args);
+
 	vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
-	cancel = (strcmp("cancel", vol_args->name) == 0);
+	if (!strcmp("cancel", vol_args->name)) {
+		cancel = true;
+	} else {
+		ret = btrfs_get_dev_args_from_path(fs_info, &args, vol_args->name);
+		if (ret)
+			goto out;
+	}
+
+	ret = mnt_want_write_file(file);
+	if (ret)
+		goto out;
 
 	ret = exclop_start_or_cancel_reloc(fs_info, BTRFS_EXCLOP_DEV_REMOVE,
 					   cancel);
 	if (ret == 0) {
-		ret = btrfs_rm_device(fs_info, vol_args->name, 0, &bdev, &mode);
+		ret = btrfs_rm_device(fs_info, &args, &bdev, &mode);
 		if (!ret)
 			btrfs_info(fs_info, "disk deleted %s", vol_args->name);
 		btrfs_exclop_finish(fs_info);
 	}
 
-	kfree(vol_args);
-out_drop_write:
 	mnt_drop_write_file(file);
 	if (bdev)
 		blkdev_put(bdev, mode);
+out:
+	btrfs_put_dev_args_from_path(&args);
+	kfree(vol_args);
 	return ret;
 }
 
@@ -3373,22 +3388,21 @@ static long btrfs_ioctl_fs_info(struct btrfs_fs_info *fs_info,
 static long btrfs_ioctl_dev_info(struct btrfs_fs_info *fs_info,
 				 void __user *arg)
 {
+	BTRFS_DEV_LOOKUP_ARGS(args);
 	struct btrfs_ioctl_dev_info_args *di_args;
 	struct btrfs_device *dev;
 	int ret = 0;
-	char *s_uuid = NULL;
 
 	di_args = memdup_user(arg, sizeof(*di_args));
 	if (IS_ERR(di_args))
 		return PTR_ERR(di_args);
 
+	args.devid = di_args->devid;
 	if (!btrfs_is_empty_uuid(di_args->uuid))
-		s_uuid = di_args->uuid;
+		args.uuid = di_args->uuid;
 
 	rcu_read_lock();
-	dev = btrfs_find_device(fs_info->fs_devices, di_args->devid, s_uuid,
-				NULL);
-
+	dev = btrfs_find_device(fs_info->fs_devices, &args);
 	if (!dev) {
 		ret = -ENODEV;
 		goto out;
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index 33461b4f9c8b..9063072b399b 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -14,6 +14,93 @@
 #include "locking.h"
 
 /*
+ * Lockdep class keys for extent_buffer->lock's in this root.  For a given
+ * eb, the lockdep key is determined by the btrfs_root it belongs to and
+ * the level the eb occupies in the tree.
+ *
+ * Different roots are used for different purposes and may nest inside each
+ * other and they require separate keysets.  As lockdep keys should be
+ * static, assign keysets according to the purpose of the root as indicated
+ * by btrfs_root->root_key.objectid.  This ensures that all special purpose
+ * roots have separate keysets.
+ *
+ * Lock-nesting across peer nodes is always done with the immediate parent
+ * node locked thus preventing deadlock.  As lockdep doesn't know this, use
+ * subclass to avoid triggering lockdep warning in such cases.
+ *
+ * The key is set by the readpage_end_io_hook after the buffer has passed
+ * csum validation but before the pages are unlocked.  It is also set by
+ * btrfs_init_new_buffer on freshly allocated blocks.
+ *
+ * We also add a check to make sure the highest level of the tree is the
+ * same as our lockdep setup here.  If BTRFS_MAX_LEVEL changes, this code
+ * needs update as well.
+ */
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+#if BTRFS_MAX_LEVEL != 8
+#error
+#endif
+
+#define DEFINE_LEVEL(stem, level)					\
+	.names[level] = "btrfs-" stem "-0" #level,
+
+#define DEFINE_NAME(stem)						\
+	DEFINE_LEVEL(stem, 0)						\
+	DEFINE_LEVEL(stem, 1)						\
+	DEFINE_LEVEL(stem, 2)						\
+	DEFINE_LEVEL(stem, 3)						\
+	DEFINE_LEVEL(stem, 4)						\
+	DEFINE_LEVEL(stem, 5)						\
+	DEFINE_LEVEL(stem, 6)						\
+	DEFINE_LEVEL(stem, 7)
+
+static struct btrfs_lockdep_keyset {
+	u64			id;		/* root objectid */
+	/* Longest entry: btrfs-free-space-00 */
+	char			names[BTRFS_MAX_LEVEL][20];
+	struct lock_class_key	keys[BTRFS_MAX_LEVEL];
+} btrfs_lockdep_keysets[] = {
+	{ .id = BTRFS_ROOT_TREE_OBJECTID,	DEFINE_NAME("root")	},
+	{ .id = BTRFS_EXTENT_TREE_OBJECTID,	DEFINE_NAME("extent")	},
+	{ .id = BTRFS_CHUNK_TREE_OBJECTID,	DEFINE_NAME("chunk")	},
+	{ .id = BTRFS_DEV_TREE_OBJECTID,	DEFINE_NAME("dev")	},
+	{ .id = BTRFS_CSUM_TREE_OBJECTID,	DEFINE_NAME("csum")	},
+	{ .id = BTRFS_QUOTA_TREE_OBJECTID,	DEFINE_NAME("quota")	},
+	{ .id = BTRFS_TREE_LOG_OBJECTID,	DEFINE_NAME("log")	},
+	{ .id = BTRFS_TREE_RELOC_OBJECTID,	DEFINE_NAME("treloc")	},
+	{ .id = BTRFS_DATA_RELOC_TREE_OBJECTID,	DEFINE_NAME("dreloc")	},
+	{ .id = BTRFS_UUID_TREE_OBJECTID,	DEFINE_NAME("uuid")	},
+	{ .id = BTRFS_FREE_SPACE_TREE_OBJECTID,	DEFINE_NAME("free-space") },
+	{ .id = 0,				DEFINE_NAME("tree")	},
+};
+
+#undef DEFINE_LEVEL
+#undef DEFINE_NAME
+
+void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb, int level)
+{
+	struct btrfs_lockdep_keyset *ks;
+
+	BUG_ON(level >= ARRAY_SIZE(ks->keys));
+
+	/* Find the matching keyset, id 0 is the default entry */
+	for (ks = btrfs_lockdep_keysets; ks->id; ks++)
+		if (ks->id == objectid)
+			break;
+
+	lockdep_set_class_and_name(&eb->lock, &ks->keys[level], ks->names[level]);
+}
+
+void btrfs_maybe_reset_lockdep_class(struct btrfs_root *root, struct extent_buffer *eb)
+{
+	if (test_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &root->state))
+		btrfs_set_buffer_lockdep_class(root->root_key.objectid,
+					       eb, btrfs_header_level(eb));
+}
+
+#endif
+
+/*
  * Extent buffer locking
  * =====================
  *
@@ -164,6 +251,8 @@ struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root)
 
 	while (1) {
 		eb = btrfs_root_node(root);
+
+		btrfs_maybe_reset_lockdep_class(root, eb);
 		btrfs_tree_lock(eb);
 		if (eb == root->node)
 			break;
@@ -185,6 +274,8 @@ struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root)
 
 	while (1) {
 		eb = btrfs_root_node(root);
+
+		btrfs_maybe_reset_lockdep_class(root, eb);
 		btrfs_tree_read_lock(eb);
 		if (eb == root->node)
 			break;
diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h
index a2e1f1f5c6e3..26a2f962c268 100644
--- a/fs/btrfs/locking.h
+++ b/fs/btrfs/locking.h
@@ -130,4 +130,18 @@ void btrfs_drew_write_unlock(struct btrfs_drew_lock *lock);
 void btrfs_drew_read_lock(struct btrfs_drew_lock *lock);
 void btrfs_drew_read_unlock(struct btrfs_drew_lock *lock);
 
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb, int level);
+void btrfs_maybe_reset_lockdep_class(struct btrfs_root *root, struct extent_buffer *eb);
+#else
+static inline void btrfs_set_buffer_lockdep_class(u64 objectid,
+					struct extent_buffer *eb, int level)
+{
+}
+static inline void btrfs_maybe_reset_lockdep_class(struct btrfs_root *root,
+						   struct extent_buffer *eb)
+{
+}
+#endif
+
 #endif
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 2c803108ea94..4ca809fa80ea 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1259,7 +1259,8 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info)
 	btrfs_tree_lock(quota_root->node);
 	btrfs_clean_tree_block(quota_root->node);
 	btrfs_tree_unlock(quota_root->node);
-	btrfs_free_tree_block(trans, quota_root, quota_root->node, 0, 1);
+	btrfs_free_tree_block(trans, btrfs_root_id(quota_root),
+			      quota_root->node, 0, 1);
 
 	btrfs_put_root(quota_root);
 
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index d8d268ca8aa7..3157a26ddf7e 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -61,7 +61,7 @@ enum btrfs_rbio_ops {
 
 struct btrfs_raid_bio {
 	struct btrfs_fs_info *fs_info;
-	struct btrfs_bio *bbio;
+	struct btrfs_io_context *bioc;
 
 	/* while we're doing rmw on a stripe
 	 * we put it into a hash table so we can
@@ -271,7 +271,7 @@ static void cache_rbio_pages(struct btrfs_raid_bio *rbio)
  */
 static int rbio_bucket(struct btrfs_raid_bio *rbio)
 {
-	u64 num = rbio->bbio->raid_map[0];
+	u64 num = rbio->bioc->raid_map[0];
 
 	/*
 	 * we shift down quite a bit.  We're using byte
@@ -324,6 +324,9 @@ static void merge_rbio(struct btrfs_raid_bio *dest,
 {
 	bio_list_merge(&dest->bio_list, &victim->bio_list);
 	dest->bio_list_bytes += victim->bio_list_bytes;
+	/* Also inherit the bitmaps from @victim. */
+	bitmap_or(dest->dbitmap, victim->dbitmap, dest->dbitmap,
+		  dest->stripe_npages);
 	dest->generic_bio_cnt += victim->generic_bio_cnt;
 	bio_list_init(&victim->bio_list);
 }
@@ -559,8 +562,7 @@ static int rbio_can_merge(struct btrfs_raid_bio *last,
 	    test_bit(RBIO_CACHE_BIT, &cur->flags))
 		return 0;
 
-	if (last->bbio->raid_map[0] !=
-	    cur->bbio->raid_map[0])
+	if (last->bioc->raid_map[0] != cur->bioc->raid_map[0])
 		return 0;
 
 	/* we can't merge with different operations */
@@ -673,7 +675,7 @@ static noinline int lock_stripe_add(struct btrfs_raid_bio *rbio)
 
 	spin_lock_irqsave(&h->lock, flags);
 	list_for_each_entry(cur, &h->hash_list, hash_list) {
-		if (cur->bbio->raid_map[0] != rbio->bbio->raid_map[0])
+		if (cur->bioc->raid_map[0] != rbio->bioc->raid_map[0])
 			continue;
 
 		spin_lock(&cur->bio_list_lock);
@@ -838,7 +840,7 @@ static void __free_raid_bio(struct btrfs_raid_bio *rbio)
 		}
 	}
 
-	btrfs_put_bbio(rbio->bbio);
+	btrfs_put_bioc(rbio->bioc);
 	kfree(rbio);
 }
 
@@ -866,6 +868,12 @@ static void rbio_orig_end_io(struct btrfs_raid_bio *rbio, blk_status_t err)
 
 	if (rbio->generic_bio_cnt)
 		btrfs_bio_counter_sub(rbio->fs_info, rbio->generic_bio_cnt);
+	/*
+	 * Clear the data bitmap, as the rbio may be cached for later usage.
+	 * do this before before unlock_stripe() so there will be no new bio
+	 * for this bio.
+	 */
+	bitmap_clear(rbio->dbitmap, 0, rbio->stripe_npages);
 
 	/*
 	 * At this moment, rbio->bio_list is empty, however since rbio does not
@@ -906,7 +914,7 @@ static void raid_write_end_io(struct bio *bio)
 
 	/* OK, we have read all the stripes we need to. */
 	max_errors = (rbio->operation == BTRFS_RBIO_PARITY_SCRUB) ?
-		     0 : rbio->bbio->max_errors;
+		     0 : rbio->bioc->max_errors;
 	if (atomic_read(&rbio->error) > max_errors)
 		err = BLK_STS_IOERR;
 
@@ -961,12 +969,12 @@ static unsigned long rbio_nr_pages(unsigned long stripe_len, int nr_stripes)
  * this does not allocate any pages for rbio->pages.
  */
 static struct btrfs_raid_bio *alloc_rbio(struct btrfs_fs_info *fs_info,
-					 struct btrfs_bio *bbio,
+					 struct btrfs_io_context *bioc,
 					 u64 stripe_len)
 {
 	struct btrfs_raid_bio *rbio;
 	int nr_data = 0;
-	int real_stripes = bbio->num_stripes - bbio->num_tgtdevs;
+	int real_stripes = bioc->num_stripes - bioc->num_tgtdevs;
 	int num_pages = rbio_nr_pages(stripe_len, real_stripes);
 	int stripe_npages = DIV_ROUND_UP(stripe_len, PAGE_SIZE);
 	void *p;
@@ -987,7 +995,7 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_fs_info *fs_info,
 	spin_lock_init(&rbio->bio_list_lock);
 	INIT_LIST_HEAD(&rbio->stripe_cache);
 	INIT_LIST_HEAD(&rbio->hash_list);
-	rbio->bbio = bbio;
+	rbio->bioc = bioc;
 	rbio->fs_info = fs_info;
 	rbio->stripe_len = stripe_len;
 	rbio->nr_pages = num_pages;
@@ -1015,9 +1023,9 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_fs_info *fs_info,
 	CONSUME_ALLOC(rbio->finish_pbitmap, BITS_TO_LONGS(stripe_npages));
 #undef  CONSUME_ALLOC
 
-	if (bbio->map_type & BTRFS_BLOCK_GROUP_RAID5)
+	if (bioc->map_type & BTRFS_BLOCK_GROUP_RAID5)
 		nr_data = real_stripes - 1;
-	else if (bbio->map_type & BTRFS_BLOCK_GROUP_RAID6)
+	else if (bioc->map_type & BTRFS_BLOCK_GROUP_RAID6)
 		nr_data = real_stripes - 2;
 	else
 		BUG();
@@ -1077,10 +1085,10 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio,
 	struct bio *last = bio_list->tail;
 	int ret;
 	struct bio *bio;
-	struct btrfs_bio_stripe *stripe;
+	struct btrfs_io_stripe *stripe;
 	u64 disk_start;
 
-	stripe = &rbio->bbio->stripes[stripe_nr];
+	stripe = &rbio->bioc->stripes[stripe_nr];
 	disk_start = stripe->physical + (page_index << PAGE_SHIFT);
 
 	/* if the device is missing, just fail this stripe */
@@ -1155,7 +1163,7 @@ static void index_rbio_pages(struct btrfs_raid_bio *rbio)
 		int i = 0;
 
 		start = bio->bi_iter.bi_sector << 9;
-		stripe_offset = start - rbio->bbio->raid_map[0];
+		stripe_offset = start - rbio->bioc->raid_map[0];
 		page_index = stripe_offset >> PAGE_SHIFT;
 
 		if (bio_flagged(bio, BIO_CLONED))
@@ -1179,7 +1187,7 @@ static void index_rbio_pages(struct btrfs_raid_bio *rbio)
  */
 static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
 {
-	struct btrfs_bio *bbio = rbio->bbio;
+	struct btrfs_io_context *bioc = rbio->bioc;
 	void **pointers = rbio->finish_pointers;
 	int nr_data = rbio->nr_data;
 	int stripe;
@@ -1198,6 +1206,9 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
 	else
 		BUG();
 
+	/* We should have at least one data sector. */
+	ASSERT(bitmap_weight(rbio->dbitmap, rbio->stripe_npages));
+
 	/* at this point we either have a full stripe,
 	 * or we've read the full stripe from the drive.
 	 * recalculate the parity and write the new results.
@@ -1269,6 +1280,11 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
 	for (stripe = 0; stripe < rbio->real_stripes; stripe++) {
 		for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
 			struct page *page;
+
+			/* This vertical stripe has no data, skip it. */
+			if (!test_bit(pagenr, rbio->dbitmap))
+				continue;
+
 			if (stripe < rbio->nr_data) {
 				page = page_in_rbio(rbio, stripe, pagenr, 1);
 				if (!page)
@@ -1284,15 +1300,20 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
 		}
 	}
 
-	if (likely(!bbio->num_tgtdevs))
+	if (likely(!bioc->num_tgtdevs))
 		goto write_data;
 
 	for (stripe = 0; stripe < rbio->real_stripes; stripe++) {
-		if (!bbio->tgtdev_map[stripe])
+		if (!bioc->tgtdev_map[stripe])
 			continue;
 
 		for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
 			struct page *page;
+
+			/* This vertical stripe has no data, skip it. */
+			if (!test_bit(pagenr, rbio->dbitmap))
+				continue;
+
 			if (stripe < rbio->nr_data) {
 				page = page_in_rbio(rbio, stripe, pagenr, 1);
 				if (!page)
@@ -1302,7 +1323,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
 			}
 
 			ret = rbio_add_io_page(rbio, &bio_list, page,
-					       rbio->bbio->tgtdev_map[stripe],
+					       rbio->bioc->tgtdev_map[stripe],
 					       pagenr, rbio->stripe_len);
 			if (ret)
 				goto cleanup;
@@ -1339,12 +1360,12 @@ static int find_bio_stripe(struct btrfs_raid_bio *rbio,
 {
 	u64 physical = bio->bi_iter.bi_sector;
 	int i;
-	struct btrfs_bio_stripe *stripe;
+	struct btrfs_io_stripe *stripe;
 
 	physical <<= 9;
 
-	for (i = 0; i < rbio->bbio->num_stripes; i++) {
-		stripe = &rbio->bbio->stripes[i];
+	for (i = 0; i < rbio->bioc->num_stripes; i++) {
+		stripe = &rbio->bioc->stripes[i];
 		if (in_range(physical, stripe->physical, rbio->stripe_len) &&
 		    stripe->dev->bdev && bio->bi_bdev == stripe->dev->bdev) {
 			return i;
@@ -1365,7 +1386,7 @@ static int find_logical_bio_stripe(struct btrfs_raid_bio *rbio,
 	int i;
 
 	for (i = 0; i < rbio->nr_data; i++) {
-		u64 stripe_start = rbio->bbio->raid_map[i];
+		u64 stripe_start = rbio->bioc->raid_map[i];
 
 		if (in_range(logical, stripe_start, rbio->stripe_len))
 			return i;
@@ -1456,7 +1477,7 @@ static void raid_rmw_end_io(struct bio *bio)
 	if (!atomic_dec_and_test(&rbio->stripes_pending))
 		return;
 
-	if (atomic_read(&rbio->error) > rbio->bbio->max_errors)
+	if (atomic_read(&rbio->error) > rbio->bioc->max_errors)
 		goto cleanup;
 
 	/*
@@ -1538,8 +1559,8 @@ static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio)
 	}
 
 	/*
-	 * the bbio may be freed once we submit the last bio.  Make sure
-	 * not to touch it after that
+	 * The bioc may be freed once we submit the last bio. Make sure not to
+	 * touch it after that.
 	 */
 	atomic_set(&rbio->stripes_pending, bios_to_read);
 	while ((bio = bio_list_pop(&bio_list))) {
@@ -1716,25 +1737,51 @@ static void btrfs_raid_unplug(struct blk_plug_cb *cb, bool from_schedule)
 	run_plug(plug);
 }
 
+/* Add the original bio into rbio->bio_list, and update rbio::dbitmap. */
+static void rbio_add_bio(struct btrfs_raid_bio *rbio, struct bio *orig_bio)
+{
+	const struct btrfs_fs_info *fs_info = rbio->fs_info;
+	const u64 orig_logical = orig_bio->bi_iter.bi_sector << SECTOR_SHIFT;
+	const u64 full_stripe_start = rbio->bioc->raid_map[0];
+	const u32 orig_len = orig_bio->bi_iter.bi_size;
+	const u32 sectorsize = fs_info->sectorsize;
+	u64 cur_logical;
+
+	ASSERT(orig_logical >= full_stripe_start &&
+	       orig_logical + orig_len <= full_stripe_start +
+	       rbio->nr_data * rbio->stripe_len);
+
+	bio_list_add(&rbio->bio_list, orig_bio);
+	rbio->bio_list_bytes += orig_bio->bi_iter.bi_size;
+
+	/* Update the dbitmap. */
+	for (cur_logical = orig_logical; cur_logical < orig_logical + orig_len;
+	     cur_logical += sectorsize) {
+		int bit = ((u32)(cur_logical - full_stripe_start) >>
+			   fs_info->sectorsize_bits) % rbio->stripe_npages;
+
+		set_bit(bit, rbio->dbitmap);
+	}
+}
+
 /*
  * our main entry point for writes from the rest of the FS.
  */
 int raid56_parity_write(struct btrfs_fs_info *fs_info, struct bio *bio,
-			struct btrfs_bio *bbio, u64 stripe_len)
+			struct btrfs_io_context *bioc, u64 stripe_len)
 {
 	struct btrfs_raid_bio *rbio;
 	struct btrfs_plug_cb *plug = NULL;
 	struct blk_plug_cb *cb;
 	int ret;
 
-	rbio = alloc_rbio(fs_info, bbio, stripe_len);
+	rbio = alloc_rbio(fs_info, bioc, stripe_len);
 	if (IS_ERR(rbio)) {
-		btrfs_put_bbio(bbio);
+		btrfs_put_bioc(bioc);
 		return PTR_ERR(rbio);
 	}
-	bio_list_add(&rbio->bio_list, bio);
-	rbio->bio_list_bytes = bio->bi_iter.bi_size;
 	rbio->operation = BTRFS_RBIO_WRITE;
+	rbio_add_bio(rbio, bio);
 
 	btrfs_bio_counter_inc_noblocked(fs_info);
 	rbio->generic_bio_cnt = 1;
@@ -1842,7 +1889,7 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
 		}
 
 		/* all raid6 handling here */
-		if (rbio->bbio->map_type & BTRFS_BLOCK_GROUP_RAID6) {
+		if (rbio->bioc->map_type & BTRFS_BLOCK_GROUP_RAID6) {
 			/*
 			 * single failure, rebuild from parity raid5
 			 * style
@@ -1874,8 +1921,8 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
 			 * here due to a crc mismatch and we can't give them the
 			 * data they want
 			 */
-			if (rbio->bbio->raid_map[failb] == RAID6_Q_STRIPE) {
-				if (rbio->bbio->raid_map[faila] ==
+			if (rbio->bioc->raid_map[failb] == RAID6_Q_STRIPE) {
+				if (rbio->bioc->raid_map[faila] ==
 				    RAID5_P_STRIPE) {
 					err = BLK_STS_IOERR;
 					goto cleanup;
@@ -1887,7 +1934,7 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
 				goto pstripe;
 			}
 
-			if (rbio->bbio->raid_map[failb] == RAID5_P_STRIPE) {
+			if (rbio->bioc->raid_map[failb] == RAID5_P_STRIPE) {
 				raid6_datap_recov(rbio->real_stripes,
 						  PAGE_SIZE, faila, pointers);
 			} else {
@@ -2006,7 +2053,7 @@ static void raid_recover_end_io(struct bio *bio)
 	if (!atomic_dec_and_test(&rbio->stripes_pending))
 		return;
 
-	if (atomic_read(&rbio->error) > rbio->bbio->max_errors)
+	if (atomic_read(&rbio->error) > rbio->bioc->max_errors)
 		rbio_orig_end_io(rbio, BLK_STS_IOERR);
 	else
 		__raid_recover_end_io(rbio);
@@ -2038,9 +2085,12 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
 	atomic_set(&rbio->error, 0);
 
 	/*
-	 * read everything that hasn't failed.  Thanks to the
-	 * stripe cache, it is possible that some or all of these
-	 * pages are going to be uptodate.
+	 * Read everything that hasn't failed. However this time we will
+	 * not trust any cached sector.
+	 * As we may read out some stale data but higher layer is not reading
+	 * that stale part.
+	 *
+	 * So here we always re-read everything in recovery path.
 	 */
 	for (stripe = 0; stripe < rbio->real_stripes; stripe++) {
 		if (rbio->faila == stripe || rbio->failb == stripe) {
@@ -2049,16 +2099,6 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
 		}
 
 		for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
-			struct page *p;
-
-			/*
-			 * the rmw code may have already read this
-			 * page in
-			 */
-			p = rbio_stripe_page(rbio, stripe, pagenr);
-			if (PageUptodate(p))
-				continue;
-
 			ret = rbio_add_io_page(rbio, &bio_list,
 				       rbio_stripe_page(rbio, stripe, pagenr),
 				       stripe, pagenr, rbio->stripe_len);
@@ -2074,7 +2114,7 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
 		 * were up to date, or we might have no bios to read because
 		 * the devices were gone.
 		 */
-		if (atomic_read(&rbio->error) <= rbio->bbio->max_errors) {
+		if (atomic_read(&rbio->error) <= rbio->bioc->max_errors) {
 			__raid_recover_end_io(rbio);
 			return 0;
 		} else {
@@ -2083,8 +2123,8 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
 	}
 
 	/*
-	 * the bbio may be freed once we submit the last bio.  Make sure
-	 * not to touch it after that
+	 * The bioc may be freed once we submit the last bio. Make sure not to
+	 * touch it after that.
 	 */
 	atomic_set(&rbio->stripes_pending, bios_to_read);
 	while ((bio = bio_list_pop(&bio_list))) {
@@ -2117,36 +2157,35 @@ cleanup:
  * of the drive.
  */
 int raid56_parity_recover(struct btrfs_fs_info *fs_info, struct bio *bio,
-			  struct btrfs_bio *bbio, u64 stripe_len,
+			  struct btrfs_io_context *bioc, u64 stripe_len,
 			  int mirror_num, int generic_io)
 {
 	struct btrfs_raid_bio *rbio;
 	int ret;
 
 	if (generic_io) {
-		ASSERT(bbio->mirror_num == mirror_num);
+		ASSERT(bioc->mirror_num == mirror_num);
 		btrfs_io_bio(bio)->mirror_num = mirror_num;
 	}
 
-	rbio = alloc_rbio(fs_info, bbio, stripe_len);
+	rbio = alloc_rbio(fs_info, bioc, stripe_len);
 	if (IS_ERR(rbio)) {
 		if (generic_io)
-			btrfs_put_bbio(bbio);
+			btrfs_put_bioc(bioc);
 		return PTR_ERR(rbio);
 	}
 
 	rbio->operation = BTRFS_RBIO_READ_REBUILD;
-	bio_list_add(&rbio->bio_list, bio);
-	rbio->bio_list_bytes = bio->bi_iter.bi_size;
+	rbio_add_bio(rbio, bio);
 
 	rbio->faila = find_logical_bio_stripe(rbio, bio);
 	if (rbio->faila == -1) {
 		btrfs_warn(fs_info,
-	"%s could not find the bad stripe in raid56 so that we cannot recover any more (bio has logical %llu len %llu, bbio has map_type %llu)",
+"%s could not find the bad stripe in raid56 so that we cannot recover any more (bio has logical %llu len %llu, bioc has map_type %llu)",
 			   __func__, bio->bi_iter.bi_sector << 9,
-			   (u64)bio->bi_iter.bi_size, bbio->map_type);
+			   (u64)bio->bi_iter.bi_size, bioc->map_type);
 		if (generic_io)
-			btrfs_put_bbio(bbio);
+			btrfs_put_bioc(bioc);
 		kfree(rbio);
 		return -EIO;
 	}
@@ -2155,7 +2194,7 @@ int raid56_parity_recover(struct btrfs_fs_info *fs_info, struct bio *bio,
 		btrfs_bio_counter_inc_noblocked(fs_info);
 		rbio->generic_bio_cnt = 1;
 	} else {
-		btrfs_get_bbio(bbio);
+		btrfs_get_bioc(bioc);
 	}
 
 	/*
@@ -2214,7 +2253,7 @@ static void read_rebuild_work(struct btrfs_work *work)
 /*
  * The following code is used to scrub/replace the parity stripe
  *
- * Caller must have already increased bio_counter for getting @bbio.
+ * Caller must have already increased bio_counter for getting @bioc.
  *
  * Note: We need make sure all the pages that add into the scrub/replace
  * raid bio are correct and not be changed during the scrub/replace. That
@@ -2223,14 +2262,14 @@ static void read_rebuild_work(struct btrfs_work *work)
 
 struct btrfs_raid_bio *
 raid56_parity_alloc_scrub_rbio(struct btrfs_fs_info *fs_info, struct bio *bio,
-			       struct btrfs_bio *bbio, u64 stripe_len,
+			       struct btrfs_io_context *bioc, u64 stripe_len,
 			       struct btrfs_device *scrub_dev,
 			       unsigned long *dbitmap, int stripe_nsectors)
 {
 	struct btrfs_raid_bio *rbio;
 	int i;
 
-	rbio = alloc_rbio(fs_info, bbio, stripe_len);
+	rbio = alloc_rbio(fs_info, bioc, stripe_len);
 	if (IS_ERR(rbio))
 		return NULL;
 	bio_list_add(&rbio->bio_list, bio);
@@ -2242,12 +2281,12 @@ raid56_parity_alloc_scrub_rbio(struct btrfs_fs_info *fs_info, struct bio *bio,
 	rbio->operation = BTRFS_RBIO_PARITY_SCRUB;
 
 	/*
-	 * After mapping bbio with BTRFS_MAP_WRITE, parities have been sorted
+	 * After mapping bioc with BTRFS_MAP_WRITE, parities have been sorted
 	 * to the end position, so this search can start from the first parity
 	 * stripe.
 	 */
 	for (i = rbio->nr_data; i < rbio->real_stripes; i++) {
-		if (bbio->stripes[i].dev == scrub_dev) {
+		if (bioc->stripes[i].dev == scrub_dev) {
 			rbio->scrubp = i;
 			break;
 		}
@@ -2260,7 +2299,7 @@ raid56_parity_alloc_scrub_rbio(struct btrfs_fs_info *fs_info, struct bio *bio,
 	bitmap_copy(rbio->dbitmap, dbitmap, stripe_nsectors);
 
 	/*
-	 * We have already increased bio_counter when getting bbio, record it
+	 * We have already increased bio_counter when getting bioc, record it
 	 * so we can free it at rbio_orig_end_io().
 	 */
 	rbio->generic_bio_cnt = 1;
@@ -2275,10 +2314,10 @@ void raid56_add_scrub_pages(struct btrfs_raid_bio *rbio, struct page *page,
 	int stripe_offset;
 	int index;
 
-	ASSERT(logical >= rbio->bbio->raid_map[0]);
-	ASSERT(logical + PAGE_SIZE <= rbio->bbio->raid_map[0] +
+	ASSERT(logical >= rbio->bioc->raid_map[0]);
+	ASSERT(logical + PAGE_SIZE <= rbio->bioc->raid_map[0] +
 				rbio->stripe_len * rbio->nr_data);
-	stripe_offset = (int)(logical - rbio->bbio->raid_map[0]);
+	stripe_offset = (int)(logical - rbio->bioc->raid_map[0]);
 	index = stripe_offset >> PAGE_SHIFT;
 	rbio->bio_pages[index] = page;
 }
@@ -2312,7 +2351,7 @@ static int alloc_rbio_essential_pages(struct btrfs_raid_bio *rbio)
 static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
 					 int need_check)
 {
-	struct btrfs_bio *bbio = rbio->bbio;
+	struct btrfs_io_context *bioc = rbio->bioc;
 	void **pointers = rbio->finish_pointers;
 	unsigned long *pbitmap = rbio->finish_pbitmap;
 	int nr_data = rbio->nr_data;
@@ -2335,7 +2374,7 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
 	else
 		BUG();
 
-	if (bbio->num_tgtdevs && bbio->tgtdev_map[rbio->scrubp]) {
+	if (bioc->num_tgtdevs && bioc->tgtdev_map[rbio->scrubp]) {
 		is_replace = 1;
 		bitmap_copy(pbitmap, rbio->dbitmap, rbio->stripe_npages);
 	}
@@ -2435,7 +2474,7 @@ writeback:
 
 		page = rbio_stripe_page(rbio, rbio->scrubp, pagenr);
 		ret = rbio_add_io_page(rbio, &bio_list, page,
-				       bbio->tgtdev_map[rbio->scrubp],
+				       bioc->tgtdev_map[rbio->scrubp],
 				       pagenr, rbio->stripe_len);
 		if (ret)
 			goto cleanup;
@@ -2483,7 +2522,7 @@ static inline int is_data_stripe(struct btrfs_raid_bio *rbio, int stripe)
  */
 static void validate_rbio_for_parity_scrub(struct btrfs_raid_bio *rbio)
 {
-	if (atomic_read(&rbio->error) > rbio->bbio->max_errors)
+	if (atomic_read(&rbio->error) > rbio->bioc->max_errors)
 		goto cleanup;
 
 	if (rbio->faila >= 0 || rbio->failb >= 0) {
@@ -2504,7 +2543,7 @@ static void validate_rbio_for_parity_scrub(struct btrfs_raid_bio *rbio)
 		 * the data, so the capability of the repair is declined.
 		 * (In the case of RAID5, we can not repair anything)
 		 */
-		if (dfail > rbio->bbio->max_errors - 1)
+		if (dfail > rbio->bioc->max_errors - 1)
 			goto cleanup;
 
 		/*
@@ -2625,8 +2664,8 @@ static void raid56_parity_scrub_stripe(struct btrfs_raid_bio *rbio)
 	}
 
 	/*
-	 * the bbio may be freed once we submit the last bio.  Make sure
-	 * not to touch it after that
+	 * The bioc may be freed once we submit the last bio. Make sure not to
+	 * touch it after that.
 	 */
 	atomic_set(&rbio->stripes_pending, bios_to_read);
 	while ((bio = bio_list_pop(&bio_list))) {
@@ -2671,11 +2710,11 @@ void raid56_parity_submit_scrub_rbio(struct btrfs_raid_bio *rbio)
 
 struct btrfs_raid_bio *
 raid56_alloc_missing_rbio(struct btrfs_fs_info *fs_info, struct bio *bio,
-			  struct btrfs_bio *bbio, u64 length)
+			  struct btrfs_io_context *bioc, u64 length)
 {
 	struct btrfs_raid_bio *rbio;
 
-	rbio = alloc_rbio(fs_info, bbio, length);
+	rbio = alloc_rbio(fs_info, bioc, length);
 	if (IS_ERR(rbio))
 		return NULL;
 
@@ -2695,7 +2734,7 @@ raid56_alloc_missing_rbio(struct btrfs_fs_info *fs_info, struct bio *bio,
 	}
 
 	/*
-	 * When we get bbio, we have already increased bio_counter, record it
+	 * When we get bioc, we have already increased bio_counter, record it
 	 * so we can free it at rbio_orig_end_io()
 	 */
 	rbio->generic_bio_cnt = 1;
diff --git a/fs/btrfs/raid56.h b/fs/btrfs/raid56.h
index 2503485db859..838d3a5e07ef 100644
--- a/fs/btrfs/raid56.h
+++ b/fs/btrfs/raid56.h
@@ -31,24 +31,24 @@ struct btrfs_raid_bio;
 struct btrfs_device;
 
 int raid56_parity_recover(struct btrfs_fs_info *fs_info, struct bio *bio,
-			  struct btrfs_bio *bbio, u64 stripe_len,
+			  struct btrfs_io_context *bioc, u64 stripe_len,
 			  int mirror_num, int generic_io);
 int raid56_parity_write(struct btrfs_fs_info *fs_info, struct bio *bio,
-			       struct btrfs_bio *bbio, u64 stripe_len);
+			struct btrfs_io_context *bioc, u64 stripe_len);
 
 void raid56_add_scrub_pages(struct btrfs_raid_bio *rbio, struct page *page,
 			    u64 logical);
 
 struct btrfs_raid_bio *
 raid56_parity_alloc_scrub_rbio(struct btrfs_fs_info *fs_info, struct bio *bio,
-			       struct btrfs_bio *bbio, u64 stripe_len,
+			       struct btrfs_io_context *bioc, u64 stripe_len,
 			       struct btrfs_device *scrub_dev,
 			       unsigned long *dbitmap, int stripe_nsectors);
 void raid56_parity_submit_scrub_rbio(struct btrfs_raid_bio *rbio);
 
 struct btrfs_raid_bio *
 raid56_alloc_missing_rbio(struct btrfs_fs_info *fs_info, struct bio *bio,
-			  struct btrfs_bio *bbio, u64 length);
+			  struct btrfs_io_context *bioc, u64 length);
 void raid56_submit_missing_rbio(struct btrfs_raid_bio *rbio);
 
 int btrfs_alloc_stripe_hash_table(struct btrfs_fs_info *info);
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 06713a8fe26b..eb96fdc3be25 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -227,7 +227,7 @@ start_machine:
 }
 
 static struct reada_zone *reada_find_zone(struct btrfs_device *dev, u64 logical,
-					  struct btrfs_bio *bbio)
+					  struct btrfs_io_context *bioc)
 {
 	struct btrfs_fs_info *fs_info = dev->fs_info;
 	int ret;
@@ -275,11 +275,11 @@ static struct reada_zone *reada_find_zone(struct btrfs_device *dev, u64 logical,
 	kref_init(&zone->refcnt);
 	zone->elems = 0;
 	zone->device = dev; /* our device always sits at index 0 */
-	for (i = 0; i < bbio->num_stripes; ++i) {
+	for (i = 0; i < bioc->num_stripes; ++i) {
 		/* bounds have already been checked */
-		zone->devs[i] = bbio->stripes[i].dev;
+		zone->devs[i] = bioc->stripes[i].dev;
 	}
-	zone->ndevs = bbio->num_stripes;
+	zone->ndevs = bioc->num_stripes;
 
 	spin_lock(&fs_info->reada_lock);
 	ret = radix_tree_insert(&dev->reada_zones,
@@ -309,7 +309,7 @@ static struct reada_extent *reada_find_extent(struct btrfs_fs_info *fs_info,
 	int ret;
 	struct reada_extent *re = NULL;
 	struct reada_extent *re_exist = NULL;
-	struct btrfs_bio *bbio = NULL;
+	struct btrfs_io_context *bioc = NULL;
 	struct btrfs_device *dev;
 	struct btrfs_device *prev_dev;
 	u64 length;
@@ -345,28 +345,28 @@ static struct reada_extent *reada_find_extent(struct btrfs_fs_info *fs_info,
 	 */
 	length = fs_info->nodesize;
 	ret = btrfs_map_block(fs_info, BTRFS_MAP_GET_READ_MIRRORS, logical,
-			&length, &bbio, 0);
-	if (ret || !bbio || length < fs_info->nodesize)
+			      &length, &bioc, 0);
+	if (ret || !bioc || length < fs_info->nodesize)
 		goto error;
 
-	if (bbio->num_stripes > BTRFS_MAX_MIRRORS) {
+	if (bioc->num_stripes > BTRFS_MAX_MIRRORS) {
 		btrfs_err(fs_info,
 			   "readahead: more than %d copies not supported",
 			   BTRFS_MAX_MIRRORS);
 		goto error;
 	}
 
-	real_stripes = bbio->num_stripes - bbio->num_tgtdevs;
+	real_stripes = bioc->num_stripes - bioc->num_tgtdevs;
 	for (nzones = 0; nzones < real_stripes; ++nzones) {
 		struct reada_zone *zone;
 
-		dev = bbio->stripes[nzones].dev;
+		dev = bioc->stripes[nzones].dev;
 
 		/* cannot read ahead on missing device. */
 		if (!dev->bdev)
 			continue;
 
-		zone = reada_find_zone(dev, logical, bbio);
+		zone = reada_find_zone(dev, logical, bioc);
 		if (!zone)
 			continue;
 
@@ -464,7 +464,7 @@ static struct reada_extent *reada_find_extent(struct btrfs_fs_info *fs_info,
 	if (!have_zone)
 		goto error;
 
-	btrfs_put_bbio(bbio);
+	btrfs_put_bioc(bioc);
 	return re;
 
 error:
@@ -488,7 +488,7 @@ error:
 		kref_put(&zone->refcnt, reada_zone_release);
 		spin_unlock(&fs_info->reada_lock);
 	}
-	btrfs_put_bbio(bbio);
+	btrfs_put_bioc(bioc);
 	kfree(re);
 	return re_exist;
 }
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index a6661f2ad2c0..becf3396d533 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -1147,7 +1147,8 @@ int replace_file_extents(struct btrfs_trans_handle *trans,
 				       num_bytes, parent);
 		ref.real_root = root->root_key.objectid;
 		btrfs_init_data_ref(&ref, btrfs_header_owner(leaf),
-				    key.objectid, key.offset);
+				    key.objectid, key.offset,
+				    root->root_key.objectid, false);
 		ret = btrfs_inc_extent_ref(trans, &ref);
 		if (ret) {
 			btrfs_abort_transaction(trans, ret);
@@ -1158,7 +1159,8 @@ int replace_file_extents(struct btrfs_trans_handle *trans,
 				       num_bytes, parent);
 		ref.real_root = root->root_key.objectid;
 		btrfs_init_data_ref(&ref, btrfs_header_owner(leaf),
-				    key.objectid, key.offset);
+				    key.objectid, key.offset,
+				    root->root_key.objectid, false);
 		ret = btrfs_free_extent(trans, &ref);
 		if (ret) {
 			btrfs_abort_transaction(trans, ret);
@@ -1324,7 +1326,9 @@ again:
 		btrfs_release_path(path);
 
 		path->lowest_level = level;
+		set_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &src->state);
 		ret = btrfs_search_slot(trans, src, &key, path, 0, 1);
+		clear_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &src->state);
 		path->lowest_level = 0;
 		if (ret) {
 			if (ret > 0)
@@ -1368,7 +1372,8 @@ again:
 		btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, old_bytenr,
 				       blocksize, path->nodes[level]->start);
 		ref.skip_qgroup = true;
-		btrfs_init_tree_ref(&ref, level - 1, src->root_key.objectid);
+		btrfs_init_tree_ref(&ref, level - 1, src->root_key.objectid,
+				    0, true);
 		ret = btrfs_inc_extent_ref(trans, &ref);
 		if (ret) {
 			btrfs_abort_transaction(trans, ret);
@@ -1377,7 +1382,8 @@ again:
 		btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, new_bytenr,
 				       blocksize, 0);
 		ref.skip_qgroup = true;
-		btrfs_init_tree_ref(&ref, level - 1, dest->root_key.objectid);
+		btrfs_init_tree_ref(&ref, level - 1, dest->root_key.objectid, 0,
+				    true);
 		ret = btrfs_inc_extent_ref(trans, &ref);
 		if (ret) {
 			btrfs_abort_transaction(trans, ret);
@@ -1386,7 +1392,8 @@ again:
 
 		btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, new_bytenr,
 				       blocksize, path->nodes[level]->start);
-		btrfs_init_tree_ref(&ref, level - 1, src->root_key.objectid);
+		btrfs_init_tree_ref(&ref, level - 1, src->root_key.objectid,
+				    0, true);
 		ref.skip_qgroup = true;
 		ret = btrfs_free_extent(trans, &ref);
 		if (ret) {
@@ -1396,7 +1403,8 @@ again:
 
 		btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, old_bytenr,
 				       blocksize, 0);
-		btrfs_init_tree_ref(&ref, level - 1, dest->root_key.objectid);
+		btrfs_init_tree_ref(&ref, level - 1, dest->root_key.objectid,
+				    0, true);
 		ref.skip_qgroup = true;
 		ret = btrfs_free_extent(trans, &ref);
 		if (ret) {
@@ -2475,7 +2483,8 @@ static int do_relocation(struct btrfs_trans_handle *trans,
 					       upper->eb->start);
 			ref.real_root = root->root_key.objectid;
 			btrfs_init_tree_ref(&ref, node->level,
-					    btrfs_header_owner(upper->eb));
+					    btrfs_header_owner(upper->eb),
+					    root->root_key.objectid, false);
 			ret = btrfs_inc_extent_ref(trans, &ref);
 			if (!ret)
 				ret = btrfs_drop_subtree(trans, root, eb,
@@ -2691,8 +2700,12 @@ static int relocate_tree_block(struct btrfs_trans_handle *trans,
 			list_add_tail(&node->list, &rc->backref_cache.changed);
 		} else {
 			path->lowest_level = node->level;
+			if (root == root->fs_info->chunk_root)
+				btrfs_reserve_chunk_metadata(trans, false);
 			ret = btrfs_search_slot(trans, root, key, path, 0, 1);
 			btrfs_release_path(path);
+			if (root == root->fs_info->chunk_root)
+				btrfs_trans_release_chunk_metadata(trans);
 			if (ret > 0)
 				ret = 0;
 		}
@@ -3565,7 +3578,12 @@ int prepare_to_relocate(struct reloc_control *rc)
 		 */
 		return PTR_ERR(trans);
 	}
-	return btrfs_commit_transaction(trans);
+
+	ret = btrfs_commit_transaction(trans);
+	if (ret)
+		unset_reloc_control(rc);
+
+	return ret;
 }
 
 static noinline_for_stack int relocate_block_group(struct reloc_control *rc)
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 1fa0e5e2e350..9328d87d9688 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -351,9 +351,10 @@ int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id,
 	key.offset = ref_id;
 again:
 	ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1);
-	if (ret < 0)
+	if (ret < 0) {
+		err = ret;
 		goto out;
-	if (ret == 0) {
+	} else if (ret == 0) {
 		leaf = path->nodes[0];
 		ref = btrfs_item_ptr(leaf, path->slots[0],
 				     struct btrfs_root_ref);
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 62f4bafbe54b..0785d9d645fc 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -57,7 +57,7 @@ struct scrub_ctx;
 
 struct scrub_recover {
 	refcount_t		refs;
-	struct btrfs_bio	*bbio;
+	struct btrfs_io_context	*bioc;
 	u64			map_length;
 };
 
@@ -254,7 +254,7 @@ static void scrub_put_ctx(struct scrub_ctx *sctx);
 static inline int scrub_is_page_on_raid56(struct scrub_page *spage)
 {
 	return spage->recover &&
-	       (spage->recover->bbio->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK);
+	       (spage->recover->bioc->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK);
 }
 
 static void scrub_pending_bio_inc(struct scrub_ctx *sctx)
@@ -798,7 +798,7 @@ static inline void scrub_put_recover(struct btrfs_fs_info *fs_info,
 {
 	if (refcount_dec_and_test(&recover->refs)) {
 		btrfs_bio_counter_dec(fs_info);
-		btrfs_put_bbio(recover->bbio);
+		btrfs_put_bioc(recover->bioc);
 		kfree(recover);
 	}
 }
@@ -1027,8 +1027,7 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check)
 			sblock_other = sblocks_for_recheck + mirror_index;
 		} else {
 			struct scrub_recover *r = sblock_bad->pagev[0]->recover;
-			int max_allowed = r->bbio->num_stripes -
-						r->bbio->num_tgtdevs;
+			int max_allowed = r->bioc->num_stripes - r->bioc->num_tgtdevs;
 
 			if (mirror_index >= max_allowed)
 				break;
@@ -1218,14 +1217,14 @@ out:
 	return 0;
 }
 
-static inline int scrub_nr_raid_mirrors(struct btrfs_bio *bbio)
+static inline int scrub_nr_raid_mirrors(struct btrfs_io_context *bioc)
 {
-	if (bbio->map_type & BTRFS_BLOCK_GROUP_RAID5)
+	if (bioc->map_type & BTRFS_BLOCK_GROUP_RAID5)
 		return 2;
-	else if (bbio->map_type & BTRFS_BLOCK_GROUP_RAID6)
+	else if (bioc->map_type & BTRFS_BLOCK_GROUP_RAID6)
 		return 3;
 	else
-		return (int)bbio->num_stripes;
+		return (int)bioc->num_stripes;
 }
 
 static inline void scrub_stripe_index_and_offset(u64 logical, u64 map_type,
@@ -1269,7 +1268,7 @@ static int scrub_setup_recheck_block(struct scrub_block *original_sblock,
 	u64 flags = original_sblock->pagev[0]->flags;
 	u64 have_csum = original_sblock->pagev[0]->have_csum;
 	struct scrub_recover *recover;
-	struct btrfs_bio *bbio;
+	struct btrfs_io_context *bioc;
 	u64 sublen;
 	u64 mapped_length;
 	u64 stripe_offset;
@@ -1288,7 +1287,7 @@ static int scrub_setup_recheck_block(struct scrub_block *original_sblock,
 	while (length > 0) {
 		sublen = min_t(u64, length, fs_info->sectorsize);
 		mapped_length = sublen;
-		bbio = NULL;
+		bioc = NULL;
 
 		/*
 		 * With a length of sectorsize, each returned stripe represents
@@ -1296,27 +1295,27 @@ static int scrub_setup_recheck_block(struct scrub_block *original_sblock,
 		 */
 		btrfs_bio_counter_inc_blocked(fs_info);
 		ret = btrfs_map_sblock(fs_info, BTRFS_MAP_GET_READ_MIRRORS,
-				logical, &mapped_length, &bbio);
-		if (ret || !bbio || mapped_length < sublen) {
-			btrfs_put_bbio(bbio);
+				       logical, &mapped_length, &bioc);
+		if (ret || !bioc || mapped_length < sublen) {
+			btrfs_put_bioc(bioc);
 			btrfs_bio_counter_dec(fs_info);
 			return -EIO;
 		}
 
 		recover = kzalloc(sizeof(struct scrub_recover), GFP_NOFS);
 		if (!recover) {
-			btrfs_put_bbio(bbio);
+			btrfs_put_bioc(bioc);
 			btrfs_bio_counter_dec(fs_info);
 			return -ENOMEM;
 		}
 
 		refcount_set(&recover->refs, 1);
-		recover->bbio = bbio;
+		recover->bioc = bioc;
 		recover->map_length = mapped_length;
 
 		BUG_ON(page_index >= SCRUB_MAX_PAGES_PER_BLOCK);
 
-		nmirrors = min(scrub_nr_raid_mirrors(bbio), BTRFS_MAX_MIRRORS);
+		nmirrors = min(scrub_nr_raid_mirrors(bioc), BTRFS_MAX_MIRRORS);
 
 		for (mirror_index = 0; mirror_index < nmirrors;
 		     mirror_index++) {
@@ -1348,17 +1347,17 @@ leave_nomem:
 				       sctx->fs_info->csum_size);
 
 			scrub_stripe_index_and_offset(logical,
-						      bbio->map_type,
-						      bbio->raid_map,
+						      bioc->map_type,
+						      bioc->raid_map,
 						      mapped_length,
-						      bbio->num_stripes -
-						      bbio->num_tgtdevs,
+						      bioc->num_stripes -
+						      bioc->num_tgtdevs,
 						      mirror_index,
 						      &stripe_index,
 						      &stripe_offset);
-			spage->physical = bbio->stripes[stripe_index].physical +
+			spage->physical = bioc->stripes[stripe_index].physical +
 					 stripe_offset;
-			spage->dev = bbio->stripes[stripe_index].dev;
+			spage->dev = bioc->stripes[stripe_index].dev;
 
 			BUG_ON(page_index >= original_sblock->page_count);
 			spage->physical_for_dev_replace =
@@ -1401,7 +1400,7 @@ static int scrub_submit_raid56_bio_wait(struct btrfs_fs_info *fs_info,
 	bio->bi_end_io = scrub_bio_wait_endio;
 
 	mirror_num = spage->sblock->pagev[0]->mirror_num;
-	ret = raid56_parity_recover(fs_info, bio, spage->recover->bbio,
+	ret = raid56_parity_recover(fs_info, bio, spage->recover->bioc,
 				    spage->recover->map_length,
 				    mirror_num, 0);
 	if (ret)
@@ -2203,7 +2202,7 @@ static void scrub_missing_raid56_pages(struct scrub_block *sblock)
 	struct btrfs_fs_info *fs_info = sctx->fs_info;
 	u64 length = sblock->page_count * PAGE_SIZE;
 	u64 logical = sblock->pagev[0]->logical;
-	struct btrfs_bio *bbio = NULL;
+	struct btrfs_io_context *bioc = NULL;
 	struct bio *bio;
 	struct btrfs_raid_bio *rbio;
 	int ret;
@@ -2211,19 +2210,19 @@ static void scrub_missing_raid56_pages(struct scrub_block *sblock)
 
 	btrfs_bio_counter_inc_blocked(fs_info);
 	ret = btrfs_map_sblock(fs_info, BTRFS_MAP_GET_READ_MIRRORS, logical,
-			&length, &bbio);
-	if (ret || !bbio || !bbio->raid_map)
-		goto bbio_out;
+			       &length, &bioc);
+	if (ret || !bioc || !bioc->raid_map)
+		goto bioc_out;
 
 	if (WARN_ON(!sctx->is_dev_replace ||
-		    !(bbio->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK))) {
+		    !(bioc->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK))) {
 		/*
 		 * We shouldn't be scrubbing a missing device. Even for dev
 		 * replace, we should only get here for RAID 5/6. We either
 		 * managed to mount something with no mirrors remaining or
 		 * there's a bug in scrub_remap_extent()/btrfs_map_block().
 		 */
-		goto bbio_out;
+		goto bioc_out;
 	}
 
 	bio = btrfs_io_bio_alloc(0);
@@ -2231,7 +2230,7 @@ static void scrub_missing_raid56_pages(struct scrub_block *sblock)
 	bio->bi_private = sblock;
 	bio->bi_end_io = scrub_missing_raid56_end_io;
 
-	rbio = raid56_alloc_missing_rbio(fs_info, bio, bbio, length);
+	rbio = raid56_alloc_missing_rbio(fs_info, bio, bioc, length);
 	if (!rbio)
 		goto rbio_out;
 
@@ -2249,9 +2248,9 @@ static void scrub_missing_raid56_pages(struct scrub_block *sblock)
 
 rbio_out:
 	bio_put(bio);
-bbio_out:
+bioc_out:
 	btrfs_bio_counter_dec(fs_info);
-	btrfs_put_bbio(bbio);
+	btrfs_put_bioc(bioc);
 	spin_lock(&sctx->stat_lock);
 	sctx->stat.malloc_errors++;
 	spin_unlock(&sctx->stat_lock);
@@ -2826,7 +2825,7 @@ static void scrub_parity_check_and_repair(struct scrub_parity *sparity)
 	struct btrfs_fs_info *fs_info = sctx->fs_info;
 	struct bio *bio;
 	struct btrfs_raid_bio *rbio;
-	struct btrfs_bio *bbio = NULL;
+	struct btrfs_io_context *bioc = NULL;
 	u64 length;
 	int ret;
 
@@ -2838,16 +2837,16 @@ static void scrub_parity_check_and_repair(struct scrub_parity *sparity)
 
 	btrfs_bio_counter_inc_blocked(fs_info);
 	ret = btrfs_map_sblock(fs_info, BTRFS_MAP_WRITE, sparity->logic_start,
-			       &length, &bbio);
-	if (ret || !bbio || !bbio->raid_map)
-		goto bbio_out;
+			       &length, &bioc);
+	if (ret || !bioc || !bioc->raid_map)
+		goto bioc_out;
 
 	bio = btrfs_io_bio_alloc(0);
 	bio->bi_iter.bi_sector = sparity->logic_start >> 9;
 	bio->bi_private = sparity;
 	bio->bi_end_io = scrub_parity_bio_endio;
 
-	rbio = raid56_parity_alloc_scrub_rbio(fs_info, bio, bbio,
+	rbio = raid56_parity_alloc_scrub_rbio(fs_info, bio, bioc,
 					      length, sparity->scrub_dev,
 					      sparity->dbitmap,
 					      sparity->nsectors);
@@ -2860,9 +2859,9 @@ static void scrub_parity_check_and_repair(struct scrub_parity *sparity)
 
 rbio_out:
 	bio_put(bio);
-bbio_out:
+bioc_out:
 	btrfs_bio_counter_dec(fs_info);
-	btrfs_put_bbio(bbio);
+	btrfs_put_bioc(bioc);
 	bitmap_or(sparity->ebitmap, sparity->ebitmap, sparity->dbitmap,
 		  sparity->nsectors);
 	spin_lock(&sctx->stat_lock);
@@ -2901,7 +2900,7 @@ static noinline_for_stack int scrub_raid56_parity(struct scrub_ctx *sctx,
 	struct btrfs_root *root = fs_info->extent_root;
 	struct btrfs_root *csum_root = fs_info->csum_root;
 	struct btrfs_extent_item *extent;
-	struct btrfs_bio *bbio = NULL;
+	struct btrfs_io_context *bioc = NULL;
 	u64 flags;
 	int ret;
 	int slot;
@@ -3044,22 +3043,22 @@ again:
 						       extent_len);
 
 			mapped_length = extent_len;
-			bbio = NULL;
+			bioc = NULL;
 			ret = btrfs_map_block(fs_info, BTRFS_MAP_READ,
-					extent_logical, &mapped_length, &bbio,
+					extent_logical, &mapped_length, &bioc,
 					0);
 			if (!ret) {
-				if (!bbio || mapped_length < extent_len)
+				if (!bioc || mapped_length < extent_len)
 					ret = -EIO;
 			}
 			if (ret) {
-				btrfs_put_bbio(bbio);
+				btrfs_put_bioc(bioc);
 				goto out;
 			}
-			extent_physical = bbio->stripes[0].physical;
-			extent_mirror_num = bbio->mirror_num;
-			extent_dev = bbio->stripes[0].dev;
-			btrfs_put_bbio(bbio);
+			extent_physical = bioc->stripes[0].physical;
+			extent_mirror_num = bioc->mirror_num;
+			extent_dev = bioc->stripes[0].dev;
+			btrfs_put_bioc(bioc);
 
 			ret = btrfs_lookup_csums_range(csum_root,
 						extent_logical,
@@ -4068,6 +4067,7 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 		    u64 end, struct btrfs_scrub_progress *progress,
 		    int readonly, int is_dev_replace)
 {
+	struct btrfs_dev_lookup_args args = { .devid = devid };
 	struct scrub_ctx *sctx;
 	int ret;
 	struct btrfs_device *dev;
@@ -4115,7 +4115,7 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 		goto out_free_ctx;
 
 	mutex_lock(&fs_info->fs_devices->device_list_mutex);
-	dev = btrfs_find_device(fs_info->fs_devices, devid, NULL, NULL);
+	dev = btrfs_find_device(fs_info->fs_devices, &args);
 	if (!dev || (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state) &&
 		     !is_dev_replace)) {
 		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
@@ -4288,11 +4288,12 @@ int btrfs_scrub_cancel_dev(struct btrfs_device *dev)
 int btrfs_scrub_progress(struct btrfs_fs_info *fs_info, u64 devid,
 			 struct btrfs_scrub_progress *progress)
 {
+	struct btrfs_dev_lookup_args args = { .devid = devid };
 	struct btrfs_device *dev;
 	struct scrub_ctx *sctx = NULL;
 
 	mutex_lock(&fs_info->fs_devices->device_list_mutex);
-	dev = btrfs_find_device(fs_info->fs_devices, devid, NULL, NULL);
+	dev = btrfs_find_device(fs_info->fs_devices, &args);
 	if (dev)
 		sctx = dev->scrub_ctx;
 	if (sctx)
@@ -4309,20 +4310,20 @@ static void scrub_remap_extent(struct btrfs_fs_info *fs_info,
 			       int *extent_mirror_num)
 {
 	u64 mapped_length;
-	struct btrfs_bio *bbio = NULL;
+	struct btrfs_io_context *bioc = NULL;
 	int ret;
 
 	mapped_length = extent_len;
 	ret = btrfs_map_block(fs_info, BTRFS_MAP_READ, extent_logical,
-			      &mapped_length, &bbio, 0);
-	if (ret || !bbio || mapped_length < extent_len ||
-	    !bbio->stripes[0].dev->bdev) {
-		btrfs_put_bbio(bbio);
+			      &mapped_length, &bioc, 0);
+	if (ret || !bioc || mapped_length < extent_len ||
+	    !bioc->stripes[0].dev->bdev) {
+		btrfs_put_bioc(bioc);
 		return;
 	}
 
-	*extent_physical = bbio->stripes[0].physical;
-	*extent_mirror_num = bbio->mirror_num;
-	*extent_dev = bbio->stripes[0].dev;
-	btrfs_put_bbio(bbio);
+	*extent_physical = bioc->stripes[0].physical;
+	*extent_mirror_num = bioc->mirror_num;
+	*extent_dev = bioc->stripes[0].dev;
+	btrfs_put_bioc(bioc);
 }
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 51382d2be3d4..a84d2d489510 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -1216,7 +1216,8 @@ static void extent_err(const struct extent_buffer *eb, int slot,
 }
 
 static int check_extent_item(struct extent_buffer *leaf,
-			     struct btrfs_key *key, int slot)
+			     struct btrfs_key *key, int slot,
+			     struct btrfs_key *prev_key)
 {
 	struct btrfs_fs_info *fs_info = leaf->fs_info;
 	struct btrfs_extent_item *ei;
@@ -1436,6 +1437,26 @@ static int check_extent_item(struct extent_buffer *leaf,
 			   total_refs, inline_refs);
 		return -EUCLEAN;
 	}
+
+	if ((prev_key->type == BTRFS_EXTENT_ITEM_KEY) ||
+	    (prev_key->type == BTRFS_METADATA_ITEM_KEY)) {
+		u64 prev_end = prev_key->objectid;
+
+		if (prev_key->type == BTRFS_METADATA_ITEM_KEY)
+			prev_end += fs_info->nodesize;
+		else
+			prev_end += prev_key->offset;
+
+		if (unlikely(prev_end > key->objectid)) {
+			extent_err(leaf, slot,
+	"previous extent [%llu %u %llu] overlaps current extent [%llu %u %llu]",
+				   prev_key->objectid, prev_key->type,
+				   prev_key->offset, key->objectid, key->type,
+				   key->offset);
+			return -EUCLEAN;
+		}
+	}
+
 	return 0;
 }
 
@@ -1604,7 +1625,7 @@ static int check_leaf_item(struct extent_buffer *leaf,
 		break;
 	case BTRFS_EXTENT_ITEM_KEY:
 	case BTRFS_METADATA_ITEM_KEY:
-		ret = check_extent_item(leaf, key, slot);
+		ret = check_extent_item(leaf, key, slot, prev_key);
 		break;
 	case BTRFS_TREE_BLOCK_REF_KEY:
 	case BTRFS_SHARED_DATA_REF_KEY:
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 1221d8483d63..727289658730 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -761,7 +761,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 						ins.objectid, ins.offset, 0);
 				btrfs_init_data_ref(&ref,
 						root->root_key.objectid,
-						key->objectid, offset);
+						key->objectid, offset, 0, false);
 				ret = btrfs_inc_extent_ref(trans, &ref);
 				if (ret)
 					goto out;
@@ -884,6 +884,26 @@ out:
 	return ret;
 }
 
+static int unlink_inode_for_log_replay(struct btrfs_trans_handle *trans,
+				       struct btrfs_inode *dir,
+				       struct btrfs_inode *inode,
+				       const char *name,
+				       int name_len)
+{
+	int ret;
+
+	ret = btrfs_unlink_inode(trans, dir, inode, name, name_len);
+	if (ret)
+		return ret;
+	/*
+	 * Whenever we need to check if a name exists or not, we check the
+	 * fs/subvolume tree. So after an unlink we must run delayed items, so
+	 * that future checks for a name during log replay see that the name
+	 * does not exists anymore.
+	 */
+	return btrfs_run_delayed_items(trans);
+}
+
 /*
  * when cleaning up conflicts between the directory names in the
  * subvolume, directory names in the log and directory names in the
@@ -926,12 +946,8 @@ static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans,
 	if (ret)
 		goto out;
 
-	ret = btrfs_unlink_inode(trans, root, dir, BTRFS_I(inode), name,
+	ret = unlink_inode_for_log_replay(trans, dir, BTRFS_I(inode), name,
 			name_len);
-	if (ret)
-		goto out;
-	else
-		ret = btrfs_run_delayed_items(trans);
 out:
 	kfree(name);
 	iput(inode);
@@ -1091,14 +1107,11 @@ again:
 				inc_nlink(&inode->vfs_inode);
 				btrfs_release_path(path);
 
-				ret = btrfs_unlink_inode(trans, root, dir, inode,
+				ret = unlink_inode_for_log_replay(trans, dir, inode,
 						victim_name, victim_name_len);
 				kfree(victim_name);
 				if (ret)
 					return ret;
-				ret = btrfs_run_delayed_items(trans);
-				if (ret)
-					return ret;
 				*search_done = 1;
 				goto again;
 			}
@@ -1119,7 +1132,9 @@ again:
 	extref = btrfs_lookup_inode_extref(NULL, root, path, name, namelen,
 					   inode_objectid, parent_objectid, 0,
 					   0);
-	if (!IS_ERR_OR_NULL(extref)) {
+	if (IS_ERR(extref)) {
+		return PTR_ERR(extref);
+	} else if (extref) {
 		u32 item_size;
 		u32 cur_offset = 0;
 		unsigned long base;
@@ -1163,14 +1178,11 @@ again:
 					inc_nlink(&inode->vfs_inode);
 					btrfs_release_path(path);
 
-					ret = btrfs_unlink_inode(trans, root,
+					ret = unlink_inode_for_log_replay(trans,
 							BTRFS_I(victim_parent),
 							inode,
 							victim_name,
 							victim_name_len);
-					if (!ret)
-						ret = btrfs_run_delayed_items(
-								  trans);
 				}
 				iput(victim_parent);
 				kfree(victim_name);
@@ -1325,19 +1337,10 @@ again:
 				kfree(name);
 				goto out;
 			}
-			ret = btrfs_unlink_inode(trans, root, BTRFS_I(dir),
+			ret = unlink_inode_for_log_replay(trans, BTRFS_I(dir),
 						 inode, name, namelen);
 			kfree(name);
 			iput(dir);
-			/*
-			 * Whenever we need to check if a name exists or not, we
-			 * check the subvolume tree. So after an unlink we must
-			 * run delayed items, so that future checks for a name
-			 * during log replay see that the name does not exists
-			 * anymore.
-			 */
-			if (!ret)
-				ret = btrfs_run_delayed_items(trans);
 			if (ret)
 				goto out;
 			goto again;
@@ -1432,8 +1435,8 @@ static int add_link(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		ret = -ENOENT;
 		goto out;
 	}
-	ret = btrfs_unlink_inode(trans, root, BTRFS_I(dir), BTRFS_I(other_inode),
-				 name, namelen);
+	ret = unlink_inode_for_log_replay(trans, BTRFS_I(dir), BTRFS_I(other_inode),
+					  name, namelen);
 	if (ret)
 		goto out;
 	/*
@@ -1441,11 +1444,7 @@ static int add_link(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	 * on the inode will not free it. We will fixup the link count later.
 	 */
 	if (other_inode->i_nlink == 0)
-		inc_nlink(other_inode);
-
-	ret = btrfs_run_delayed_items(trans);
-	if (ret)
-		goto out;
+		set_nlink(other_inode, 1);
 add_link:
 	ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode),
 			     name, namelen, 0, ref_index);
@@ -1578,7 +1577,7 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 			ret = btrfs_inode_ref_exists(inode, dir, key->type,
 						     name, namelen);
 			if (ret > 0) {
-				ret = btrfs_unlink_inode(trans, root,
+				ret = unlink_inode_for_log_replay(trans,
 							 BTRFS_I(dir),
 							 BTRFS_I(inode),
 							 name, namelen);
@@ -1588,16 +1587,7 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 				 * free it. We will fixup the link count later.
 				 */
 				if (!ret && inode->i_nlink == 0)
-					inc_nlink(inode);
-				/*
-				 * Whenever we need to check if a name exists or
-				 * not, we check the subvolume tree. So after an
-				 * unlink we must run delayed items, so that future
-				 * checks for a name during log replay see that the
-				 * name does not exists anymore.
-				 */
-				if (!ret)
-					ret = btrfs_run_delayed_items(trans);
+					set_nlink(inode, 1);
 			}
 			if (ret < 0)
 				goto out;
@@ -2195,7 +2185,7 @@ static noinline int replay_one_dir_item(struct btrfs_trans_handle *trans,
  */
 static noinline int find_dir_range(struct btrfs_root *root,
 				   struct btrfs_path *path,
-				   u64 dirid, int key_type,
+				   u64 dirid,
 				   u64 *start_ret, u64 *end_ret)
 {
 	struct btrfs_key key;
@@ -2208,7 +2198,7 @@ static noinline int find_dir_range(struct btrfs_root *root,
 		return 1;
 
 	key.objectid = dirid;
-	key.type = key_type;
+	key.type = BTRFS_DIR_LOG_INDEX_KEY;
 	key.offset = *start_ret;
 
 	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
@@ -2222,7 +2212,7 @@ static noinline int find_dir_range(struct btrfs_root *root,
 	if (ret != 0)
 		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
 
-	if (key.type != key_type || key.objectid != dirid) {
+	if (key.type != BTRFS_DIR_LOG_INDEX_KEY || key.objectid != dirid) {
 		ret = 1;
 		goto next;
 	}
@@ -2249,7 +2239,7 @@ next:
 
 	btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
 
-	if (key.type != key_type || key.objectid != dirid) {
+	if (key.type != BTRFS_DIR_LOG_INDEX_KEY || key.objectid != dirid) {
 		ret = 1;
 		goto out;
 	}
@@ -2280,95 +2270,75 @@ static noinline int check_item_in_log(struct btrfs_trans_handle *trans,
 	int ret;
 	struct extent_buffer *eb;
 	int slot;
-	u32 item_size;
 	struct btrfs_dir_item *di;
-	struct btrfs_dir_item *log_di;
 	int name_len;
-	unsigned long ptr;
-	unsigned long ptr_end;
 	char *name;
-	struct inode *inode;
+	struct inode *inode = NULL;
 	struct btrfs_key location;
 
-again:
+	/*
+	 * Currenly we only log dir index keys. Even if we replay a log created
+	 * by an older kernel that logged both dir index and dir item keys, all
+	 * we need to do is process the dir index keys, we (and our caller) can
+	 * safely ignore dir item keys (key type BTRFS_DIR_ITEM_KEY).
+	 */
+	ASSERT(dir_key->type == BTRFS_DIR_INDEX_KEY);
+
 	eb = path->nodes[0];
 	slot = path->slots[0];
-	item_size = btrfs_item_size_nr(eb, slot);
-	ptr = btrfs_item_ptr_offset(eb, slot);
-	ptr_end = ptr + item_size;
-	while (ptr < ptr_end) {
-		di = (struct btrfs_dir_item *)ptr;
-		name_len = btrfs_dir_name_len(eb, di);
-		name = kmalloc(name_len, GFP_NOFS);
-		if (!name) {
-			ret = -ENOMEM;
-			goto out;
-		}
-		read_extent_buffer(eb, name, (unsigned long)(di + 1),
-				  name_len);
-		log_di = NULL;
-		if (log && dir_key->type == BTRFS_DIR_ITEM_KEY) {
-			log_di = btrfs_lookup_dir_item(trans, log, log_path,
-						       dir_key->objectid,
-						       name, name_len, 0);
-		} else if (log && dir_key->type == BTRFS_DIR_INDEX_KEY) {
-			log_di = btrfs_lookup_dir_index_item(trans, log,
-						     log_path,
-						     dir_key->objectid,
-						     dir_key->offset,
-						     name, name_len, 0);
-		}
-		if (!log_di) {
-			btrfs_dir_item_key_to_cpu(eb, di, &location);
-			btrfs_release_path(path);
-			btrfs_release_path(log_path);
-			inode = read_one_inode(root, location.objectid);
-			if (!inode) {
-				kfree(name);
-				return -EIO;
-			}
+	di = btrfs_item_ptr(eb, slot, struct btrfs_dir_item);
+	name_len = btrfs_dir_name_len(eb, di);
+	name = kmalloc(name_len, GFP_NOFS);
+	if (!name) {
+		ret = -ENOMEM;
+		goto out;
+	}
 
-			ret = link_to_fixup_dir(trans, root,
-						path, location.objectid);
-			if (ret) {
-				kfree(name);
-				iput(inode);
-				goto out;
-			}
+	read_extent_buffer(eb, name, (unsigned long)(di + 1), name_len);
 
-			inc_nlink(inode);
-			ret = btrfs_unlink_inode(trans, root, BTRFS_I(dir),
-					BTRFS_I(inode), name, name_len);
-			if (!ret)
-				ret = btrfs_run_delayed_items(trans);
-			kfree(name);
-			iput(inode);
-			if (ret)
-				goto out;
+	if (log) {
+		struct btrfs_dir_item *log_di;
 
-			/* there might still be more names under this key
-			 * check and repeat if required
-			 */
-			ret = btrfs_search_slot(NULL, root, dir_key, path,
-						0, 0);
-			if (ret == 0)
-				goto again;
+		log_di = btrfs_lookup_dir_index_item(trans, log, log_path,
+						     dir_key->objectid,
+						     dir_key->offset,
+						     name, name_len, 0);
+		if (IS_ERR(log_di)) {
+			ret = PTR_ERR(log_di);
+			goto out;
+		} else if (log_di) {
+			/* The dentry exists in the log, we have nothing to do. */
 			ret = 0;
 			goto out;
-		} else if (IS_ERR(log_di)) {
-			kfree(name);
-			return PTR_ERR(log_di);
 		}
-		btrfs_release_path(log_path);
-		kfree(name);
+	}
 
-		ptr = (unsigned long)(di + 1);
-		ptr += name_len;
+	btrfs_dir_item_key_to_cpu(eb, di, &location);
+	btrfs_release_path(path);
+	btrfs_release_path(log_path);
+	inode = read_one_inode(root, location.objectid);
+	if (!inode) {
+		ret = -EIO;
+		goto out;
 	}
-	ret = 0;
+
+	ret = link_to_fixup_dir(trans, root, path, location.objectid);
+	if (ret)
+		goto out;
+
+	inc_nlink(inode);
+	ret = unlink_inode_for_log_replay(trans, BTRFS_I(dir), BTRFS_I(inode),
+					  name, name_len);
+	/*
+	 * Unlike dir item keys, dir index keys can only have one name (entry) in
+	 * them, as there are no key collisions since each key has a unique offset
+	 * (an index number), so we're done.
+	 */
 out:
 	btrfs_release_path(path);
 	btrfs_release_path(log_path);
+	kfree(name);
+	iput(inode);
 	return ret;
 }
 
@@ -2488,7 +2458,6 @@ static noinline int replay_dir_deletes(struct btrfs_trans_handle *trans,
 {
 	u64 range_start;
 	u64 range_end;
-	int key_type = BTRFS_DIR_LOG_ITEM_KEY;
 	int ret = 0;
 	struct btrfs_key dir_key;
 	struct btrfs_key found_key;
@@ -2496,7 +2465,7 @@ static noinline int replay_dir_deletes(struct btrfs_trans_handle *trans,
 	struct inode *dir;
 
 	dir_key.objectid = dirid;
-	dir_key.type = BTRFS_DIR_ITEM_KEY;
+	dir_key.type = BTRFS_DIR_INDEX_KEY;
 	log_path = btrfs_alloc_path();
 	if (!log_path)
 		return -ENOMEM;
@@ -2510,14 +2479,14 @@ static noinline int replay_dir_deletes(struct btrfs_trans_handle *trans,
 		btrfs_free_path(log_path);
 		return 0;
 	}
-again:
+
 	range_start = 0;
 	range_end = 0;
 	while (1) {
 		if (del_all)
 			range_end = (u64)-1;
 		else {
-			ret = find_dir_range(log, path, dirid, key_type,
+			ret = find_dir_range(log, path, dirid,
 					     &range_start, &range_end);
 			if (ret < 0)
 				goto out;
@@ -2544,8 +2513,10 @@ again:
 			btrfs_item_key_to_cpu(path->nodes[0], &found_key,
 					      path->slots[0]);
 			if (found_key.objectid != dirid ||
-			    found_key.type != dir_key.type)
-				goto next_type;
+			    found_key.type != dir_key.type) {
+				ret = 0;
+				goto out;
+			}
 
 			if (found_key.offset > range_end)
 				break;
@@ -2564,15 +2535,7 @@ again:
 			break;
 		range_start = range_end + 1;
 	}
-
-next_type:
 	ret = 0;
-	if (key_type == BTRFS_DIR_LOG_ITEM_KEY) {
-		key_type = BTRFS_DIR_LOG_INDEX_KEY;
-		dir_key.type = BTRFS_DIR_INDEX_KEY;
-		btrfs_release_path(path);
-		goto again;
-	}
 out:
 	btrfs_release_path(path);
 	btrfs_free_path(log_path);
@@ -6626,14 +6589,25 @@ void btrfs_record_snapshot_destroy(struct btrfs_trans_handle *trans,
 	mutex_unlock(&dir->log_mutex);
 }
 
-/*
- * Call this after adding a new name for a file and it will properly
- * update the log to reflect the new name.
+/**
+ * Update the log after adding a new name for an inode.
+ *
+ * @trans:              Transaction handle.
+ * @old_dentry:         The dentry associated with the old name and the old
+ *                      parent directory.
+ * @old_dir:            The inode of the previous parent directory for the case
+ *                      of a rename. For a link operation, it must be NULL.
+ * @parent:             The dentry associated with the directory under which the
+ *                      new name is located.
+ *
+ * Call this after adding a new name for an inode, as a result of a link or
+ * rename operation, and it will properly update the log to reflect the new name.
  */
 void btrfs_log_new_name(struct btrfs_trans_handle *trans,
-			struct btrfs_inode *inode, struct btrfs_inode *old_dir,
+			struct dentry *old_dentry, struct btrfs_inode *old_dir,
 			struct dentry *parent)
 {
+	struct btrfs_inode *inode = BTRFS_I(d_inode(old_dentry));
 	struct btrfs_log_ctx ctx;
 
 	/*
diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h
index 731bd9c029f5..7ffcac8a8990 100644
--- a/fs/btrfs/tree-log.h
+++ b/fs/btrfs/tree-log.h
@@ -84,7 +84,7 @@ void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans,
 void btrfs_record_snapshot_destroy(struct btrfs_trans_handle *trans,
 				   struct btrfs_inode *dir);
 void btrfs_log_new_name(struct btrfs_trans_handle *trans,
-			struct btrfs_inode *inode, struct btrfs_inode *old_dir,
+			struct dentry *old_dentry, struct btrfs_inode *old_dir,
 			struct dentry *parent);
 
 #endif
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 378e03a93e10..0f22d91e2392 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -251,7 +251,7 @@ static void btrfs_dev_stat_print_on_load(struct btrfs_device *device);
 static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
 			     enum btrfs_map_op op,
 			     u64 logical, u64 *length,
-			     struct btrfs_bio **bbio_ret,
+			     struct btrfs_io_context **bioc_ret,
 			     int mirror_num, int need_raid_map);
 
 /*
@@ -844,9 +844,13 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 
 		device = NULL;
 	} else {
+		struct btrfs_dev_lookup_args args = {
+			.devid = devid,
+			.uuid = disk_super->dev_item.uuid,
+		};
+
 		mutex_lock(&fs_devices->device_list_mutex);
-		device = btrfs_find_device(fs_devices, devid,
-				disk_super->dev_item.uuid, NULL);
+		device = btrfs_find_device(fs_devices, &args);
 
 		/*
 		 * If this disk has been pulled into an fs devices created by
@@ -951,6 +955,11 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 		/*
 		 * We are going to replace the device path for a given devid,
 		 * make sure it's the same device if the device is mounted
+		 *
+		 * NOTE: the device->fs_info may not be reliable here so pass
+		 * in a NULL to message helpers instead. This avoids a possible
+		 * use-after-free when the fs_info and fs_info->sb are already
+		 * torn down.
 		 */
 		if (device->bdev) {
 			int error;
@@ -964,12 +973,6 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 
 			if (device->bdev->bd_dev != path_dev) {
 				mutex_unlock(&fs_devices->device_list_mutex);
-				/*
-				 * device->fs_info may not be reliable here, so
-				 * pass in a NULL instead. This avoids a
-				 * possible use-after-free when the fs_info and
-				 * fs_info->sb are already torn down.
-				 */
 				btrfs_warn_in_rcu(NULL,
 	"duplicate device %s devid %llu generation %llu scanned by %s (%d)",
 						  path, devid, found_transid,
@@ -977,7 +980,7 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 						  task_pid_nr(current));
 				return ERR_PTR(-EEXIST);
 			}
-			btrfs_info_in_rcu(device->fs_info,
+			btrfs_info_in_rcu(NULL,
 	"devid %llu device path %s changed to %s scanned by %s (%d)",
 					  devid, rcu_str_deref(device->name),
 					  path, current->comm,
@@ -1879,8 +1882,10 @@ static int btrfs_add_dev_item(struct btrfs_trans_handle *trans,
 	key.type = BTRFS_DEV_ITEM_KEY;
 	key.offset = device->devid;
 
+	btrfs_reserve_chunk_metadata(trans, true);
 	ret = btrfs_insert_empty_item(trans, trans->fs_info->chunk_root, path,
 				      &key, sizeof(*dev_item));
+	btrfs_trans_release_chunk_metadata(trans);
 	if (ret)
 		goto out;
 
@@ -1936,46 +1941,34 @@ static void update_dev_time(const char *device_path)
 	path_put(&path);
 }
 
-static int btrfs_rm_dev_item(struct btrfs_device *device)
+static int btrfs_rm_dev_item(struct btrfs_trans_handle *trans,
+			     struct btrfs_device *device)
 {
 	struct btrfs_root *root = device->fs_info->chunk_root;
 	int ret;
 	struct btrfs_path *path;
 	struct btrfs_key key;
-	struct btrfs_trans_handle *trans;
 
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
 
-	trans = btrfs_start_transaction(root, 0);
-	if (IS_ERR(trans)) {
-		btrfs_free_path(path);
-		return PTR_ERR(trans);
-	}
 	key.objectid = BTRFS_DEV_ITEMS_OBJECTID;
 	key.type = BTRFS_DEV_ITEM_KEY;
 	key.offset = device->devid;
 
+	btrfs_reserve_chunk_metadata(trans, false);
 	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
+	btrfs_trans_release_chunk_metadata(trans);
 	if (ret) {
 		if (ret > 0)
 			ret = -ENOENT;
-		btrfs_abort_transaction(trans, ret);
-		btrfs_end_transaction(trans);
 		goto out;
 	}
 
 	ret = btrfs_del_item(trans, root, path);
-	if (ret) {
-		btrfs_abort_transaction(trans, ret);
-		btrfs_end_transaction(trans);
-	}
-
 out:
 	btrfs_free_path(path);
-	if (!ret)
-		ret = btrfs_commit_transaction(trans);
 	return ret;
 }
 
@@ -2112,9 +2105,11 @@ void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info,
 	update_dev_time(device_path);
 }
 
-int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path,
-		    u64 devid, struct block_device **bdev, fmode_t *mode)
+int btrfs_rm_device(struct btrfs_fs_info *fs_info,
+		    struct btrfs_dev_lookup_args *args,
+		    struct block_device **bdev, fmode_t *mode)
 {
+	struct btrfs_trans_handle *trans;
 	struct btrfs_device *device;
 	struct btrfs_fs_devices *cur_devices;
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
@@ -2130,37 +2125,30 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path,
 
 	ret = btrfs_check_raid_min_devices(fs_info, num_devices - 1);
 	if (ret)
-		goto out;
-
-	device = btrfs_find_device_by_devspec(fs_info, devid, device_path);
+		return ret;
 
-	if (IS_ERR(device)) {
-		if (PTR_ERR(device) == -ENOENT &&
-		    device_path && strcmp(device_path, "missing") == 0)
+	device = btrfs_find_device(fs_info->fs_devices, args);
+	if (!device) {
+		if (args->missing)
 			ret = BTRFS_ERROR_DEV_MISSING_NOT_FOUND;
 		else
-			ret = PTR_ERR(device);
-		goto out;
+			ret = -ENOENT;
+		return ret;
 	}
 
 	if (btrfs_pinned_by_swapfile(fs_info, device)) {
 		btrfs_warn_in_rcu(fs_info,
 		  "cannot remove device %s (devid %llu) due to active swapfile",
 				  rcu_str_deref(device->name), device->devid);
-		ret = -ETXTBSY;
-		goto out;
+		return -ETXTBSY;
 	}
 
-	if (test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) {
-		ret = BTRFS_ERROR_DEV_TGT_REPLACE;
-		goto out;
-	}
+	if (test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state))
+		return BTRFS_ERROR_DEV_TGT_REPLACE;
 
 	if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) &&
-	    fs_info->fs_devices->rw_devices == 1) {
-		ret = BTRFS_ERROR_DEV_ONLY_WRITABLE;
-		goto out;
-	}
+	    fs_info->fs_devices->rw_devices == 1)
+		return BTRFS_ERROR_DEV_ONLY_WRITABLE;
 
 	if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
 		mutex_lock(&fs_info->chunk_mutex);
@@ -2175,14 +2163,22 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path,
 	if (ret)
 		goto error_undo;
 
-	/*
-	 * TODO: the superblock still includes this device in its num_devices
-	 * counter although write_all_supers() is not locked out. This
-	 * could give a filesystem state which requires a degraded mount.
-	 */
-	ret = btrfs_rm_dev_item(device);
-	if (ret)
+	trans = btrfs_start_transaction(fs_info->chunk_root, 0);
+	if (IS_ERR(trans)) {
+		ret = PTR_ERR(trans);
 		goto error_undo;
+	}
+
+	ret = btrfs_rm_dev_item(trans, device);
+	if (ret) {
+		/* Any error in dev item removal is critical */
+		btrfs_crit(fs_info,
+			   "failed to remove device item for devid %llu: %d",
+			   device->devid, ret);
+		btrfs_abort_transaction(trans, ret);
+		btrfs_end_transaction(trans);
+		return ret;
+	}
 
 	clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
 	btrfs_scrub_cancel_dev(device);
@@ -2257,7 +2253,8 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path,
 		free_fs_devices(cur_devices);
 	}
 
-out:
+	ret = btrfs_commit_transaction(trans);
+
 	return ret;
 
 error_undo:
@@ -2269,7 +2266,7 @@ error_undo:
 		device->fs_devices->rw_devices++;
 		mutex_unlock(&fs_info->chunk_mutex);
 	}
-	goto out;
+	return ret;
 }
 
 void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_device *srcdev)
@@ -2353,69 +2350,101 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_device *tgtdev)
 	btrfs_free_device(tgtdev);
 }
 
-static struct btrfs_device *btrfs_find_device_by_path(
-		struct btrfs_fs_info *fs_info, const char *device_path)
+/**
+ * Populate args from device at path
+ *
+ * @fs_info:	the filesystem
+ * @args:	the args to populate
+ * @path:	the path to the device
+ *
+ * This will read the super block of the device at @path and populate @args with
+ * the devid, fsid, and uuid.  This is meant to be used for ioctls that need to
+ * lookup a device to operate on, but need to do it before we take any locks.
+ * This properly handles the special case of "missing" that a user may pass in,
+ * and does some basic sanity checks.  The caller must make sure that @path is
+ * properly NUL terminated before calling in, and must call
+ * btrfs_put_dev_args_from_path() in order to free up the temporary fsid and
+ * uuid buffers.
+ *
+ * Return: 0 for success, -errno for failure
+ */
+int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info,
+				 struct btrfs_dev_lookup_args *args,
+				 const char *path)
 {
-	int ret = 0;
 	struct btrfs_super_block *disk_super;
-	u64 devid;
-	u8 *dev_uuid;
 	struct block_device *bdev;
-	struct btrfs_device *device;
+	int ret;
 
-	ret = btrfs_get_bdev_and_sb(device_path, FMODE_READ,
-				    fs_info->bdev_holder, 0, &bdev, &disk_super);
-	if (ret)
-		return ERR_PTR(ret);
+	if (!path || !path[0])
+		return -EINVAL;
+	if (!strcmp(path, "missing")) {
+		args->missing = true;
+		return 0;
+	}
 
-	devid = btrfs_stack_device_id(&disk_super->dev_item);
-	dev_uuid = disk_super->dev_item.uuid;
+	args->uuid = kzalloc(BTRFS_UUID_SIZE, GFP_KERNEL);
+	args->fsid = kzalloc(BTRFS_FSID_SIZE, GFP_KERNEL);
+	if (!args->uuid || !args->fsid) {
+		btrfs_put_dev_args_from_path(args);
+		return -ENOMEM;
+	}
+
+	ret = btrfs_get_bdev_and_sb(path, FMODE_READ, fs_info->bdev_holder, 0,
+				    &bdev, &disk_super);
+	if (ret) {
+		btrfs_put_dev_args_from_path(args);
+		return ret;
+	}
+
+	args->devid = btrfs_stack_device_id(&disk_super->dev_item);
+	memcpy(args->uuid, disk_super->dev_item.uuid, BTRFS_UUID_SIZE);
 	if (btrfs_fs_incompat(fs_info, METADATA_UUID))
-		device = btrfs_find_device(fs_info->fs_devices, devid, dev_uuid,
-					   disk_super->metadata_uuid);
+		memcpy(args->fsid, disk_super->metadata_uuid, BTRFS_FSID_SIZE);
 	else
-		device = btrfs_find_device(fs_info->fs_devices, devid, dev_uuid,
-					   disk_super->fsid);
-
+		memcpy(args->fsid, disk_super->fsid, BTRFS_FSID_SIZE);
 	btrfs_release_disk_super(disk_super);
-	if (!device)
-		device = ERR_PTR(-ENOENT);
 	blkdev_put(bdev, FMODE_READ);
-	return device;
+	return 0;
 }
 
 /*
- * Lookup a device given by device id, or the path if the id is 0.
+ * Only use this jointly with btrfs_get_dev_args_from_path() because we will
+ * allocate our ->uuid and ->fsid pointers, everybody else uses local variables
+ * that don't need to be freed.
  */
+void btrfs_put_dev_args_from_path(struct btrfs_dev_lookup_args *args)
+{
+	kfree(args->uuid);
+	kfree(args->fsid);
+	args->uuid = NULL;
+	args->fsid = NULL;
+}
+
 struct btrfs_device *btrfs_find_device_by_devspec(
 		struct btrfs_fs_info *fs_info, u64 devid,
 		const char *device_path)
 {
+	BTRFS_DEV_LOOKUP_ARGS(args);
 	struct btrfs_device *device;
+	int ret;
 
 	if (devid) {
-		device = btrfs_find_device(fs_info->fs_devices, devid, NULL,
-					   NULL);
+		args.devid = devid;
+		device = btrfs_find_device(fs_info->fs_devices, &args);
 		if (!device)
 			return ERR_PTR(-ENOENT);
 		return device;
 	}
 
-	if (!device_path || !device_path[0])
-		return ERR_PTR(-EINVAL);
-
-	if (strcmp(device_path, "missing") == 0) {
-		/* Find first missing device */
-		list_for_each_entry(device, &fs_info->fs_devices->devices,
-				    dev_list) {
-			if (test_bit(BTRFS_DEV_STATE_IN_FS_METADATA,
-				     &device->dev_state) && !device->bdev)
-				return device;
-		}
+	ret = btrfs_get_dev_args_from_path(fs_info, &args, device_path);
+	if (ret)
+		return ERR_PTR(ret);
+	device = btrfs_find_device(fs_info->fs_devices, &args);
+	btrfs_put_dev_args_from_path(&args);
+	if (!device)
 		return ERR_PTR(-ENOENT);
-	}
-
-	return btrfs_find_device_by_path(fs_info, device_path);
+	return device;
 }
 
 /*
@@ -2492,6 +2521,7 @@ static int btrfs_prepare_sprout(struct btrfs_fs_info *fs_info)
  */
 static int btrfs_finish_sprout(struct btrfs_trans_handle *trans)
 {
+	BTRFS_DEV_LOOKUP_ARGS(args);
 	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *root = fs_info->chunk_root;
 	struct btrfs_path *path;
@@ -2501,7 +2531,6 @@ static int btrfs_finish_sprout(struct btrfs_trans_handle *trans)
 	struct btrfs_key key;
 	u8 fs_uuid[BTRFS_FSID_SIZE];
 	u8 dev_uuid[BTRFS_UUID_SIZE];
-	u64 devid;
 	int ret;
 
 	path = btrfs_alloc_path();
@@ -2513,7 +2542,9 @@ static int btrfs_finish_sprout(struct btrfs_trans_handle *trans)
 	key.type = BTRFS_DEV_ITEM_KEY;
 
 	while (1) {
+		btrfs_reserve_chunk_metadata(trans, false);
 		ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
+		btrfs_trans_release_chunk_metadata(trans);
 		if (ret < 0)
 			goto error;
 
@@ -2538,13 +2569,14 @@ next_slot:
 
 		dev_item = btrfs_item_ptr(leaf, path->slots[0],
 					  struct btrfs_dev_item);
-		devid = btrfs_device_id(leaf, dev_item);
+		args.devid = btrfs_device_id(leaf, dev_item);
 		read_extent_buffer(leaf, dev_uuid, btrfs_device_uuid(dev_item),
 				   BTRFS_UUID_SIZE);
 		read_extent_buffer(leaf, fs_uuid, btrfs_device_fsid(dev_item),
 				   BTRFS_FSID_SIZE);
-		device = btrfs_find_device(fs_info->fs_devices, devid, dev_uuid,
-					   fs_uuid);
+		args.uuid = dev_uuid;
+		args.fsid = fs_uuid;
+		device = btrfs_find_device(fs_info->fs_devices, &args);
 		BUG_ON(!device); /* Logic error */
 
 		if (device->fs_devices->seeding) {
@@ -2861,6 +2893,7 @@ int btrfs_grow_device(struct btrfs_trans_handle *trans,
 	struct btrfs_super_block *super_copy = fs_info->super_copy;
 	u64 old_total;
 	u64 diff;
+	int ret;
 
 	if (!test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state))
 		return -EACCES;
@@ -2889,7 +2922,11 @@ int btrfs_grow_device(struct btrfs_trans_handle *trans,
 			      &trans->transaction->dev_update_list);
 	mutex_unlock(&fs_info->chunk_mutex);
 
-	return btrfs_update_device(trans, device);
+	btrfs_reserve_chunk_metadata(trans, false);
+	ret = btrfs_update_device(trans, device);
+	btrfs_trans_release_chunk_metadata(trans);
+
+	return ret;
 }
 
 static int btrfs_free_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset)
@@ -3131,7 +3168,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset)
 		const u64 sys_flags = btrfs_system_alloc_profile(fs_info);
 		struct btrfs_block_group *sys_bg;
 
-		sys_bg = btrfs_alloc_chunk(trans, sys_flags);
+		sys_bg = btrfs_create_chunk(trans, sys_flags);
 		if (IS_ERR(sys_bg)) {
 			ret = PTR_ERR(sys_bg);
 			btrfs_abort_transaction(trans, ret);
@@ -4926,8 +4963,10 @@ again:
 			round_down(old_total - diff, fs_info->sectorsize));
 	mutex_unlock(&fs_info->chunk_mutex);
 
+	btrfs_reserve_chunk_metadata(trans, false);
 	/* Now btrfs_update_device() will change the on-disk size. */
 	ret = btrfs_update_device(trans, device);
+	btrfs_trans_release_chunk_metadata(trans);
 	if (ret < 0) {
 		btrfs_abort_transaction(trans, ret);
 		btrfs_end_transaction(trans);
@@ -5010,7 +5049,7 @@ static void check_raid1c34_incompat_flag(struct btrfs_fs_info *info, u64 type)
 }
 
 /*
- * Structure used internally for __btrfs_alloc_chunk() function.
+ * Structure used internally for btrfs_create_chunk() function.
  * Wraps needed parameters.
  */
 struct alloc_chunk_ctl {
@@ -5414,7 +5453,7 @@ error_del_extent:
 	return block_group;
 }
 
-struct btrfs_block_group *btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
+struct btrfs_block_group *btrfs_create_chunk(struct btrfs_trans_handle *trans,
 					    u64 type)
 {
 	struct btrfs_fs_info *info = trans->fs_info;
@@ -5615,12 +5654,12 @@ static noinline int init_first_rw_device(struct btrfs_trans_handle *trans)
 	 */
 
 	alloc_profile = btrfs_metadata_alloc_profile(fs_info);
-	meta_bg = btrfs_alloc_chunk(trans, alloc_profile);
+	meta_bg = btrfs_create_chunk(trans, alloc_profile);
 	if (IS_ERR(meta_bg))
 		return PTR_ERR(meta_bg);
 
 	alloc_profile = btrfs_system_alloc_profile(fs_info);
-	sys_bg = btrfs_alloc_chunk(trans, alloc_profile);
+	sys_bg = btrfs_create_chunk(trans, alloc_profile);
 	if (IS_ERR(sys_bg))
 		return PTR_ERR(sys_bg);
 
@@ -5832,7 +5871,7 @@ static int find_live_mirror(struct btrfs_fs_info *fs_info,
 }
 
 /* Bubble-sort the stripe set to put the parity/syndrome stripes last */
-static void sort_parity_stripes(struct btrfs_bio *bbio, int num_stripes)
+static void sort_parity_stripes(struct btrfs_io_context *bioc, int num_stripes)
 {
 	int i;
 	int again = 1;
@@ -5841,52 +5880,53 @@ static void sort_parity_stripes(struct btrfs_bio *bbio, int num_stripes)
 		again = 0;
 		for (i = 0; i < num_stripes - 1; i++) {
 			/* Swap if parity is on a smaller index */
-			if (bbio->raid_map[i] > bbio->raid_map[i + 1]) {
-				swap(bbio->stripes[i], bbio->stripes[i + 1]);
-				swap(bbio->raid_map[i], bbio->raid_map[i + 1]);
+			if (bioc->raid_map[i] > bioc->raid_map[i + 1]) {
+				swap(bioc->stripes[i], bioc->stripes[i + 1]);
+				swap(bioc->raid_map[i], bioc->raid_map[i + 1]);
 				again = 1;
 			}
 		}
 	}
 }
 
-static struct btrfs_bio *alloc_btrfs_bio(int total_stripes, int real_stripes)
+static struct btrfs_io_context *alloc_btrfs_io_context(int total_stripes,
+						       int real_stripes)
 {
-	struct btrfs_bio *bbio = kzalloc(
-		 /* the size of the btrfs_bio */
-		sizeof(struct btrfs_bio) +
-		/* plus the variable array for the stripes */
-		sizeof(struct btrfs_bio_stripe) * (total_stripes) +
-		/* plus the variable array for the tgt dev */
+	struct btrfs_io_context *bioc = kzalloc(
+		 /* The size of btrfs_io_context */
+		sizeof(struct btrfs_io_context) +
+		/* Plus the variable array for the stripes */
+		sizeof(struct btrfs_io_stripe) * (total_stripes) +
+		/* Plus the variable array for the tgt dev */
 		sizeof(int) * (real_stripes) +
 		/*
-		 * plus the raid_map, which includes both the tgt dev
-		 * and the stripes
+		 * Plus the raid_map, which includes both the tgt dev
+		 * and the stripes.
 		 */
 		sizeof(u64) * (total_stripes),
 		GFP_NOFS|__GFP_NOFAIL);
 
-	atomic_set(&bbio->error, 0);
-	refcount_set(&bbio->refs, 1);
+	atomic_set(&bioc->error, 0);
+	refcount_set(&bioc->refs, 1);
 
-	bbio->tgtdev_map = (int *)(bbio->stripes + total_stripes);
-	bbio->raid_map = (u64 *)(bbio->tgtdev_map + real_stripes);
+	bioc->tgtdev_map = (int *)(bioc->stripes + total_stripes);
+	bioc->raid_map = (u64 *)(bioc->tgtdev_map + real_stripes);
 
-	return bbio;
+	return bioc;
 }
 
-void btrfs_get_bbio(struct btrfs_bio *bbio)
+void btrfs_get_bioc(struct btrfs_io_context *bioc)
 {
-	WARN_ON(!refcount_read(&bbio->refs));
-	refcount_inc(&bbio->refs);
+	WARN_ON(!refcount_read(&bioc->refs));
+	refcount_inc(&bioc->refs);
 }
 
-void btrfs_put_bbio(struct btrfs_bio *bbio)
+void btrfs_put_bioc(struct btrfs_io_context *bioc)
 {
-	if (!bbio)
+	if (!bioc)
 		return;
-	if (refcount_dec_and_test(&bbio->refs))
-		kfree(bbio);
+	if (refcount_dec_and_test(&bioc->refs))
+		kfree(bioc);
 }
 
 /* can REQ_OP_DISCARD be sent with other REQ like REQ_OP_WRITE? */
@@ -5896,11 +5936,11 @@ void btrfs_put_bbio(struct btrfs_bio *bbio)
  */
 static int __btrfs_map_block_for_discard(struct btrfs_fs_info *fs_info,
 					 u64 logical, u64 *length_ret,
-					 struct btrfs_bio **bbio_ret)
+					 struct btrfs_io_context **bioc_ret)
 {
 	struct extent_map *em;
 	struct map_lookup *map;
-	struct btrfs_bio *bbio;
+	struct btrfs_io_context *bioc;
 	u64 length = *length_ret;
 	u64 offset;
 	u64 stripe_nr;
@@ -5919,8 +5959,8 @@ static int __btrfs_map_block_for_discard(struct btrfs_fs_info *fs_info,
 	int ret = 0;
 	int i;
 
-	/* discard always return a bbio */
-	ASSERT(bbio_ret);
+	/* Discard always returns a bioc. */
+	ASSERT(bioc_ret);
 
 	em = btrfs_get_chunk_map(fs_info, logical, length);
 	if (IS_ERR(em))
@@ -5983,26 +6023,25 @@ static int __btrfs_map_block_for_discard(struct btrfs_fs_info *fs_info,
 					&stripe_index);
 	}
 
-	bbio = alloc_btrfs_bio(num_stripes, 0);
-	if (!bbio) {
+	bioc = alloc_btrfs_io_context(num_stripes, 0);
+	if (!bioc) {
 		ret = -ENOMEM;
 		goto out;
 	}
 
 	for (i = 0; i < num_stripes; i++) {
-		bbio->stripes[i].physical =
+		bioc->stripes[i].physical =
 			map->stripes[stripe_index].physical +
 			stripe_offset + stripe_nr * map->stripe_len;
-		bbio->stripes[i].dev = map->stripes[stripe_index].dev;
+		bioc->stripes[i].dev = map->stripes[stripe_index].dev;
 
 		if (map->type & (BTRFS_BLOCK_GROUP_RAID0 |
 				 BTRFS_BLOCK_GROUP_RAID10)) {
-			bbio->stripes[i].length = stripes_per_dev *
+			bioc->stripes[i].length = stripes_per_dev *
 				map->stripe_len;
 
 			if (i / sub_stripes < remaining_stripes)
-				bbio->stripes[i].length +=
-					map->stripe_len;
+				bioc->stripes[i].length += map->stripe_len;
 
 			/*
 			 * Special for the first stripe and
@@ -6013,19 +6052,17 @@ static int __btrfs_map_block_for_discard(struct btrfs_fs_info *fs_info,
 			 *    off     end_off
 			 */
 			if (i < sub_stripes)
-				bbio->stripes[i].length -=
-					stripe_offset;
+				bioc->stripes[i].length -= stripe_offset;
 
 			if (stripe_index >= last_stripe &&
 			    stripe_index <= (last_stripe +
 					     sub_stripes - 1))
-				bbio->stripes[i].length -=
-					stripe_end_offset;
+				bioc->stripes[i].length -= stripe_end_offset;
 
 			if (i == sub_stripes - 1)
 				stripe_offset = 0;
 		} else {
-			bbio->stripes[i].length = length;
+			bioc->stripes[i].length = length;
 		}
 
 		stripe_index++;
@@ -6035,9 +6072,9 @@ static int __btrfs_map_block_for_discard(struct btrfs_fs_info *fs_info,
 		}
 	}
 
-	*bbio_ret = bbio;
-	bbio->map_type = map->type;
-	bbio->num_stripes = num_stripes;
+	*bioc_ret = bioc;
+	bioc->map_type = map->type;
+	bioc->num_stripes = num_stripes;
 out:
 	free_extent_map(em);
 	return ret;
@@ -6061,7 +6098,7 @@ static int get_extra_mirror_from_replace(struct btrfs_fs_info *fs_info,
 					 u64 srcdev_devid, int *mirror_num,
 					 u64 *physical)
 {
-	struct btrfs_bio *bbio = NULL;
+	struct btrfs_io_context *bioc = NULL;
 	int num_stripes;
 	int index_srcdev = 0;
 	int found = 0;
@@ -6070,20 +6107,20 @@ static int get_extra_mirror_from_replace(struct btrfs_fs_info *fs_info,
 	int ret = 0;
 
 	ret = __btrfs_map_block(fs_info, BTRFS_MAP_GET_READ_MIRRORS,
-				logical, &length, &bbio, 0, 0);
+				logical, &length, &bioc, 0, 0);
 	if (ret) {
-		ASSERT(bbio == NULL);
+		ASSERT(bioc == NULL);
 		return ret;
 	}
 
-	num_stripes = bbio->num_stripes;
+	num_stripes = bioc->num_stripes;
 	if (*mirror_num > num_stripes) {
 		/*
 		 * BTRFS_MAP_GET_READ_MIRRORS does not contain this mirror,
 		 * that means that the requested area is not left of the left
 		 * cursor
 		 */
-		btrfs_put_bbio(bbio);
+		btrfs_put_bioc(bioc);
 		return -EIO;
 	}
 
@@ -6093,7 +6130,7 @@ static int get_extra_mirror_from_replace(struct btrfs_fs_info *fs_info,
 	 * pointer to the one of the target drive.
 	 */
 	for (i = 0; i < num_stripes; i++) {
-		if (bbio->stripes[i].dev->devid != srcdev_devid)
+		if (bioc->stripes[i].dev->devid != srcdev_devid)
 			continue;
 
 		/*
@@ -6101,15 +6138,15 @@ static int get_extra_mirror_from_replace(struct btrfs_fs_info *fs_info,
 		 * mirror with the lowest physical address
 		 */
 		if (found &&
-		    physical_of_found <= bbio->stripes[i].physical)
+		    physical_of_found <= bioc->stripes[i].physical)
 			continue;
 
 		index_srcdev = i;
 		found = 1;
-		physical_of_found = bbio->stripes[i].physical;
+		physical_of_found = bioc->stripes[i].physical;
 	}
 
-	btrfs_put_bbio(bbio);
+	btrfs_put_bioc(bioc);
 
 	ASSERT(found);
 	if (!found)
@@ -6140,12 +6177,12 @@ static bool is_block_group_to_copy(struct btrfs_fs_info *fs_info, u64 logical)
 }
 
 static void handle_ops_on_dev_replace(enum btrfs_map_op op,
-				      struct btrfs_bio **bbio_ret,
+				      struct btrfs_io_context **bioc_ret,
 				      struct btrfs_dev_replace *dev_replace,
 				      u64 logical,
 				      int *num_stripes_ret, int *max_errors_ret)
 {
-	struct btrfs_bio *bbio = *bbio_ret;
+	struct btrfs_io_context *bioc = *bioc_ret;
 	u64 srcdev_devid = dev_replace->srcdev->devid;
 	int tgtdev_indexes = 0;
 	int num_stripes = *num_stripes_ret;
@@ -6175,17 +6212,17 @@ static void handle_ops_on_dev_replace(enum btrfs_map_op op,
 		 */
 		index_where_to_add = num_stripes;
 		for (i = 0; i < num_stripes; i++) {
-			if (bbio->stripes[i].dev->devid == srcdev_devid) {
+			if (bioc->stripes[i].dev->devid == srcdev_devid) {
 				/* write to new disk, too */
-				struct btrfs_bio_stripe *new =
-					bbio->stripes + index_where_to_add;
-				struct btrfs_bio_stripe *old =
-					bbio->stripes + i;
+				struct btrfs_io_stripe *new =
+					bioc->stripes + index_where_to_add;
+				struct btrfs_io_stripe *old =
+					bioc->stripes + i;
 
 				new->physical = old->physical;
 				new->length = old->length;
 				new->dev = dev_replace->tgtdev;
-				bbio->tgtdev_map[i] = index_where_to_add;
+				bioc->tgtdev_map[i] = index_where_to_add;
 				index_where_to_add++;
 				max_errors++;
 				tgtdev_indexes++;
@@ -6205,30 +6242,29 @@ static void handle_ops_on_dev_replace(enum btrfs_map_op op,
 		 * full copy of the source drive.
 		 */
 		for (i = 0; i < num_stripes; i++) {
-			if (bbio->stripes[i].dev->devid == srcdev_devid) {
+			if (bioc->stripes[i].dev->devid == srcdev_devid) {
 				/*
 				 * In case of DUP, in order to keep it simple,
 				 * only add the mirror with the lowest physical
 				 * address
 				 */
 				if (found &&
-				    physical_of_found <=
-				     bbio->stripes[i].physical)
+				    physical_of_found <= bioc->stripes[i].physical)
 					continue;
 				index_srcdev = i;
 				found = 1;
-				physical_of_found = bbio->stripes[i].physical;
+				physical_of_found = bioc->stripes[i].physical;
 			}
 		}
 		if (found) {
-			struct btrfs_bio_stripe *tgtdev_stripe =
-				bbio->stripes + num_stripes;
+			struct btrfs_io_stripe *tgtdev_stripe =
+				bioc->stripes + num_stripes;
 
 			tgtdev_stripe->physical = physical_of_found;
 			tgtdev_stripe->length =
-				bbio->stripes[index_srcdev].length;
+				bioc->stripes[index_srcdev].length;
 			tgtdev_stripe->dev = dev_replace->tgtdev;
-			bbio->tgtdev_map[index_srcdev] = num_stripes;
+			bioc->tgtdev_map[index_srcdev] = num_stripes;
 
 			tgtdev_indexes++;
 			num_stripes++;
@@ -6237,8 +6273,8 @@ static void handle_ops_on_dev_replace(enum btrfs_map_op op,
 
 	*num_stripes_ret = num_stripes;
 	*max_errors_ret = max_errors;
-	bbio->num_tgtdevs = tgtdev_indexes;
-	*bbio_ret = bbio;
+	bioc->num_tgtdevs = tgtdev_indexes;
+	*bioc_ret = bioc;
 }
 
 static bool need_full_stripe(enum btrfs_map_op op)
@@ -6341,7 +6377,7 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, struct extent_map *em,
 static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
 			     enum btrfs_map_op op,
 			     u64 logical, u64 *length,
-			     struct btrfs_bio **bbio_ret,
+			     struct btrfs_io_context **bioc_ret,
 			     int mirror_num, int need_raid_map)
 {
 	struct extent_map *em;
@@ -6356,7 +6392,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
 	int num_stripes;
 	int max_errors = 0;
 	int tgtdev_indexes = 0;
-	struct btrfs_bio *bbio = NULL;
+	struct btrfs_io_context *bioc = NULL;
 	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
 	int dev_replace_is_ongoing = 0;
 	int num_alloc_stripes;
@@ -6365,7 +6401,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
 	u64 raid56_full_stripe_start = (u64)-1;
 	struct btrfs_io_geometry geom;
 
-	ASSERT(bbio_ret);
+	ASSERT(bioc_ret);
 	ASSERT(op != BTRFS_MAP_DISCARD);
 
 	em = btrfs_get_chunk_map(fs_info, logical, *length);
@@ -6509,20 +6545,20 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
 		tgtdev_indexes = num_stripes;
 	}
 
-	bbio = alloc_btrfs_bio(num_alloc_stripes, tgtdev_indexes);
-	if (!bbio) {
+	bioc = alloc_btrfs_io_context(num_alloc_stripes, tgtdev_indexes);
+	if (!bioc) {
 		ret = -ENOMEM;
 		goto out;
 	}
 
 	for (i = 0; i < num_stripes; i++) {
-		bbio->stripes[i].physical = map->stripes[stripe_index].physical +
+		bioc->stripes[i].physical = map->stripes[stripe_index].physical +
 			stripe_offset + stripe_nr * map->stripe_len;
-		bbio->stripes[i].dev = map->stripes[stripe_index].dev;
+		bioc->stripes[i].dev = map->stripes[stripe_index].dev;
 		stripe_index++;
 	}
 
-	/* build raid_map */
+	/* Build raid_map */
 	if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK && need_raid_map &&
 	    (need_full_stripe(op) || mirror_num > 1)) {
 		u64 tmp;
@@ -6534,15 +6570,15 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
 		/* Fill in the logical address of each stripe */
 		tmp = stripe_nr * data_stripes;
 		for (i = 0; i < data_stripes; i++)
-			bbio->raid_map[(i+rot) % num_stripes] =
+			bioc->raid_map[(i + rot) % num_stripes] =
 				em->start + (tmp + i) * map->stripe_len;
 
-		bbio->raid_map[(i+rot) % map->num_stripes] = RAID5_P_STRIPE;
+		bioc->raid_map[(i + rot) % map->num_stripes] = RAID5_P_STRIPE;
 		if (map->type & BTRFS_BLOCK_GROUP_RAID6)
-			bbio->raid_map[(i+rot+1) % num_stripes] =
+			bioc->raid_map[(i + rot + 1) % num_stripes] =
 				RAID6_Q_STRIPE;
 
-		sort_parity_stripes(bbio, num_stripes);
+		sort_parity_stripes(bioc, num_stripes);
 	}
 
 	if (need_full_stripe(op))
@@ -6550,15 +6586,15 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
 
 	if (dev_replace_is_ongoing && dev_replace->tgtdev != NULL &&
 	    need_full_stripe(op)) {
-		handle_ops_on_dev_replace(op, &bbio, dev_replace, logical,
+		handle_ops_on_dev_replace(op, &bioc, dev_replace, logical,
 					  &num_stripes, &max_errors);
 	}
 
-	*bbio_ret = bbio;
-	bbio->map_type = map->type;
-	bbio->num_stripes = num_stripes;
-	bbio->max_errors = max_errors;
-	bbio->mirror_num = mirror_num;
+	*bioc_ret = bioc;
+	bioc->map_type = map->type;
+	bioc->num_stripes = num_stripes;
+	bioc->max_errors = max_errors;
+	bioc->mirror_num = mirror_num;
 
 	/*
 	 * this is the case that REQ_READ && dev_replace_is_ongoing &&
@@ -6567,9 +6603,9 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
 	 */
 	if (patch_the_first_stripe_for_dev_replace && num_stripes > 0) {
 		WARN_ON(num_stripes > 1);
-		bbio->stripes[0].dev = dev_replace->tgtdev;
-		bbio->stripes[0].physical = physical_to_patch_in_first_stripe;
-		bbio->mirror_num = map->num_stripes + 1;
+		bioc->stripes[0].dev = dev_replace->tgtdev;
+		bioc->stripes[0].physical = physical_to_patch_in_first_stripe;
+		bioc->mirror_num = map->num_stripes + 1;
 	}
 out:
 	if (dev_replace_is_ongoing) {
@@ -6583,40 +6619,40 @@ out:
 
 int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 		      u64 logical, u64 *length,
-		      struct btrfs_bio **bbio_ret, int mirror_num)
+		      struct btrfs_io_context **bioc_ret, int mirror_num)
 {
 	if (op == BTRFS_MAP_DISCARD)
 		return __btrfs_map_block_for_discard(fs_info, logical,
-						     length, bbio_ret);
+						     length, bioc_ret);
 
-	return __btrfs_map_block(fs_info, op, logical, length, bbio_ret,
+	return __btrfs_map_block(fs_info, op, logical, length, bioc_ret,
 				 mirror_num, 0);
 }
 
 /* For Scrub/replace */
 int btrfs_map_sblock(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 		     u64 logical, u64 *length,
-		     struct btrfs_bio **bbio_ret)
+		     struct btrfs_io_context **bioc_ret)
 {
-	return __btrfs_map_block(fs_info, op, logical, length, bbio_ret, 0, 1);
+	return __btrfs_map_block(fs_info, op, logical, length, bioc_ret, 0, 1);
 }
 
-static inline void btrfs_end_bbio(struct btrfs_bio *bbio, struct bio *bio)
+static inline void btrfs_end_bioc(struct btrfs_io_context *bioc, struct bio *bio)
 {
-	bio->bi_private = bbio->private;
-	bio->bi_end_io = bbio->end_io;
+	bio->bi_private = bioc->private;
+	bio->bi_end_io = bioc->end_io;
 	bio_endio(bio);
 
-	btrfs_put_bbio(bbio);
+	btrfs_put_bioc(bioc);
 }
 
 static void btrfs_end_bio(struct bio *bio)
 {
-	struct btrfs_bio *bbio = bio->bi_private;
+	struct btrfs_io_context *bioc = bio->bi_private;
 	int is_orig_bio = 0;
 
 	if (bio->bi_status) {
-		atomic_inc(&bbio->error);
+		atomic_inc(&bioc->error);
 		if (bio->bi_status == BLK_STS_IOERR ||
 		    bio->bi_status == BLK_STS_TARGET) {
 			struct btrfs_device *dev = btrfs_io_bio(bio)->device;
@@ -6634,22 +6670,22 @@ static void btrfs_end_bio(struct bio *bio)
 		}
 	}
 
-	if (bio == bbio->orig_bio)
+	if (bio == bioc->orig_bio)
 		is_orig_bio = 1;
 
-	btrfs_bio_counter_dec(bbio->fs_info);
+	btrfs_bio_counter_dec(bioc->fs_info);
 
-	if (atomic_dec_and_test(&bbio->stripes_pending)) {
+	if (atomic_dec_and_test(&bioc->stripes_pending)) {
 		if (!is_orig_bio) {
 			bio_put(bio);
-			bio = bbio->orig_bio;
+			bio = bioc->orig_bio;
 		}
 
-		btrfs_io_bio(bio)->mirror_num = bbio->mirror_num;
+		btrfs_io_bio(bio)->mirror_num = bioc->mirror_num;
 		/* only send an error to the higher layers if it is
 		 * beyond the tolerance of the btrfs bio
 		 */
-		if (atomic_read(&bbio->error) > bbio->max_errors) {
+		if (atomic_read(&bioc->error) > bioc->max_errors) {
 			bio->bi_status = BLK_STS_IOERR;
 		} else {
 			/*
@@ -6659,18 +6695,18 @@ static void btrfs_end_bio(struct bio *bio)
 			bio->bi_status = BLK_STS_OK;
 		}
 
-		btrfs_end_bbio(bbio, bio);
+		btrfs_end_bioc(bioc, bio);
 	} else if (!is_orig_bio) {
 		bio_put(bio);
 	}
 }
 
-static void submit_stripe_bio(struct btrfs_bio *bbio, struct bio *bio,
+static void submit_stripe_bio(struct btrfs_io_context *bioc, struct bio *bio,
 			      u64 physical, struct btrfs_device *dev)
 {
-	struct btrfs_fs_info *fs_info = bbio->fs_info;
+	struct btrfs_fs_info *fs_info = bioc->fs_info;
 
-	bio->bi_private = bbio;
+	bio->bi_private = bioc;
 	btrfs_io_bio(bio)->device = dev;
 	bio->bi_end_io = btrfs_end_bio;
 	bio->bi_iter.bi_sector = physical >> 9;
@@ -6700,20 +6736,20 @@ static void submit_stripe_bio(struct btrfs_bio *bbio, struct bio *bio,
 	btrfsic_submit_bio(bio);
 }
 
-static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical)
+static void bioc_error(struct btrfs_io_context *bioc, struct bio *bio, u64 logical)
 {
-	atomic_inc(&bbio->error);
-	if (atomic_dec_and_test(&bbio->stripes_pending)) {
+	atomic_inc(&bioc->error);
+	if (atomic_dec_and_test(&bioc->stripes_pending)) {
 		/* Should be the original bio. */
-		WARN_ON(bio != bbio->orig_bio);
+		WARN_ON(bio != bioc->orig_bio);
 
-		btrfs_io_bio(bio)->mirror_num = bbio->mirror_num;
+		btrfs_io_bio(bio)->mirror_num = bioc->mirror_num;
 		bio->bi_iter.bi_sector = logical >> 9;
-		if (atomic_read(&bbio->error) > bbio->max_errors)
+		if (atomic_read(&bioc->error) > bioc->max_errors)
 			bio->bi_status = BLK_STS_IOERR;
 		else
 			bio->bi_status = BLK_STS_OK;
-		btrfs_end_bbio(bbio, bio);
+		btrfs_end_bioc(bioc, bio);
 	}
 }
 
@@ -6728,35 +6764,35 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 	int ret;
 	int dev_nr;
 	int total_devs;
-	struct btrfs_bio *bbio = NULL;
+	struct btrfs_io_context *bioc = NULL;
 
 	length = bio->bi_iter.bi_size;
 	map_length = length;
 
 	btrfs_bio_counter_inc_blocked(fs_info);
 	ret = __btrfs_map_block(fs_info, btrfs_op(bio), logical,
-				&map_length, &bbio, mirror_num, 1);
+				&map_length, &bioc, mirror_num, 1);
 	if (ret) {
 		btrfs_bio_counter_dec(fs_info);
 		return errno_to_blk_status(ret);
 	}
 
-	total_devs = bbio->num_stripes;
-	bbio->orig_bio = first_bio;
-	bbio->private = first_bio->bi_private;
-	bbio->end_io = first_bio->bi_end_io;
-	bbio->fs_info = fs_info;
-	atomic_set(&bbio->stripes_pending, bbio->num_stripes);
+	total_devs = bioc->num_stripes;
+	bioc->orig_bio = first_bio;
+	bioc->private = first_bio->bi_private;
+	bioc->end_io = first_bio->bi_end_io;
+	bioc->fs_info = fs_info;
+	atomic_set(&bioc->stripes_pending, bioc->num_stripes);
 
-	if ((bbio->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) &&
+	if ((bioc->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) &&
 	    ((btrfs_op(bio) == BTRFS_MAP_WRITE) || (mirror_num > 1))) {
 		/* In this case, map_length has been set to the length of
 		   a single stripe; not the whole write */
 		if (btrfs_op(bio) == BTRFS_MAP_WRITE) {
-			ret = raid56_parity_write(fs_info, bio, bbio,
+			ret = raid56_parity_write(fs_info, bio, bioc,
 						  map_length);
 		} else {
-			ret = raid56_parity_recover(fs_info, bio, bbio,
+			ret = raid56_parity_recover(fs_info, bio, bioc,
 						    map_length, mirror_num, 1);
 		}
 
@@ -6772,12 +6808,12 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 	}
 
 	for (dev_nr = 0; dev_nr < total_devs; dev_nr++) {
-		dev = bbio->stripes[dev_nr].dev;
+		dev = bioc->stripes[dev_nr].dev;
 		if (!dev || !dev->bdev || test_bit(BTRFS_DEV_STATE_MISSING,
 						   &dev->dev_state) ||
 		    (btrfs_op(first_bio) == BTRFS_MAP_WRITE &&
 		    !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state))) {
-			bbio_error(bbio, first_bio, logical);
+			bioc_error(bioc, first_bio, logical);
 			continue;
 		}
 
@@ -6786,12 +6822,39 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 		else
 			bio = first_bio;
 
-		submit_stripe_bio(bbio, bio, bbio->stripes[dev_nr].physical, dev);
+		submit_stripe_bio(bioc, bio, bioc->stripes[dev_nr].physical, dev);
 	}
 	btrfs_bio_counter_dec(fs_info);
 	return BLK_STS_OK;
 }
 
+static bool dev_args_match_fs_devices(const struct btrfs_dev_lookup_args *args,
+				      const struct btrfs_fs_devices *fs_devices)
+{
+	if (args->fsid == NULL)
+		return true;
+	if (memcmp(fs_devices->metadata_uuid, args->fsid, BTRFS_FSID_SIZE) == 0)
+		return true;
+	return false;
+}
+
+static bool dev_args_match_device(const struct btrfs_dev_lookup_args *args,
+				  const struct btrfs_device *device)
+{
+	ASSERT((args->devid != (u64)-1) || args->missing);
+
+	if ((args->devid != (u64)-1) && device->devid != args->devid)
+		return false;
+	if (args->uuid && memcmp(device->uuid, args->uuid, BTRFS_UUID_SIZE) != 0)
+		return false;
+	if (!args->missing)
+		return true;
+	if (test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state) &&
+	    !device->bdev)
+		return true;
+	return false;
+}
+
 /*
  * Find a device specified by @devid or @uuid in the list of @fs_devices, or
  * return NULL.
@@ -6799,31 +6862,25 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
  * If devid and uuid are both specified, the match must be exact, otherwise
  * only devid is used.
  */
-struct btrfs_device *btrfs_find_device(struct btrfs_fs_devices *fs_devices,
-				       u64 devid, u8 *uuid, u8 *fsid)
+struct btrfs_device *btrfs_find_device(const struct btrfs_fs_devices *fs_devices,
+				       const struct btrfs_dev_lookup_args *args)
 {
 	struct btrfs_device *device;
 	struct btrfs_fs_devices *seed_devs;
 
-	if (!fsid || !memcmp(fs_devices->metadata_uuid, fsid, BTRFS_FSID_SIZE)) {
+	if (dev_args_match_fs_devices(args, fs_devices)) {
 		list_for_each_entry(device, &fs_devices->devices, dev_list) {
-			if (device->devid == devid &&
-			    (!uuid || memcmp(device->uuid, uuid,
-					     BTRFS_UUID_SIZE) == 0))
+			if (dev_args_match_device(args, device))
 				return device;
 		}
 	}
 
 	list_for_each_entry(seed_devs, &fs_devices->seed_list, seed_list) {
-		if (!fsid ||
-		    !memcmp(seed_devs->metadata_uuid, fsid, BTRFS_FSID_SIZE)) {
-			list_for_each_entry(device, &seed_devs->devices,
-					    dev_list) {
-				if (device->devid == devid &&
-				    (!uuid || memcmp(device->uuid, uuid,
-						     BTRFS_UUID_SIZE) == 0))
-					return device;
-			}
+		if (!dev_args_match_fs_devices(args, seed_devs))
+			continue;
+		list_for_each_entry(device, &seed_devs->devices, dev_list) {
+			if (dev_args_match_device(args, device))
+				return device;
 		}
 	}
 
@@ -6989,6 +7046,7 @@ static void warn_32bit_meta_chunk(struct btrfs_fs_info *fs_info,
 static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf,
 			  struct btrfs_chunk *chunk)
 {
+	BTRFS_DEV_LOOKUP_ARGS(args);
 	struct btrfs_fs_info *fs_info = leaf->fs_info;
 	struct extent_map_tree *map_tree = &fs_info->mapping_tree;
 	struct map_lookup *map;
@@ -7066,11 +7124,12 @@ static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf,
 		map->stripes[i].physical =
 			btrfs_stripe_offset_nr(leaf, chunk, i);
 		devid = btrfs_stripe_devid_nr(leaf, chunk, i);
+		args.devid = devid;
 		read_extent_buffer(leaf, uuid, (unsigned long)
 				   btrfs_stripe_dev_uuid_nr(chunk, i),
 				   BTRFS_UUID_SIZE);
-		map->stripes[i].dev = btrfs_find_device(fs_info->fs_devices,
-							devid, uuid, NULL);
+		args.uuid = uuid;
+		map->stripes[i].dev = btrfs_find_device(fs_info->fs_devices, &args);
 		if (!map->stripes[i].dev &&
 		    !btrfs_test_opt(fs_info, DEGRADED)) {
 			free_extent_map(em);
@@ -7188,6 +7247,7 @@ static struct btrfs_fs_devices *open_seed_devices(struct btrfs_fs_info *fs_info,
 static int read_one_dev(struct extent_buffer *leaf,
 			struct btrfs_dev_item *dev_item)
 {
+	BTRFS_DEV_LOOKUP_ARGS(args);
 	struct btrfs_fs_info *fs_info = leaf->fs_info;
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
 	struct btrfs_device *device;
@@ -7196,11 +7256,13 @@ static int read_one_dev(struct extent_buffer *leaf,
 	u8 fs_uuid[BTRFS_FSID_SIZE];
 	u8 dev_uuid[BTRFS_UUID_SIZE];
 
-	devid = btrfs_device_id(leaf, dev_item);
+	devid = args.devid = btrfs_device_id(leaf, dev_item);
 	read_extent_buffer(leaf, dev_uuid, btrfs_device_uuid(dev_item),
 			   BTRFS_UUID_SIZE);
 	read_extent_buffer(leaf, fs_uuid, btrfs_device_fsid(dev_item),
 			   BTRFS_FSID_SIZE);
+	args.uuid = dev_uuid;
+	args.fsid = fs_uuid;
 
 	if (memcmp(fs_uuid, fs_devices->metadata_uuid, BTRFS_FSID_SIZE)) {
 		fs_devices = open_seed_devices(fs_info, fs_uuid);
@@ -7208,8 +7270,7 @@ static int read_one_dev(struct extent_buffer *leaf,
 			return PTR_ERR(fs_devices);
 	}
 
-	device = btrfs_find_device(fs_info->fs_devices, devid, dev_uuid,
-				   fs_uuid);
+	device = btrfs_find_device(fs_info->fs_devices, &args);
 	if (!device) {
 		if (!btrfs_test_opt(fs_info, DEGRADED)) {
 			btrfs_report_missing_device(fs_info, devid,
@@ -7886,12 +7947,14 @@ static void btrfs_dev_stat_print_on_load(struct btrfs_device *dev)
 int btrfs_get_dev_stats(struct btrfs_fs_info *fs_info,
 			struct btrfs_ioctl_get_dev_stats *stats)
 {
+	BTRFS_DEV_LOOKUP_ARGS(args);
 	struct btrfs_device *dev;
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
 	int i;
 
 	mutex_lock(&fs_devices->device_list_mutex);
-	dev = btrfs_find_device(fs_info->fs_devices, stats->devid, NULL, NULL);
+	args.devid = stats->devid;
+	dev = btrfs_find_device(fs_info->fs_devices, &args);
 	mutex_unlock(&fs_devices->device_list_mutex);
 
 	if (!dev) {
@@ -7967,6 +8030,7 @@ static int verify_one_dev_extent(struct btrfs_fs_info *fs_info,
 				 u64 chunk_offset, u64 devid,
 				 u64 physical_offset, u64 physical_len)
 {
+	struct btrfs_dev_lookup_args args = { .devid = devid };
 	struct extent_map_tree *em_tree = &fs_info->mapping_tree;
 	struct extent_map *em;
 	struct map_lookup *map;
@@ -8022,7 +8086,7 @@ static int verify_one_dev_extent(struct btrfs_fs_info *fs_info,
 	}
 
 	/* Make sure no dev extent is beyond device boundary */
-	dev = btrfs_find_device(fs_info->fs_devices, devid, NULL, NULL);
+	dev = btrfs_find_device(fs_info->fs_devices, &args);
 	if (!dev) {
 		btrfs_err(fs_info, "failed to find devid %llu", devid);
 		ret = -EUCLEAN;
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 4db10d071d67..dfd7457709b3 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -306,11 +306,11 @@ struct btrfs_fs_devices {
 /*
  * we need the mirror number and stripe index to be passed around
  * the call chain while we are processing end_io (especially errors).
- * Really, what we need is a btrfs_bio structure that has this info
+ * Really, what we need is a btrfs_io_context structure that has this info
  * and is properly sized with its stripe array, but we're not there
  * quite yet.  We have our own btrfs bioset, and all of the bios
  * we allocate are actually btrfs_io_bios.  We'll cram as much of
- * struct btrfs_bio as we can into this over time.
+ * struct btrfs_io_context as we can into this over time.
  */
 struct btrfs_io_bio {
 	unsigned int mirror_num;
@@ -339,13 +339,29 @@ static inline void btrfs_io_bio_free_csum(struct btrfs_io_bio *io_bio)
 	}
 }
 
-struct btrfs_bio_stripe {
+struct btrfs_io_stripe {
 	struct btrfs_device *dev;
 	u64 physical;
 	u64 length; /* only used for discard mappings */
 };
 
-struct btrfs_bio {
+/*
+ * Context for IO subsmission for device stripe.
+ *
+ * - Track the unfinished mirrors for mirror based profiles
+ *   Mirror based profiles are SINGLE/DUP/RAID1/RAID10.
+ *
+ * - Contain the logical -> physical mapping info
+ *   Used by submit_stripe_bio() for mapping logical bio
+ *   into physical device address.
+ *
+ * - Contain device replace info
+ *   Used by handle_ops_on_dev_replace() to copy logical bios
+ *   into the new device.
+ *
+ * - Contain RAID56 full stripe logical bytenrs
+ */
+struct btrfs_io_context {
 	refcount_t refs;
 	atomic_t stripes_pending;
 	struct btrfs_fs_info *fs_info;
@@ -365,7 +381,7 @@ struct btrfs_bio {
 	 * so raid_map[0] is the start of our full stripe
 	 */
 	u64 *raid_map;
-	struct btrfs_bio_stripe stripes[];
+	struct btrfs_io_stripe stripes[];
 };
 
 struct btrfs_device_info {
@@ -400,11 +416,11 @@ struct map_lookup {
 	int num_stripes;
 	int sub_stripes;
 	int verified_stripes; /* For mount time dev extent verification */
-	struct btrfs_bio_stripe stripes[];
+	struct btrfs_io_stripe stripes[];
 };
 
 #define map_lookup_size(n) (sizeof(struct map_lookup) + \
-			    (sizeof(struct btrfs_bio_stripe) * (n)))
+			    (sizeof(struct btrfs_io_stripe) * (n)))
 
 struct btrfs_balance_args;
 struct btrfs_balance_progress;
@@ -418,6 +434,22 @@ struct btrfs_balance_control {
 	struct btrfs_balance_progress stat;
 };
 
+/*
+ * Search for a given device by the set parameters
+ */
+struct btrfs_dev_lookup_args {
+	u64 devid;
+	u8 *uuid;
+	u8 *fsid;
+	bool missing;
+};
+
+/* We have to initialize to -1 because BTRFS_DEV_REPLACE_DEVID is 0 */
+#define BTRFS_DEV_LOOKUP_ARGS_INIT { .devid = (u64)-1 }
+
+#define BTRFS_DEV_LOOKUP_ARGS(name) \
+	struct btrfs_dev_lookup_args name = BTRFS_DEV_LOOKUP_ARGS_INIT
+
 enum btrfs_map_op {
 	BTRFS_MAP_READ,
 	BTRFS_MAP_WRITE,
@@ -441,20 +473,20 @@ static inline enum btrfs_map_op btrfs_op(struct bio *bio)
 	}
 }
 
-void btrfs_get_bbio(struct btrfs_bio *bbio);
-void btrfs_put_bbio(struct btrfs_bio *bbio);
+void btrfs_get_bioc(struct btrfs_io_context *bioc);
+void btrfs_put_bioc(struct btrfs_io_context *bioc);
 int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 		    u64 logical, u64 *length,
-		    struct btrfs_bio **bbio_ret, int mirror_num);
+		    struct btrfs_io_context **bioc_ret, int mirror_num);
 int btrfs_map_sblock(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 		     u64 logical, u64 *length,
-		     struct btrfs_bio **bbio_ret);
+		     struct btrfs_io_context **bioc_ret);
 int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, struct extent_map *map,
 			  enum btrfs_map_op op, u64 logical,
 			  struct btrfs_io_geometry *io_geom);
 int btrfs_read_sys_array(struct btrfs_fs_info *fs_info);
 int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info);
-struct btrfs_block_group *btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
+struct btrfs_block_group *btrfs_create_chunk(struct btrfs_trans_handle *trans,
 					    u64 type);
 void btrfs_mapping_tree_free(struct extent_map_tree *tree);
 blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
@@ -471,19 +503,23 @@ void btrfs_assign_next_active_device(struct btrfs_device *device,
 struct btrfs_device *btrfs_find_device_by_devspec(struct btrfs_fs_info *fs_info,
 						  u64 devid,
 						  const char *devpath);
+int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info,
+				 struct btrfs_dev_lookup_args *args,
+				 const char *path);
 struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
 					const u64 *devid,
 					const u8 *uuid);
+void btrfs_put_dev_args_from_path(struct btrfs_dev_lookup_args *args);
 void btrfs_free_device(struct btrfs_device *device);
 int btrfs_rm_device(struct btrfs_fs_info *fs_info,
-		    const char *device_path, u64 devid,
+		    struct btrfs_dev_lookup_args *args,
 		    struct block_device **bdev, fmode_t *mode);
 void __exit btrfs_cleanup_fs_uuids(void);
 int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len);
 int btrfs_grow_device(struct btrfs_trans_handle *trans,
 		      struct btrfs_device *device, u64 new_size);
-struct btrfs_device *btrfs_find_device(struct btrfs_fs_devices *fs_devices,
-				       u64 devid, u8 *uuid, u8 *fsid);
+struct btrfs_device *btrfs_find_device(const struct btrfs_fs_devices *fs_devices,
+				       const struct btrfs_dev_lookup_args *args);
 int btrfs_shrink_device(struct btrfs_device *device, u64 new_size);
 int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *path);
 int btrfs_balance(struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index c5c5b97c2a85..43fe2c2a955e 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -391,6 +391,9 @@ static int btrfs_xattr_handler_set(const struct xattr_handler *handler,
 				   const char *name, const void *buffer,
 				   size_t size, int flags)
 {
+	if (btrfs_root_readonly(BTRFS_I(inode)->root))
+		return -EROFS;
+
 	name = xattr_full_name(handler, name);
 	return btrfs_setxattr_trans(inode, name, buffer, size, flags);
 }
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 596b2148807d..96958ca474bd 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -386,6 +386,25 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache)
 	nr_sectors = bdev_nr_sectors(bdev);
 	zone_info->zone_size_shift = ilog2(zone_info->zone_size);
 	zone_info->nr_zones = nr_sectors >> ilog2(zone_sectors);
+	/*
+	 * We limit max_zone_append_size also by max_segments *
+	 * PAGE_SIZE. Technically, we can have multiple pages per segment. But,
+	 * since btrfs adds the pages one by one to a bio, and btrfs cannot
+	 * increase the metadata reservation even if it increases the number of
+	 * extents, it is safe to stick with the limit.
+	 *
+	 * With the zoned emulation, we can have non-zoned device on the zoned
+	 * mode. In this case, we don't have a valid max zone append size. So,
+	 * use max_segments * PAGE_SIZE as the pseudo max_zone_append_size.
+	 */
+	if (bdev_is_zoned(bdev)) {
+		zone_info->max_zone_append_size = min_t(u64,
+			(u64)bdev_max_zone_append_sectors(bdev) << SECTOR_SHIFT,
+			(u64)bdev_max_segments(bdev) << PAGE_SHIFT);
+	} else {
+		zone_info->max_zone_append_size =
+			(u64)bdev_max_segments(bdev) << PAGE_SHIFT;
+	}
 	if (!IS_ALIGNED(nr_sectors, zone_sectors))
 		zone_info->nr_zones++;
 
@@ -570,6 +589,7 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info)
 	u64 zoned_devices = 0;
 	u64 nr_devices = 0;
 	u64 zone_size = 0;
+	u64 max_zone_append_size = 0;
 	const bool incompat_zoned = btrfs_fs_incompat(fs_info, ZONED);
 	int ret = 0;
 
@@ -605,6 +625,11 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info)
 				ret = -EINVAL;
 				goto out;
 			}
+			if (!max_zone_append_size ||
+			    (zone_info->max_zone_append_size &&
+			     zone_info->max_zone_append_size < max_zone_append_size))
+				max_zone_append_size =
+					zone_info->max_zone_append_size;
 		}
 		nr_devices++;
 	}
@@ -636,7 +661,7 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info)
 
 	/*
 	 * stripe_size is always aligned to BTRFS_STRIPE_LEN in
-	 * __btrfs_alloc_chunk(). Since we want stripe_len == zone_size,
+	 * btrfs_create_chunk(). Since we want stripe_len == zone_size,
 	 * check the alignment here.
 	 */
 	if (!IS_ALIGNED(zone_size, BTRFS_STRIPE_LEN)) {
@@ -654,7 +679,11 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info)
 	}
 
 	fs_info->zone_size = zone_size;
+	fs_info->max_zone_append_size = ALIGN_DOWN(max_zone_append_size,
+						   fs_info->sectorsize);
 	fs_info->fs_devices->chunk_alloc_policy = BTRFS_CHUNK_ALLOC_ZONED;
+	if (fs_info->max_zone_append_size < fs_info->max_extent_size)
+		fs_info->max_extent_size = fs_info->max_zone_append_size;
 
 	/*
 	 * Check mount options here, because we might change fs_info->zoned
@@ -1502,27 +1531,29 @@ int btrfs_zoned_issue_zeroout(struct btrfs_device *device, u64 physical, u64 len
 static int read_zone_info(struct btrfs_fs_info *fs_info, u64 logical,
 			  struct blk_zone *zone)
 {
-	struct btrfs_bio *bbio = NULL;
+	struct btrfs_io_context *bioc = NULL;
 	u64 mapped_length = PAGE_SIZE;
 	unsigned int nofs_flag;
 	int nmirrors;
 	int i, ret;
 
 	ret = btrfs_map_sblock(fs_info, BTRFS_MAP_GET_READ_MIRRORS, logical,
-			       &mapped_length, &bbio);
-	if (ret || !bbio || mapped_length < PAGE_SIZE) {
-		btrfs_put_bbio(bbio);
-		return -EIO;
+			       &mapped_length, &bioc);
+	if (ret || !bioc || mapped_length < PAGE_SIZE) {
+		ret = -EIO;
+		goto out_put_bioc;
 	}
 
-	if (bbio->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK)
-		return -EINVAL;
+	if (bioc->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
+		ret = -EINVAL;
+		goto out_put_bioc;
+	}
 
 	nofs_flag = memalloc_nofs_save();
-	nmirrors = (int)bbio->num_stripes;
+	nmirrors = (int)bioc->num_stripes;
 	for (i = 0; i < nmirrors; i++) {
-		u64 physical = bbio->stripes[i].physical;
-		struct btrfs_device *dev = bbio->stripes[i].dev;
+		u64 physical = bioc->stripes[i].physical;
+		struct btrfs_device *dev = bioc->stripes[i].dev;
 
 		/* Missing device */
 		if (!dev->bdev)
@@ -1535,7 +1566,8 @@ static int read_zone_info(struct btrfs_fs_info *fs_info, u64 logical,
 		break;
 	}
 	memalloc_nofs_restore(nofs_flag);
-
+out_put_bioc:
+	btrfs_put_bioc(bioc);
 	return ret;
 }
 
@@ -1620,3 +1652,30 @@ void btrfs_free_zone_cache(struct btrfs_fs_info *fs_info)
 	}
 	mutex_unlock(&fs_devices->device_list_mutex);
 }
+
+void btrfs_zoned_release_data_reloc_bg(struct btrfs_fs_info *fs_info, u64 logical,
+				       u64 length)
+{
+	struct btrfs_block_group *block_group;
+
+	if (!btrfs_is_zoned(fs_info))
+		return;
+
+	block_group = btrfs_lookup_block_group(fs_info, logical);
+	/* It should be called on a previous data relocation block group. */
+	ASSERT(block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA));
+
+	spin_lock(&block_group->lock);
+	if (!block_group->zoned_data_reloc_ongoing)
+		goto out;
+
+	/* All relocation extents are written. */
+	if (block_group->start + block_group->alloc_offset == logical + length) {
+		/* Now, release this block group for further allocations. */
+		block_group->zoned_data_reloc_ongoing = 0;
+	}
+
+out:
+	spin_unlock(&block_group->lock);
+	btrfs_put_block_group(block_group);
+}
diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h
index 813aa3cddc11..1ef493fcd504 100644
--- a/fs/btrfs/zoned.h
+++ b/fs/btrfs/zoned.h
@@ -8,6 +8,7 @@
 #include "volumes.h"
 #include "disk-io.h"
 #include "block-group.h"
+#include "btrfs_inode.h"
 
 /*
  * Block groups with more than this value (percents) of unusable space will be
@@ -22,6 +23,7 @@ struct btrfs_zoned_device_info {
 	 */
 	u64 zone_size;
 	u8  zone_size_shift;
+	u64 max_zone_append_size;
 	u32 nr_zones;
 	unsigned long *seq_zones;
 	unsigned long *empty_zones;
@@ -69,6 +71,8 @@ struct btrfs_device *btrfs_zoned_get_device(struct btrfs_fs_info *fs_info,
 					    u64 logical, u64 length);
 void btrfs_clear_data_reloc_bg(struct btrfs_block_group *bg);
 void btrfs_free_zone_cache(struct btrfs_fs_info *fs_info);
+void btrfs_zoned_release_data_reloc_bg(struct btrfs_fs_info *fs_info, u64 logical,
+				       u64 length);
 #else /* CONFIG_BLK_DEV_ZONED */
 static inline int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos,
 				     struct blk_zone *zone)
@@ -206,6 +210,9 @@ static inline struct btrfs_device *btrfs_zoned_get_device(
 static inline void btrfs_clear_data_reloc_bg(struct btrfs_block_group *bg) { }
 
 static inline void btrfs_free_zone_cache(struct btrfs_fs_info *fs_info) { }
+
+static inline void btrfs_zoned_release_data_reloc_bg(struct btrfs_fs_info *fs_info,
+						     u64 logical, u64 length) { }
 #endif
 
 static inline bool btrfs_dev_is_sequential(struct btrfs_device *device, u64 pos)
@@ -324,4 +331,20 @@ static inline void btrfs_clear_treelog_bg(struct btrfs_block_group *bg)
 	spin_unlock(&fs_info->treelog_bg_lock);
 }
 
+static inline void btrfs_zoned_data_reloc_lock(struct btrfs_inode *inode)
+{
+	struct btrfs_root *root = inode->root;
+
+	if (btrfs_is_data_reloc_root(root) && btrfs_is_zoned(root->fs_info))
+		mutex_lock(&root->fs_info->zoned_data_reloc_io_lock);
+}
+
+static inline void btrfs_zoned_data_reloc_unlock(struct btrfs_inode *inode)
+{
+	struct btrfs_root *root = inode->root;
+
+	if (btrfs_is_data_reloc_root(root) && btrfs_is_zoned(root->fs_info))
+		mutex_unlock(&root->fs_info->zoned_data_reloc_io_lock);
+}
+
 #endif
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 99b80b5c7a93..b218a26291b8 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -179,7 +179,7 @@ static int ceph_releasepage(struct page *page, gfp_t gfp)
 
 static void ceph_netfs_expand_readahead(struct netfs_read_request *rreq)
 {
-	struct inode *inode = rreq->mapping->host;
+	struct inode *inode = rreq->inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_file_layout *lo = &ci->i_layout;
 	u32 blockoff;
@@ -196,7 +196,7 @@ static void ceph_netfs_expand_readahead(struct netfs_read_request *rreq)
 
 static bool ceph_netfs_clamp_length(struct netfs_read_subrequest *subreq)
 {
-	struct inode *inode = subreq->rreq->mapping->host;
+	struct inode *inode = subreq->rreq->inode;
 	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	u64 objno, objoff;
@@ -242,7 +242,7 @@ static void finish_netfs_read(struct ceph_osd_request *req)
 static void ceph_netfs_issue_op(struct netfs_read_subrequest *subreq)
 {
 	struct netfs_read_request *rreq = subreq->rreq;
-	struct inode *inode = rreq->mapping->host;
+	struct inode *inode = rreq->inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
 	struct ceph_osd_request *req;
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index d1faa9d2f1e8..883bb91ee257 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -3543,24 +3543,23 @@ static void handle_cap_grant(struct inode *inode,
 			fill_inline = true;
 	}
 
-	if (ci->i_auth_cap == cap &&
-	    le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT) {
-		if (newcaps & ~extra_info->issued)
-			wake = true;
+	if (le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT) {
+		if (ci->i_auth_cap == cap) {
+			if (newcaps & ~extra_info->issued)
+				wake = true;
+
+			if (ci->i_requested_max_size > max_size ||
+			    !(le32_to_cpu(grant->wanted) & CEPH_CAP_ANY_FILE_WR)) {
+				/* re-request max_size if necessary */
+				ci->i_requested_max_size = 0;
+				wake = true;
+			}
 
-		if (ci->i_requested_max_size > max_size ||
-		    !(le32_to_cpu(grant->wanted) & CEPH_CAP_ANY_FILE_WR)) {
-			/* re-request max_size if necessary */
-			ci->i_requested_max_size = 0;
-			wake = true;
+			ceph_kick_flushing_inode_caps(session, ci);
 		}
-
-		ceph_kick_flushing_inode_caps(session, ci);
-		spin_unlock(&ci->i_ceph_lock);
 		up_read(&session->s_mdsc->snap_rwsem);
-	} else {
-		spin_unlock(&ci->i_ceph_lock);
 	}
+	spin_unlock(&ci->i_ceph_lock);
 
 	if (fill_inline)
 		ceph_fill_inline_data(inode, NULL, extra_info->inline_data,
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 912903de4de4..78d052dc1798 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1196,14 +1196,17 @@ static int encode_supported_features(void **p, void *end)
 	if (count > 0) {
 		size_t i;
 		size_t size = FEATURE_BYTES(count);
+		unsigned long bit;
 
 		if (WARN_ON_ONCE(*p + 4 + size > end))
 			return -ERANGE;
 
 		ceph_encode_32(p, size);
 		memset(*p, 0, size);
-		for (i = 0; i < count; i++)
-			((unsigned char*)(*p))[i / 8] |= BIT(feature_bits[i] % 8);
+		for (i = 0; i < count; i++) {
+			bit = feature_bits[i];
+			((unsigned char *)(*p))[bit / 8] |= BIT(bit % 8);
+		}
 		*p += size;
 	} else {
 		if (WARN_ON_ONCE(*p + 4 > end))
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 97c7f7bfa55f..2667350eb72c 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -33,10 +33,6 @@ enum ceph_feature_type {
 	CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_METRIC_COLLECT,
 };
 
-/*
- * This will always have the highest feature bit value
- * as the last element of the array.
- */
 #define CEPHFS_FEATURES_CLIENT_SUPPORTED {	\
 	0, 1, 2, 3, 4, 5, 6, 7,			\
 	CEPHFS_FEATURE_MIMIC,			\
@@ -45,8 +41,6 @@ enum ceph_feature_type {
 	CEPHFS_FEATURE_MULTI_RECONNECT,		\
 	CEPHFS_FEATURE_DELEG_INO,		\
 	CEPHFS_FEATURE_METRIC_COLLECT,		\
-						\
-	CEPHFS_FEATURE_MAX,			\
 }
 #define CEPHFS_FEATURES_CLIENT_REQUIRED {}
 
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 70da1d27be3d..278634a63895 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -519,9 +519,6 @@ cifs_readv_from_socket(struct TCP_Server_Info *server, struct msghdr *smb_msg)
 	int length = 0;
 	int total_read;
 
-	smb_msg->msg_control = NULL;
-	smb_msg->msg_controllen = 0;
-
 	for (total_read = 0; msg_data_left(smb_msg); total_read += length) {
 		try_to_freeze();
 
@@ -572,7 +569,7 @@ int
 cifs_read_from_socket(struct TCP_Server_Info *server, char *buf,
 		      unsigned int to_read)
 {
-	struct msghdr smb_msg;
+	struct msghdr smb_msg = {};
 	struct kvec iov = {.iov_base = buf, .iov_len = to_read};
 	iov_iter_kvec(&smb_msg.msg_iter, READ, &iov, 1, to_read);
 
@@ -582,15 +579,13 @@ cifs_read_from_socket(struct TCP_Server_Info *server, char *buf,
 ssize_t
 cifs_discard_from_socket(struct TCP_Server_Info *server, size_t to_read)
 {
-	struct msghdr smb_msg;
+	struct msghdr smb_msg = {};
 
 	/*
 	 *  iov_iter_discard already sets smb_msg.type and count and iov_offset
 	 *  and cifs_readv_from_socket sets msg_control and msg_controllen
 	 *  so little to initialize in struct msghdr
 	 */
-	smb_msg.msg_name = NULL;
-	smb_msg.msg_namelen = 0;
 	iov_iter_discard(&smb_msg.msg_iter, READ, to_read);
 
 	return cifs_readv_from_socket(server, &smb_msg);
@@ -600,7 +595,7 @@ int
 cifs_read_page_from_socket(struct TCP_Server_Info *server, struct page *page,
 	unsigned int page_offset, unsigned int to_read)
 {
-	struct msghdr smb_msg;
+	struct msghdr smb_msg = {};
 	struct bio_vec bv = {
 		.bv_page = page, .bv_len = to_read, .bv_offset = page_offset};
 	iov_iter_bvec(&smb_msg.msg_iter, READ, &bv, 1, to_read);
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index b23f6b489bb9..2ef57bc054d2 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -3318,6 +3318,9 @@ static ssize_t __cifs_writev(
 
 ssize_t cifs_direct_writev(struct kiocb *iocb, struct iov_iter *from)
 {
+	struct file *file = iocb->ki_filp;
+
+	cifs_revalidate_mapping(file->f_inode);
 	return __cifs_writev(iocb, from, true);
 }
 
@@ -4855,8 +4858,6 @@ void cifs_oplock_break(struct work_struct *work)
 	struct TCP_Server_Info *server = tcon->ses->server;
 	int rc = 0;
 	bool purge_cache = false;
-	bool is_deferred = false;
-	struct cifs_deferred_close *dclose;
 
 	wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS,
 			TASK_UNINTERRUPTIBLE);
@@ -4893,22 +4894,6 @@ void cifs_oplock_break(struct work_struct *work)
 
 oplock_break_ack:
 	/*
-	 * When oplock break is received and there are no active
-	 * file handles but cached, then schedule deferred close immediately.
-	 * So, new open will not use cached handle.
-	 */
-	spin_lock(&CIFS_I(inode)->deferred_lock);
-	is_deferred = cifs_is_deferred_close(cfile, &dclose);
-	spin_unlock(&CIFS_I(inode)->deferred_lock);
-	if (is_deferred &&
-	    cfile->deferred_close_scheduled &&
-	    delayed_work_pending(&cfile->deferred)) {
-		if (cancel_delayed_work(&cfile->deferred)) {
-			_cifsFileInfo_put(cfile, false, false);
-			goto oplock_break_done;
-		}
-	}
-	/*
 	 * releasing stale oplock after recent reconnect of smb session using
 	 * a now incorrect file handle is not a data integrity issue but do
 	 * not bother sending an oplock release if session to server still is
@@ -4919,7 +4904,7 @@ oplock_break_ack:
 							     cinode);
 		cifs_dbg(FYI, "Oplock release rc = %d\n", rc);
 	}
-oplock_break_done:
+
 	_cifsFileInfo_put(cfile, false /* do not wait for ourself */, false);
 	cifs_done_oplock_break(cinode);
 }
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 5906f7f140eb..699f676ded47 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -736,6 +736,8 @@ cifs_close_deferred_file(struct cifsInodeInfo *cifs_inode)
 	list_for_each_entry(cfile, &cifs_inode->openFileList, flist) {
 		if (delayed_work_pending(&cfile->deferred)) {
 			if (cancel_delayed_work(&cfile->deferred)) {
+				cifs_del_deferred_close(cfile);
+
 				tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC);
 				if (tmp_list == NULL)
 					break;
@@ -767,6 +769,8 @@ cifs_close_all_deferred_files(struct cifs_tcon *tcon)
 		cfile = list_entry(tmp, struct cifsFileInfo, tlist);
 		if (delayed_work_pending(&cfile->deferred)) {
 			if (cancel_delayed_work(&cfile->deferred)) {
+				cifs_del_deferred_close(cfile);
+
 				tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC);
 				if (tmp_list == NULL)
 					break;
@@ -802,6 +806,8 @@ cifs_close_deferred_file_under_dentry(struct cifs_tcon *tcon, const char *path)
 		if (strstr(full_path, path)) {
 			if (delayed_work_pending(&cfile->deferred)) {
 				if (cancel_delayed_work(&cfile->deferred)) {
+					cifs_del_deferred_close(cfile);
+
 					tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC);
 					if (tmp_list == NULL)
 						break;
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 735aafee63be..2d31860d56e9 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -1105,9 +1105,7 @@ move_smb2_ea_to_cifs(char *dst, size_t dst_size,
 	size_t name_len, value_len, user_name_len;
 
 	while (src_size > 0) {
-		name = &src->ea_data[0];
 		name_len = (size_t)src->ea_name_length;
-		value = &src->ea_data[src->ea_name_length + 1];
 		value_len = (size_t)le16_to_cpu(src->ea_value_length);
 
 		if (name_len == 0)
@@ -1119,6 +1117,9 @@ move_smb2_ea_to_cifs(char *dst, size_t dst_size,
 			goto out;
 		}
 
+		name = &src->ea_data[0];
+		value = &src->ea_data[src->ea_name_length + 1];
+
 		if (ea_name) {
 			if (ea_name_len == name_len &&
 			    memcmp(ea_name, name, name_len) == 0) {
@@ -3598,7 +3599,7 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
 static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon,
 			    loff_t offset, loff_t len)
 {
-	struct inode *inode;
+	struct inode *inode = file_inode(file);
 	struct cifsFileInfo *cfile = file->private_data;
 	struct file_zero_data_information fsctl_buf;
 	long rc;
@@ -3607,14 +3608,12 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon,
 
 	xid = get_xid();
 
-	inode = d_inode(cfile->dentry);
-
+	inode_lock(inode);
 	/* Need to make file sparse, if not already, before freeing range. */
 	/* Consider adding equivalent for compressed since it could also work */
 	if (!smb2_set_sparse(xid, tcon, cfile, inode, set_sparse)) {
 		rc = -EOPNOTSUPP;
-		free_xid(xid);
-		return rc;
+		goto out;
 	}
 
 	filemap_invalidate_lock(inode->i_mapping);
@@ -3634,8 +3633,10 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon,
 			true /* is_fctl */, (char *)&fsctl_buf,
 			sizeof(struct file_zero_data_information),
 			CIFSMaxBufSize, NULL, NULL);
-	free_xid(xid);
 	filemap_invalidate_unlock(inode->i_mapping);
+out:
+	inode_unlock(inode);
+	free_xid(xid);
 	return rc;
 }
 
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 49ba3617db59..a423d1403539 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -933,16 +933,17 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 	} else if (rc != 0)
 		goto neg_exit;
 
+	rc = -EIO;
 	if (strcmp(server->vals->version_string,
 		   SMB3ANY_VERSION_STRING) == 0) {
 		if (rsp->DialectRevision == cpu_to_le16(SMB20_PROT_ID)) {
 			cifs_server_dbg(VFS,
 				"SMB2 dialect returned but not requested\n");
-			return -EIO;
+			goto neg_exit;
 		} else if (rsp->DialectRevision == cpu_to_le16(SMB21_PROT_ID)) {
 			cifs_server_dbg(VFS,
 				"SMB2.1 dialect returned but not requested\n");
-			return -EIO;
+			goto neg_exit;
 		} else if (rsp->DialectRevision == cpu_to_le16(SMB311_PROT_ID)) {
 			/* ops set to 3.0 by default for default so update */
 			server->ops = &smb311_operations;
@@ -953,7 +954,7 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 		if (rsp->DialectRevision == cpu_to_le16(SMB20_PROT_ID)) {
 			cifs_server_dbg(VFS,
 				"SMB2 dialect returned but not requested\n");
-			return -EIO;
+			goto neg_exit;
 		} else if (rsp->DialectRevision == cpu_to_le16(SMB21_PROT_ID)) {
 			/* ops set to 3.0 by default for default so update */
 			server->ops = &smb21_operations;
@@ -967,7 +968,7 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 		/* if requested single dialect ensure returned dialect matched */
 		cifs_server_dbg(VFS, "Invalid 0x%x dialect returned: not requested\n",
 				le16_to_cpu(rsp->DialectRevision));
-		return -EIO;
+		goto neg_exit;
 	}
 
 	cifs_dbg(FYI, "mode 0x%x\n", rsp->SecurityMode);
@@ -985,9 +986,10 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 	else {
 		cifs_server_dbg(VFS, "Invalid dialect returned by server 0x%x\n",
 				le16_to_cpu(rsp->DialectRevision));
-		rc = -EIO;
 		goto neg_exit;
 	}
+
+	rc = 0;
 	server->dialect = le16_to_cpu(rsp->DialectRevision);
 
 	/*
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 61ea3d3f95b4..514056605fa7 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -196,10 +196,6 @@ smb_send_kvec(struct TCP_Server_Info *server, struct msghdr *smb_msg,
 
 	*sent = 0;
 
-	smb_msg->msg_name = (struct sockaddr *) &server->dstaddr;
-	smb_msg->msg_namelen = sizeof(struct sockaddr);
-	smb_msg->msg_control = NULL;
-	smb_msg->msg_controllen = 0;
 	if (server->noblocksnd)
 		smb_msg->msg_flags = MSG_DONTWAIT + MSG_NOSIGNAL;
 	else
@@ -311,7 +307,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst,
 	sigset_t mask, oldmask;
 	size_t total_len = 0, sent, size;
 	struct socket *ssocket = server->ssocket;
-	struct msghdr smb_msg;
+	struct msghdr smb_msg = {};
 	__be32 rfc1002_marker;
 
 	if (cifs_rdma_enabled(server)) {
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 2f117c57160d..26f9cd328291 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -735,6 +735,28 @@ void debugfs_remove(struct dentry *dentry)
 EXPORT_SYMBOL_GPL(debugfs_remove);
 
 /**
+ * debugfs_lookup_and_remove - lookup a directory or file and recursively remove it
+ * @name: a pointer to a string containing the name of the item to look up.
+ * @parent: a pointer to the parent dentry of the item.
+ *
+ * This is the equlivant of doing something like
+ * debugfs_remove(debugfs_lookup(..)) but with the proper reference counting
+ * handled for the directory being looked up.
+ */
+void debugfs_lookup_and_remove(const char *name, struct dentry *parent)
+{
+	struct dentry *dentry;
+
+	dentry = debugfs_lookup(name, parent);
+	if (!dentry)
+		return;
+
+	debugfs_remove(dentry);
+	dput(dentry);
+}
+EXPORT_SYMBOL_GPL(debugfs_lookup_and_remove);
+
+/**
  * debugfs_rename - rename a file/directory in the debugfs filesystem
  * @old_dir: a pointer to the parent dentry for the renamed object. This
  *          should be a directory dentry.
diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c
index bb9e85e8819c..9f93496d2cc9 100644
--- a/fs/dlm/lock.c
+++ b/fs/dlm/lock.c
@@ -4065,13 +4065,14 @@ static void send_repeat_remove(struct dlm_ls *ls, char *ms_name, int len)
 	rv = _create_message(ls, sizeof(struct dlm_message) + len,
 			     dir_nodeid, DLM_MSG_REMOVE, &ms, &mh);
 	if (rv)
-		return;
+		goto out;
 
 	memcpy(ms->m_extra, name, len);
 	ms->m_hash = hash;
 
 	send_message(mh, ms);
 
+out:
 	spin_lock(&ls->ls_remove_spin);
 	ls->ls_remove_len = 0;
 	memset(ls->ls_remove_name, 0, DLM_RESNAME_MAXLEN);
diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c
index ad3f31380e6b..8193c14bb111 100644
--- a/fs/erofs/decompressor.c
+++ b/fs/erofs/decompressor.c
@@ -93,14 +93,18 @@ static int z_erofs_lz4_prepare_destpages(struct z_erofs_decompress_req *rq,
 
 		if (page) {
 			__clear_bit(j, bounced);
-			if (kaddr) {
-				if (kaddr + PAGE_SIZE == page_address(page))
+			if (!PageHighMem(page)) {
+				if (!i) {
+					kaddr = page_address(page);
+					continue;
+				}
+				if (kaddr &&
+				    kaddr + PAGE_SIZE == page_address(page)) {
 					kaddr += PAGE_SIZE;
-				else
-					kaddr = NULL;
-			} else if (!i) {
-				kaddr = page_address(page);
+					continue;
+				}
 			}
+			kaddr = NULL;
 			continue;
 		}
 		kaddr = NULL;
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index 9524e155b38f..b77acf09726c 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -143,7 +143,6 @@ struct erofs_workgroup {
 	atomic_t refcount;
 };
 
-#if defined(CONFIG_SMP)
 static inline bool erofs_workgroup_try_to_freeze(struct erofs_workgroup *grp,
 						 int val)
 {
@@ -172,34 +171,6 @@ static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp)
 	return atomic_cond_read_relaxed(&grp->refcount,
 					VAL != EROFS_LOCKED_MAGIC);
 }
-#else
-static inline bool erofs_workgroup_try_to_freeze(struct erofs_workgroup *grp,
-						 int val)
-{
-	preempt_disable();
-	/* no need to spin on UP platforms, let's just disable preemption. */
-	if (val != atomic_read(&grp->refcount)) {
-		preempt_enable();
-		return false;
-	}
-	return true;
-}
-
-static inline void erofs_workgroup_unfreeze(struct erofs_workgroup *grp,
-					    int orig_val)
-{
-	preempt_enable();
-}
-
-static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp)
-{
-	int v = atomic_read(&grp->refcount);
-
-	/* workgroup is never freezed on uniprocessor systems */
-	DBG_BUGON(v == EROFS_LOCKED_MAGIC);
-	return v;
-}
-#endif	/* !CONFIG_SMP */
 #endif	/* !CONFIG_EROFS_FS_ZIP */
 
 /* we strictly follow PAGE_SIZE and no buffer head yet */
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 06f4c5ae1451..cf326c53db0f 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1740,6 +1740,21 @@ static struct timespec64 *ep_timeout_to_timespec(struct timespec64 *to, long ms)
 	return to;
 }
 
+/*
+ * autoremove_wake_function, but remove even on failure to wake up, because we
+ * know that default_wake_function/ttwu will only fail if the thread is already
+ * woken, and in that case the ep_poll loop will remove the entry anyways, not
+ * try to reuse it.
+ */
+static int ep_autoremove_wake_function(struct wait_queue_entry *wq_entry,
+				       unsigned int mode, int sync, void *key)
+{
+	int ret = default_wake_function(wq_entry, mode, sync, key);
+
+	list_del_init(&wq_entry->entry);
+	return ret;
+}
+
 /**
  * ep_poll - Retrieves ready events, and delivers them to the caller-supplied
  *           event buffer.
@@ -1821,8 +1836,15 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 		 * normal wakeup path no need to call __remove_wait_queue()
 		 * explicitly, thus ep->lock is not taken, which halts the
 		 * event delivery.
+		 *
+		 * In fact, we now use an even more aggressive function that
+		 * unconditionally removes, because we don't reuse the wait
+		 * entry between loop iterations. This lets us also avoid the
+		 * performance issue if a process is killed, causing all of its
+		 * threads to wake up without being removed normally.
 		 */
 		init_wait(&wait);
+		wait.func = ep_autoremove_wake_function;
 
 		write_lock_irq(&ep->lock);
 		/*
diff --git a/fs/exec.c b/fs/exec.c
index 29e865c59854..7d424337b4ec 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1298,7 +1298,10 @@ int begin_new_exec(struct linux_binprm * bprm)
 	bprm->mm = NULL;
 
 #ifdef CONFIG_POSIX_TIMERS
-	exit_itimers(me->signal);
+	spin_lock_irq(&me->sighand->siglock);
+	posix_cpu_timers_exit(me);
+	spin_unlock_irq(&me->sighand->siglock);
+	exit_itimers(me);
 	flush_itimer_signals();
 #endif
 
diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c
index 9d8ada781250..8a7f4c0830f3 100644
--- a/fs/exfat/namei.c
+++ b/fs/exfat/namei.c
@@ -1069,6 +1069,7 @@ static int exfat_rename_file(struct inode *inode, struct exfat_chain *p_dir,
 
 		exfat_remove_entries(inode, p_dir, oldentry, 0,
 			num_old_entries);
+		ei->dir = *p_dir;
 		ei->entry = newentry;
 	} else {
 		if (exfat_get_entry_type(epold) == TYPE_FILE) {
@@ -1159,28 +1160,6 @@ static int exfat_move_file(struct inode *inode, struct exfat_chain *p_olddir,
 	return 0;
 }
 
-static void exfat_update_parent_info(struct exfat_inode_info *ei,
-		struct inode *parent_inode)
-{
-	struct exfat_sb_info *sbi = EXFAT_SB(parent_inode->i_sb);
-	struct exfat_inode_info *parent_ei = EXFAT_I(parent_inode);
-	loff_t parent_isize = i_size_read(parent_inode);
-
-	/*
-	 * the problem that struct exfat_inode_info caches wrong parent info.
-	 *
-	 * because of flag-mismatch of ei->dir,
-	 * there is abnormal traversing cluster chain.
-	 */
-	if (unlikely(parent_ei->flags != ei->dir.flags ||
-		     parent_isize != EXFAT_CLU_TO_B(ei->dir.size, sbi) ||
-		     parent_ei->start_clu != ei->dir.dir)) {
-		exfat_chain_set(&ei->dir, parent_ei->start_clu,
-			EXFAT_B_TO_CLU_ROUND_UP(parent_isize, sbi),
-			parent_ei->flags);
-	}
-}
-
 /* rename or move a old file into a new file */
 static int __exfat_rename(struct inode *old_parent_inode,
 		struct exfat_inode_info *ei, struct inode *new_parent_inode,
@@ -1211,9 +1190,9 @@ static int __exfat_rename(struct inode *old_parent_inode,
 		return -ENOENT;
 	}
 
-	exfat_update_parent_info(ei, old_parent_inode);
-
-	exfat_chain_dup(&olddir, &ei->dir);
+	exfat_chain_set(&olddir, EXFAT_I(old_parent_inode)->start_clu,
+		EXFAT_B_TO_CLU_ROUND_UP(i_size_read(old_parent_inode), sbi),
+		EXFAT_I(old_parent_inode)->flags);
 	dentry = ei->entry;
 
 	ep = exfat_get_dentry(sb, &olddir, dentry, &old_bh, NULL);
@@ -1233,8 +1212,6 @@ static int __exfat_rename(struct inode *old_parent_inode,
 			goto out;
 		}
 
-		exfat_update_parent_info(new_ei, new_parent_inode);
-
 		p_dir = &(new_ei->dir);
 		new_entry = new_ei->entry;
 		ep = exfat_get_dentry(sb, p_dir, new_entry, &new_bh, NULL);
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 3d21279fe2cb..fd855574ef09 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -1058,9 +1058,10 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 			sbi->s_frags_per_group);
 		goto failed_mount;
 	}
-	if (sbi->s_inodes_per_group > sb->s_blocksize * 8) {
+	if (sbi->s_inodes_per_group < sbi->s_inodes_per_block ||
+	    sbi->s_inodes_per_group > sb->s_blocksize * 8) {
 		ext2_msg(sb, KERN_ERR,
-			"error: #inodes per group too big: %lu",
+			"error: invalid #inodes per group: %lu",
 			sbi->s_inodes_per_group);
 		goto failed_mount;
 	}
@@ -1070,6 +1071,13 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_groups_count = ((le32_to_cpu(es->s_blocks_count) -
 				le32_to_cpu(es->s_first_data_block) - 1)
 					/ EXT2_BLOCKS_PER_GROUP(sb)) + 1;
+	if ((u64)sbi->s_groups_count * sbi->s_inodes_per_group !=
+	    le32_to_cpu(es->s_inodes_count)) {
+		ext2_msg(sb, KERN_ERR, "error: invalid #inodes: %u vs computed %llu",
+			 le32_to_cpu(es->s_inodes_count),
+			 (u64)sbi->s_groups_count * sbi->s_inodes_per_group);
+		goto failed_mount;
+	}
 	db_count = (sbi->s_groups_count + EXT2_DESC_PER_BLOCK(sb) - 1) /
 		   EXT2_DESC_PER_BLOCK(sb);
 	sbi->s_group_desc = kmalloc_array(db_count,
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 28bc431cf5ba..38ad09e802e4 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -35,6 +35,9 @@ static int get_max_inline_xattr_value_size(struct inode *inode,
 	struct ext4_inode *raw_inode;
 	int free, min_offs;
 
+	if (!EXT4_INODE_HAS_XATTR_SPACE(inode))
+		return 0;
+
 	min_offs = EXT4_SB(inode->i_sb)->s_inode_size -
 			EXT4_GOOD_OLD_INODE_SIZE -
 			EXT4_I(inode)->i_extra_isize -
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index f0350d60ba50..98f381f6fc18 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -179,6 +179,8 @@ void ext4_evict_inode(struct inode *inode)
 
 	trace_ext4_evict_inode(inode);
 
+	if (EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)
+		ext4_evict_ea_inode(inode);
 	if (inode->i_nlink) {
 		/*
 		 * When journalling data dirty buffers are tracked only in the
@@ -1560,7 +1562,14 @@ static void mpage_release_unused_pages(struct mpage_da_data *mpd,
 		ext4_lblk_t start, last;
 		start = index << (PAGE_SHIFT - inode->i_blkbits);
 		last = end << (PAGE_SHIFT - inode->i_blkbits);
+
+		/*
+		 * avoid racing with extent status tree scans made by
+		 * ext4_insert_delayed_block()
+		 */
+		down_write(&EXT4_I(inode)->i_data_sem);
 		ext4_es_remove_extent(inode, start, last - start + 1);
+		up_write(&EXT4_I(inode)->i_data_sem);
 	}
 
 	pagevec_init(&pvec);
@@ -3130,13 +3139,15 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block)
 {
 	struct inode *inode = mapping->host;
 	journal_t *journal;
+	sector_t ret = 0;
 	int err;
 
+	inode_lock_shared(inode);
 	/*
 	 * We can get here for an inline file via the FIBMAP ioctl
 	 */
 	if (ext4_has_inline_data(inode))
-		return 0;
+		goto out;
 
 	if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) &&
 			test_opt(inode->i_sb, DELALLOC)) {
@@ -3175,10 +3186,14 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block)
 		jbd2_journal_unlock_updates(journal);
 
 		if (err)
-			return 0;
+			goto out;
 	}
 
-	return iomap_bmap(mapping, block, &ext4_iomap_ops);
+	ret = iomap_bmap(mapping, block, &ext4_iomap_ops);
+
+out:
+	inode_unlock_shared(inode);
+	return ret;
 }
 
 static int ext4_readpage(struct file *file, struct page *page)
@@ -4509,8 +4524,7 @@ static inline int ext4_iget_extra_inode(struct inode *inode,
 	__le32 *magic = (void *)raw_inode +
 			EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize;
 
-	if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize + sizeof(__le32) <=
-	    EXT4_INODE_SIZE(inode->i_sb) &&
+	if (EXT4_INODE_HAS_XATTR_SPACE(inode)  &&
 	    *magic == cpu_to_le32(EXT4_XATTR_MAGIC)) {
 		ext4_set_inode_state(inode, EXT4_STATE_XATTR);
 		return ext4_find_inline_data_nolock(inode);
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index ff8916e1d38e..af5a75a89e6e 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -417,7 +417,7 @@ int ext4_ext_migrate(struct inode *inode)
 	struct inode *tmp_inode = NULL;
 	struct migrate_struct lb;
 	unsigned long max_entries;
-	__u32 goal;
+	__u32 goal, tmp_csum_seed;
 	uid_t owner[2];
 
 	/*
@@ -465,6 +465,7 @@ int ext4_ext_migrate(struct inode *inode)
 	 * the migration.
 	 */
 	ei = EXT4_I(inode);
+	tmp_csum_seed = EXT4_I(tmp_inode)->i_csum_seed;
 	EXT4_I(tmp_inode)->i_csum_seed = ei->i_csum_seed;
 	i_size_write(tmp_inode, i_size_read(inode));
 	/*
@@ -575,6 +576,7 @@ err_out:
 	 * the inode is not visible to user space.
 	 */
 	tmp_inode->i_blocks = 0;
+	EXT4_I(tmp_inode)->i_csum_seed = tmp_csum_seed;
 
 	/* Reset the extent details */
 	ext4_ext_tree_init(handle, tmp_inode);
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 871eebf12bf4..7d3ec39121f7 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -54,6 +54,7 @@ static struct buffer_head *ext4_append(handle_t *handle,
 					struct inode *inode,
 					ext4_lblk_t *block)
 {
+	struct ext4_map_blocks map;
 	struct buffer_head *bh;
 	int err;
 
@@ -63,6 +64,21 @@ static struct buffer_head *ext4_append(handle_t *handle,
 		return ERR_PTR(-ENOSPC);
 
 	*block = inode->i_size >> inode->i_sb->s_blocksize_bits;
+	map.m_lblk = *block;
+	map.m_len = 1;
+
+	/*
+	 * We're appending new directory block. Make sure the block is not
+	 * allocated yet, otherwise we will end up corrupting the
+	 * directory.
+	 */
+	err = ext4_map_blocks(NULL, inode, &map, 0);
+	if (err < 0)
+		return ERR_PTR(err);
+	if (err) {
+		EXT4_ERROR_INODE(inode, "Logical block already allocated");
+		return ERR_PTR(-EFSCORRUPTED);
+	}
 
 	bh = ext4_bread(handle, inode, *block, EXT4_GET_BLOCKS_CREATE);
 	if (IS_ERR(bh))
@@ -110,6 +126,13 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode,
 	struct ext4_dir_entry *dirent;
 	int is_dx_block = 0;
 
+	if (block >= inode->i_size) {
+		ext4_error_inode(inode, func, line, block,
+		       "Attempting to read directory block (%u) that is past i_size (%llu)",
+		       block, inode->i_size);
+		return ERR_PTR(-EFSCORRUPTED);
+	}
+
 	if (ext4_simulate_fail(inode->i_sb, EXT4_SIM_DIRBLOCK_EIO))
 		bh = ERR_PTR(-EIO);
 	else
@@ -3067,11 +3090,8 @@ bool ext4_empty_dir(struct inode *inode)
 		de = (struct ext4_dir_entry_2 *) (bh->b_data +
 					(offset & (sb->s_blocksize - 1)));
 		if (ext4_check_dir_entry(inode, NULL, de, bh,
-					 bh->b_data, bh->b_size, offset)) {
-			offset = (offset | (sb->s_blocksize - 1)) + 1;
-			continue;
-		}
-		if (le32_to_cpu(de->inode)) {
+					 bh->b_data, bh->b_size, offset) ||
+		    le32_to_cpu(de->inode)) {
 			brelse(bh);
 			return false;
 		}
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 56c9ef0687fc..862cbbc01d6e 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -1472,6 +1472,7 @@ static void ext4_update_super(struct super_block *sb,
 	 * Update the fs overhead information
 	 */
 	ext4_calculate_overhead(sb);
+	es->s_overhead_clusters = cpu_to_le32(sbi->s_overhead);
 
 	if (test_opt(sb, DEBUG))
 		printk(KERN_DEBUG "EXT4-fs: added group %u:"
@@ -1976,6 +1977,16 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count)
 	}
 	brelse(bh);
 
+	/*
+	 * For bigalloc, trim the requested size to the nearest cluster
+	 * boundary to avoid creating an unusable filesystem. We do this
+	 * silently, instead of returning an error, to avoid breaking
+	 * callers that blindly resize the filesystem to the full size of
+	 * the underlying block device.
+	 */
+	if (ext4_has_feature_bigalloc(sb))
+		n_blocks_count &= ~((1 << EXT4_CLUSTER_BITS(sb)) - 1);
+
 retry:
 	o_blocks_count = ext4_blocks_count(es);
 
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 042325349098..533216e80fa2 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -436,6 +436,21 @@ error:
 	return err;
 }
 
+/* Remove entry from mbcache when EA inode is getting evicted */
+void ext4_evict_ea_inode(struct inode *inode)
+{
+	struct mb_cache_entry *oe;
+
+	if (!EA_INODE_CACHE(inode))
+		return;
+	/* Wait for entry to get unused so that we can remove it */
+	while ((oe = mb_cache_entry_delete_or_get(EA_INODE_CACHE(inode),
+			ext4_xattr_inode_get_hash(inode), inode->i_ino))) {
+		mb_cache_entry_wait_unused(oe);
+		mb_cache_entry_put(EA_INODE_CACHE(inode), oe);
+	}
+}
+
 static int
 ext4_xattr_inode_verify_hashes(struct inode *ea_inode,
 			       struct ext4_xattr_entry *entry, void *buffer,
@@ -976,10 +991,8 @@ int __ext4_xattr_set_credits(struct super_block *sb, struct inode *inode,
 static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode,
 				       int ref_change)
 {
-	struct mb_cache *ea_inode_cache = EA_INODE_CACHE(ea_inode);
 	struct ext4_iloc iloc;
 	s64 ref_count;
-	u32 hash;
 	int ret;
 
 	inode_lock(ea_inode);
@@ -1002,14 +1015,6 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode,
 
 			set_nlink(ea_inode, 1);
 			ext4_orphan_del(handle, ea_inode);
-
-			if (ea_inode_cache) {
-				hash = ext4_xattr_inode_get_hash(ea_inode);
-				mb_cache_entry_create(ea_inode_cache,
-						      GFP_NOFS, hash,
-						      ea_inode->i_ino,
-						      true /* reusable */);
-			}
 		}
 	} else {
 		WARN_ONCE(ref_count < 0, "EA inode %lu ref_count=%lld",
@@ -1022,12 +1027,6 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode,
 
 			clear_nlink(ea_inode);
 			ext4_orphan_add(handle, ea_inode);
-
-			if (ea_inode_cache) {
-				hash = ext4_xattr_inode_get_hash(ea_inode);
-				mb_cache_entry_delete(ea_inode_cache, hash,
-						      ea_inode->i_ino);
-			}
 		}
 	}
 
@@ -1237,6 +1236,7 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
 	if (error)
 		goto out;
 
+retry_ref:
 	lock_buffer(bh);
 	hash = le32_to_cpu(BHDR(bh)->h_hash);
 	ref = le32_to_cpu(BHDR(bh)->h_refcount);
@@ -1246,9 +1246,18 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
 		 * This must happen under buffer lock for
 		 * ext4_xattr_block_set() to reliably detect freed block
 		 */
-		if (ea_block_cache)
-			mb_cache_entry_delete(ea_block_cache, hash,
-					      bh->b_blocknr);
+		if (ea_block_cache) {
+			struct mb_cache_entry *oe;
+
+			oe = mb_cache_entry_delete_or_get(ea_block_cache, hash,
+							  bh->b_blocknr);
+			if (oe) {
+				unlock_buffer(bh);
+				mb_cache_entry_wait_unused(oe);
+				mb_cache_entry_put(ea_block_cache, oe);
+				goto retry_ref;
+			}
+		}
 		get_bh(bh);
 		unlock_buffer(bh);
 
@@ -1858,6 +1867,8 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 #define header(x) ((struct ext4_xattr_header *)(x))
 
 	if (s->base) {
+		int offset = (char *)s->here - bs->bh->b_data;
+
 		BUFFER_TRACE(bs->bh, "get_write_access");
 		error = ext4_journal_get_write_access(handle, sb, bs->bh,
 						      EXT4_JTR_NONE);
@@ -1873,9 +1884,20 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 			 * ext4_xattr_block_set() to reliably detect modified
 			 * block
 			 */
-			if (ea_block_cache)
-				mb_cache_entry_delete(ea_block_cache, hash,
-						      bs->bh->b_blocknr);
+			if (ea_block_cache) {
+				struct mb_cache_entry *oe;
+
+				oe = mb_cache_entry_delete_or_get(ea_block_cache,
+					hash, bs->bh->b_blocknr);
+				if (oe) {
+					/*
+					 * Xattr block is getting reused. Leave
+					 * it alone.
+					 */
+					mb_cache_entry_put(ea_block_cache, oe);
+					goto clone_block;
+				}
+			}
 			ea_bdebug(bs->bh, "modifying in-place");
 			error = ext4_xattr_set_entry(i, s, handle, inode,
 						     true /* is_block */);
@@ -1890,50 +1912,47 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 			if (error)
 				goto cleanup;
 			goto inserted;
-		} else {
-			int offset = (char *)s->here - bs->bh->b_data;
+		}
+clone_block:
+		unlock_buffer(bs->bh);
+		ea_bdebug(bs->bh, "cloning");
+		s->base = kmemdup(BHDR(bs->bh), bs->bh->b_size, GFP_NOFS);
+		error = -ENOMEM;
+		if (s->base == NULL)
+			goto cleanup;
+		s->first = ENTRY(header(s->base)+1);
+		header(s->base)->h_refcount = cpu_to_le32(1);
+		s->here = ENTRY(s->base + offset);
+		s->end = s->base + bs->bh->b_size;
 
-			unlock_buffer(bs->bh);
-			ea_bdebug(bs->bh, "cloning");
-			s->base = kmalloc(bs->bh->b_size, GFP_NOFS);
-			error = -ENOMEM;
-			if (s->base == NULL)
+		/*
+		 * If existing entry points to an xattr inode, we need
+		 * to prevent ext4_xattr_set_entry() from decrementing
+		 * ref count on it because the reference belongs to the
+		 * original block. In this case, make the entry look
+		 * like it has an empty value.
+		 */
+		if (!s->not_found && s->here->e_value_inum) {
+			ea_ino = le32_to_cpu(s->here->e_value_inum);
+			error = ext4_xattr_inode_iget(inode, ea_ino,
+				      le32_to_cpu(s->here->e_hash),
+				      &tmp_inode);
+			if (error)
 				goto cleanup;
-			memcpy(s->base, BHDR(bs->bh), bs->bh->b_size);
-			s->first = ENTRY(header(s->base)+1);
-			header(s->base)->h_refcount = cpu_to_le32(1);
-			s->here = ENTRY(s->base + offset);
-			s->end = s->base + bs->bh->b_size;
-
-			/*
-			 * If existing entry points to an xattr inode, we need
-			 * to prevent ext4_xattr_set_entry() from decrementing
-			 * ref count on it because the reference belongs to the
-			 * original block. In this case, make the entry look
-			 * like it has an empty value.
-			 */
-			if (!s->not_found && s->here->e_value_inum) {
-				ea_ino = le32_to_cpu(s->here->e_value_inum);
-				error = ext4_xattr_inode_iget(inode, ea_ino,
-					      le32_to_cpu(s->here->e_hash),
-					      &tmp_inode);
-				if (error)
-					goto cleanup;
-
-				if (!ext4_test_inode_state(tmp_inode,
-						EXT4_STATE_LUSTRE_EA_INODE)) {
-					/*
-					 * Defer quota free call for previous
-					 * inode until success is guaranteed.
-					 */
-					old_ea_inode_quota = le32_to_cpu(
-							s->here->e_value_size);
-				}
-				iput(tmp_inode);
 
-				s->here->e_value_inum = 0;
-				s->here->e_value_size = 0;
+			if (!ext4_test_inode_state(tmp_inode,
+					EXT4_STATE_LUSTRE_EA_INODE)) {
+				/*
+				 * Defer quota free call for previous
+				 * inode until success is guaranteed.
+				 */
+				old_ea_inode_quota = le32_to_cpu(
+						s->here->e_value_size);
 			}
+			iput(tmp_inode);
+
+			s->here->e_value_inum = 0;
+			s->here->e_value_size = 0;
 		}
 	} else {
 		/* Allocate a buffer where we construct the new block. */
@@ -2000,18 +2019,13 @@ inserted:
 				lock_buffer(new_bh);
 				/*
 				 * We have to be careful about races with
-				 * freeing, rehashing or adding references to
-				 * xattr block. Once we hold buffer lock xattr
-				 * block's state is stable so we can check
-				 * whether the block got freed / rehashed or
-				 * not.  Since we unhash mbcache entry under
-				 * buffer lock when freeing / rehashing xattr
-				 * block, checking whether entry is still
-				 * hashed is reliable. Same rules hold for
-				 * e_reusable handling.
+				 * adding references to xattr block. Once we
+				 * hold buffer lock xattr block's state is
+				 * stable so we can check the additional
+				 * reference fits.
 				 */
-				if (hlist_bl_unhashed(&ce->e_hash_list) ||
-				    !ce->e_reusable) {
+				ref = le32_to_cpu(BHDR(new_bh)->h_refcount) + 1;
+				if (ref > EXT4_XATTR_REFCOUNT_MAX) {
 					/*
 					 * Undo everything and check mbcache
 					 * again.
@@ -2026,9 +2040,8 @@ inserted:
 					new_bh = NULL;
 					goto inserted;
 				}
-				ref = le32_to_cpu(BHDR(new_bh)->h_refcount) + 1;
 				BHDR(new_bh)->h_refcount = cpu_to_le32(ref);
-				if (ref >= EXT4_XATTR_REFCOUNT_MAX)
+				if (ref == EXT4_XATTR_REFCOUNT_MAX)
 					ce->e_reusable = 0;
 				ea_bdebug(new_bh, "reusing; refcount now=%d",
 					  ref);
@@ -2176,8 +2189,9 @@ int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i,
 	struct ext4_inode *raw_inode;
 	int error;
 
-	if (EXT4_I(inode)->i_extra_isize == 0)
+	if (!EXT4_INODE_HAS_XATTR_SPACE(inode))
 		return 0;
+
 	raw_inode = ext4_raw_inode(&is->iloc);
 	header = IHDR(inode, raw_inode);
 	is->s.base = is->s.first = IFIRST(header);
@@ -2205,8 +2219,9 @@ int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode,
 	struct ext4_xattr_search *s = &is->s;
 	int error;
 
-	if (EXT4_I(inode)->i_extra_isize == 0)
+	if (!EXT4_INODE_HAS_XATTR_SPACE(inode))
 		return -ENOSPC;
+
 	error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */);
 	if (error)
 		return error;
diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h
index 77efb9a627ad..e5e36bd11f05 100644
--- a/fs/ext4/xattr.h
+++ b/fs/ext4/xattr.h
@@ -95,6 +95,19 @@ struct ext4_xattr_entry {
 
 #define EXT4_ZERO_XATTR_VALUE ((void *)-1)
 
+/*
+ * If we want to add an xattr to the inode, we should make sure that
+ * i_extra_isize is not 0 and that the inode size is not less than
+ * EXT4_GOOD_OLD_INODE_SIZE + extra_isize + pad.
+ *   EXT4_GOOD_OLD_INODE_SIZE   extra_isize header   entry   pad  data
+ * |--------------------------|------------|------|---------|---|-------|
+ */
+#define EXT4_INODE_HAS_XATTR_SPACE(inode)				\
+	((EXT4_I(inode)->i_extra_isize != 0) &&				\
+	 (EXT4_GOOD_OLD_INODE_SIZE + EXT4_I(inode)->i_extra_isize +	\
+	  sizeof(struct ext4_xattr_ibody_header) + EXT4_XATTR_PAD <=	\
+	  EXT4_INODE_SIZE((inode)->i_sb)))
+
 struct ext4_xattr_info {
 	const char *name;
 	const void *value;
@@ -178,6 +191,7 @@ extern void ext4_xattr_inode_array_free(struct ext4_xattr_inode_array *array);
 
 extern int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
 			    struct ext4_inode *raw_inode, handle_t *handle);
+extern void ext4_evict_ea_inode(struct inode *inode);
 
 extern const struct xattr_handler *ext4_xattr_handlers[];
 
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index bfcafc20eada..758048a885d2 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -1869,10 +1869,7 @@ static int f2fs_setflags_common(struct inode *inode, u32 iflags, u32 mask)
 		if (masked_flags & F2FS_COMPR_FL) {
 			if (!f2fs_disable_compressed_file(inode))
 				return -EINVAL;
-		}
-		if (iflags & F2FS_NOCOMP_FL)
-			return -EINVAL;
-		if (iflags & F2FS_COMPR_FL) {
+		} else {
 			if (!f2fs_may_compress(inode))
 				return -EINVAL;
 			if (S_ISREG(inode->i_mode) && inode->i_size)
@@ -1881,10 +1878,6 @@ static int f2fs_setflags_common(struct inode *inode, u32 iflags, u32 mask)
 			set_compress_context(inode);
 		}
 	}
-	if ((iflags ^ masked_flags) & F2FS_NOCOMP_FL) {
-		if (masked_flags & F2FS_COMPR_FL)
-			return -EINVAL;
-	}
 
 	fi->i_flags = iflags | (fi->i_flags & ~mask);
 	f2fs_bug_on(F2FS_I_SB(inode), (fi->i_flags & F2FS_COMPR_FL) &&
@@ -4018,8 +4011,8 @@ static int f2fs_ioc_decompress_file(struct file *filp, unsigned long arg)
 		goto out;
 	}
 
-	if (f2fs_is_mmap_file(inode)) {
-		ret = -EBUSY;
+	if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) {
+		ret = -EINVAL;
 		goto out;
 	}
 
@@ -4090,8 +4083,8 @@ static int f2fs_ioc_compress_file(struct file *filp, unsigned long arg)
 		goto out;
 	}
 
-	if (f2fs_is_mmap_file(inode)) {
-		ret = -EBUSY;
+	if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) {
+		ret = -EINVAL;
 		goto out;
 	}
 
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 69c6bcaf5aae..0e6e73bc42d4 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -1291,7 +1291,11 @@ struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs)
 		dec_valid_node_count(sbi, dn->inode, !ofs);
 		goto fail;
 	}
-	f2fs_bug_on(sbi, new_ni.blk_addr != NULL_ADDR);
+	if (unlikely(new_ni.blk_addr != NULL_ADDR)) {
+		err = -EFSCORRUPTED;
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
+		goto fail;
+	}
 #endif
 	new_ni.nid = dn->nid;
 	new_ni.ino = dn->inode->i_ino;
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 841a978da083..e98c90bd8ef6 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -4537,6 +4537,12 @@ static int build_sit_entries(struct f2fs_sb_info *sbi)
 				return err;
 			seg_info_from_raw_sit(se, &sit);
 
+			if (se->type >= NR_PERSISTENT_LOG) {
+				f2fs_err(sbi, "Invalid segment type: %u, segno: %u",
+							se->type, start);
+				return -EFSCORRUPTED;
+			}
+
 			sit_valid_blocks[SE_PAGETYPE(se)] += se->valid_blocks;
 
 			if (f2fs_block_unit_discard(sbi)) {
@@ -4585,6 +4591,13 @@ static int build_sit_entries(struct f2fs_sb_info *sbi)
 			break;
 		seg_info_from_raw_sit(se, &sit);
 
+		if (se->type >= NR_PERSISTENT_LOG) {
+			f2fs_err(sbi, "Invalid segment type: %u, segno: %u",
+							se->type, start);
+			err = -EFSCORRUPTED;
+			break;
+		}
+
 		sit_valid_blocks[SE_PAGETYPE(se)] += se->valid_blocks;
 
 		if (f2fs_block_unit_discard(sbi)) {
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 1fd8d09416c4..9761470a7ecf 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -134,10 +134,10 @@ static bool inode_io_list_move_locked(struct inode *inode,
 
 static void wb_wakeup(struct bdi_writeback *wb)
 {
-	spin_lock_bh(&wb->work_lock);
+	spin_lock_irq(&wb->work_lock);
 	if (test_bit(WB_registered, &wb->state))
 		mod_delayed_work(bdi_wq, &wb->dwork, 0);
-	spin_unlock_bh(&wb->work_lock);
+	spin_unlock_irq(&wb->work_lock);
 }
 
 static void finish_writeback_work(struct bdi_writeback *wb,
@@ -164,7 +164,7 @@ static void wb_queue_work(struct bdi_writeback *wb,
 	if (work->done)
 		atomic_inc(&work->done->cnt);
 
-	spin_lock_bh(&wb->work_lock);
+	spin_lock_irq(&wb->work_lock);
 
 	if (test_bit(WB_registered, &wb->state)) {
 		list_add_tail(&work->list, &wb->work_list);
@@ -172,7 +172,7 @@ static void wb_queue_work(struct bdi_writeback *wb,
 	} else
 		finish_writeback_work(wb, work);
 
-	spin_unlock_bh(&wb->work_lock);
+	spin_unlock_irq(&wb->work_lock);
 }
 
 /**
@@ -2109,13 +2109,13 @@ static struct wb_writeback_work *get_next_work_item(struct bdi_writeback *wb)
 {
 	struct wb_writeback_work *work = NULL;
 
-	spin_lock_bh(&wb->work_lock);
+	spin_lock_irq(&wb->work_lock);
 	if (!list_empty(&wb->work_list)) {
 		work = list_entry(wb->work_list.next,
 				  struct wb_writeback_work, list);
 		list_del_init(&work->list);
 	}
-	spin_unlock_bh(&wb->work_lock);
+	spin_unlock_irq(&wb->work_lock);
 	return work;
 }
 
diff --git a/fs/fuse/control.c b/fs/fuse/control.c
index 000d2e5627e9..79f01d09c78c 100644
--- a/fs/fuse/control.c
+++ b/fs/fuse/control.c
@@ -275,7 +275,7 @@ int fuse_ctl_add_conn(struct fuse_conn *fc)
 	struct dentry *parent;
 	char name[32];
 
-	if (!fuse_control_sb)
+	if (!fuse_control_sb || fc->no_control)
 		return 0;
 
 	parent = fuse_control_sb->s_root;
@@ -313,7 +313,7 @@ void fuse_ctl_remove_conn(struct fuse_conn *fc)
 {
 	int i;
 
-	if (!fuse_control_sb)
+	if (!fuse_control_sb || fc->no_control)
 		return;
 
 	for (i = fc->ctl_ndents - 1; i >= 0; i--) {
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 2f999d38c9b4..50365143f50e 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -181,6 +181,12 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
 	inode->i_uid     = make_kuid(fc->user_ns, attr->uid);
 	inode->i_gid     = make_kgid(fc->user_ns, attr->gid);
 	inode->i_blocks  = attr->blocks;
+
+	/* Sanitize nsecs */
+	attr->atimensec = min_t(u32, attr->atimensec, NSEC_PER_SEC - 1);
+	attr->mtimensec = min_t(u32, attr->mtimensec, NSEC_PER_SEC - 1);
+	attr->ctimensec = min_t(u32, attr->ctimensec, NSEC_PER_SEC - 1);
+
 	inode->i_atime.tv_sec   = attr->atime;
 	inode->i_atime.tv_nsec  = attr->atimensec;
 	/* mtime from server may be stale due to local buffered write */
diff --git a/fs/fuse/ioctl.c b/fs/fuse/ioctl.c
index fc69e1797a33..e91d40703839 100644
--- a/fs/fuse/ioctl.c
+++ b/fs/fuse/ioctl.c
@@ -9,6 +9,17 @@
 #include <linux/compat.h>
 #include <linux/fileattr.h>
 
+static ssize_t fuse_send_ioctl(struct fuse_mount *fm, struct fuse_args *args)
+{
+	ssize_t ret = fuse_simple_request(fm, args);
+
+	/* Translate ENOSYS, which shouldn't be returned from fs */
+	if (ret == -ENOSYS)
+		ret = -ENOTTY;
+
+	return ret;
+}
+
 /*
  * CUSE servers compiled on 32bit broke on 64bit kernels because the
  * ABI was defined to be 'struct iovec' which is different on 32bit
@@ -259,7 +270,7 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
 	ap.args.out_pages = true;
 	ap.args.out_argvar = true;
 
-	transferred = fuse_simple_request(fm, &ap.args);
+	transferred = fuse_send_ioctl(fm, &ap.args);
 	err = transferred;
 	if (transferred < 0)
 		goto out;
@@ -393,7 +404,7 @@ static int fuse_priv_ioctl(struct inode *inode, struct fuse_file *ff,
 	args.out_args[1].size = inarg.out_size;
 	args.out_args[1].value = ptr;
 
-	err = fuse_simple_request(fm, &args);
+	err = fuse_send_ioctl(fm, &args);
 	if (!err) {
 		if (outarg.result < 0)
 			err = outarg.result;
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 60390f9dc31f..e93185d804e0 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -1086,6 +1086,7 @@ out_uninit:
 	gfs2_holder_uninit(gh);
 	if (statfs_gh)
 		kfree(statfs_gh);
+	from->count = orig_count - read;
 	return read ? read : ret;
 }
 
diff --git a/fs/io_uring.c b/fs/io_uring.c
index a8470a98f84d..ed6abd74f386 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -486,8 +486,6 @@ struct io_poll_iocb {
 	struct file			*file;
 	struct wait_queue_head		*head;
 	__poll_t			events;
-	bool				done;
-	bool				canceled;
 	struct wait_queue_entry		wait;
 };
 
@@ -885,6 +883,9 @@ struct io_kiocb {
 
 	/* store used ubuf, so we can prevent reloading */
 	struct io_mapped_ubuf		*imu;
+	/* stores selected buf, valid IFF REQ_F_BUFFER_SELECTED is set */
+	struct io_buffer		*kbuf;
+	atomic_t			poll_refs;
 };
 
 struct io_tctx_node {
@@ -1079,8 +1080,8 @@ static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
 					 bool cancel_all);
 static void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd);
 
-static bool io_cqring_fill_event(struct io_ring_ctx *ctx, u64 user_data,
-				 long res, unsigned int cflags);
+static void io_fill_cqe_req(struct io_kiocb *req, s32 res, u32 cflags);
+
 static void io_put_req(struct io_kiocb *req);
 static void io_put_req_deferred(struct io_kiocb *req);
 static void io_dismantle_req(struct io_kiocb *req);
@@ -1154,12 +1155,6 @@ static inline bool req_ref_put_and_test(struct io_kiocb *req)
 	return atomic_dec_and_test(&req->refs);
 }
 
-static inline void req_ref_put(struct io_kiocb *req)
-{
-	WARN_ON_ONCE(!(req->flags & REQ_F_REFCOUNT));
-	WARN_ON_ONCE(req_ref_put_and_test(req));
-}
-
 static inline void req_ref_get(struct io_kiocb *req)
 {
 	WARN_ON_ONCE(!(req->flags & REQ_F_REFCOUNT));
@@ -1405,7 +1400,7 @@ static void io_req_track_inflight(struct io_kiocb *req)
 {
 	if (!(req->flags & REQ_F_INFLIGHT)) {
 		req->flags |= REQ_F_INFLIGHT;
-		atomic_inc(&current->io_uring->inflight_tracked);
+		atomic_inc(&req->task->io_uring->inflight_tracked);
 	}
 }
 
@@ -1515,7 +1510,7 @@ static void io_kill_timeout(struct io_kiocb *req, int status)
 		atomic_set(&req->ctx->cq_timeouts,
 			atomic_read(&req->ctx->cq_timeouts) + 1);
 		list_del_init(&req->timeout.list);
-		io_cqring_fill_event(req->ctx, req->user_data, status, 0);
+		io_fill_cqe_req(req, status, 0);
 		io_put_req_deferred(req);
 	}
 }
@@ -1763,7 +1758,7 @@ static __cold void io_uring_drop_tctx_refs(struct task_struct *task)
 }
 
 static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data,
-				     long res, unsigned int cflags)
+				     s32 res, u32 cflags)
 {
 	struct io_overflow_cqe *ocqe;
 
@@ -1790,8 +1785,8 @@ static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data,
 	return true;
 }
 
-static inline bool __io_cqring_fill_event(struct io_ring_ctx *ctx, u64 user_data,
-					  long res, unsigned int cflags)
+static inline bool __io_fill_cqe(struct io_ring_ctx *ctx, u64 user_data,
+				 s32 res, u32 cflags)
 {
 	struct io_uring_cqe *cqe;
 
@@ -1812,20 +1807,25 @@ static inline bool __io_cqring_fill_event(struct io_ring_ctx *ctx, u64 user_data
 	return io_cqring_event_overflow(ctx, user_data, res, cflags);
 }
 
-/* not as hot to bloat with inlining */
-static noinline bool io_cqring_fill_event(struct io_ring_ctx *ctx, u64 user_data,
-					  long res, unsigned int cflags)
+static noinline void io_fill_cqe_req(struct io_kiocb *req, s32 res, u32 cflags)
 {
-	return __io_cqring_fill_event(ctx, user_data, res, cflags);
+	__io_fill_cqe(req->ctx, req->user_data, res, cflags);
 }
 
-static void io_req_complete_post(struct io_kiocb *req, long res,
-				 unsigned int cflags)
+static noinline bool io_fill_cqe_aux(struct io_ring_ctx *ctx, u64 user_data,
+				     s32 res, u32 cflags)
+{
+	ctx->cq_extra++;
+	return __io_fill_cqe(ctx, user_data, res, cflags);
+}
+
+static void io_req_complete_post(struct io_kiocb *req, s32 res,
+				 u32 cflags)
 {
 	struct io_ring_ctx *ctx = req->ctx;
 
 	spin_lock(&ctx->completion_lock);
-	__io_cqring_fill_event(ctx, req->user_data, res, cflags);
+	__io_fill_cqe(ctx, req->user_data, res, cflags);
 	/*
 	 * If we're the last reference to this request, add to our locked
 	 * free_list cache.
@@ -1861,8 +1861,8 @@ static inline bool io_req_needs_clean(struct io_kiocb *req)
 	return req->flags & IO_REQ_CLEAN_FLAGS;
 }
 
-static void io_req_complete_state(struct io_kiocb *req, long res,
-				  unsigned int cflags)
+static inline void io_req_complete_state(struct io_kiocb *req, s32 res,
+					 u32 cflags)
 {
 	if (io_req_needs_clean(req))
 		io_clean_op(req);
@@ -1872,7 +1872,7 @@ static void io_req_complete_state(struct io_kiocb *req, long res,
 }
 
 static inline void __io_req_complete(struct io_kiocb *req, unsigned issue_flags,
-				     long res, unsigned cflags)
+				     s32 res, u32 cflags)
 {
 	if (issue_flags & IO_URING_F_COMPLETE_DEFER)
 		io_req_complete_state(req, res, cflags);
@@ -1880,12 +1880,12 @@ static inline void __io_req_complete(struct io_kiocb *req, unsigned issue_flags,
 		io_req_complete_post(req, res, cflags);
 }
 
-static inline void io_req_complete(struct io_kiocb *req, long res)
+static inline void io_req_complete(struct io_kiocb *req, s32 res)
 {
 	__io_req_complete(req, 0, res, 0);
 }
 
-static void io_req_complete_failed(struct io_kiocb *req, long res)
+static void io_req_complete_failed(struct io_kiocb *req, s32 res)
 {
 	req_set_fail(req);
 	io_req_complete_post(req, res, 0);
@@ -2051,8 +2051,7 @@ static bool io_kill_linked_timeout(struct io_kiocb *req)
 		link->timeout.head = NULL;
 		if (hrtimer_try_to_cancel(&io->timer) != -1) {
 			list_del(&link->timeout.list);
-			io_cqring_fill_event(link->ctx, link->user_data,
-					     -ECANCELED, 0);
+			io_fill_cqe_req(link, -ECANCELED, 0);
 			io_put_req_deferred(link);
 			return true;
 		}
@@ -2076,7 +2075,7 @@ static void io_fail_links(struct io_kiocb *req)
 		link->link = NULL;
 
 		trace_io_uring_fail_link(req, link);
-		io_cqring_fill_event(link->ctx, link->user_data, res, 0);
+		io_fill_cqe_req(link, res, 0);
 		io_put_req_deferred(link);
 		link = nxt;
 	}
@@ -2093,8 +2092,7 @@ static bool io_disarm_next(struct io_kiocb *req)
 		req->flags &= ~REQ_F_ARM_LTIMEOUT;
 		if (link && link->opcode == IORING_OP_LINK_TIMEOUT) {
 			io_remove_next_linked(req);
-			io_cqring_fill_event(link->ctx, link->user_data,
-					     -ECANCELED, 0);
+			io_fill_cqe_req(link, -ECANCELED, 0);
 			io_put_req_deferred(link);
 			posted = true;
 		}
@@ -2370,8 +2368,8 @@ static void io_submit_flush_completions(struct io_ring_ctx *ctx)
 	for (i = 0; i < nr; i++) {
 		struct io_kiocb *req = state->compl_reqs[i];
 
-		__io_cqring_fill_event(ctx, req->user_data, req->result,
-					req->compl.cflags);
+		__io_fill_cqe(ctx, req->user_data, req->result,
+			      req->compl.cflags);
 	}
 	io_commit_cqring(ctx);
 	spin_unlock(&ctx->completion_lock);
@@ -2482,8 +2480,7 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
 		req = list_first_entry(done, struct io_kiocb, inflight_entry);
 		list_del(&req->inflight_entry);
 
-		__io_cqring_fill_event(ctx, req->user_data, req->result,
-					io_put_rw_kbuf(req));
+		io_fill_cqe_req(req, req->result, io_put_rw_kbuf(req));
 		(*nr_events)++;
 
 		if (req_ref_put_and_test(req))
@@ -2686,8 +2683,12 @@ static bool io_rw_should_reissue(struct io_kiocb *req)
 
 static bool __io_complete_rw_common(struct io_kiocb *req, long res)
 {
-	if (req->rw.kiocb.ki_flags & IOCB_WRITE)
+	if (req->rw.kiocb.ki_flags & IOCB_WRITE) {
 		kiocb_end_write(req);
+		fsnotify_modify(req->file);
+	} else {
+		fsnotify_access(req->file);
+	}
 	if (res != req->result) {
 		if ((res == -EAGAIN || res == -EOPNOTSUPP) &&
 		    io_rw_should_reissue(req)) {
@@ -2703,7 +2704,7 @@ static bool __io_complete_rw_common(struct io_kiocb *req, long res)
 static void io_req_task_complete(struct io_kiocb *req, bool *locked)
 {
 	unsigned int cflags = io_put_rw_kbuf(req);
-	long res = req->result;
+	int res = req->result;
 
 	if (*locked) {
 		struct io_ring_ctx *ctx = req->ctx;
@@ -3716,7 +3717,12 @@ done:
 copy_iov:
 		iov_iter_restore(iter, state);
 		ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false);
-		return ret ?: -EAGAIN;
+		if (!ret) {
+			if (kiocb->ki_flags & IOCB_WRITE)
+				kiocb_end_write(req);
+			return -EAGAIN;
+		}
+		return ret;
 	}
 out_free:
 	/* it's reportedly faster than delegating the null check to kfree() */
@@ -4183,6 +4189,8 @@ static int io_fallocate(struct io_kiocb *req, unsigned int issue_flags)
 				req->sync.len);
 	if (ret < 0)
 		req_set_fail(req);
+	else
+		fsnotify_modify(req->file);
 	io_req_complete(req, ret);
 	return 0;
 }
@@ -4471,7 +4479,8 @@ static int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags)
 
 	ret = io_add_buffers(p, &head);
 	if (ret >= 0 && !list) {
-		ret = xa_insert(&ctx->io_buffers, p->bgid, head, GFP_KERNEL);
+		ret = xa_insert(&ctx->io_buffers, p->bgid, head,
+				GFP_KERNEL_ACCOUNT);
 		if (ret < 0)
 			__io_remove_buffers(ctx, head, p->bgid, -1U);
 	}
@@ -4788,6 +4797,8 @@ static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		return -EINVAL;
 	if (unlikely(sqe->addr2 || sqe->file_index))
 		return -EINVAL;
+	if (unlikely(sqe->addr2 || sqe->file_index || sqe->ioprio))
+		return -EINVAL;
 
 	sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr));
 	sr->len = READ_ONCE(sqe->len);
@@ -5011,6 +5022,8 @@ static int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		return -EINVAL;
 	if (unlikely(sqe->addr2 || sqe->file_index))
 		return -EINVAL;
+	if (unlikely(sqe->addr2 || sqe->file_index || sqe->ioprio))
+		return -EINVAL;
 
 	sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr));
 	sr->len = READ_ONCE(sqe->len);
@@ -5300,52 +5313,23 @@ struct io_poll_table {
 	int error;
 };
 
-static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll,
-			   __poll_t mask, io_req_tw_func_t func)
-{
-	/* for instances that support it check for an event match first: */
-	if (mask && !(mask & poll->events))
-		return 0;
-
-	trace_io_uring_task_add(req->ctx, req->opcode, req->user_data, mask);
-
-	list_del_init(&poll->wait.entry);
+#define IO_POLL_CANCEL_FLAG	BIT(31)
+#define IO_POLL_REF_MASK	GENMASK(30, 0)
 
-	req->result = mask;
-	req->io_task_work.func = func;
-
-	/*
-	 * If this fails, then the task is exiting. When a task exits, the
-	 * work gets canceled, so just cancel this request as well instead
-	 * of executing it. We can't safely execute it anyway, as we may not
-	 * have the needed state needed for it anyway.
-	 */
-	io_req_task_work_add(req);
-	return 1;
+/*
+ * If refs part of ->poll_refs (see IO_POLL_REF_MASK) is 0, it's free. We can
+ * bump it and acquire ownership. It's disallowed to modify requests while not
+ * owning it, that prevents from races for enqueueing task_work's and b/w
+ * arming poll and wakeups.
+ */
+static inline bool io_poll_get_ownership(struct io_kiocb *req)
+{
+	return !(atomic_fetch_inc(&req->poll_refs) & IO_POLL_REF_MASK);
 }
 
-static bool io_poll_rewait(struct io_kiocb *req, struct io_poll_iocb *poll)
-	__acquires(&req->ctx->completion_lock)
+static void io_poll_mark_cancelled(struct io_kiocb *req)
 {
-	struct io_ring_ctx *ctx = req->ctx;
-
-	/* req->task == current here, checking PF_EXITING is safe */
-	if (unlikely(req->task->flags & PF_EXITING))
-		WRITE_ONCE(poll->canceled, true);
-
-	if (!req->result && !READ_ONCE(poll->canceled)) {
-		struct poll_table_struct pt = { ._key = poll->events };
-
-		req->result = vfs_poll(req->file, &pt) & poll->events;
-	}
-
-	spin_lock(&ctx->completion_lock);
-	if (!req->result && !READ_ONCE(poll->canceled)) {
-		add_wait_queue(poll->head, &poll->wait);
-		return true;
-	}
-
-	return false;
+	atomic_or(IO_POLL_CANCEL_FLAG, &req->poll_refs);
 }
 
 static struct io_poll_iocb *io_poll_get_double(struct io_kiocb *req)
@@ -5363,141 +5347,231 @@ static struct io_poll_iocb *io_poll_get_single(struct io_kiocb *req)
 	return &req->apoll->poll;
 }
 
-static void io_poll_remove_double(struct io_kiocb *req)
-	__must_hold(&req->ctx->completion_lock)
+static void io_poll_req_insert(struct io_kiocb *req)
 {
-	struct io_poll_iocb *poll = io_poll_get_double(req);
+	struct io_ring_ctx *ctx = req->ctx;
+	struct hlist_head *list;
 
-	lockdep_assert_held(&req->ctx->completion_lock);
+	list = &ctx->cancel_hash[hash_long(req->user_data, ctx->cancel_hash_bits)];
+	hlist_add_head(&req->hash_node, list);
+}
 
-	if (poll && poll->head) {
-		struct wait_queue_head *head = poll->head;
+static void io_init_poll_iocb(struct io_poll_iocb *poll, __poll_t events,
+			      wait_queue_func_t wake_func)
+{
+	poll->head = NULL;
+#define IO_POLL_UNMASK	(EPOLLERR|EPOLLHUP|EPOLLNVAL|EPOLLRDHUP)
+	/* mask in events that we always want/need */
+	poll->events = events | IO_POLL_UNMASK;
+	INIT_LIST_HEAD(&poll->wait.entry);
+	init_waitqueue_func_entry(&poll->wait, wake_func);
+}
+
+static inline void io_poll_remove_entry(struct io_poll_iocb *poll)
+{
+	struct wait_queue_head *head = smp_load_acquire(&poll->head);
 
+	if (head) {
 		spin_lock_irq(&head->lock);
 		list_del_init(&poll->wait.entry);
-		if (poll->wait.private)
-			req_ref_put(req);
 		poll->head = NULL;
 		spin_unlock_irq(&head->lock);
 	}
 }
 
-static bool __io_poll_complete(struct io_kiocb *req, __poll_t mask)
-	__must_hold(&req->ctx->completion_lock)
+static void io_poll_remove_entries(struct io_kiocb *req)
+{
+	struct io_poll_iocb *poll = io_poll_get_single(req);
+	struct io_poll_iocb *poll_double = io_poll_get_double(req);
+
+	/*
+	 * While we hold the waitqueue lock and the waitqueue is nonempty,
+	 * wake_up_pollfree() will wait for us.  However, taking the waitqueue
+	 * lock in the first place can race with the waitqueue being freed.
+	 *
+	 * We solve this as eventpoll does: by taking advantage of the fact that
+	 * all users of wake_up_pollfree() will RCU-delay the actual free.  If
+	 * we enter rcu_read_lock() and see that the pointer to the queue is
+	 * non-NULL, we can then lock it without the memory being freed out from
+	 * under us.
+	 *
+	 * Keep holding rcu_read_lock() as long as we hold the queue lock, in
+	 * case the caller deletes the entry from the queue, leaving it empty.
+	 * In that case, only RCU prevents the queue memory from being freed.
+	 */
+	rcu_read_lock();
+	io_poll_remove_entry(poll);
+	if (poll_double)
+		io_poll_remove_entry(poll_double);
+	rcu_read_unlock();
+}
+
+/*
+ * All poll tw should go through this. Checks for poll events, manages
+ * references, does rewait, etc.
+ *
+ * Returns a negative error on failure. >0 when no action require, which is
+ * either spurious wakeup or multishot CQE is served. 0 when it's done with
+ * the request, then the mask is stored in req->result.
+ */
+static int io_poll_check_events(struct io_kiocb *req)
 {
 	struct io_ring_ctx *ctx = req->ctx;
-	unsigned flags = IORING_CQE_F_MORE;
-	int error;
+	struct io_poll_iocb *poll = io_poll_get_single(req);
+	int v;
+
+	/* req->task == current here, checking PF_EXITING is safe */
+	if (unlikely(req->task->flags & PF_EXITING))
+		io_poll_mark_cancelled(req);
+
+	do {
+		v = atomic_read(&req->poll_refs);
+
+		/* tw handler should be the owner, and so have some references */
+		if (WARN_ON_ONCE(!(v & IO_POLL_REF_MASK)))
+			return 0;
+		if (v & IO_POLL_CANCEL_FLAG)
+			return -ECANCELED;
+
+		if (!req->result) {
+			struct poll_table_struct pt = { ._key = poll->events };
+
+			req->result = vfs_poll(req->file, &pt) & poll->events;
+		}
+
+		/* multishot, just fill an CQE and proceed */
+		if (req->result && !(poll->events & EPOLLONESHOT)) {
+			__poll_t mask = mangle_poll(req->result & poll->events);
+			bool filled;
+
+			spin_lock(&ctx->completion_lock);
+			filled = io_fill_cqe_aux(ctx, req->user_data, mask,
+						 IORING_CQE_F_MORE);
+			io_commit_cqring(ctx);
+			spin_unlock(&ctx->completion_lock);
+			if (unlikely(!filled))
+				return -ECANCELED;
+			io_cqring_ev_posted(ctx);
+		} else if (req->result) {
+			return 0;
+		}
+
+		/*
+		 * Release all references, retry if someone tried to restart
+		 * task_work while we were executing it.
+		 */
+	} while (atomic_sub_return(v & IO_POLL_REF_MASK, &req->poll_refs));
+
+	return 1;
+}
 
-	if (READ_ONCE(req->poll.canceled)) {
-		error = -ECANCELED;
-		req->poll.events |= EPOLLONESHOT;
+static void io_poll_task_func(struct io_kiocb *req, bool *locked)
+{
+	struct io_ring_ctx *ctx = req->ctx;
+	int ret;
+
+	ret = io_poll_check_events(req);
+	if (ret > 0)
+		return;
+
+	if (!ret) {
+		req->result = mangle_poll(req->result & req->poll.events);
 	} else {
-		error = mangle_poll(mask);
-	}
-	if (req->poll.events & EPOLLONESHOT)
-		flags = 0;
-	if (!io_cqring_fill_event(ctx, req->user_data, error, flags)) {
-		req->poll.events |= EPOLLONESHOT;
-		flags = 0;
+		req->result = ret;
+		req_set_fail(req);
 	}
-	if (flags & IORING_CQE_F_MORE)
-		ctx->cq_extra++;
 
-	return !(flags & IORING_CQE_F_MORE);
+	io_poll_remove_entries(req);
+	spin_lock(&ctx->completion_lock);
+	hash_del(&req->hash_node);
+	spin_unlock(&ctx->completion_lock);
+	io_req_complete_post(req, req->result, 0);
 }
 
-static inline bool io_poll_complete(struct io_kiocb *req, __poll_t mask)
-	__must_hold(&req->ctx->completion_lock)
+static void io_apoll_task_func(struct io_kiocb *req, bool *locked)
 {
-	bool done;
+	struct io_ring_ctx *ctx = req->ctx;
+	int ret;
+
+	ret = io_poll_check_events(req);
+	if (ret > 0)
+		return;
+
+	io_poll_remove_entries(req);
+	spin_lock(&ctx->completion_lock);
+	hash_del(&req->hash_node);
+	spin_unlock(&ctx->completion_lock);
 
-	done = __io_poll_complete(req, mask);
-	io_commit_cqring(req->ctx);
-	return done;
+	if (!ret)
+		io_req_task_submit(req, locked);
+	else
+		io_req_complete_failed(req, ret);
 }
 
-static void io_poll_task_func(struct io_kiocb *req, bool *locked)
+static void __io_poll_execute(struct io_kiocb *req, int mask)
 {
-	struct io_ring_ctx *ctx = req->ctx;
-	struct io_kiocb *nxt;
+	req->result = mask;
+	if (req->opcode == IORING_OP_POLL_ADD)
+		req->io_task_work.func = io_poll_task_func;
+	else
+		req->io_task_work.func = io_apoll_task_func;
 
-	if (io_poll_rewait(req, &req->poll)) {
-		spin_unlock(&ctx->completion_lock);
-	} else {
-		bool done;
+	trace_io_uring_task_add(req->ctx, req->opcode, req->user_data, mask);
+	io_req_task_work_add(req);
+}
 
-		if (req->poll.done) {
-			spin_unlock(&ctx->completion_lock);
-			return;
-		}
-		done = __io_poll_complete(req, req->result);
-		if (done) {
-			io_poll_remove_double(req);
-			hash_del(&req->hash_node);
-			req->poll.done = true;
-		} else {
-			req->result = 0;
-			add_wait_queue(req->poll.head, &req->poll.wait);
-		}
-		io_commit_cqring(ctx);
-		spin_unlock(&ctx->completion_lock);
-		io_cqring_ev_posted(ctx);
+static inline void io_poll_execute(struct io_kiocb *req, int res)
+{
+	if (io_poll_get_ownership(req))
+		__io_poll_execute(req, res);
+}
 
-		if (done) {
-			nxt = io_put_req_find_next(req);
-			if (nxt)
-				io_req_task_submit(nxt, locked);
-		}
-	}
+static void io_poll_cancel_req(struct io_kiocb *req)
+{
+	io_poll_mark_cancelled(req);
+	/* kick tw, which should complete the request */
+	io_poll_execute(req, 0);
 }
 
-static int io_poll_double_wake(struct wait_queue_entry *wait, unsigned mode,
-			       int sync, void *key)
+static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
+			void *key)
 {
 	struct io_kiocb *req = wait->private;
-	struct io_poll_iocb *poll = io_poll_get_single(req);
+	struct io_poll_iocb *poll = container_of(wait, struct io_poll_iocb,
+						 wait);
 	__poll_t mask = key_to_poll(key);
-	unsigned long flags;
 
-	/* for instances that support it check for an event match first: */
-	if (mask && !(mask & poll->events))
-		return 0;
-	if (!(poll->events & EPOLLONESHOT))
-		return poll->wait.func(&poll->wait, mode, sync, key);
+	if (unlikely(mask & POLLFREE)) {
+		io_poll_mark_cancelled(req);
+		/* we have to kick tw in case it's not already */
+		io_poll_execute(req, 0);
 
-	list_del_init(&wait->entry);
+		/*
+		 * If the waitqueue is being freed early but someone is already
+		 * holds ownership over it, we have to tear down the request as
+		 * best we can. That means immediately removing the request from
+		 * its waitqueue and preventing all further accesses to the
+		 * waitqueue via the request.
+		 */
+		list_del_init(&poll->wait.entry);
 
-	if (poll->head) {
-		bool done;
-
-		spin_lock_irqsave(&poll->head->lock, flags);
-		done = list_empty(&poll->wait.entry);
-		if (!done)
-			list_del_init(&poll->wait.entry);
-		/* make sure double remove sees this as being gone */
-		wait->private = NULL;
-		spin_unlock_irqrestore(&poll->head->lock, flags);
-		if (!done) {
-			/* use wait func handler, so it matches the rq type */
-			poll->wait.func(&poll->wait, mode, sync, key);
-		}
+		/*
+		 * Careful: this *must* be the last step, since as soon
+		 * as req->head is NULL'ed out, the request can be
+		 * completed and freed, since aio_poll_complete_work()
+		 * will no longer need to take the waitqueue lock.
+		 */
+		smp_store_release(&poll->head, NULL);
+		return 1;
 	}
-	req_ref_put(req);
-	return 1;
-}
 
-static void io_init_poll_iocb(struct io_poll_iocb *poll, __poll_t events,
-			      wait_queue_func_t wake_func)
-{
-	poll->head = NULL;
-	poll->done = false;
-	poll->canceled = false;
-#define IO_POLL_UNMASK	(EPOLLERR|EPOLLHUP|EPOLLNVAL|EPOLLRDHUP)
-	/* mask in events that we always want/need */
-	poll->events = events | IO_POLL_UNMASK;
-	INIT_LIST_HEAD(&poll->wait.entry);
-	init_waitqueue_func_entry(&poll->wait, wake_func);
+	/* for instances that support it check for an event match first */
+	if (mask && !(mask & poll->events))
+		return 0;
+
+	if (io_poll_get_ownership(req))
+		__io_poll_execute(req, mask);
+	return 1;
 }
 
 static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt,
@@ -5512,10 +5586,10 @@ static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt,
 	 * if this happens.
 	 */
 	if (unlikely(pt->nr_entries)) {
-		struct io_poll_iocb *poll_one = poll;
+		struct io_poll_iocb *first = poll;
 
 		/* double add on the same waitqueue head, ignore */
-		if (poll_one->head == head)
+		if (first->head == head)
 			return;
 		/* already have a 2nd entry, fail a third attempt */
 		if (*poll_ptr) {
@@ -5524,25 +5598,19 @@ static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt,
 			pt->error = -EINVAL;
 			return;
 		}
-		/*
-		 * Can't handle multishot for double wait for now, turn it
-		 * into one-shot mode.
-		 */
-		if (!(poll_one->events & EPOLLONESHOT))
-			poll_one->events |= EPOLLONESHOT;
+
 		poll = kmalloc(sizeof(*poll), GFP_ATOMIC);
 		if (!poll) {
 			pt->error = -ENOMEM;
 			return;
 		}
-		io_init_poll_iocb(poll, poll_one->events, io_poll_double_wake);
-		req_ref_get(req);
-		poll->wait.private = req;
+		io_init_poll_iocb(poll, first->events, first->wait.func);
 		*poll_ptr = poll;
 	}
 
 	pt->nr_entries++;
 	poll->head = head;
+	poll->wait.private = req;
 
 	if (poll->events & EPOLLEXCLUSIVE)
 		add_wait_queue_exclusive(head, &poll->wait);
@@ -5550,70 +5618,24 @@ static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt,
 		add_wait_queue(head, &poll->wait);
 }
 
-static void io_async_queue_proc(struct file *file, struct wait_queue_head *head,
+static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head,
 			       struct poll_table_struct *p)
 {
 	struct io_poll_table *pt = container_of(p, struct io_poll_table, pt);
-	struct async_poll *apoll = pt->req->apoll;
-
-	__io_queue_proc(&apoll->poll, pt, head, &apoll->double_poll);
-}
-
-static void io_async_task_func(struct io_kiocb *req, bool *locked)
-{
-	struct async_poll *apoll = req->apoll;
-	struct io_ring_ctx *ctx = req->ctx;
-
-	trace_io_uring_task_run(req->ctx, req, req->opcode, req->user_data);
-
-	if (io_poll_rewait(req, &apoll->poll)) {
-		spin_unlock(&ctx->completion_lock);
-		return;
-	}
-
-	hash_del(&req->hash_node);
-	io_poll_remove_double(req);
-	apoll->poll.done = true;
-	spin_unlock(&ctx->completion_lock);
-
-	if (!READ_ONCE(apoll->poll.canceled))
-		io_req_task_submit(req, locked);
-	else
-		io_req_complete_failed(req, -ECANCELED);
-}
-
-static int io_async_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
-			void *key)
-{
-	struct io_kiocb *req = wait->private;
-	struct io_poll_iocb *poll = &req->apoll->poll;
-
-	trace_io_uring_poll_wake(req->ctx, req->opcode, req->user_data,
-					key_to_poll(key));
 
-	return __io_async_wake(req, poll, key_to_poll(key), io_async_task_func);
-}
-
-static void io_poll_req_insert(struct io_kiocb *req)
-{
-	struct io_ring_ctx *ctx = req->ctx;
-	struct hlist_head *list;
-
-	list = &ctx->cancel_hash[hash_long(req->user_data, ctx->cancel_hash_bits)];
-	hlist_add_head(&req->hash_node, list);
+	__io_queue_proc(&pt->req->poll, pt, head,
+			(struct io_poll_iocb **) &pt->req->async_data);
 }
 
-static __poll_t __io_arm_poll_handler(struct io_kiocb *req,
-				      struct io_poll_iocb *poll,
-				      struct io_poll_table *ipt, __poll_t mask,
-				      wait_queue_func_t wake_func)
-	__acquires(&ctx->completion_lock)
+static int __io_arm_poll_handler(struct io_kiocb *req,
+				 struct io_poll_iocb *poll,
+				 struct io_poll_table *ipt, __poll_t mask)
 {
 	struct io_ring_ctx *ctx = req->ctx;
-	bool cancel = false;
+	int v;
 
 	INIT_HLIST_NODE(&req->hash_node);
-	io_init_poll_iocb(poll, mask, wake_func);
+	io_init_poll_iocb(poll, mask, io_poll_wake);
 	poll->file = req->file;
 	poll->wait.private = req;
 
@@ -5622,31 +5644,56 @@ static __poll_t __io_arm_poll_handler(struct io_kiocb *req,
 	ipt->error = 0;
 	ipt->nr_entries = 0;
 
+	/*
+	 * Take the ownership to delay any tw execution up until we're done
+	 * with poll arming. see io_poll_get_ownership().
+	 */
+	atomic_set(&req->poll_refs, 1);
 	mask = vfs_poll(req->file, &ipt->pt) & poll->events;
-	if (unlikely(!ipt->nr_entries) && !ipt->error)
-		ipt->error = -EINVAL;
+
+	if (mask && (poll->events & EPOLLONESHOT)) {
+		io_poll_remove_entries(req);
+		/* no one else has access to the req, forget about the ref */
+		return mask;
+	}
+	if (!mask && unlikely(ipt->error || !ipt->nr_entries)) {
+		io_poll_remove_entries(req);
+		if (!ipt->error)
+			ipt->error = -EINVAL;
+		return 0;
+	}
 
 	spin_lock(&ctx->completion_lock);
-	if (ipt->error || (mask && (poll->events & EPOLLONESHOT)))
-		io_poll_remove_double(req);
-	if (likely(poll->head)) {
-		spin_lock_irq(&poll->head->lock);
-		if (unlikely(list_empty(&poll->wait.entry))) {
-			if (ipt->error)
-				cancel = true;
+	io_poll_req_insert(req);
+	spin_unlock(&ctx->completion_lock);
+
+	if (mask) {
+		/* can't multishot if failed, just queue the event we've got */
+		if (unlikely(ipt->error || !ipt->nr_entries)) {
+			poll->events |= EPOLLONESHOT;
 			ipt->error = 0;
-			mask = 0;
 		}
-		if ((mask && (poll->events & EPOLLONESHOT)) || ipt->error)
-			list_del_init(&poll->wait.entry);
-		else if (cancel)
-			WRITE_ONCE(poll->canceled, true);
-		else if (!poll->done) /* actually waiting for an event */
-			io_poll_req_insert(req);
-		spin_unlock_irq(&poll->head->lock);
+		__io_poll_execute(req, mask);
+		return 0;
 	}
 
-	return mask;
+	/*
+	 * Release ownership. If someone tried to queue a tw while it was
+	 * locked, kick it off for them.
+	 */
+	v = atomic_dec_return(&req->poll_refs);
+	if (unlikely(v & IO_POLL_REF_MASK))
+		__io_poll_execute(req, 0);
+	return 0;
+}
+
+static void io_async_queue_proc(struct file *file, struct wait_queue_head *head,
+			       struct poll_table_struct *p)
+{
+	struct io_poll_table *pt = container_of(p, struct io_poll_table, pt);
+	struct async_poll *apoll = pt->req->apoll;
+
+	__io_queue_proc(&apoll->poll, pt, head, &apoll->double_poll);
 }
 
 enum {
@@ -5661,7 +5708,8 @@ static int io_arm_poll_handler(struct io_kiocb *req)
 	struct io_ring_ctx *ctx = req->ctx;
 	struct async_poll *apoll;
 	struct io_poll_table ipt;
-	__poll_t ret, mask = EPOLLONESHOT | POLLERR | POLLPRI;
+	__poll_t mask = EPOLLONESHOT | POLLERR | POLLPRI;
+	int ret;
 
 	if (!req->file || !file_can_poll(req->file))
 		return IO_APOLL_ABORTED;
@@ -5688,11 +5736,8 @@ static int io_arm_poll_handler(struct io_kiocb *req)
 	req->apoll = apoll;
 	req->flags |= REQ_F_POLLED;
 	ipt.pt._qproc = io_async_queue_proc;
-	io_req_set_refcount(req);
 
-	ret = __io_arm_poll_handler(req, &apoll->poll, &ipt, mask,
-					io_async_wake);
-	spin_unlock(&ctx->completion_lock);
+	ret = __io_arm_poll_handler(req, &apoll->poll, &ipt, mask);
 	if (ret || ipt.error)
 		return ret ? IO_APOLL_READY : IO_APOLL_ABORTED;
 
@@ -5701,43 +5746,6 @@ static int io_arm_poll_handler(struct io_kiocb *req)
 	return IO_APOLL_OK;
 }
 
-static bool __io_poll_remove_one(struct io_kiocb *req,
-				 struct io_poll_iocb *poll, bool do_cancel)
-	__must_hold(&req->ctx->completion_lock)
-{
-	bool do_complete = false;
-
-	if (!poll->head)
-		return false;
-	spin_lock_irq(&poll->head->lock);
-	if (do_cancel)
-		WRITE_ONCE(poll->canceled, true);
-	if (!list_empty(&poll->wait.entry)) {
-		list_del_init(&poll->wait.entry);
-		do_complete = true;
-	}
-	spin_unlock_irq(&poll->head->lock);
-	hash_del(&req->hash_node);
-	return do_complete;
-}
-
-static bool io_poll_remove_one(struct io_kiocb *req)
-	__must_hold(&req->ctx->completion_lock)
-{
-	bool do_complete;
-
-	io_poll_remove_double(req);
-	do_complete = __io_poll_remove_one(req, io_poll_get_single(req), true);
-
-	if (do_complete) {
-		io_cqring_fill_event(req->ctx, req->user_data, -ECANCELED, 0);
-		io_commit_cqring(req->ctx);
-		req_set_fail(req);
-		io_put_req_deferred(req);
-	}
-	return do_complete;
-}
-
 /*
  * Returns true if we found and killed one or more poll requests
  */
@@ -5746,7 +5754,8 @@ static bool io_poll_remove_all(struct io_ring_ctx *ctx, struct task_struct *tsk,
 {
 	struct hlist_node *tmp;
 	struct io_kiocb *req;
-	int posted = 0, i;
+	bool found = false;
+	int i;
 
 	spin_lock(&ctx->completion_lock);
 	for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) {
@@ -5754,16 +5763,15 @@ static bool io_poll_remove_all(struct io_ring_ctx *ctx, struct task_struct *tsk,
 
 		list = &ctx->cancel_hash[i];
 		hlist_for_each_entry_safe(req, tmp, list, hash_node) {
-			if (io_match_task_safe(req, tsk, cancel_all))
-				posted += io_poll_remove_one(req);
+			if (io_match_task_safe(req, tsk, cancel_all)) {
+				hlist_del_init(&req->hash_node);
+				io_poll_cancel_req(req);
+				found = true;
+			}
 		}
 	}
 	spin_unlock(&ctx->completion_lock);
-
-	if (posted)
-		io_cqring_ev_posted(ctx);
-
-	return posted != 0;
+	return found;
 }
 
 static struct io_kiocb *io_poll_find(struct io_ring_ctx *ctx, __u64 sqe_addr,
@@ -5784,19 +5792,26 @@ static struct io_kiocb *io_poll_find(struct io_ring_ctx *ctx, __u64 sqe_addr,
 	return NULL;
 }
 
+static bool io_poll_disarm(struct io_kiocb *req)
+	__must_hold(&ctx->completion_lock)
+{
+	if (!io_poll_get_ownership(req))
+		return false;
+	io_poll_remove_entries(req);
+	hash_del(&req->hash_node);
+	return true;
+}
+
 static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr,
 			  bool poll_only)
 	__must_hold(&ctx->completion_lock)
 {
-	struct io_kiocb *req;
+	struct io_kiocb *req = io_poll_find(ctx, sqe_addr, poll_only);
 
-	req = io_poll_find(ctx, sqe_addr, poll_only);
 	if (!req)
 		return -ENOENT;
-	if (io_poll_remove_one(req))
-		return 0;
-
-	return -EALREADY;
+	io_poll_cancel_req(req);
+	return 0;
 }
 
 static __poll_t io_poll_parse_events(const struct io_uring_sqe *sqe,
@@ -5846,23 +5861,6 @@ static int io_poll_update_prep(struct io_kiocb *req,
 	return 0;
 }
 
-static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
-			void *key)
-{
-	struct io_kiocb *req = wait->private;
-	struct io_poll_iocb *poll = &req->poll;
-
-	return __io_async_wake(req, poll, key_to_poll(key), io_poll_task_func);
-}
-
-static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head,
-			       struct poll_table_struct *p)
-{
-	struct io_poll_table *pt = container_of(p, struct io_poll_table, pt);
-
-	__io_queue_proc(&pt->req->poll, pt, head, (struct io_poll_iocb **) &pt->req->async_data);
-}
-
 static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_poll_iocb *poll = &req->poll;
@@ -5884,90 +5882,57 @@ static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe
 static int io_poll_add(struct io_kiocb *req, unsigned int issue_flags)
 {
 	struct io_poll_iocb *poll = &req->poll;
-	struct io_ring_ctx *ctx = req->ctx;
 	struct io_poll_table ipt;
-	__poll_t mask;
-	bool done;
+	int ret;
 
 	ipt.pt._qproc = io_poll_queue_proc;
 
-	mask = __io_arm_poll_handler(req, &req->poll, &ipt, poll->events,
-					io_poll_wake);
-
-	if (mask) { /* no async, we'd stolen it */
-		ipt.error = 0;
-		done = io_poll_complete(req, mask);
-	}
-	spin_unlock(&ctx->completion_lock);
-
-	if (mask) {
-		io_cqring_ev_posted(ctx);
-		if (done)
-			io_put_req(req);
-	}
-	return ipt.error;
+	ret = __io_arm_poll_handler(req, &req->poll, &ipt, poll->events);
+	if (!ret && ipt.error)
+		req_set_fail(req);
+	ret = ret ?: ipt.error;
+	if (ret)
+		__io_req_complete(req, issue_flags, ret, 0);
+	return 0;
 }
 
 static int io_poll_update(struct io_kiocb *req, unsigned int issue_flags)
 {
 	struct io_ring_ctx *ctx = req->ctx;
 	struct io_kiocb *preq;
-	bool completing;
-	int ret;
+	int ret2, ret = 0;
 
 	spin_lock(&ctx->completion_lock);
 	preq = io_poll_find(ctx, req->poll_update.old_user_data, true);
-	if (!preq) {
-		ret = -ENOENT;
-		goto err;
+	if (!preq || !io_poll_disarm(preq)) {
+		spin_unlock(&ctx->completion_lock);
+		ret = preq ? -EALREADY : -ENOENT;
+		goto out;
 	}
+	spin_unlock(&ctx->completion_lock);
 
-	if (!req->poll_update.update_events && !req->poll_update.update_user_data) {
-		completing = true;
-		ret = io_poll_remove_one(preq) ? 0 : -EALREADY;
-		goto err;
-	}
+	if (req->poll_update.update_events || req->poll_update.update_user_data) {
+		/* only mask one event flags, keep behavior flags */
+		if (req->poll_update.update_events) {
+			preq->poll.events &= ~0xffff;
+			preq->poll.events |= req->poll_update.events & 0xffff;
+			preq->poll.events |= IO_POLL_UNMASK;
+		}
+		if (req->poll_update.update_user_data)
+			preq->user_data = req->poll_update.new_user_data;
 
-	/*
-	 * Don't allow racy completion with singleshot, as we cannot safely
-	 * update those. For multishot, if we're racing with completion, just
-	 * let completion re-add it.
-	 */
-	io_poll_remove_double(preq);
-	completing = !__io_poll_remove_one(preq, &preq->poll, false);
-	if (completing && (preq->poll.events & EPOLLONESHOT)) {
-		ret = -EALREADY;
-		goto err;
+		ret2 = io_poll_add(preq, issue_flags);
+		/* successfully updated, don't complete poll request */
+		if (!ret2)
+			goto out;
 	}
-	/* we now have a detached poll request. reissue. */
-	ret = 0;
-err:
-	if (ret < 0) {
-		spin_unlock(&ctx->completion_lock);
+	req_set_fail(preq);
+	io_req_complete(preq, -ECANCELED);
+out:
+	if (ret < 0)
 		req_set_fail(req);
-		io_req_complete(req, ret);
-		return 0;
-	}
-	/* only mask one event flags, keep behavior flags */
-	if (req->poll_update.update_events) {
-		preq->poll.events &= ~0xffff;
-		preq->poll.events |= req->poll_update.events & 0xffff;
-		preq->poll.events |= IO_POLL_UNMASK;
-	}
-	if (req->poll_update.update_user_data)
-		preq->user_data = req->poll_update.new_user_data;
-	spin_unlock(&ctx->completion_lock);
-
 	/* complete update request, we're done with it */
 	io_req_complete(req, ret);
-
-	if (!completing) {
-		ret = io_poll_add(preq, issue_flags);
-		if (ret < 0) {
-			req_set_fail(preq);
-			io_req_complete(preq, ret);
-		}
-	}
 	return 0;
 }
 
@@ -6029,7 +5994,7 @@ static int io_timeout_cancel(struct io_ring_ctx *ctx, __u64 user_data)
 		return PTR_ERR(req);
 
 	req_set_fail(req);
-	io_cqring_fill_event(ctx, req->user_data, -ECANCELED, 0);
+	io_fill_cqe_req(req, -ECANCELED, 0);
 	io_put_req_deferred(req);
 	return 0;
 }
@@ -6856,7 +6821,7 @@ static void io_wq_submit_work(struct io_wq_work *work)
 			 * forcing a sync submission from here, since we can't
 			 * wait for request slots on the block side.
 			 */
-			if (ret != -EAGAIN)
+			if (ret != -EAGAIN || !(req->ctx->flags & IORING_SETUP_IOPOLL))
 				break;
 			cond_resched();
 		} while (1);
@@ -8255,8 +8220,7 @@ static void __io_rsrc_put_work(struct io_rsrc_node *ref_node)
 
 			io_ring_submit_lock(ctx, lock_ring);
 			spin_lock(&ctx->completion_lock);
-			io_cqring_fill_event(ctx, prsrc->tag, 0, 0);
-			ctx->cq_extra++;
+			io_fill_cqe_aux(ctx, prsrc->tag, 0, 0);
 			io_commit_cqring(ctx);
 			spin_unlock(&ctx->completion_lock);
 			io_cqring_ev_posted(ctx);
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 34b1406c06fd..69538061c551 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -564,13 +564,13 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	 */
 	jbd2_journal_switch_revoke_table(journal);
 
+	write_lock(&journal->j_state_lock);
 	/*
 	 * Reserved credits cannot be claimed anymore, free them
 	 */
 	atomic_sub(atomic_read(&journal->j_reserved_credits),
 		   &commit_transaction->t_outstanding_credits);
 
-	write_lock(&journal->j_state_lock);
 	trace_jbd2_commit_flushing(journal, commit_transaction);
 	stats.run.rs_flushing = jiffies;
 	stats.run.rs_locked = jbd2_time_diff(stats.run.rs_locked,
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 6a3caedd2285..53cb236b53db 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1477,8 +1477,6 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 	struct journal_head *jh;
 	int ret = 0;
 
-	if (is_handle_aborted(handle))
-		return -EROFS;
 	if (!buffer_jbd(bh))
 		return -EUCLEAN;
 
@@ -1525,6 +1523,18 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 	journal = transaction->t_journal;
 	spin_lock(&jh->b_state_lock);
 
+	if (is_handle_aborted(handle)) {
+		/*
+		 * Check journal aborting with @jh->b_state_lock locked,
+		 * since 'jh->b_transaction' could be replaced with
+		 * 'jh->b_next_transaction' during old transaction
+		 * committing if journal aborted, which may fail
+		 * assertion on 'jh->b_frozen_data == NULL'.
+		 */
+		ret = -EROFS;
+		goto out_unlock_bh;
+	}
+
 	if (jh->b_modified == 0) {
 		/*
 		 * This buffer's got modified and becoming part
diff --git a/fs/ksmbd/mgmt/tree_connect.c b/fs/ksmbd/mgmt/tree_connect.c
index 0d28e723a28c..940385c6a913 100644
--- a/fs/ksmbd/mgmt/tree_connect.c
+++ b/fs/ksmbd/mgmt/tree_connect.c
@@ -18,7 +18,7 @@
 struct ksmbd_tree_conn_status
 ksmbd_tree_conn_connect(struct ksmbd_session *sess, char *share_name)
 {
-	struct ksmbd_tree_conn_status status = {-EINVAL, NULL};
+	struct ksmbd_tree_conn_status status = {-ENOENT, NULL};
 	struct ksmbd_tree_connect_response *resp = NULL;
 	struct ksmbd_share_config *sc;
 	struct ksmbd_tree_connect *tree_conn = NULL;
diff --git a/fs/ksmbd/smb2misc.c b/fs/ksmbd/smb2misc.c
index 612ac15a7cf8..b47be71be4c8 100644
--- a/fs/ksmbd/smb2misc.c
+++ b/fs/ksmbd/smb2misc.c
@@ -91,11 +91,6 @@ static int smb2_get_data_area_len(unsigned int *off, unsigned int *len,
 	*off = 0;
 	*len = 0;
 
-	/* error reqeusts do not have data area */
-	if (hdr->Status && hdr->Status != STATUS_MORE_PROCESSING_REQUIRED &&
-	    (((struct smb2_err_rsp *)hdr)->StructureSize) == SMB2_ERROR_STRUCTURE_SIZE2_LE)
-		return ret;
-
 	/*
 	 * Following commands have data areas so we have to get the location
 	 * of the data buffer offset and data buffer length for the particular
@@ -137,8 +132,11 @@ static int smb2_get_data_area_len(unsigned int *off, unsigned int *len,
 		*len = le16_to_cpu(((struct smb2_read_req *)hdr)->ReadChannelInfoLength);
 		break;
 	case SMB2_WRITE:
-		if (((struct smb2_write_req *)hdr)->DataOffset) {
-			*off = le16_to_cpu(((struct smb2_write_req *)hdr)->DataOffset);
+		if (((struct smb2_write_req *)hdr)->DataOffset ||
+		    ((struct smb2_write_req *)hdr)->Length) {
+			*off = max_t(unsigned int,
+				     le16_to_cpu(((struct smb2_write_req *)hdr)->DataOffset),
+				     offsetof(struct smb2_write_req, Buffer) - 4);
 			*len = le32_to_cpu(((struct smb2_write_req *)hdr)->Length);
 			break;
 		}
diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c
index 1ed3046dd5b3..55ee639703ff 100644
--- a/fs/ksmbd/smb2pdu.c
+++ b/fs/ksmbd/smb2pdu.c
@@ -541,9 +541,10 @@ int smb2_allocate_rsp_buf(struct ksmbd_work *work)
 		struct smb2_query_info_req *req;
 
 		req = work->request_buf;
-		if (req->InfoType == SMB2_O_INFO_FILE &&
-		    (req->FileInfoClass == FILE_FULL_EA_INFORMATION ||
-		     req->FileInfoClass == FILE_ALL_INFORMATION))
+		if ((req->InfoType == SMB2_O_INFO_FILE &&
+		     (req->FileInfoClass == FILE_FULL_EA_INFORMATION ||
+		      req->FileInfoClass == FILE_ALL_INFORMATION)) ||
+		    req->InfoType == SMB2_O_INFO_SECURITY)
 			sz = large_sz;
 	}
 
@@ -1146,12 +1147,16 @@ int smb2_handle_negotiate(struct ksmbd_work *work)
 			       status);
 			rsp->hdr.Status = status;
 			rc = -EINVAL;
+			kfree(conn->preauth_info);
+			conn->preauth_info = NULL;
 			goto err_out;
 		}
 
 		rc = init_smb3_11_server(conn);
 		if (rc < 0) {
 			rsp->hdr.Status = STATUS_INVALID_PARAMETER;
+			kfree(conn->preauth_info);
+			conn->preauth_info = NULL;
 			goto err_out;
 		}
 
@@ -1927,8 +1932,9 @@ out_err1:
 		rsp->hdr.Status = STATUS_SUCCESS;
 		rc = 0;
 		break;
+	case -ENOENT:
 	case KSMBD_TREE_CONN_STATUS_NO_SHARE:
-		rsp->hdr.Status = STATUS_BAD_NETWORK_PATH;
+		rsp->hdr.Status = STATUS_BAD_NETWORK_NAME;
 		break;
 	case -ENOMEM:
 	case KSMBD_TREE_CONN_STATUS_NOMEM:
@@ -2040,6 +2046,7 @@ int smb2_tree_disconnect(struct ksmbd_work *work)
 
 	ksmbd_close_tree_conn_fds(work);
 	ksmbd_tree_conn_disconnect(sess, tcon);
+	work->tcon = NULL;
 	return 0;
 }
 
@@ -2312,15 +2319,15 @@ static int smb2_remove_smb_xattrs(struct path *path)
 			name += strlen(name) + 1) {
 		ksmbd_debug(SMB, "%s, len %zd\n", name, strlen(name));
 
-		if (strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) &&
-		    strncmp(&name[XATTR_USER_PREFIX_LEN], DOS_ATTRIBUTE_PREFIX,
-			    DOS_ATTRIBUTE_PREFIX_LEN) &&
-		    strncmp(&name[XATTR_USER_PREFIX_LEN], STREAM_PREFIX, STREAM_PREFIX_LEN))
-			continue;
-
-		err = ksmbd_vfs_remove_xattr(user_ns, path->dentry, name);
-		if (err)
-			ksmbd_debug(SMB, "remove xattr failed : %s\n", name);
+		if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) &&
+		    !strncmp(&name[XATTR_USER_PREFIX_LEN], STREAM_PREFIX,
+			     STREAM_PREFIX_LEN)) {
+			err = ksmbd_vfs_remove_xattr(user_ns, path->dentry,
+						     name);
+			if (err)
+				ksmbd_debug(SMB, "remove xattr failed : %s\n",
+					    name);
+		}
 	}
 out:
 	kvfree(xattr_list);
@@ -2976,7 +2983,7 @@ int smb2_open(struct ksmbd_work *work)
 						goto err_out;
 
 					rc = build_sec_desc(user_ns,
-							    pntsd, NULL,
+							    pntsd, NULL, 0,
 							    OWNER_SECINFO |
 							    GROUP_SECINFO |
 							    DACL_SECINFO,
@@ -3819,6 +3826,15 @@ static int verify_info_level(int info_level)
 	return 0;
 }
 
+static int smb2_resp_buf_len(struct ksmbd_work *work, unsigned short hdr2_len)
+{
+	int free_len;
+
+	free_len = (int)(work->response_sz -
+		(get_rfc1002_len(work->response_buf) + 4)) - hdr2_len;
+	return free_len;
+}
+
 static int smb2_calc_max_out_buf_len(struct ksmbd_work *work,
 				     unsigned short hdr2_len,
 				     unsigned int out_buf_len)
@@ -3828,9 +3844,7 @@ static int smb2_calc_max_out_buf_len(struct ksmbd_work *work,
 	if (out_buf_len > work->conn->vals->max_trans_size)
 		return -EINVAL;
 
-	free_len = (int)(work->response_sz -
-			 (get_rfc1002_len(work->response_buf) + 4)) -
-		hdr2_len;
+	free_len = smb2_resp_buf_len(work, hdr2_len);
 	if (free_len < 0)
 		return -EINVAL;
 
@@ -5082,10 +5096,10 @@ static int smb2_get_info_sec(struct ksmbd_work *work,
 	struct smb_ntsd *pntsd = (struct smb_ntsd *)rsp->Buffer, *ppntsd = NULL;
 	struct smb_fattr fattr = {{0}};
 	struct inode *inode;
-	__u32 secdesclen;
+	__u32 secdesclen = 0;
 	unsigned int id = KSMBD_NO_FID, pid = KSMBD_NO_FID;
 	int addition_info = le32_to_cpu(req->AdditionalInformation);
-	int rc;
+	int rc = 0, ppntsd_size = 0;
 
 	if (addition_info & ~(OWNER_SECINFO | GROUP_SECINFO | DACL_SECINFO |
 			      PROTECTED_DACL_SECINFO |
@@ -5131,11 +5145,14 @@ static int smb2_get_info_sec(struct ksmbd_work *work,
 
 	if (test_share_config_flag(work->tcon->share_conf,
 				   KSMBD_SHARE_FLAG_ACL_XATTR))
-		ksmbd_vfs_get_sd_xattr(work->conn, user_ns,
-				       fp->filp->f_path.dentry, &ppntsd);
-
-	rc = build_sec_desc(user_ns, pntsd, ppntsd, addition_info,
-			    &secdesclen, &fattr);
+		ppntsd_size = ksmbd_vfs_get_sd_xattr(work->conn, user_ns,
+						     fp->filp->f_path.dentry,
+						     &ppntsd);
+
+	/* Check if sd buffer size exceeds response buffer size */
+	if (smb2_resp_buf_len(work, 8) > ppntsd_size)
+		rc = build_sec_desc(user_ns, pntsd, ppntsd, ppntsd_size,
+				    addition_info, &secdesclen, &fattr);
 	posix_acl_release(fattr.cf_acls);
 	posix_acl_release(fattr.cf_dacls);
 	kfree(ppntsd);
@@ -6466,10 +6483,8 @@ int smb2_write(struct ksmbd_work *work)
 		    (offsetof(struct smb2_write_req, Buffer) - 4)) {
 			data_buf = (char *)&req->Buffer[0];
 		} else {
-			if ((u64)le16_to_cpu(req->DataOffset) + length > get_rfc1002_len(req)) {
-				pr_err("invalid write data offset %u, smb_len %u\n",
-				       le16_to_cpu(req->DataOffset),
-				       get_rfc1002_len(req));
+			if (le16_to_cpu(req->DataOffset) <
+			    offsetof(struct smb2_write_req, Buffer)) {
 				err = -EINVAL;
 				goto out;
 			}
@@ -7684,7 +7699,7 @@ int smb2_ioctl(struct ksmbd_work *work)
 	{
 		struct file_zero_data_information *zero_data;
 		struct ksmbd_file *fp;
-		loff_t off, len;
+		loff_t off, len, bfz;
 
 		if (!test_tree_conn_flag(work->tcon, KSMBD_TREE_CONN_FLAG_WRITABLE)) {
 			ksmbd_debug(SMB,
@@ -7701,19 +7716,26 @@ int smb2_ioctl(struct ksmbd_work *work)
 		zero_data =
 			(struct file_zero_data_information *)&req->Buffer[0];
 
-		fp = ksmbd_lookup_fd_fast(work, id);
-		if (!fp) {
-			ret = -ENOENT;
+		off = le64_to_cpu(zero_data->FileOffset);
+		bfz = le64_to_cpu(zero_data->BeyondFinalZero);
+		if (off > bfz) {
+			ret = -EINVAL;
 			goto out;
 		}
 
-		off = le64_to_cpu(zero_data->FileOffset);
-		len = le64_to_cpu(zero_data->BeyondFinalZero) - off;
+		len = bfz - off;
+		if (len) {
+			fp = ksmbd_lookup_fd_fast(work, id);
+			if (!fp) {
+				ret = -ENOENT;
+				goto out;
+			}
 
-		ret = ksmbd_vfs_zero_data(work, fp, off, len);
-		ksmbd_fd_put(work, fp);
-		if (ret < 0)
-			goto out;
+			ret = ksmbd_vfs_zero_data(work, fp, off, len);
+			ksmbd_fd_put(work, fp);
+			if (ret < 0)
+				goto out;
+		}
 		break;
 	}
 	case FSCTL_QUERY_ALLOCATED_RANGES:
@@ -7787,14 +7809,24 @@ int smb2_ioctl(struct ksmbd_work *work)
 		src_off = le64_to_cpu(dup_ext->SourceFileOffset);
 		dst_off = le64_to_cpu(dup_ext->TargetFileOffset);
 		length = le64_to_cpu(dup_ext->ByteCount);
-		cloned = vfs_clone_file_range(fp_in->filp, src_off, fp_out->filp,
-					      dst_off, length, 0);
+		/*
+		 * XXX: It is not clear if FSCTL_DUPLICATE_EXTENTS_TO_FILE
+		 * should fall back to vfs_copy_file_range().  This could be
+		 * beneficial when re-exporting nfs/smb mount, but note that
+		 * this can result in partial copy that returns an error status.
+		 * If/when FSCTL_DUPLICATE_EXTENTS_TO_FILE_EX is implemented,
+		 * fall back to vfs_copy_file_range(), should be avoided when
+		 * the flag DUPLICATE_EXTENTS_DATA_EX_SOURCE_ATOMIC is set.
+		 */
+		cloned = vfs_clone_file_range(fp_in->filp, src_off,
+					      fp_out->filp, dst_off, length, 0);
 		if (cloned == -EXDEV || cloned == -EOPNOTSUPP) {
 			ret = -EOPNOTSUPP;
 			goto dup_ext_out;
 		} else if (cloned != length) {
 			cloned = vfs_copy_file_range(fp_in->filp, src_off,
-						     fp_out->filp, dst_off, length, 0);
+						     fp_out->filp, dst_off,
+						     length, 0);
 			if (cloned != length) {
 				if (cloned < 0)
 					ret = cloned;
diff --git a/fs/ksmbd/smbacl.c b/fs/ksmbd/smbacl.c
index 38f23bf981ac..3781bca2c8fc 100644
--- a/fs/ksmbd/smbacl.c
+++ b/fs/ksmbd/smbacl.c
@@ -690,6 +690,7 @@ posix_default_acl:
 static void set_ntacl_dacl(struct user_namespace *user_ns,
 			   struct smb_acl *pndacl,
 			   struct smb_acl *nt_dacl,
+			   unsigned int aces_size,
 			   const struct smb_sid *pownersid,
 			   const struct smb_sid *pgrpsid,
 			   struct smb_fattr *fattr)
@@ -703,9 +704,19 @@ static void set_ntacl_dacl(struct user_namespace *user_ns,
 	if (nt_num_aces) {
 		ntace = (struct smb_ace *)((char *)nt_dacl + sizeof(struct smb_acl));
 		for (i = 0; i < nt_num_aces; i++) {
-			memcpy((char *)pndace + size, ntace, le16_to_cpu(ntace->size));
-			size += le16_to_cpu(ntace->size);
-			ntace = (struct smb_ace *)((char *)ntace + le16_to_cpu(ntace->size));
+			unsigned short nt_ace_size;
+
+			if (offsetof(struct smb_ace, access_req) > aces_size)
+				break;
+
+			nt_ace_size = le16_to_cpu(ntace->size);
+			if (nt_ace_size > aces_size)
+				break;
+
+			memcpy((char *)pndace + size, ntace, nt_ace_size);
+			size += nt_ace_size;
+			aces_size -= nt_ace_size;
+			ntace = (struct smb_ace *)((char *)ntace + nt_ace_size);
 			num_aces++;
 		}
 	}
@@ -878,7 +889,7 @@ int parse_sec_desc(struct user_namespace *user_ns, struct smb_ntsd *pntsd,
 /* Convert permission bits from mode to equivalent CIFS ACL */
 int build_sec_desc(struct user_namespace *user_ns,
 		   struct smb_ntsd *pntsd, struct smb_ntsd *ppntsd,
-		   int addition_info, __u32 *secdesclen,
+		   int ppntsd_size, int addition_info, __u32 *secdesclen,
 		   struct smb_fattr *fattr)
 {
 	int rc = 0;
@@ -938,15 +949,25 @@ int build_sec_desc(struct user_namespace *user_ns,
 
 		if (!ppntsd) {
 			set_mode_dacl(user_ns, dacl_ptr, fattr);
-		} else if (!ppntsd->dacloffset) {
-			goto out;
 		} else {
 			struct smb_acl *ppdacl_ptr;
+			unsigned int dacl_offset = le32_to_cpu(ppntsd->dacloffset);
+			int ppdacl_size, ntacl_size = ppntsd_size - dacl_offset;
+
+			if (!dacl_offset ||
+			    (dacl_offset + sizeof(struct smb_acl) > ppntsd_size))
+				goto out;
+
+			ppdacl_ptr = (struct smb_acl *)((char *)ppntsd + dacl_offset);
+			ppdacl_size = le16_to_cpu(ppdacl_ptr->size);
+			if (ppdacl_size > ntacl_size ||
+			    ppdacl_size < sizeof(struct smb_acl))
+				goto out;
 
-			ppdacl_ptr = (struct smb_acl *)((char *)ppntsd +
-						le32_to_cpu(ppntsd->dacloffset));
 			set_ntacl_dacl(user_ns, dacl_ptr, ppdacl_ptr,
-				       nowner_sid_ptr, ngroup_sid_ptr, fattr);
+				       ntacl_size - sizeof(struct smb_acl),
+				       nowner_sid_ptr, ngroup_sid_ptr,
+				       fattr);
 		}
 		pntsd->dacloffset = cpu_to_le32(offset);
 		offset += le16_to_cpu(dacl_ptr->size);
@@ -980,24 +1001,31 @@ int smb_inherit_dacl(struct ksmbd_conn *conn,
 	struct smb_sid owner_sid, group_sid;
 	struct dentry *parent = path->dentry->d_parent;
 	struct user_namespace *user_ns = mnt_user_ns(path->mnt);
-	int inherited_flags = 0, flags = 0, i, ace_cnt = 0, nt_size = 0;
-	int rc = 0, num_aces, dacloffset, pntsd_type, acl_len;
+	int inherited_flags = 0, flags = 0, i, ace_cnt = 0, nt_size = 0, pdacl_size;
+	int rc = 0, num_aces, dacloffset, pntsd_type, pntsd_size, acl_len, aces_size;
 	char *aces_base;
 	bool is_dir = S_ISDIR(d_inode(path->dentry)->i_mode);
 
-	acl_len = ksmbd_vfs_get_sd_xattr(conn, user_ns,
-					 parent, &parent_pntsd);
-	if (acl_len <= 0)
+	pntsd_size = ksmbd_vfs_get_sd_xattr(conn, user_ns,
+					    parent, &parent_pntsd);
+	if (pntsd_size <= 0)
 		return -ENOENT;
 	dacloffset = le32_to_cpu(parent_pntsd->dacloffset);
-	if (!dacloffset) {
+	if (!dacloffset || (dacloffset + sizeof(struct smb_acl) > pntsd_size)) {
 		rc = -EINVAL;
 		goto free_parent_pntsd;
 	}
 
 	parent_pdacl = (struct smb_acl *)((char *)parent_pntsd + dacloffset);
+	acl_len = pntsd_size - dacloffset;
 	num_aces = le32_to_cpu(parent_pdacl->num_aces);
 	pntsd_type = le16_to_cpu(parent_pntsd->type);
+	pdacl_size = le16_to_cpu(parent_pdacl->size);
+
+	if (pdacl_size > acl_len || pdacl_size < sizeof(struct smb_acl)) {
+		rc = -EINVAL;
+		goto free_parent_pntsd;
+	}
 
 	aces_base = kmalloc(sizeof(struct smb_ace) * num_aces * 2, GFP_KERNEL);
 	if (!aces_base) {
@@ -1008,11 +1036,23 @@ int smb_inherit_dacl(struct ksmbd_conn *conn,
 	aces = (struct smb_ace *)aces_base;
 	parent_aces = (struct smb_ace *)((char *)parent_pdacl +
 			sizeof(struct smb_acl));
+	aces_size = acl_len - sizeof(struct smb_acl);
 
 	if (pntsd_type & DACL_AUTO_INHERITED)
 		inherited_flags = INHERITED_ACE;
 
 	for (i = 0; i < num_aces; i++) {
+		int pace_size;
+
+		if (offsetof(struct smb_ace, access_req) > aces_size)
+			break;
+
+		pace_size = le16_to_cpu(parent_aces->size);
+		if (pace_size > aces_size)
+			break;
+
+		aces_size -= pace_size;
+
 		flags = parent_aces->flags;
 		if (!smb_inherit_flags(flags, is_dir))
 			goto pass;
@@ -1057,8 +1097,7 @@ int smb_inherit_dacl(struct ksmbd_conn *conn,
 		aces = (struct smb_ace *)((char *)aces + le16_to_cpu(aces->size));
 		ace_cnt++;
 pass:
-		parent_aces =
-			(struct smb_ace *)((char *)parent_aces + le16_to_cpu(parent_aces->size));
+		parent_aces = (struct smb_ace *)((char *)parent_aces + pace_size);
 	}
 
 	if (nt_size > 0) {
@@ -1153,7 +1192,7 @@ int smb_check_perm_dacl(struct ksmbd_conn *conn, struct path *path,
 	struct smb_ntsd *pntsd = NULL;
 	struct smb_acl *pdacl;
 	struct posix_acl *posix_acls;
-	int rc = 0, acl_size;
+	int rc = 0, pntsd_size, acl_size, aces_size, pdacl_size, dacl_offset;
 	struct smb_sid sid;
 	int granted = le32_to_cpu(*pdaccess & ~FILE_MAXIMAL_ACCESS_LE);
 	struct smb_ace *ace;
@@ -1162,37 +1201,33 @@ int smb_check_perm_dacl(struct ksmbd_conn *conn, struct path *path,
 	struct smb_ace *others_ace = NULL;
 	struct posix_acl_entry *pa_entry;
 	unsigned int sid_type = SIDOWNER;
-	char *end_of_acl;
+	unsigned short ace_size;
 
 	ksmbd_debug(SMB, "check permission using windows acl\n");
-	acl_size = ksmbd_vfs_get_sd_xattr(conn, user_ns,
-					  path->dentry, &pntsd);
-	if (acl_size <= 0 || !pntsd || !pntsd->dacloffset) {
-		kfree(pntsd);
-		return 0;
-	}
+	pntsd_size = ksmbd_vfs_get_sd_xattr(conn, user_ns,
+					    path->dentry, &pntsd);
+	if (pntsd_size <= 0 || !pntsd)
+		goto err_out;
+
+	dacl_offset = le32_to_cpu(pntsd->dacloffset);
+	if (!dacl_offset ||
+	    (dacl_offset + sizeof(struct smb_acl) > pntsd_size))
+		goto err_out;
 
 	pdacl = (struct smb_acl *)((char *)pntsd + le32_to_cpu(pntsd->dacloffset));
-	end_of_acl = ((char *)pntsd) + acl_size;
-	if (end_of_acl <= (char *)pdacl) {
-		kfree(pntsd);
-		return 0;
-	}
+	acl_size = pntsd_size - dacl_offset;
+	pdacl_size = le16_to_cpu(pdacl->size);
 
-	if (end_of_acl < (char *)pdacl + le16_to_cpu(pdacl->size) ||
-	    le16_to_cpu(pdacl->size) < sizeof(struct smb_acl)) {
-		kfree(pntsd);
-		return 0;
-	}
+	if (pdacl_size > acl_size || pdacl_size < sizeof(struct smb_acl))
+		goto err_out;
 
 	if (!pdacl->num_aces) {
-		if (!(le16_to_cpu(pdacl->size) - sizeof(struct smb_acl)) &&
+		if (!(pdacl_size - sizeof(struct smb_acl)) &&
 		    *pdaccess & ~(FILE_READ_CONTROL_LE | FILE_WRITE_DAC_LE)) {
 			rc = -EACCES;
 			goto err_out;
 		}
-		kfree(pntsd);
-		return 0;
+		goto err_out;
 	}
 
 	if (*pdaccess & FILE_MAXIMAL_ACCESS_LE) {
@@ -1200,11 +1235,16 @@ int smb_check_perm_dacl(struct ksmbd_conn *conn, struct path *path,
 			DELETE;
 
 		ace = (struct smb_ace *)((char *)pdacl + sizeof(struct smb_acl));
+		aces_size = acl_size - sizeof(struct smb_acl);
 		for (i = 0; i < le32_to_cpu(pdacl->num_aces); i++) {
+			if (offsetof(struct smb_ace, access_req) > aces_size)
+				break;
+			ace_size = le16_to_cpu(ace->size);
+			if (ace_size > aces_size)
+				break;
+			aces_size -= ace_size;
 			granted |= le32_to_cpu(ace->access_req);
 			ace = (struct smb_ace *)((char *)ace + le16_to_cpu(ace->size));
-			if (end_of_acl < (char *)ace)
-				goto err_out;
 		}
 
 		if (!pdacl->num_aces)
@@ -1216,7 +1256,15 @@ int smb_check_perm_dacl(struct ksmbd_conn *conn, struct path *path,
 	id_to_sid(uid, sid_type, &sid);
 
 	ace = (struct smb_ace *)((char *)pdacl + sizeof(struct smb_acl));
+	aces_size = acl_size - sizeof(struct smb_acl);
 	for (i = 0; i < le32_to_cpu(pdacl->num_aces); i++) {
+		if (offsetof(struct smb_ace, access_req) > aces_size)
+			break;
+		ace_size = le16_to_cpu(ace->size);
+		if (ace_size > aces_size)
+			break;
+		aces_size -= ace_size;
+
 		if (!compare_sids(&sid, &ace->sid) ||
 		    !compare_sids(&sid_unix_NFS_mode, &ace->sid)) {
 			found = 1;
@@ -1226,8 +1274,6 @@ int smb_check_perm_dacl(struct ksmbd_conn *conn, struct path *path,
 			others_ace = ace;
 
 		ace = (struct smb_ace *)((char *)ace + le16_to_cpu(ace->size));
-		if (end_of_acl < (char *)ace)
-			goto err_out;
 	}
 
 	if (*pdaccess & FILE_MAXIMAL_ACCESS_LE && found) {
diff --git a/fs/ksmbd/smbacl.h b/fs/ksmbd/smbacl.h
index 811af3309429..fcb2c83f2992 100644
--- a/fs/ksmbd/smbacl.h
+++ b/fs/ksmbd/smbacl.h
@@ -193,7 +193,7 @@ struct posix_acl_state {
 int parse_sec_desc(struct user_namespace *user_ns, struct smb_ntsd *pntsd,
 		   int acl_len, struct smb_fattr *fattr);
 int build_sec_desc(struct user_namespace *user_ns, struct smb_ntsd *pntsd,
-		   struct smb_ntsd *ppntsd, int addition_info,
+		   struct smb_ntsd *ppntsd, int ppntsd_size, int addition_info,
 		   __u32 *secdesclen, struct smb_fattr *fattr);
 int init_acl_state(struct posix_acl_state *state, int cnt);
 void free_acl_state(struct posix_acl_state *state);
diff --git a/fs/ksmbd/transport_tcp.c b/fs/ksmbd/transport_tcp.c
index 82a1429bbe12..755329c295ca 100644
--- a/fs/ksmbd/transport_tcp.c
+++ b/fs/ksmbd/transport_tcp.c
@@ -230,7 +230,7 @@ static int ksmbd_kthread_fn(void *p)
 			break;
 		}
 		ret = kernel_accept(iface->ksmbd_socket, &client_sk,
-				    O_NONBLOCK);
+				    SOCK_NONBLOCK);
 		mutex_unlock(&iface->sock_release_lock);
 		if (ret) {
 			if (ret == -EAGAIN)
diff --git a/fs/ksmbd/vfs.c b/fs/ksmbd/vfs.c
index 835b384b0895..513989b1c8cd 100644
--- a/fs/ksmbd/vfs.c
+++ b/fs/ksmbd/vfs.c
@@ -1018,7 +1018,9 @@ int ksmbd_vfs_zero_data(struct ksmbd_work *work, struct ksmbd_file *fp,
 				     FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
 				     off, len);
 
-	return vfs_fallocate(fp->filp, FALLOC_FL_ZERO_RANGE, off, len);
+	return vfs_fallocate(fp->filp,
+			     FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE,
+			     off, len);
 }
 
 int ksmbd_vfs_fqar_lseek(struct ksmbd_file *fp, loff_t start, loff_t length,
@@ -1049,7 +1051,7 @@ int ksmbd_vfs_fqar_lseek(struct ksmbd_file *fp, loff_t start, loff_t length,
 	*out_count = 0;
 	end = start + length;
 	while (start < end && *out_count < in_count) {
-		extent_start = f->f_op->llseek(f, start, SEEK_DATA);
+		extent_start = vfs_llseek(f, start, SEEK_DATA);
 		if (extent_start < 0) {
 			if (extent_start != -ENXIO)
 				ret = (int)extent_start;
@@ -1059,7 +1061,7 @@ int ksmbd_vfs_fqar_lseek(struct ksmbd_file *fp, loff_t start, loff_t length,
 		if (extent_start >= end)
 			break;
 
-		extent_end = f->f_op->llseek(f, extent_start, SEEK_HOLE);
+		extent_end = vfs_llseek(f, extent_start, SEEK_HOLE);
 		if (extent_end < 0) {
 			if (extent_end != -ENXIO)
 				ret = (int)extent_end;
@@ -1541,6 +1543,11 @@ int ksmbd_vfs_get_sd_xattr(struct ksmbd_conn *conn,
 	}
 
 	*pntsd = acl.sd_buf;
+	if (acl.sd_size < sizeof(struct smb_ntsd)) {
+		pr_err("sd size is invalid\n");
+		goto out_free;
+	}
+
 	(*pntsd)->osidoffset = cpu_to_le32(le32_to_cpu((*pntsd)->osidoffset) -
 					   NDR_NTSD_OFFSETOF);
 	(*pntsd)->gsidoffset = cpu_to_le32(le32_to_cpu((*pntsd)->gsidoffset) -
@@ -1780,6 +1787,10 @@ int ksmbd_vfs_copy_file_ranges(struct ksmbd_work *work,
 
 		ret = vfs_copy_file_range(src_fp->filp, src_off,
 					  dst_fp->filp, dst_off, len, 0);
+		if (ret == -EOPNOTSUPP || ret == -EXDEV)
+			ret = generic_copy_file_range(src_fp->filp, src_off,
+						      dst_fp->filp, dst_off,
+						      len, 0);
 		if (ret < 0)
 			return ret;
 
diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index e10ae2c41279..1c9214801e69 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -32,6 +32,10 @@ nlm4svc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp,
 	if (!nlmsvc_ops)
 		return nlm_lck_denied_nolocks;
 
+	if (lock->lock_start > OFFSET_MAX ||
+	    (lock->lock_len && ((lock->lock_len - 1) > (OFFSET_MAX - lock->lock_start))))
+		return nlm4_fbig;
+
 	/* Obtain host handle */
 	if (!(host = nlmsvc_lookup_host(rqstp, lock->caller, lock->len))
 	 || (argp->monitor && nsm_monitor(host) < 0))
@@ -50,6 +54,10 @@ nlm4svc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp,
 		/* Set up the missing parts of the file_lock structure */
 		lock->fl.fl_file  = file->f_file[mode];
 		lock->fl.fl_pid = current->tgid;
+		lock->fl.fl_start = (loff_t)lock->lock_start;
+		lock->fl.fl_end = lock->lock_len ?
+				   (loff_t)(lock->lock_start + lock->lock_len - 1) :
+				   OFFSET_MAX;
 		lock->fl.fl_lmops = &nlmsvc_lock_operations;
 		nlmsvc_locks_init_private(&lock->fl, host, (pid_t)lock->svid);
 		if (!lock->fl.fl_owner) {
diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c
index 0a22a2faf552..e1c4617de771 100644
--- a/fs/lockd/svcsubs.c
+++ b/fs/lockd/svcsubs.c
@@ -176,7 +176,7 @@ nlm_delete_file(struct nlm_file *file)
 	}
 }
 
-static int nlm_unlock_files(struct nlm_file *file)
+static int nlm_unlock_files(struct nlm_file *file, fl_owner_t owner)
 {
 	struct file_lock lock;
 
@@ -184,6 +184,7 @@ static int nlm_unlock_files(struct nlm_file *file)
 	lock.fl_type  = F_UNLCK;
 	lock.fl_start = 0;
 	lock.fl_end   = OFFSET_MAX;
+	lock.fl_owner = owner;
 	if (file->f_file[O_RDONLY] &&
 	    vfs_lock_file(file->f_file[O_RDONLY], F_SETLK, &lock, NULL))
 		goto out_err;
@@ -225,7 +226,7 @@ again:
 		if (match(lockhost, host)) {
 
 			spin_unlock(&flctx->flc_lock);
-			if (nlm_unlock_files(file))
+			if (nlm_unlock_files(file, fl->fl_owner))
 				return 1;
 			goto again;
 		}
@@ -282,11 +283,10 @@ nlm_file_inuse(struct nlm_file *file)
 
 static void nlm_close_files(struct nlm_file *file)
 {
-	struct file *f;
-
-	for (f = file->f_file[0]; f <= file->f_file[1]; f++)
-		if (f)
-			nlmsvc_ops->fclose(f);
+	if (file->f_file[O_RDONLY])
+		nlmsvc_ops->fclose(file->f_file[O_RDONLY]);
+	if (file->f_file[O_WRONLY])
+		nlmsvc_ops->fclose(file->f_file[O_WRONLY]);
 }
 
 /*
diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c
index 98e957e4566c..72f7d190fb3b 100644
--- a/fs/lockd/xdr4.c
+++ b/fs/lockd/xdr4.c
@@ -20,13 +20,6 @@
 
 #include "svcxdr.h"
 
-static inline loff_t
-s64_to_loff_t(__s64 offset)
-{
-	return (loff_t)offset;
-}
-
-
 static inline s64
 loff_t_to_s64(loff_t offset)
 {
@@ -70,8 +63,6 @@ static bool
 svcxdr_decode_lock(struct xdr_stream *xdr, struct nlm_lock *lock)
 {
 	struct file_lock *fl = &lock->fl;
-	u64 len, start;
-	s64 end;
 
 	if (!svcxdr_decode_string(xdr, &lock->caller, &lock->len))
 		return false;
@@ -81,20 +72,14 @@ svcxdr_decode_lock(struct xdr_stream *xdr, struct nlm_lock *lock)
 		return false;
 	if (xdr_stream_decode_u32(xdr, &lock->svid) < 0)
 		return false;
-	if (xdr_stream_decode_u64(xdr, &start) < 0)
+	if (xdr_stream_decode_u64(xdr, &lock->lock_start) < 0)
 		return false;
-	if (xdr_stream_decode_u64(xdr, &len) < 0)
+	if (xdr_stream_decode_u64(xdr, &lock->lock_len) < 0)
 		return false;
 
 	locks_init_lock(fl);
 	fl->fl_flags = FL_POSIX;
 	fl->fl_type  = F_RDLCK;
-	end = start + len - 1;
-	fl->fl_start = s64_to_loff_t(start);
-	if (len == 0 || end < 0)
-		fl->fl_end = OFFSET_MAX;
-	else
-		fl->fl_end = s64_to_loff_t(end);
 
 	return true;
 }
diff --git a/fs/mbcache.c b/fs/mbcache.c
index 97c54d3a2227..2010bc80a3f2 100644
--- a/fs/mbcache.c
+++ b/fs/mbcache.c
@@ -11,7 +11,7 @@
 /*
  * Mbcache is a simple key-value store. Keys need not be unique, however
  * key-value pairs are expected to be unique (we use this fact in
- * mb_cache_entry_delete()).
+ * mb_cache_entry_delete_or_get()).
  *
  * Ext2 and ext4 use this cache for deduplication of extended attribute blocks.
  * Ext4 also uses it for deduplication of xattr values stored in inodes.
@@ -125,6 +125,19 @@ void __mb_cache_entry_free(struct mb_cache_entry *entry)
 }
 EXPORT_SYMBOL(__mb_cache_entry_free);
 
+/*
+ * mb_cache_entry_wait_unused - wait to be the last user of the entry
+ *
+ * @entry - entry to work on
+ *
+ * Wait to be the last user of the entry.
+ */
+void mb_cache_entry_wait_unused(struct mb_cache_entry *entry)
+{
+	wait_var_event(&entry->e_refcnt, atomic_read(&entry->e_refcnt) <= 3);
+}
+EXPORT_SYMBOL(mb_cache_entry_wait_unused);
+
 static struct mb_cache_entry *__entry_find(struct mb_cache *cache,
 					   struct mb_cache_entry *entry,
 					   u32 key)
@@ -217,7 +230,7 @@ out:
 }
 EXPORT_SYMBOL(mb_cache_entry_get);
 
-/* mb_cache_entry_delete - remove a cache entry
+/* mb_cache_entry_delete - try to remove a cache entry
  * @cache - cache we work with
  * @key - key
  * @value - value
@@ -254,6 +267,55 @@ void mb_cache_entry_delete(struct mb_cache *cache, u32 key, u64 value)
 }
 EXPORT_SYMBOL(mb_cache_entry_delete);
 
+/* mb_cache_entry_delete_or_get - remove a cache entry if it has no users
+ * @cache - cache we work with
+ * @key - key
+ * @value - value
+ *
+ * Remove entry from cache @cache with key @key and value @value. The removal
+ * happens only if the entry is unused. The function returns NULL in case the
+ * entry was successfully removed or there's no entry in cache. Otherwise the
+ * function grabs reference of the entry that we failed to delete because it
+ * still has users and return it.
+ */
+struct mb_cache_entry *mb_cache_entry_delete_or_get(struct mb_cache *cache,
+						    u32 key, u64 value)
+{
+	struct hlist_bl_node *node;
+	struct hlist_bl_head *head;
+	struct mb_cache_entry *entry;
+
+	head = mb_cache_entry_head(cache, key);
+	hlist_bl_lock(head);
+	hlist_bl_for_each_entry(entry, node, head, e_hash_list) {
+		if (entry->e_key == key && entry->e_value == value) {
+			if (atomic_read(&entry->e_refcnt) > 2) {
+				atomic_inc(&entry->e_refcnt);
+				hlist_bl_unlock(head);
+				return entry;
+			}
+			/* We keep hash list reference to keep entry alive */
+			hlist_bl_del_init(&entry->e_hash_list);
+			hlist_bl_unlock(head);
+			spin_lock(&cache->c_list_lock);
+			if (!list_empty(&entry->e_list)) {
+				list_del_init(&entry->e_list);
+				if (!WARN_ONCE(cache->c_entry_count == 0,
+		"mbcache: attempt to decrement c_entry_count past zero"))
+					cache->c_entry_count--;
+				atomic_dec(&entry->e_refcnt);
+			}
+			spin_unlock(&cache->c_list_lock);
+			mb_cache_entry_put(cache, entry);
+			return NULL;
+		}
+	}
+	hlist_bl_unlock(head);
+
+	return NULL;
+}
+EXPORT_SYMBOL(mb_cache_entry_delete_or_get);
+
 /* mb_cache_entry_touch - cache entry got used
  * @cache - cache the entry belongs to
  * @entry - entry that got used
@@ -288,7 +350,7 @@ static unsigned long mb_cache_shrink(struct mb_cache *cache,
 	while (nr_to_scan-- && !list_empty(&cache->c_list)) {
 		entry = list_first_entry(&cache->c_list,
 					 struct mb_cache_entry, e_list);
-		if (entry->e_referenced) {
+		if (entry->e_referenced || atomic_read(&entry->e_refcnt) > 2) {
 			entry->e_referenced = 0;
 			list_move_tail(&entry->e_list, &cache->c_list);
 			continue;
@@ -302,6 +364,14 @@ static unsigned long mb_cache_shrink(struct mb_cache *cache,
 		spin_unlock(&cache->c_list_lock);
 		head = mb_cache_entry_head(cache, entry->e_key);
 		hlist_bl_lock(head);
+		/* Now a reliable check if the entry didn't get used... */
+		if (atomic_read(&entry->e_refcnt) > 2) {
+			hlist_bl_unlock(head);
+			spin_lock(&cache->c_list_lock);
+			list_add_tail(&entry->e_list, &cache->c_list);
+			cache->c_entry_count++;
+			continue;
+		}
 		if (!hlist_bl_unhashed(&entry->e_hash_list)) {
 			hlist_bl_del_init(&entry->e_hash_list);
 			atomic_dec(&entry->e_refcnt);
diff --git a/fs/namei.c b/fs/namei.c
index 2ea15d043412..1fd854d4cd2c 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1461,6 +1461,8 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
 				 * becoming unpinned.
 				 */
 				flags = dentry->d_flags;
+				if (read_seqretry(&mount_lock, nd->m_seq))
+					return false;
 				continue;
 			}
 			if (read_seqretry(&mount_lock, nd->m_seq))
@@ -3523,6 +3525,8 @@ struct dentry *vfs_tmpfile(struct user_namespace *mnt_userns,
 	child = d_alloc(dentry, &slash_name);
 	if (unlikely(!child))
 		goto out_err;
+	if (!IS_POSIXACL(dir))
+		mode &= ~current_umask();
 	error = dir->i_op->tmpfile(mnt_userns, dir, child, mode);
 	if (error)
 		goto out_err;
diff --git a/fs/namespace.c b/fs/namespace.c
index dc31ad6b370f..d946298691ed 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -4168,6 +4168,13 @@ static int build_mount_idmapped(const struct mount_attr *attr, size_t usize,
 		err = -EPERM;
 		goto out_fput;
 	}
+
+	/* We're not controlling the target namespace. */
+	if (!ns_capable(mnt_userns, CAP_SYS_ADMIN)) {
+		err = -EPERM;
+		goto out_fput;
+	}
+
 	kattr->mnt_userns = get_user_ns(mnt_userns);
 
 out_fput:
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 78219396788b..32c3d0c454b1 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -78,6 +78,7 @@ static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir
 		ctx->attr_gencount = nfsi->attr_gencount;
 		ctx->dir_cookie = 0;
 		ctx->dup_cookie = 0;
+		ctx->page_index = 0;
 		spin_lock(&dir->i_lock);
 		if (list_empty(&nfsi->open_files) &&
 		    (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER))
@@ -85,6 +86,7 @@ static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir
 					      NFS_INO_INVALID_DATA |
 						      NFS_INO_REVAL_FORCED);
 		list_add(&ctx->list, &nfsi->open_files);
+		clear_bit(NFS_INO_FORCE_READDIR, &nfsi->flags);
 		spin_unlock(&dir->i_lock);
 		return ctx;
 	}
@@ -626,8 +628,7 @@ void nfs_force_use_readdirplus(struct inode *dir)
 	if (nfs_server_capable(dir, NFS_CAP_READDIRPLUS) &&
 	    !list_empty(&nfsi->open_files)) {
 		set_bit(NFS_INO_ADVISE_RDPLUS, &nfsi->flags);
-		invalidate_mapping_pages(dir->i_mapping,
-			nfsi->page_index + 1, -1);
+		set_bit(NFS_INO_FORCE_READDIR, &nfsi->flags);
 	}
 }
 
@@ -938,10 +939,8 @@ static int find_and_lock_cache_page(struct nfs_readdir_descriptor *desc)
 			       sizeof(nfsi->cookieverf));
 	}
 	res = nfs_readdir_search_array(desc);
-	if (res == 0) {
-		nfsi->page_index = desc->page_index;
+	if (res == 0)
 		return 0;
-	}
 	nfs_readdir_page_unlock_and_put_cached(desc);
 	return res;
 }
@@ -1081,6 +1080,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs_open_dir_context *dir_ctx = file->private_data;
 	struct nfs_readdir_descriptor *desc;
+	pgoff_t page_index;
 	int res;
 
 	dfprintk(FILE, "NFS: readdir(%pD2) starting at cookie %llu\n",
@@ -1111,10 +1111,15 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 	desc->dir_cookie = dir_ctx->dir_cookie;
 	desc->dup_cookie = dir_ctx->dup_cookie;
 	desc->duped = dir_ctx->duped;
+	page_index = dir_ctx->page_index;
 	desc->attr_gencount = dir_ctx->attr_gencount;
 	memcpy(desc->verf, dir_ctx->verf, sizeof(desc->verf));
 	spin_unlock(&file->f_lock);
 
+	if (test_and_clear_bit(NFS_INO_FORCE_READDIR, &nfsi->flags) &&
+	    list_is_singular(&nfsi->open_files))
+		invalidate_mapping_pages(inode->i_mapping, page_index + 1, -1);
+
 	do {
 		res = readdir_search_pagecache(desc);
 
@@ -1151,6 +1156,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 	dir_ctx->dup_cookie = desc->dup_cookie;
 	dir_ctx->duped = desc->duped;
 	dir_ctx->attr_gencount = desc->attr_gencount;
+	dir_ctx->page_index = desc->page_index;
 	memcpy(dir_ctx->verf, desc->verf, sizeof(dir_ctx->verf));
 	spin_unlock(&file->f_lock);
 
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index a8693cc50c7c..ad5114e48009 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -223,8 +223,10 @@ nfs_file_fsync_commit(struct file *file, int datasync)
 int
 nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 {
-	struct nfs_open_context *ctx = nfs_file_open_context(file);
 	struct inode *inode = file_inode(file);
+	struct nfs_inode *nfsi = NFS_I(inode);
+	long save_nredirtied = atomic_long_read(&nfsi->redirtied_pages);
+	long nredirtied;
 	int ret;
 
 	trace_nfs_fsync_enter(inode);
@@ -239,15 +241,10 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 		ret = pnfs_sync_inode(inode, !!datasync);
 		if (ret != 0)
 			break;
-		if (!test_and_clear_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags))
+		nredirtied = atomic_long_read(&nfsi->redirtied_pages);
+		if (nredirtied == save_nredirtied)
 			break;
-		/*
-		 * If nfs_file_fsync_commit detected a server reboot, then
-		 * resend all dirty pages that might have been covered by
-		 * the NFS_CONTEXT_RESEND_WRITES flag
-		 */
-		start = 0;
-		end = LLONG_MAX;
+		save_nredirtied = nredirtied;
 	}
 
 	trace_nfs_fsync_exit(inode, ret);
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index d383de00d486..ceef75b4d249 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1140,6 +1140,8 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task,
 	case -EIO:
 	case -ETIMEDOUT:
 	case -EPIPE:
+	case -EPROTO:
+	case -ENODEV:
 		dprintk("%s DS connection error %d\n", __func__,
 			task->tk_status);
 		nfs4_delete_deviceid(devid->ld, devid->nfs_client,
@@ -1245,6 +1247,8 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg,
 		case -ENOBUFS:
 		case -EPIPE:
 		case -EPERM:
+		case -EPROTO:
+		case -ENODEV:
 			*op_status = status = NFS4ERR_NXIO;
 			break;
 		case -EACCES:
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index cb407af9e9e9..e4524635a129 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -431,6 +431,23 @@ nfs_ilookup(struct super_block *sb, struct nfs_fattr *fattr, struct nfs_fh *fh)
 	return inode;
 }
 
+static void nfs_inode_init_regular(struct nfs_inode *nfsi)
+{
+	atomic_long_set(&nfsi->nrequests, 0);
+	atomic_long_set(&nfsi->redirtied_pages, 0);
+	INIT_LIST_HEAD(&nfsi->commit_info.list);
+	atomic_long_set(&nfsi->commit_info.ncommit, 0);
+	atomic_set(&nfsi->commit_info.rpcs_out, 0);
+	mutex_init(&nfsi->commit_mutex);
+}
+
+static void nfs_inode_init_dir(struct nfs_inode *nfsi)
+{
+	nfsi->cache_change_attribute = 0;
+	memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
+	init_rwsem(&nfsi->rmdir_sem);
+}
+
 /*
  * This is our front-end to iget that looks up inodes by file handle
  * instead of inode number.
@@ -485,10 +502,12 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
 		if (S_ISREG(inode->i_mode)) {
 			inode->i_fop = NFS_SB(sb)->nfs_client->rpc_ops->file_ops;
 			inode->i_data.a_ops = &nfs_file_aops;
+			nfs_inode_init_regular(nfsi);
 		} else if (S_ISDIR(inode->i_mode)) {
 			inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->dir_inode_ops;
 			inode->i_fop = &nfs_dir_operations;
 			inode->i_data.a_ops = &nfs_dir_aops;
+			nfs_inode_init_dir(nfsi);
 			/* Deal with crossing mountpoints */
 			if (fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT ||
 					fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) {
@@ -514,7 +533,6 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
 		inode->i_uid = make_kuid(&init_user_ns, -2);
 		inode->i_gid = make_kgid(&init_user_ns, -2);
 		inode->i_blocks = 0;
-		memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
 		nfsi->write_io = 0;
 		nfsi->read_io = 0;
 
@@ -2282,14 +2300,7 @@ static void init_once(void *foo)
 	INIT_LIST_HEAD(&nfsi->open_files);
 	INIT_LIST_HEAD(&nfsi->access_cache_entry_lru);
 	INIT_LIST_HEAD(&nfsi->access_cache_inode_lru);
-	INIT_LIST_HEAD(&nfsi->commit_info.list);
-	atomic_long_set(&nfsi->nrequests, 0);
-	atomic_long_set(&nfsi->commit_info.ncommit, 0);
-	atomic_set(&nfsi->commit_info.rpcs_out, 0);
-	init_rwsem(&nfsi->rmdir_sem);
-	mutex_init(&nfsi->commit_mutex);
 	nfs4_init_once(nfsi);
-	nfsi->cache_change_attribute = 0;
 }
 
 static int __init nfs_init_inodecache(void)
diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c
index 5601e47360c2..b49359afac88 100644
--- a/fs/nfs/nfs3client.c
+++ b/fs/nfs/nfs3client.c
@@ -108,7 +108,6 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv,
 	if (mds_srv->flags & NFS_MOUNT_NORESVPORT)
 		__set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
 
-	__set_bit(NFS_CS_NOPING, &cl_init.init_flags);
 	__set_bit(NFS_CS_DS, &cl_init.init_flags);
 
 	/* Use the MDS nfs_client cl_ipaddr. */
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 4120e1cb3fee..14f2efdecc2f 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -319,7 +319,7 @@ static int read_name_gen = 1;
 static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt,
 		struct nfs_fh *src_fh, nfs4_stateid *stateid)
 {
-	struct nfs_fattr fattr;
+	struct nfs_fattr *fattr = nfs_alloc_fattr();
 	struct file *filep, *res;
 	struct nfs_server *server;
 	struct inode *r_ino = NULL;
@@ -330,14 +330,20 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt,
 
 	server = NFS_SERVER(ss_mnt->mnt_root->d_inode);
 
-	nfs_fattr_init(&fattr);
+	if (!fattr)
+		return ERR_PTR(-ENOMEM);
 
-	status = nfs4_proc_getattr(server, src_fh, &fattr, NULL, NULL);
+	status = nfs4_proc_getattr(server, src_fh, fattr, NULL, NULL);
 	if (status < 0) {
 		res = ERR_PTR(status);
 		goto out;
 	}
 
+	if (!S_ISREG(fattr->mode)) {
+		res = ERR_PTR(-EBADF);
+		goto out;
+	}
+
 	res = ERR_PTR(-ENOMEM);
 	len = strlen(SSC_READ_NAME_BODY) + 16;
 	read_name = kzalloc(len, GFP_NOFS);
@@ -345,7 +351,7 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt,
 		goto out;
 	snprintf(read_name, len, SSC_READ_NAME_BODY, read_name_gen++);
 
-	r_ino = nfs_fhget(ss_mnt->mnt_root->d_inode->i_sb, src_fh, &fattr,
+	r_ino = nfs_fhget(ss_mnt->mnt_root->d_inode->i_sb, src_fh, fattr,
 			NULL);
 	if (IS_ERR(r_ino)) {
 		res = ERR_CAST(r_ino);
@@ -356,6 +362,7 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt,
 				     r_ino->i_fop);
 	if (IS_ERR(filep)) {
 		res = ERR_CAST(filep);
+		iput(r_ino);
 		goto out_free_name;
 	}
 	filep->f_mode |= FMODE_READ;
@@ -390,6 +397,7 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt,
 out_free_name:
 	kfree(read_name);
 out:
+	nfs_free_fattr(fattr);
 	return res;
 out_stateowner:
 	nfs4_put_state_owner(sp);
diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c
index f331866dd418..ec6afd3c4bca 100644
--- a/fs/nfs/nfs4idmap.c
+++ b/fs/nfs/nfs4idmap.c
@@ -561,22 +561,20 @@ nfs_idmap_prepare_pipe_upcall(struct idmap *idmap,
 	return true;
 }
 
-static void
-nfs_idmap_complete_pipe_upcall_locked(struct idmap *idmap, int ret)
+static void nfs_idmap_complete_pipe_upcall(struct idmap_legacy_upcalldata *data,
+					   int ret)
 {
-	struct key *authkey = idmap->idmap_upcall_data->authkey;
-
-	kfree(idmap->idmap_upcall_data);
-	idmap->idmap_upcall_data = NULL;
-	complete_request_key(authkey, ret);
-	key_put(authkey);
+	complete_request_key(data->authkey, ret);
+	key_put(data->authkey);
+	kfree(data);
 }
 
-static void
-nfs_idmap_abort_pipe_upcall(struct idmap *idmap, int ret)
+static void nfs_idmap_abort_pipe_upcall(struct idmap *idmap,
+					struct idmap_legacy_upcalldata *data,
+					int ret)
 {
-	if (idmap->idmap_upcall_data != NULL)
-		nfs_idmap_complete_pipe_upcall_locked(idmap, ret);
+	if (cmpxchg(&idmap->idmap_upcall_data, data, NULL) == data)
+		nfs_idmap_complete_pipe_upcall(data, ret);
 }
 
 static int nfs_idmap_legacy_upcall(struct key *authkey, void *aux)
@@ -613,7 +611,7 @@ static int nfs_idmap_legacy_upcall(struct key *authkey, void *aux)
 
 	ret = rpc_queue_upcall(idmap->idmap_pipe, msg);
 	if (ret < 0)
-		nfs_idmap_abort_pipe_upcall(idmap, ret);
+		nfs_idmap_abort_pipe_upcall(idmap, data, ret);
 
 	return ret;
 out2:
@@ -669,6 +667,7 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
 	struct request_key_auth *rka;
 	struct rpc_inode *rpci = RPC_I(file_inode(filp));
 	struct idmap *idmap = (struct idmap *)rpci->private;
+	struct idmap_legacy_upcalldata *data;
 	struct key *authkey;
 	struct idmap_msg im;
 	size_t namelen_in;
@@ -678,10 +677,11 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
 	 * will have been woken up and someone else may now have used
 	 * idmap_key_cons - so after this point we may no longer touch it.
 	 */
-	if (idmap->idmap_upcall_data == NULL)
+	data = xchg(&idmap->idmap_upcall_data, NULL);
+	if (data == NULL)
 		goto out_noupcall;
 
-	authkey = idmap->idmap_upcall_data->authkey;
+	authkey = data->authkey;
 	rka = get_request_key_auth(authkey);
 
 	if (mlen != sizeof(im)) {
@@ -703,18 +703,17 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
 	if (namelen_in == 0 || namelen_in == IDMAP_NAMESZ) {
 		ret = -EINVAL;
 		goto out;
-}
+	}
 
-	ret = nfs_idmap_read_and_verify_message(&im,
-			&idmap->idmap_upcall_data->idmap_msg,
-			rka->target_key, authkey);
+	ret = nfs_idmap_read_and_verify_message(&im, &data->idmap_msg,
+						rka->target_key, authkey);
 	if (ret >= 0) {
 		key_set_timeout(rka->target_key, nfs_idmap_cache_timeout);
 		ret = mlen;
 	}
 
 out:
-	nfs_idmap_complete_pipe_upcall_locked(idmap, ret);
+	nfs_idmap_complete_pipe_upcall(data, ret);
 out_noupcall:
 	return ret;
 }
@@ -728,7 +727,7 @@ idmap_pipe_destroy_msg(struct rpc_pipe_msg *msg)
 	struct idmap *idmap = data->idmap;
 
 	if (msg->errno)
-		nfs_idmap_abort_pipe_upcall(idmap, msg->errno);
+		nfs_idmap_abort_pipe_upcall(idmap, data, msg->errno);
 }
 
 static void
@@ -736,8 +735,11 @@ idmap_release_pipe(struct inode *inode)
 {
 	struct rpc_inode *rpci = RPC_I(inode);
 	struct idmap *idmap = (struct idmap *)rpci->private;
+	struct idmap_legacy_upcalldata *data;
 
-	nfs_idmap_abort_pipe_upcall(idmap, -EPIPE);
+	data = xchg(&idmap->idmap_upcall_data, NULL);
+	if (data)
+		nfs_idmap_complete_pipe_upcall(data, -EPIPE);
 }
 
 int nfs_map_name_to_uid(const struct nfs_server *server, const char *name, size_t namelen, kuid_t *uid)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index cbb39aff8182..a808763c52c1 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -787,10 +787,9 @@ static void nfs4_slot_sequence_record_sent(struct nfs4_slot *slot,
 	if ((s32)(seqnr - slot->seq_nr_highest_sent) > 0)
 		slot->seq_nr_highest_sent = seqnr;
 }
-static void nfs4_slot_sequence_acked(struct nfs4_slot *slot,
-		u32 seqnr)
+static void nfs4_slot_sequence_acked(struct nfs4_slot *slot, u32 seqnr)
 {
-	slot->seq_nr_highest_sent = seqnr;
+	nfs4_slot_sequence_record_sent(slot, seqnr);
 	slot->seq_nr_last_acked = seqnr;
 }
 
@@ -857,7 +856,6 @@ static int nfs41_sequence_process(struct rpc_task *task,
 			__func__,
 			slot->slot_nr,
 			slot->seq_nr);
-		nfs4_slot_sequence_acked(slot, slot->seq_nr);
 		goto out_retry;
 	case -NFS4ERR_RETRY_UNCACHED_REP:
 	case -NFS4ERR_SEQ_FALSE_RETRY:
@@ -3108,12 +3106,13 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
 	}
 
 out:
-	if (opendata->lgp) {
-		nfs4_lgopen_release(opendata->lgp);
-		opendata->lgp = NULL;
-	}
-	if (!opendata->cancelled)
+	if (!opendata->cancelled) {
+		if (opendata->lgp) {
+			nfs4_lgopen_release(opendata->lgp);
+			opendata->lgp = NULL;
+		}
 		nfs4_sequence_free_slot(&opendata->o_res.seq_res);
+	}
 	return ret;
 }
 
@@ -9410,6 +9409,9 @@ static int nfs41_reclaim_complete_handle_errors(struct rpc_task *task, struct nf
 		rpc_delay(task, NFS4_POLL_RETRY_MAX);
 		fallthrough;
 	case -NFS4ERR_RETRY_UNCACHED_REP:
+	case -EACCES:
+		dprintk("%s: failed to reclaim complete error %d for server %s, retrying\n",
+			__func__, task->tk_status, clp->cl_hostname);
 		return -EAGAIN;
 	case -NFS4ERR_BADSESSION:
 	case -NFS4ERR_DEADSESSION:
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index e65c83494c05..a847011f36c9 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1046,22 +1046,31 @@ static void nfs_fill_super(struct super_block *sb, struct nfs_fs_context *ctx)
 	if (ctx->bsize)
 		sb->s_blocksize = nfs_block_size(ctx->bsize, &sb->s_blocksize_bits);
 
-	if (server->nfs_client->rpc_ops->version != 2) {
-		/* The VFS shouldn't apply the umask to mode bits. We will do
-		 * so ourselves when necessary.
+	switch (server->nfs_client->rpc_ops->version) {
+	case 2:
+		sb->s_time_gran = 1000;
+		sb->s_time_min = 0;
+		sb->s_time_max = U32_MAX;
+		break;
+	case 3:
+		/*
+		 * The VFS shouldn't apply the umask to mode bits.
+		 * We will do so ourselves when necessary.
 		 */
 		sb->s_flags |= SB_POSIXACL;
 		sb->s_time_gran = 1;
-		sb->s_export_op = &nfs_export_ops;
-	} else
-		sb->s_time_gran = 1000;
-
-	if (server->nfs_client->rpc_ops->version != 4) {
 		sb->s_time_min = 0;
 		sb->s_time_max = U32_MAX;
-	} else {
+		sb->s_export_op = &nfs_export_ops;
+		break;
+	case 4:
+		sb->s_flags |= SB_POSIXACL;
+		sb->s_time_gran = 1;
 		sb->s_time_min = S64_MIN;
 		sb->s_time_max = S64_MAX;
+		if (server->caps & NFS_CAP_ATOMIC_OPEN_V1)
+			sb->s_export_op = &nfs_export_ops;
+		break;
 	}
 
 	sb->s_magic = NFS_SUPER_MAGIC;
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index cdb29fd23549..be70874bc329 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1394,10 +1394,12 @@ static void nfs_initiate_write(struct nfs_pgio_header *hdr,
  */
 static void nfs_redirty_request(struct nfs_page *req)
 {
+	struct nfs_inode *nfsi = NFS_I(page_file_mapping(req->wb_page)->host);
+
 	/* Bump the transmission count */
 	req->wb_nio++;
 	nfs_mark_request_dirty(req);
-	set_bit(NFS_CONTEXT_RESEND_WRITES, &nfs_req_openctx(req)->flags);
+	atomic_long_inc(&nfsi->redirtied_pages);
 	nfs_end_page_writeback(req);
 	nfs_release_request(req);
 }
@@ -1870,7 +1872,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
 		/* We have a mismatch. Write the page again */
 		dprintk_cont(" mismatch\n");
 		nfs_mark_request_dirty(req);
-		set_bit(NFS_CONTEXT_RESEND_WRITES, &nfs_req_openctx(req)->flags);
+		atomic_long_inc(&NFS_I(data->inode)->redirtied_pages);
 	next:
 		nfs_unlock_and_release_request(req);
 		/* Latency breaker */
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index 87d984e0cdc0..1e8c31ed6c7c 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -187,12 +187,6 @@ nfsd_file_alloc(struct inode *inode, unsigned int may, unsigned int hashval,
 		nf->nf_hashval = hashval;
 		refcount_set(&nf->nf_ref, 1);
 		nf->nf_may = may & NFSD_FILE_MAY_MASK;
-		if (may & NFSD_MAY_NOT_BREAK_LEASE) {
-			if (may & NFSD_MAY_WRITE)
-				__set_bit(NFSD_FILE_BREAK_WRITE, &nf->nf_flags);
-			if (may & NFSD_MAY_READ)
-				__set_bit(NFSD_FILE_BREAK_READ, &nf->nf_flags);
-		}
 		nf->nf_mark = NULL;
 		trace_nfsd_file_alloc(nf);
 	}
@@ -990,21 +984,7 @@ wait_for_construction:
 
 	this_cpu_inc(nfsd_file_cache_hits);
 
-	if (!(may_flags & NFSD_MAY_NOT_BREAK_LEASE)) {
-		bool write = (may_flags & NFSD_MAY_WRITE);
-
-		if (test_bit(NFSD_FILE_BREAK_READ, &nf->nf_flags) ||
-		    (test_bit(NFSD_FILE_BREAK_WRITE, &nf->nf_flags) && write)) {
-			status = nfserrno(nfsd_open_break_lease(
-					file_inode(nf->nf_file), may_flags));
-			if (status == nfs_ok) {
-				clear_bit(NFSD_FILE_BREAK_READ, &nf->nf_flags);
-				if (write)
-					clear_bit(NFSD_FILE_BREAK_WRITE,
-						  &nf->nf_flags);
-			}
-		}
-	}
+	status = nfserrno(nfsd_open_break_lease(file_inode(nf->nf_file), may_flags));
 out:
 	if (status == nfs_ok) {
 		*pnf = nf;
diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h
index 435ceab27897..63104be2865c 100644
--- a/fs/nfsd/filecache.h
+++ b/fs/nfsd/filecache.h
@@ -37,9 +37,7 @@ struct nfsd_file {
 	struct net		*nf_net;
 #define NFSD_FILE_HASHED	(0)
 #define NFSD_FILE_PENDING	(1)
-#define NFSD_FILE_BREAK_READ	(2)
-#define NFSD_FILE_BREAK_WRITE	(3)
-#define NFSD_FILE_REFERENCED	(4)
+#define NFSD_FILE_REFERENCED	(2)
 	unsigned long		nf_flags;
 	struct inode		*nf_inode;
 	unsigned int		nf_hashval;
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index b540489ea240..936eebd4c56d 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -660,15 +660,9 @@ nfsd3_proc_commit(struct svc_rqst *rqstp)
 				argp->count,
 				(unsigned long long) argp->offset);
 
-	if (argp->offset > NFS_OFFSET_MAX) {
-		resp->status = nfserr_inval;
-		goto out;
-	}
-
 	fh_copy(&resp->fh, &argp->fh);
 	resp->status = nfsd_commit(rqstp, &resp->fh, argp->offset,
 				   argp->count, resp->verf);
-out:
 	return rpc_success;
 }
 
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index b302836c7fdf..0fc1fa6f28e0 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -636,18 +636,10 @@ DEFINE_CLID_EVENT(confirmed_r);
 /*
  * from fs/nfsd/filecache.h
  */
-TRACE_DEFINE_ENUM(NFSD_FILE_HASHED);
-TRACE_DEFINE_ENUM(NFSD_FILE_PENDING);
-TRACE_DEFINE_ENUM(NFSD_FILE_BREAK_READ);
-TRACE_DEFINE_ENUM(NFSD_FILE_BREAK_WRITE);
-TRACE_DEFINE_ENUM(NFSD_FILE_REFERENCED);
-
 #define show_nf_flags(val)						\
 	__print_flags(val, "|",						\
 		{ 1 << NFSD_FILE_HASHED,	"HASHED" },		\
 		{ 1 << NFSD_FILE_PENDING,	"PENDING" },		\
-		{ 1 << NFSD_FILE_BREAK_READ,	"BREAK_READ" },		\
-		{ 1 << NFSD_FILE_BREAK_WRITE,	"BREAK_WRITE" },	\
 		{ 1 << NFSD_FILE_REFERENCED,	"REFERENCED"})
 
 DECLARE_EVENT_CLASS(nfsd_file_class,
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 7bfb68583154..abfbb6953e89 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -560,6 +560,7 @@ out_err:
 ssize_t nfsd_copy_file_range(struct file *src, u64 src_pos, struct file *dst,
 			     u64 dst_pos, u64 count)
 {
+	ssize_t ret;
 
 	/*
 	 * Limit copy to 4MB to prevent indefinitely blocking an nfsd
@@ -570,7 +571,12 @@ ssize_t nfsd_copy_file_range(struct file *src, u64 src_pos, struct file *dst,
 	 * limit like this and pipeline multiple COPY requests.
 	 */
 	count = min_t(u64, count, 1 << 22);
-	return vfs_copy_file_range(src, src_pos, dst, dst_pos, count, 0);
+	ret = vfs_copy_file_range(src, src_pos, dst, dst_pos, count, 0);
+
+	if (ret == -EOPNOTSUPP || ret == -EXDEV)
+		ret = generic_copy_file_range(src, src_pos, dst, dst_pos,
+					      count, 0);
+	return ret;
 }
 
 __be32 nfsd4_vfs_fallocate(struct svc_rqst *rqstp, struct svc_fh *fhp,
@@ -1102,58 +1108,77 @@ out:
 }
 
 #ifdef CONFIG_NFSD_V3
-/*
- * Commit all pending writes to stable storage.
+/**
+ * nfsd_commit - Commit pending writes to stable storage
+ * @rqstp: RPC request being processed
+ * @fhp: NFS filehandle
+ * @offset: raw offset from beginning of file
+ * @count: raw count of bytes to sync
+ * @verf: filled in with the server's current write verifier
  *
- * Note: we only guarantee that data that lies within the range specified
- * by the 'offset' and 'count' parameters will be synced.
+ * Note: we guarantee that data that lies within the range specified
+ * by the 'offset' and 'count' parameters will be synced. The server
+ * is permitted to sync data that lies outside this range at the
+ * same time.
  *
  * Unfortunately we cannot lock the file to make sure we return full WCC
  * data to the client, as locking happens lower down in the filesystem.
+ *
+ * Return values:
+ *   An nfsstat value in network byte order.
  */
 __be32
-nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp,
-               loff_t offset, unsigned long count, __be32 *verf)
+nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, u64 offset,
+	    u32 count, __be32 *verf)
 {
+	u64			maxbytes;
+	loff_t			start, end;
+	struct nfsd_net		*nn;
 	struct nfsd_file	*nf;
-	loff_t			end = LLONG_MAX;
-	__be32			err = nfserr_inval;
-
-	if (offset < 0)
-		goto out;
-	if (count != 0) {
-		end = offset + (loff_t)count - 1;
-		if (end < offset)
-			goto out;
-	}
+	__be32			err;
 
 	err = nfsd_file_acquire(rqstp, fhp,
 			NFSD_MAY_WRITE|NFSD_MAY_NOT_BREAK_LEASE, &nf);
 	if (err)
 		goto out;
+
+	/*
+	 * Convert the client-provided (offset, count) range to a
+	 * (start, end) range. If the client-provided range falls
+	 * outside the maximum file size of the underlying FS,
+	 * clamp the sync range appropriately.
+	 */
+	start = 0;
+	end = LLONG_MAX;
+	maxbytes = (u64)fhp->fh_dentry->d_sb->s_maxbytes;
+	if (offset < maxbytes) {
+		start = offset;
+		if (count && (offset + count - 1 < maxbytes))
+			end = offset + count - 1;
+	}
+
+	nn = net_generic(nf->nf_net, nfsd_net_id);
 	if (EX_ISSYNC(fhp->fh_export)) {
 		errseq_t since = READ_ONCE(nf->nf_file->f_wb_err);
 		int err2;
 
-		err2 = vfs_fsync_range(nf->nf_file, offset, end, 0);
+		err2 = vfs_fsync_range(nf->nf_file, start, end, 0);
 		switch (err2) {
 		case 0:
-			nfsd_copy_boot_verifier(verf, net_generic(nf->nf_net,
-						nfsd_net_id));
+			nfsd_copy_boot_verifier(verf, nn);
 			err2 = filemap_check_wb_err(nf->nf_file->f_mapping,
 						    since);
+			err = nfserrno(err2);
 			break;
 		case -EINVAL:
 			err = nfserr_notsupp;
 			break;
 		default:
-			nfsd_reset_boot_verifier(net_generic(nf->nf_net,
-						 nfsd_net_id));
+			nfsd_reset_boot_verifier(nn);
+			err = nfserrno(err2);
 		}
-		err = nfserrno(err2);
 	} else
-		nfsd_copy_boot_verifier(verf, net_generic(nf->nf_net,
-					nfsd_net_id));
+		nfsd_copy_boot_verifier(verf, nn);
 
 	nfsd_file_put(nf);
 out:
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index b21b76e6b9a8..3cf5a8a13da5 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -73,8 +73,8 @@ __be32		do_nfsd_create(struct svc_rqst *, struct svc_fh *,
 				char *name, int len, struct iattr *attrs,
 				struct svc_fh *res, int createmode,
 				u32 *verifier, bool *truncp, bool *created);
-__be32		nfsd_commit(struct svc_rqst *, struct svc_fh *,
-				loff_t, unsigned long, __be32 *verf);
+__be32		nfsd_commit(struct svc_rqst *rqst, struct svc_fh *fhp,
+				u64 offset, u32 count, __be32 *verf);
 #endif /* CONFIG_NFSD_V3 */
 #ifdef CONFIG_NFSD_V4
 __be32		nfsd_getxattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h
index 7dcb77d38759..aceb8aadca14 100644
--- a/fs/nilfs2/nilfs.h
+++ b/fs/nilfs2/nilfs.h
@@ -198,6 +198,9 @@ static inline int nilfs_acl_chmod(struct inode *inode)
 
 static inline int nilfs_init_acl(struct inode *inode, struct inode *dir)
 {
+	if (S_ISLNK(inode->i_mode))
+		return 0;
+
 	inode->i_mode &= ~current_umask();
 	return 0;
 }
diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c
index d563abc3e136..914e99173130 100644
--- a/fs/ntfs/attrib.c
+++ b/fs/ntfs/attrib.c
@@ -592,8 +592,12 @@ static int ntfs_attr_find(const ATTR_TYPE type, const ntfschar *name,
 		a = (ATTR_RECORD*)((u8*)ctx->attr +
 				le32_to_cpu(ctx->attr->length));
 	for (;;	a = (ATTR_RECORD*)((u8*)a + le32_to_cpu(a->length))) {
-		if ((u8*)a < (u8*)ctx->mrec || (u8*)a > (u8*)ctx->mrec +
-				le32_to_cpu(ctx->mrec->bytes_allocated))
+		u8 *mrec_end = (u8 *)ctx->mrec +
+		               le32_to_cpu(ctx->mrec->bytes_allocated);
+		u8 *name_end = (u8 *)a + le16_to_cpu(a->name_offset) +
+			       a->name_length * sizeof(ntfschar);
+		if ((u8*)a < (u8*)ctx->mrec || (u8*)a > mrec_end ||
+		    name_end > mrec_end)
 			break;
 		ctx->attr = a;
 		if (unlikely(le32_to_cpu(a->type) > le32_to_cpu(type) ||
diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c
index 49b7df616778..614513460b8e 100644
--- a/fs/ntfs3/fslog.c
+++ b/fs/ntfs3/fslog.c
@@ -5057,7 +5057,7 @@ undo_action_next:
 		goto add_allocated_vcns;
 
 	vcn = le64_to_cpu(lrh->target_vcn);
-	vcn &= ~(log->clst_per_page - 1);
+	vcn &= ~(u64)(log->clst_per_page - 1);
 
 add_allocated_vcns:
 	for (i = 0, vcn = le64_to_cpu(lrh->target_vcn),
diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c
index 4de9acb16968..24b57c3cc625 100644
--- a/fs/ntfs3/fsntfs.c
+++ b/fs/ntfs3/fsntfs.c
@@ -831,10 +831,15 @@ int ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait)
 {
 	int err;
 	struct super_block *sb = sbi->sb;
-	u32 blocksize = sb->s_blocksize;
+	u32 blocksize;
 	sector_t block1, block2;
 	u32 bytes;
 
+	if (!sb)
+		return -EINVAL;
+
+	blocksize = sb->s_blocksize;
+
 	if (!(sbi->flags & NTFS_FLAGS_MFTMIRR))
 		return 0;
 
diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c
index 6f81e3a49abf..76ebea253fa2 100644
--- a/fs/ntfs3/index.c
+++ b/fs/ntfs3/index.c
@@ -1994,7 +1994,7 @@ static int indx_free_children(struct ntfs_index *indx, struct ntfs_inode *ni,
 			      const struct NTFS_DE *e, bool trim)
 {
 	int err;
-	struct indx_node *n;
+	struct indx_node *n = NULL;
 	struct INDEX_HDR *hdr;
 	CLST vbn = de_get_vbn(e);
 	size_t i;
diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c
index 879952254071..b2cc1191be69 100644
--- a/fs/ntfs3/inode.c
+++ b/fs/ntfs3/inode.c
@@ -430,6 +430,7 @@ end_enum:
 	} else if (fname && fname->home.low == cpu_to_le32(MFT_REC_EXTEND) &&
 		   fname->home.seq == cpu_to_le16(MFT_REC_EXTEND)) {
 		/* Records in $Extend are not a files or general directories. */
+		inode->i_op = &ntfs_file_inode_operations;
 	} else {
 		err = -EINVAL;
 		goto out;
diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c
index 7f85ec83e196..f3b88c7e35f7 100644
--- a/fs/ntfs3/super.c
+++ b/fs/ntfs3/super.c
@@ -30,6 +30,7 @@
 #include <linux/fs_context.h>
 #include <linux/fs_parser.h>
 #include <linux/log2.h>
+#include <linux/minmax.h>
 #include <linux/module.h>
 #include <linux/nls.h>
 #include <linux/seq_file.h>
@@ -390,7 +391,7 @@ static int ntfs_fs_reconfigure(struct fs_context *fc)
 		return -EINVAL;
 	}
 
-	memcpy(sbi->options, new_opts, sizeof(*new_opts));
+	swap(sbi->options, fc->fs_private);
 
 	return 0;
 }
@@ -901,6 +902,8 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc)
 	ref.high = 0;
 
 	sbi->sb = sb;
+	sbi->options = fc->fs_private;
+	fc->fs_private = NULL;
 	sb->s_flags |= SB_NODIRATIME;
 	sb->s_magic = 0x7366746e; // "ntfs"
 	sb->s_op = &ntfs_sops;
@@ -1264,8 +1267,6 @@ load_root:
 		goto put_inode_out;
 	}
 
-	fc->fs_private = NULL;
-
 	return 0;
 
 put_inode_out:
@@ -1418,7 +1419,6 @@ static int ntfs_init_fs_context(struct fs_context *fc)
 	mutex_init(&sbi->compress.mtx_lzx);
 #endif
 
-	sbi->options = opts;
 	fc->s_fs_info = sbi;
 ok:
 	fc->fs_private = opts;
diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c
index 0968565ff2ca..4652b9796995 100644
--- a/fs/ntfs3/xattr.c
+++ b/fs/ntfs3/xattr.c
@@ -118,7 +118,7 @@ static int ntfs_read_ea(struct ntfs_inode *ni, struct EA_FULL **ea,
 
 		run_init(&run);
 
-		err = attr_load_runs(attr_ea, ni, &run, NULL);
+		err = attr_load_runs_range(ni, ATTR_EA, NULL, 0, &run, 0, size);
 		if (!err)
 			err = ntfs_read_run_nb(sbi, &run, 0, ea_p, size, NULL);
 		run_close(&run);
@@ -443,6 +443,11 @@ update_ea:
 		/* Delete xattr, ATTR_EA */
 		ni_remove_attr_le(ni, attr, mi, le);
 	} else if (attr->non_res) {
+		err = attr_load_runs_range(ni, ATTR_EA, NULL, 0, &ea_run, 0,
+					   size);
+		if (err)
+			goto out;
+
 		err = ntfs_sb_write_run(sbi, &ea_run, 0, ea_all, size, 0);
 		if (err)
 			goto out;
@@ -476,8 +481,7 @@ out:
 }
 
 #ifdef CONFIG_NTFS3_FS_POSIX_ACL
-static struct posix_acl *ntfs_get_acl_ex(struct user_namespace *mnt_userns,
-					 struct inode *inode, int type,
+static struct posix_acl *ntfs_get_acl_ex(struct inode *inode, int type,
 					 int locked)
 {
 	struct ntfs_inode *ni = ntfs_i(inode);
@@ -512,7 +516,7 @@ static struct posix_acl *ntfs_get_acl_ex(struct user_namespace *mnt_userns,
 
 	/* Translate extended attribute to acl. */
 	if (err >= 0) {
-		acl = posix_acl_from_xattr(mnt_userns, buf, err);
+		acl = posix_acl_from_xattr(&init_user_ns, buf, err);
 	} else if (err == -ENODATA) {
 		acl = NULL;
 	} else {
@@ -535,8 +539,7 @@ struct posix_acl *ntfs_get_acl(struct inode *inode, int type, bool rcu)
 	if (rcu)
 		return ERR_PTR(-ECHILD);
 
-	/* TODO: init_user_ns? */
-	return ntfs_get_acl_ex(&init_user_ns, inode, type, 0);
+	return ntfs_get_acl_ex(inode, type, 0);
 }
 
 static noinline int ntfs_set_acl_ex(struct user_namespace *mnt_userns,
@@ -545,28 +548,23 @@ static noinline int ntfs_set_acl_ex(struct user_namespace *mnt_userns,
 {
 	const char *name;
 	size_t size, name_len;
-	void *value = NULL;
-	int err = 0;
+	void *value;
+	int err;
 	int flags;
+	umode_t mode;
 
 	if (S_ISLNK(inode->i_mode))
 		return -EOPNOTSUPP;
 
+	mode = inode->i_mode;
 	switch (type) {
 	case ACL_TYPE_ACCESS:
 		/* Do not change i_mode if we are in init_acl */
 		if (acl && !init_acl) {
-			umode_t mode;
-
 			err = posix_acl_update_mode(mnt_userns, inode, &mode,
 						    &acl);
 			if (err)
-				goto out;
-
-			if (inode->i_mode != mode) {
-				inode->i_mode = mode;
-				mark_inode_dirty(inode);
-			}
+				return err;
 		}
 		name = XATTR_NAME_POSIX_ACL_ACCESS;
 		name_len = sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1;
@@ -593,7 +591,7 @@ static noinline int ntfs_set_acl_ex(struct user_namespace *mnt_userns,
 		value = kmalloc(size, GFP_NOFS);
 		if (!value)
 			return -ENOMEM;
-		err = posix_acl_to_xattr(mnt_userns, acl, value, size);
+		err = posix_acl_to_xattr(&init_user_ns, acl, value, size);
 		if (err < 0)
 			goto out;
 		flags = 0;
@@ -602,8 +600,13 @@ static noinline int ntfs_set_acl_ex(struct user_namespace *mnt_userns,
 	err = ntfs_set_ea(inode, name, name_len, value, size, flags);
 	if (err == -ENODATA && !size)
 		err = 0; /* Removing non existed xattr. */
-	if (!err)
+	if (!err) {
 		set_cached_acl(inode, type, acl);
+		if (inode->i_mode != mode) {
+			inode->i_mode = mode;
+			mark_inode_dirty(inode);
+		}
+	}
 
 out:
 	kfree(value);
@@ -639,7 +642,7 @@ static int ntfs_xattr_get_acl(struct user_namespace *mnt_userns,
 	if (!acl)
 		return -ENODATA;
 
-	err = posix_acl_to_xattr(mnt_userns, acl, buffer, size);
+	err = posix_acl_to_xattr(&init_user_ns, acl, buffer, size);
 	posix_acl_release(acl);
 
 	return err;
@@ -663,12 +666,12 @@ static int ntfs_xattr_set_acl(struct user_namespace *mnt_userns,
 	if (!value) {
 		acl = NULL;
 	} else {
-		acl = posix_acl_from_xattr(mnt_userns, value, size);
+		acl = posix_acl_from_xattr(&init_user_ns, value, size);
 		if (IS_ERR(acl))
 			return PTR_ERR(acl);
 
 		if (acl) {
-			err = posix_acl_valid(mnt_userns, acl);
+			err = posix_acl_valid(&init_user_ns, acl);
 			if (err)
 				goto release_and_out;
 		}
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index bb62cc2e0211..cf21aecdf547 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -277,7 +277,6 @@ enum ocfs2_mount_options
 	OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT = 1 << 15,  /* Journal Async Commit */
 	OCFS2_MOUNT_ERRORS_CONT = 1 << 16, /* Return EIO to the calling process on error */
 	OCFS2_MOUNT_ERRORS_ROFS = 1 << 17, /* Change filesystem to read-only on error */
-	OCFS2_MOUNT_NOCLUSTER = 1 << 18, /* No cluster aware filesystem mount */
 };
 
 #define OCFS2_OSB_SOFT_RO	0x0001
@@ -673,8 +672,7 @@ static inline int ocfs2_cluster_o2cb_global_heartbeat(struct ocfs2_super *osb)
 
 static inline int ocfs2_mount_local(struct ocfs2_super *osb)
 {
-	return ((osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT)
-		|| (osb->s_mount_opt & OCFS2_MOUNT_NOCLUSTER));
+	return (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT);
 }
 
 static inline int ocfs2_uses_extended_slot_map(struct ocfs2_super *osb)
diff --git a/fs/ocfs2/slot_map.c b/fs/ocfs2/slot_map.c
index 0b0ae3ebb0cf..da7718cef735 100644
--- a/fs/ocfs2/slot_map.c
+++ b/fs/ocfs2/slot_map.c
@@ -252,16 +252,14 @@ static int __ocfs2_find_empty_slot(struct ocfs2_slot_info *si,
 	int i, ret = -ENOSPC;
 
 	if ((preferred >= 0) && (preferred < si->si_num_slots)) {
-		if (!si->si_slots[preferred].sl_valid ||
-		    !si->si_slots[preferred].sl_node_num) {
+		if (!si->si_slots[preferred].sl_valid) {
 			ret = preferred;
 			goto out;
 		}
 	}
 
 	for(i = 0; i < si->si_num_slots; i++) {
-		if (!si->si_slots[i].sl_valid ||
-		    !si->si_slots[i].sl_node_num) {
+		if (!si->si_slots[i].sl_valid) {
 			ret = i;
 			break;
 		}
@@ -456,30 +454,24 @@ int ocfs2_find_slot(struct ocfs2_super *osb)
 	spin_lock(&osb->osb_lock);
 	ocfs2_update_slot_info(si);
 
-	if (ocfs2_mount_local(osb))
-		/* use slot 0 directly in local mode */
-		slot = 0;
-	else {
-		/* search for ourselves first and take the slot if it already
-		 * exists. Perhaps we need to mark this in a variable for our
-		 * own journal recovery? Possibly not, though we certainly
-		 * need to warn to the user */
-		slot = __ocfs2_node_num_to_slot(si, osb->node_num);
+	/* search for ourselves first and take the slot if it already
+	 * exists. Perhaps we need to mark this in a variable for our
+	 * own journal recovery? Possibly not, though we certainly
+	 * need to warn to the user */
+	slot = __ocfs2_node_num_to_slot(si, osb->node_num);
+	if (slot < 0) {
+		/* if no slot yet, then just take 1st available
+		 * one. */
+		slot = __ocfs2_find_empty_slot(si, osb->preferred_slot);
 		if (slot < 0) {
-			/* if no slot yet, then just take 1st available
-			 * one. */
-			slot = __ocfs2_find_empty_slot(si, osb->preferred_slot);
-			if (slot < 0) {
-				spin_unlock(&osb->osb_lock);
-				mlog(ML_ERROR, "no free slots available!\n");
-				status = -EINVAL;
-				goto bail;
-			}
-		} else
-			printk(KERN_INFO "ocfs2: Slot %d on device (%s) was "
-			       "already allocated to this node!\n",
-			       slot, osb->dev_str);
-	}
+			spin_unlock(&osb->osb_lock);
+			mlog(ML_ERROR, "no free slots available!\n");
+			status = -EINVAL;
+			goto bail;
+		}
+	} else
+		printk(KERN_INFO "ocfs2: Slot %d on device (%s) was already "
+		       "allocated to this node!\n", slot, osb->dev_str);
 
 	ocfs2_set_slot(si, slot, osb->node_num);
 	osb->slot_num = slot;
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 7ba3dabe16f0..a03f0cabff0b 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -173,7 +173,6 @@ enum {
 	Opt_dir_resv_level,
 	Opt_journal_async_commit,
 	Opt_err_cont,
-	Opt_nocluster,
 	Opt_err,
 };
 
@@ -207,7 +206,6 @@ static const match_table_t tokens = {
 	{Opt_dir_resv_level, "dir_resv_level=%u"},
 	{Opt_journal_async_commit, "journal_async_commit"},
 	{Opt_err_cont, "errors=continue"},
-	{Opt_nocluster, "nocluster"},
 	{Opt_err, NULL}
 };
 
@@ -619,13 +617,6 @@ static int ocfs2_remount(struct super_block *sb, int *flags, char *data)
 		goto out;
 	}
 
-	tmp = OCFS2_MOUNT_NOCLUSTER;
-	if ((osb->s_mount_opt & tmp) != (parsed_options.mount_opt & tmp)) {
-		ret = -EINVAL;
-		mlog(ML_ERROR, "Cannot change nocluster option on remount\n");
-		goto out;
-	}
-
 	tmp = OCFS2_MOUNT_HB_LOCAL | OCFS2_MOUNT_HB_GLOBAL |
 		OCFS2_MOUNT_HB_NONE;
 	if ((osb->s_mount_opt & tmp) != (parsed_options.mount_opt & tmp)) {
@@ -866,7 +857,6 @@ static int ocfs2_verify_userspace_stack(struct ocfs2_super *osb,
 	}
 
 	if (ocfs2_userspace_stack(osb) &&
-	    !(osb->s_mount_opt & OCFS2_MOUNT_NOCLUSTER) &&
 	    strncmp(osb->osb_cluster_stack, mopt->cluster_stack,
 		    OCFS2_STACK_LABEL_LEN)) {
 		mlog(ML_ERROR,
@@ -1145,11 +1135,6 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
 	       osb->s_mount_opt & OCFS2_MOUNT_DATA_WRITEBACK ? "writeback" :
 	       "ordered");
 
-	if ((osb->s_mount_opt & OCFS2_MOUNT_NOCLUSTER) &&
-	   !(osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT))
-		printk(KERN_NOTICE "ocfs2: The shared device (%s) is mounted "
-		       "without cluster aware mode.\n", osb->dev_str);
-
 	atomic_set(&osb->vol_state, VOLUME_MOUNTED);
 	wake_up(&osb->osb_mount_event);
 
@@ -1456,9 +1441,6 @@ static int ocfs2_parse_options(struct super_block *sb,
 		case Opt_journal_async_commit:
 			mopt->mount_opt |= OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT;
 			break;
-		case Opt_nocluster:
-			mopt->mount_opt |= OCFS2_MOUNT_NOCLUSTER;
-			break;
 		default:
 			mlog(ML_ERROR,
 			     "Unrecognized mount option \"%s\" "
@@ -1570,9 +1552,6 @@ static int ocfs2_show_options(struct seq_file *s, struct dentry *root)
 	if (opts & OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT)
 		seq_printf(s, ",journal_async_commit");
 
-	if (opts & OCFS2_MOUNT_NOCLUSTER)
-		seq_printf(s, ",nocluster");
-
 	return 0;
 }
 
diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c
index ebde05c9cf62..dbb944b5f81e 100644
--- a/fs/overlayfs/export.c
+++ b/fs/overlayfs/export.c
@@ -259,7 +259,7 @@ static int ovl_encode_fh(struct inode *inode, u32 *fid, int *max_len,
 		return FILEID_INVALID;
 
 	dentry = d_find_any_alias(inode);
-	if (WARN_ON(!dentry))
+	if (!dentry)
 		return FILEID_INVALID;
 
 	bytes = ovl_dentry_to_fid(ofs, dentry, fid, buflen);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 7bb0a47cb615..9837aaf9caf1 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -1413,11 +1413,12 @@ static int ovl_make_workdir(struct super_block *sb, struct ovl_fs *ofs,
 	 */
 	err = ovl_do_setxattr(ofs, ofs->workdir, OVL_XATTR_OPAQUE, "0", 1);
 	if (err) {
+		pr_warn("failed to set xattr on upper\n");
 		ofs->noxattr = true;
 		if (ofs->config.index || ofs->config.metacopy) {
 			ofs->config.index = false;
 			ofs->config.metacopy = false;
-			pr_warn("upper fs does not support xattr, falling back to index=off,metacopy=off.\n");
+			pr_warn("...falling back to index=off,metacopy=off.\n");
 		}
 		/*
 		 * xattr support is required for persistent st_ino.
@@ -1425,8 +1426,10 @@ static int ovl_make_workdir(struct super_block *sb, struct ovl_fs *ofs,
 		 */
 		if (ofs->config.xino == OVL_XINO_AUTO) {
 			ofs->config.xino = OVL_XINO_OFF;
-			pr_warn("upper fs does not support xattr, falling back to xino=off.\n");
+			pr_warn("...falling back to xino=off.\n");
 		}
+		if (err == -EPERM && !ofs->config.userxattr)
+			pr_info("try mounting with 'userxattr' option\n");
 		err = 0;
 	} else {
 		ovl_do_removexattr(ofs, ofs->workdir, OVL_XATTR_OPAQUE);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 1f394095eb88..300d53ee7040 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1886,7 +1886,7 @@ void proc_pid_evict_inode(struct proc_inode *ei)
 	put_pid(pid);
 }
 
-struct inode *proc_pid_make_inode(struct super_block * sb,
+struct inode *proc_pid_make_inode(struct super_block *sb,
 				  struct task_struct *task, umode_t mode)
 {
 	struct inode * inode;
@@ -1915,11 +1915,6 @@ struct inode *proc_pid_make_inode(struct super_block * sb,
 
 	/* Let the pid remember us for quick removal */
 	ei->pid = pid;
-	if (S_ISDIR(mode)) {
-		spin_lock(&pid->lock);
-		hlist_add_head_rcu(&ei->sibling_inodes, &pid->inodes);
-		spin_unlock(&pid->lock);
-	}
 
 	task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid);
 	security_task_to_inode(task, inode);
@@ -1932,6 +1927,39 @@ out_unlock:
 	return NULL;
 }
 
+/*
+ * Generating an inode and adding it into @pid->inodes, so that task will
+ * invalidate inode's dentry before being released.
+ *
+ * This helper is used for creating dir-type entries under '/proc' and
+ * '/proc/<tgid>/task'. Other entries(eg. fd, stat) under '/proc/<tgid>'
+ * can be released by invalidating '/proc/<tgid>' dentry.
+ * In theory, dentries under '/proc/<tgid>/task' can also be released by
+ * invalidating '/proc/<tgid>' dentry, we reserve it to handle single
+ * thread exiting situation: Any one of threads should invalidate its
+ * '/proc/<tgid>/task/<pid>' dentry before released.
+ */
+static struct inode *proc_pid_make_base_inode(struct super_block *sb,
+				struct task_struct *task, umode_t mode)
+{
+	struct inode *inode;
+	struct proc_inode *ei;
+	struct pid *pid;
+
+	inode = proc_pid_make_inode(sb, task, mode);
+	if (!inode)
+		return NULL;
+
+	/* Let proc_flush_pid find this directory inode */
+	ei = PROC_I(inode);
+	pid = ei->pid;
+	spin_lock(&pid->lock);
+	hlist_add_head_rcu(&ei->sibling_inodes, &pid->inodes);
+	spin_unlock(&pid->lock);
+
+	return inode;
+}
+
 int pid_getattr(struct user_namespace *mnt_userns, const struct path *path,
 		struct kstat *stat, u32 request_mask, unsigned int query_flags)
 {
@@ -3349,7 +3377,8 @@ static struct dentry *proc_pid_instantiate(struct dentry * dentry,
 {
 	struct inode *inode;
 
-	inode = proc_pid_make_inode(dentry->d_sb, task, S_IFDIR | S_IRUGO | S_IXUGO);
+	inode = proc_pid_make_base_inode(dentry->d_sb, task,
+					 S_IFDIR | S_IRUGO | S_IXUGO);
 	if (!inode)
 		return ERR_PTR(-ENOENT);
 
@@ -3648,7 +3677,8 @@ static struct dentry *proc_task_instantiate(struct dentry *dentry,
 	struct task_struct *task, const void *ptr)
 {
 	struct inode *inode;
-	inode = proc_pid_make_inode(dentry->d_sb, task, S_IFDIR | S_IRUGO | S_IXUGO);
+	inode = proc_pid_make_base_inode(dentry->d_sb, task,
+					 S_IFDIR | S_IRUGO | S_IXUGO);
 	if (!inode)
 		return ERR_PTR(-ENOENT);
 
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 5d66faecd4ef..013fc5931bc3 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -25,7 +25,7 @@ static const struct file_operations proc_sys_dir_file_operations;
 static const struct inode_operations proc_sys_dir_operations;
 
 /* shared constants to be used in various sysctls */
-const int sysctl_vals[] = { 0, 1, INT_MAX };
+const int sysctl_vals[] = { -1, 0, 1, 2, 4, 100, 200, 1000, 3000, INT_MAX };
 EXPORT_SYMBOL(sysctl_vals);
 
 /* Support for permanently empty directories */
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 79ca4d69dfd6..d9c07eecd787 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -503,10 +503,12 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 	struct vm_area_struct *vma = walk->vma;
 	bool locked = !!(vma->vm_flags & VM_LOCKED);
 	struct page *page = NULL;
-	bool migration = false;
+	bool migration = false, young = false, dirty = false;
 
 	if (pte_present(*pte)) {
 		page = vm_normal_page(vma, addr, *pte);
+		young = pte_young(*pte);
+		dirty = pte_dirty(*pte);
 	} else if (is_swap_pte(*pte)) {
 		swp_entry_t swpent = pte_to_swp_entry(*pte);
 
@@ -540,8 +542,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 	if (!page)
 		return;
 
-	smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte),
-		      locked, migration);
+	smaps_account(mss, page, false, young, dirty, locked, migration);
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
diff --git a/fs/read_write.c b/fs/read_write.c
index af057c57bdc6..8d3ec975514d 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1250,6 +1250,9 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
 					  count, fl);
 		file_end_write(out.file);
 	} else {
+		if (out.file->f_flags & O_NONBLOCK)
+			fl |= SPLICE_F_NONBLOCK;
+
 		retval = splice_file_to_pipe(in.file, opipe, &pos, count, fl);
 	}
 
@@ -1384,28 +1387,6 @@ ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in,
 }
 EXPORT_SYMBOL(generic_copy_file_range);
 
-static ssize_t do_copy_file_range(struct file *file_in, loff_t pos_in,
-				  struct file *file_out, loff_t pos_out,
-				  size_t len, unsigned int flags)
-{
-	/*
-	 * Although we now allow filesystems to handle cross sb copy, passing
-	 * a file of the wrong filesystem type to filesystem driver can result
-	 * in an attempt to dereference the wrong type of ->private_data, so
-	 * avoid doing that until we really have a good reason.  NFS defines
-	 * several different file_system_type structures, but they all end up
-	 * using the same ->copy_file_range() function pointer.
-	 */
-	if (file_out->f_op->copy_file_range &&
-	    file_out->f_op->copy_file_range == file_in->f_op->copy_file_range)
-		return file_out->f_op->copy_file_range(file_in, pos_in,
-						       file_out, pos_out,
-						       len, flags);
-
-	return generic_copy_file_range(file_in, pos_in, file_out, pos_out, len,
-				       flags);
-}
-
 /*
  * Performs necessary checks before doing a file copy
  *
@@ -1427,6 +1408,24 @@ static int generic_copy_file_checks(struct file *file_in, loff_t pos_in,
 	if (ret)
 		return ret;
 
+	/*
+	 * We allow some filesystems to handle cross sb copy, but passing
+	 * a file of the wrong filesystem type to filesystem driver can result
+	 * in an attempt to dereference the wrong type of ->private_data, so
+	 * avoid doing that until we really have a good reason.
+	 *
+	 * nfs and cifs define several different file_system_type structures
+	 * and several different sets of file_operations, but they all end up
+	 * using the same ->copy_file_range() function pointer.
+	 */
+	if (file_out->f_op->copy_file_range) {
+		if (file_in->f_op->copy_file_range !=
+		    file_out->f_op->copy_file_range)
+			return -EXDEV;
+	} else if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb) {
+		return -EXDEV;
+	}
+
 	/* Don't touch certain kinds of inodes */
 	if (IS_IMMUTABLE(inode_out))
 		return -EPERM;
@@ -1492,26 +1491,41 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
 	file_start_write(file_out);
 
 	/*
-	 * Try cloning first, this is supported by more file systems, and
-	 * more efficient if both clone and copy are supported (e.g. NFS).
+	 * Cloning is supported by more file systems, so we implement copy on
+	 * same sb using clone, but for filesystems where both clone and copy
+	 * are supported (e.g. nfs,cifs), we only call the copy method.
 	 */
+	if (file_out->f_op->copy_file_range) {
+		ret = file_out->f_op->copy_file_range(file_in, pos_in,
+						      file_out, pos_out,
+						      len, flags);
+		goto done;
+	}
+
 	if (file_in->f_op->remap_file_range &&
 	    file_inode(file_in)->i_sb == file_inode(file_out)->i_sb) {
-		loff_t cloned;
-
-		cloned = file_in->f_op->remap_file_range(file_in, pos_in,
+		ret = file_in->f_op->remap_file_range(file_in, pos_in,
 				file_out, pos_out,
 				min_t(loff_t, MAX_RW_COUNT, len),
 				REMAP_FILE_CAN_SHORTEN);
-		if (cloned > 0) {
-			ret = cloned;
+		if (ret > 0)
 			goto done;
-		}
 	}
 
-	ret = do_copy_file_range(file_in, pos_in, file_out, pos_out, len,
-				flags);
-	WARN_ON_ONCE(ret == -EOPNOTSUPP);
+	/*
+	 * We can get here for same sb copy of filesystems that do not implement
+	 * ->copy_file_range() in case filesystem does not support clone or in
+	 * case filesystem supports clone but rejected the clone request (e.g.
+	 * because it was not block aligned).
+	 *
+	 * In both cases, fall back to kernel copy so we are able to maintain a
+	 * consistent story about which filesystems support copy_file_range()
+	 * and which filesystems do not, that will allow userspace tools to
+	 * make consistent desicions w.r.t using copy_file_range().
+	 */
+	ret = generic_copy_file_range(file_in, pos_in, file_out, pos_out, len,
+				      flags);
+
 done:
 	if (ret > 0) {
 		fsnotify_access(file_in);
diff --git a/fs/remap_range.c b/fs/remap_range.c
index 6d4a9beaa097..e69bafb96f09 100644
--- a/fs/remap_range.c
+++ b/fs/remap_range.c
@@ -71,7 +71,8 @@ static int generic_remap_checks(struct file *file_in, loff_t pos_in,
 	 * Otherwise, make sure the count is also block-aligned, having
 	 * already confirmed the starting offsets' block alignment.
 	 */
-	if (pos_in + count == size_in) {
+	if (pos_in + count == size_in &&
+	    (!(remap_flags & REMAP_FILE_DEDUP) || pos_out + count == size_out)) {
 		bcount = ALIGN(size_in, bs) - pos_in;
 	} else {
 		if (!IS_ALIGNED(count, bs))
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 4a2cda04d3e2..b17ee4c4f618 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -947,6 +947,38 @@ struct list_head *seq_list_next(void *v, struct list_head *head, loff_t *ppos)
 }
 EXPORT_SYMBOL(seq_list_next);
 
+struct list_head *seq_list_start_rcu(struct list_head *head, loff_t pos)
+{
+	struct list_head *lh;
+
+	list_for_each_rcu(lh, head)
+		if (pos-- == 0)
+			return lh;
+
+	return NULL;
+}
+EXPORT_SYMBOL(seq_list_start_rcu);
+
+struct list_head *seq_list_start_head_rcu(struct list_head *head, loff_t pos)
+{
+	if (!pos)
+		return head;
+
+	return seq_list_start_rcu(head, pos - 1);
+}
+EXPORT_SYMBOL(seq_list_start_head_rcu);
+
+struct list_head *seq_list_next_rcu(void *v, struct list_head *head,
+				    loff_t *ppos)
+{
+	struct list_head *lh;
+
+	lh = list_next_rcu((struct list_head *)v);
+	++*ppos;
+	return lh == head ? NULL : lh;
+}
+EXPORT_SYMBOL(seq_list_next_rcu);
+
 /**
  * seq_hlist_start - start an iteration of a hlist
  * @head: the head of the hlist
diff --git a/fs/splice.c b/fs/splice.c
index 5dbce4dcc1a7..3abcd7fbc9f2 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -814,17 +814,15 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd,
 {
 	struct pipe_inode_info *pipe;
 	long ret, bytes;
-	umode_t i_mode;
 	size_t len;
 	int i, flags, more;
 
 	/*
-	 * We require the input being a regular file, as we don't want to
-	 * randomly drop data for eg socket -> socket splicing. Use the
-	 * piped splicing for that!
+	 * We require the input to be seekable, as we don't want to randomly
+	 * drop data for eg socket -> socket splicing. Use the piped splicing
+	 * for that!
 	 */
-	i_mode = file_inode(in)->i_mode;
-	if (unlikely(!S_ISREG(i_mode) && !S_ISBLK(i_mode)))
+	if (unlikely(!(in->f_mode & FMODE_LSEEK)))
 		return -EINVAL;
 
 	/*
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index f2625a372a3a..066e8344934d 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -141,6 +141,8 @@ struct tracefs_mount_opts {
 	kuid_t uid;
 	kgid_t gid;
 	umode_t mode;
+	/* Opt_* bitfield. */
+	unsigned int opts;
 };
 
 enum {
@@ -241,6 +243,7 @@ static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts)
 	kgid_t gid;
 	char *p;
 
+	opts->opts = 0;
 	opts->mode = TRACEFS_DEFAULT_MODE;
 
 	while ((p = strsep(&data, ",")) != NULL) {
@@ -275,24 +278,36 @@ static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts)
 		 * but traditionally tracefs has ignored all mount options
 		 */
 		}
+
+		opts->opts |= BIT(token);
 	}
 
 	return 0;
 }
 
-static int tracefs_apply_options(struct super_block *sb)
+static int tracefs_apply_options(struct super_block *sb, bool remount)
 {
 	struct tracefs_fs_info *fsi = sb->s_fs_info;
 	struct inode *inode = sb->s_root->d_inode;
 	struct tracefs_mount_opts *opts = &fsi->mount_opts;
 
-	inode->i_mode &= ~S_IALLUGO;
-	inode->i_mode |= opts->mode;
+	/*
+	 * On remount, only reset mode/uid/gid if they were provided as mount
+	 * options.
+	 */
+
+	if (!remount || opts->opts & BIT(Opt_mode)) {
+		inode->i_mode &= ~S_IALLUGO;
+		inode->i_mode |= opts->mode;
+	}
 
-	inode->i_uid = opts->uid;
+	if (!remount || opts->opts & BIT(Opt_uid))
+		inode->i_uid = opts->uid;
 
-	/* Set all the group ids to the mount option */
-	set_gid(sb->s_root, opts->gid);
+	if (!remount || opts->opts & BIT(Opt_gid)) {
+		/* Set all the group ids to the mount option */
+		set_gid(sb->s_root, opts->gid);
+	}
 
 	return 0;
 }
@@ -307,7 +322,7 @@ static int tracefs_remount(struct super_block *sb, int *flags, char *data)
 	if (err)
 		goto fail;
 
-	tracefs_apply_options(sb);
+	tracefs_apply_options(sb, true);
 
 fail:
 	return err;
@@ -359,7 +374,7 @@ static int trace_fill_super(struct super_block *sb, void *data, int silent)
 
 	sb->s_op = &tracefs_super_operations;
 
-	tracefs_apply_options(sb);
+	tracefs_apply_options(sb, false);
 
 	return 0;
 
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index 4c6f9045baca..3f597cad2c33 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -116,23 +116,29 @@ void xfs_perag_put(struct xfs_perag *pag);
 
 /*
  * Perag iteration APIs
- *
- * XXX: for_each_perag_range() usage really needs an iterator to clean up when
- * we terminate at end_agno because we may have taken a reference to the perag
- * beyond end_agno. Right now callers have to be careful to catch and clean that
- * up themselves. This is not necessary for the callers of for_each_perag() and
- * for_each_perag_from() because they terminate at sb_agcount where there are
- * no perag structures in tree beyond end_agno.
  */
-#define for_each_perag_range(mp, next_agno, end_agno, pag) \
-	for ((pag) = xfs_perag_get((mp), (next_agno)); \
-		(pag) != NULL && (next_agno) <= (end_agno); \
-		(next_agno) = (pag)->pag_agno + 1, \
-		xfs_perag_put(pag), \
-		(pag) = xfs_perag_get((mp), (next_agno)))
+static inline struct xfs_perag *
+xfs_perag_next(
+	struct xfs_perag	*pag,
+	xfs_agnumber_t		*agno,
+	xfs_agnumber_t		end_agno)
+{
+	struct xfs_mount	*mp = pag->pag_mount;
+
+	*agno = pag->pag_agno + 1;
+	xfs_perag_put(pag);
+	if (*agno > end_agno)
+		return NULL;
+	return xfs_perag_get(mp, *agno);
+}
+
+#define for_each_perag_range(mp, agno, end_agno, pag) \
+	for ((pag) = xfs_perag_get((mp), (agno)); \
+		(pag) != NULL; \
+		(pag) = xfs_perag_next((pag), &(agno), (end_agno)))
 
-#define for_each_perag_from(mp, next_agno, pag) \
-	for_each_perag_range((mp), (next_agno), (mp)->m_sb.sb_agcount, (pag))
+#define for_each_perag_from(mp, agno, pag) \
+	for_each_perag_range((mp), (agno), (mp)->m_sb.sb_agcount - 1, (pag))
 
 
 #define for_each_perag(mp, agno, pag) \
diff --git a/fs/xfs/libxfs/xfs_btree_staging.c b/fs/xfs/libxfs/xfs_btree_staging.c
index ac9e80152b5c..89c8a1498df1 100644
--- a/fs/xfs/libxfs/xfs_btree_staging.c
+++ b/fs/xfs/libxfs/xfs_btree_staging.c
@@ -662,7 +662,7 @@ xfs_btree_bload_compute_geometry(
 	xfs_btree_bload_ensure_slack(cur, &bbl->node_slack, 1);
 
 	bbl->nr_records = nr_this_level = nr_records;
-	for (cur->bc_nlevels = 1; cur->bc_nlevels < XFS_BTREE_MAXLEVELS;) {
+	for (cur->bc_nlevels = 1; cur->bc_nlevels <= XFS_BTREE_MAXLEVELS;) {
 		uint64_t	level_blocks;
 		uint64_t	dontcare64;
 		unsigned int	level = cur->bc_nlevels - 1;
@@ -724,7 +724,7 @@ xfs_btree_bload_compute_geometry(
 		nr_this_level = level_blocks;
 	}
 
-	if (cur->bc_nlevels == XFS_BTREE_MAXLEVELS)
+	if (cur->bc_nlevels > XFS_BTREE_MAXLEVELS)
 		return -EOVERFLOW;
 
 	bbl->btree_height = cur->bc_nlevels;
diff --git a/fs/xfs/xfs_bio_io.c b/fs/xfs/xfs_bio_io.c
index 667e297f59b1..17f36db2f792 100644
--- a/fs/xfs/xfs_bio_io.c
+++ b/fs/xfs/xfs_bio_io.c
@@ -9,41 +9,6 @@ static inline unsigned int bio_max_vecs(unsigned int count)
 	return bio_max_segs(howmany(count, PAGE_SIZE));
 }
 
-static void
-xfs_flush_bdev_async_endio(
-	struct bio	*bio)
-{
-	complete(bio->bi_private);
-}
-
-/*
- * Submit a request for an async cache flush to run. If the request queue does
- * not require flush operations, just skip it altogether. If the caller needs
- * to wait for the flush completion at a later point in time, they must supply a
- * valid completion. This will be signalled when the flush completes.  The
- * caller never sees the bio that is issued here.
- */
-void
-xfs_flush_bdev_async(
-	struct bio		*bio,
-	struct block_device	*bdev,
-	struct completion	*done)
-{
-	struct request_queue	*q = bdev->bd_disk->queue;
-
-	if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags)) {
-		complete(done);
-		return;
-	}
-
-	bio_init(bio, NULL, 0);
-	bio_set_dev(bio, bdev);
-	bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC;
-	bio->bi_private = done;
-	bio->bi_end_io = xfs_flush_bdev_async_endio;
-
-	submit_bio(bio);
-}
 int
 xfs_rw_bdev(
 	struct block_device	*bdev,
diff --git a/fs/xfs/xfs_filestream.c b/fs/xfs/xfs_filestream.c
index 6a3ce0f6dc9e..be9bcf8a1f99 100644
--- a/fs/xfs/xfs_filestream.c
+++ b/fs/xfs/xfs_filestream.c
@@ -128,11 +128,12 @@ xfs_filestream_pick_ag(
 		if (!pag->pagf_init) {
 			err = xfs_alloc_pagf_init(mp, NULL, ag, trylock);
 			if (err) {
-				xfs_perag_put(pag);
-				if (err != -EAGAIN)
+				if (err != -EAGAIN) {
+					xfs_perag_put(pag);
 					return err;
+				}
 				/* Couldn't lock the AGF, skip this AG. */
-				continue;
+				goto next_ag;
 			}
 		}
 
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 33e26690a8c4..5b5b68affe66 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -430,46 +430,36 @@ xfs_reserve_blocks(
 	 * If the request is larger than the current reservation, reserve the
 	 * blocks before we update the reserve counters. Sample m_fdblocks and
 	 * perform a partial reservation if the request exceeds free space.
+	 *
+	 * The code below estimates how many blocks it can request from
+	 * fdblocks to stash in the reserve pool.  This is a classic TOCTOU
+	 * race since fdblocks updates are not always coordinated via
+	 * m_sb_lock.  Set the reserve size even if there's not enough free
+	 * space to fill it because mod_fdblocks will refill an undersized
+	 * reserve when it can.
 	 */
-	error = -ENOSPC;
-	do {
-		free = percpu_counter_sum(&mp->m_fdblocks) -
-						mp->m_alloc_set_aside;
-		if (free <= 0)
-			break;
-
-		delta = request - mp->m_resblks;
-		lcounter = free - delta;
-		if (lcounter < 0)
-			/* We can't satisfy the request, just get what we can */
-			fdblks_delta = free;
-		else
-			fdblks_delta = delta;
-
+	free = percpu_counter_sum(&mp->m_fdblocks) -
+						xfs_fdblocks_unavailable(mp);
+	delta = request - mp->m_resblks;
+	mp->m_resblks = request;
+	if (delta > 0 && free > 0) {
 		/*
 		 * We'll either succeed in getting space from the free block
-		 * count or we'll get an ENOSPC. If we get a ENOSPC, it means
-		 * things changed while we were calculating fdblks_delta and so
-		 * we should try again to see if there is anything left to
-		 * reserve.
+		 * count or we'll get an ENOSPC.  Don't set the reserved flag
+		 * here - we don't want to reserve the extra reserve blocks
+		 * from the reserve.
 		 *
-		 * Don't set the reserved flag here - we don't want to reserve
-		 * the extra reserve blocks from the reserve.....
+		 * The desired reserve size can change after we drop the lock.
+		 * Use mod_fdblocks to put the space into the reserve or into
+		 * fdblocks as appropriate.
 		 */
+		fdblks_delta = min(free, delta);
 		spin_unlock(&mp->m_sb_lock);
 		error = xfs_mod_fdblocks(mp, -fdblks_delta, 0);
+		if (!error)
+			xfs_mod_fdblocks(mp, fdblks_delta, 0);
 		spin_lock(&mp->m_sb_lock);
-	} while (error == -ENOSPC);
-
-	/*
-	 * Update the reserve counters if blocks have been successfully
-	 * allocated.
-	 */
-	if (!error && fdblks_delta) {
-		mp->m_resblks += fdblks_delta;
-		mp->m_resblks_avail += fdblks_delta;
 	}
-
 out:
 	if (outval) {
 		outval->resblks = mp->m_resblks;
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index f2210d927481..5e44d7bbd8fc 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1872,28 +1872,20 @@ xfs_inodegc_worker(
 }
 
 /*
- * Force all currently queued inode inactivation work to run immediately, and
- * wait for the work to finish. Two pass - queue all the work first pass, wait
- * for it in a second pass.
+ * Force all currently queued inode inactivation work to run immediately and
+ * wait for the work to finish.
  */
 void
 xfs_inodegc_flush(
 	struct xfs_mount	*mp)
 {
-	struct xfs_inodegc	*gc;
-	int			cpu;
-
 	if (!xfs_is_inodegc_enabled(mp))
 		return;
 
 	trace_xfs_inodegc_flush(mp, __return_address);
 
 	xfs_inodegc_queue_all(mp);
-
-	for_each_online_cpu(cpu) {
-		gc = per_cpu_ptr(mp->m_inodegc, cpu);
-		flush_work(&gc->work);
-	}
+	flush_workqueue(mp->m_inodegc_wq);
 }
 
 /*
@@ -1904,18 +1896,12 @@ void
 xfs_inodegc_stop(
 	struct xfs_mount	*mp)
 {
-	struct xfs_inodegc	*gc;
-	int			cpu;
-
 	if (!xfs_clear_inodegc_enabled(mp))
 		return;
 
 	xfs_inodegc_queue_all(mp);
+	drain_workqueue(mp->m_inodegc_wq);
 
-	for_each_online_cpu(cpu) {
-		gc = per_cpu_ptr(mp->m_inodegc, cpu);
-		cancel_work_sync(&gc->work);
-	}
 	trace_xfs_inodegc_stop(mp, __return_address);
 }
 
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 2477e301fa82..fb7a97cdf99f 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1223,7 +1223,7 @@ xfs_link(
 {
 	xfs_mount_t		*mp = tdp->i_mount;
 	xfs_trans_t		*tp;
-	int			error;
+	int			error, nospace_error = 0;
 	int			resblks;
 
 	trace_xfs_link(tdp, target_name);
@@ -1242,19 +1242,11 @@ xfs_link(
 		goto std_return;
 
 	resblks = XFS_LINK_SPACE_RES(mp, target_name->len);
-	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_link, resblks, 0, 0, &tp);
-	if (error == -ENOSPC) {
-		resblks = 0;
-		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_link, 0, 0, 0, &tp);
-	}
+	error = xfs_trans_alloc_dir(tdp, &M_RES(mp)->tr_link, sip, &resblks,
+			&tp, &nospace_error);
 	if (error)
 		goto std_return;
 
-	xfs_lock_two_inodes(sip, XFS_ILOCK_EXCL, tdp, XFS_ILOCK_EXCL);
-
-	xfs_trans_ijoin(tp, sip, XFS_ILOCK_EXCL);
-	xfs_trans_ijoin(tp, tdp, XFS_ILOCK_EXCL);
-
 	error = xfs_iext_count_may_overflow(tdp, XFS_DATA_FORK,
 			XFS_IEXT_DIR_MANIP_CNT(mp));
 	if (error)
@@ -1312,6 +1304,8 @@ xfs_link(
  error_return:
 	xfs_trans_cancel(tp);
  std_return:
+	if (error == -ENOSPC && nospace_error)
+		error = nospace_error;
 	return error;
 }
 
@@ -2761,6 +2755,7 @@ xfs_remove(
 	xfs_mount_t		*mp = dp->i_mount;
 	xfs_trans_t             *tp = NULL;
 	int			is_dir = S_ISDIR(VFS_I(ip)->i_mode);
+	int			dontcare;
 	int                     error = 0;
 	uint			resblks;
 
@@ -2778,31 +2773,24 @@ xfs_remove(
 		goto std_return;
 
 	/*
-	 * We try to get the real space reservation first,
-	 * allowing for directory btree deletion(s) implying
-	 * possible bmap insert(s).  If we can't get the space
-	 * reservation then we use 0 instead, and avoid the bmap
-	 * btree insert(s) in the directory code by, if the bmap
-	 * insert tries to happen, instead trimming the LAST
-	 * block from the directory.
+	 * We try to get the real space reservation first, allowing for
+	 * directory btree deletion(s) implying possible bmap insert(s).  If we
+	 * can't get the space reservation then we use 0 instead, and avoid the
+	 * bmap btree insert(s) in the directory code by, if the bmap insert
+	 * tries to happen, instead trimming the LAST block from the directory.
+	 *
+	 * Ignore EDQUOT and ENOSPC being returned via nospace_error because
+	 * the directory code can handle a reservationless update and we don't
+	 * want to prevent a user from trying to free space by deleting things.
 	 */
 	resblks = XFS_REMOVE_SPACE_RES(mp);
-	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_remove, resblks, 0, 0, &tp);
-	if (error == -ENOSPC) {
-		resblks = 0;
-		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_remove, 0, 0, 0,
-				&tp);
-	}
+	error = xfs_trans_alloc_dir(dp, &M_RES(mp)->tr_remove, ip, &resblks,
+			&tp, &dontcare);
 	if (error) {
 		ASSERT(error != -ENOSPC);
 		goto std_return;
 	}
 
-	xfs_lock_two_inodes(dp, XFS_ILOCK_EXCL, ip, XFS_ILOCK_EXCL);
-
-	xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL);
-	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
-
 	/*
 	 * If we're removing a directory perform some additional validation.
 	 */
@@ -3115,7 +3103,8 @@ xfs_rename(
 	bool			new_parent = (src_dp != target_dp);
 	bool			src_is_directory = S_ISDIR(VFS_I(src_ip)->i_mode);
 	int			spaceres;
-	int			error;
+	bool			retried = false;
+	int			error, nospace_error = 0;
 
 	trace_xfs_rename(src_dp, target_dp, src_name, target_name);
 
@@ -3128,7 +3117,6 @@ xfs_rename(
 	 * appropriately.
 	 */
 	if (flags & RENAME_WHITEOUT) {
-		ASSERT(!(flags & (RENAME_NOREPLACE | RENAME_EXCHANGE)));
 		error = xfs_rename_alloc_whiteout(mnt_userns, target_dp, &wip);
 		if (error)
 			return error;
@@ -3140,9 +3128,12 @@ xfs_rename(
 	xfs_sort_for_rename(src_dp, target_dp, src_ip, target_ip, wip,
 				inodes, &num_inodes);
 
+retry:
+	nospace_error = 0;
 	spaceres = XFS_RENAME_SPACE_RES(mp, target_name->len);
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_rename, spaceres, 0, 0, &tp);
 	if (error == -ENOSPC) {
+		nospace_error = error;
 		spaceres = 0;
 		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_rename, 0, 0, 0,
 				&tp);
@@ -3197,6 +3188,31 @@ xfs_rename(
 					spaceres);
 
 	/*
+	 * Try to reserve quota to handle an expansion of the target directory.
+	 * We'll allow the rename to continue in reservationless mode if we hit
+	 * a space usage constraint.  If we trigger reservationless mode, save
+	 * the errno if there isn't any free space in the target directory.
+	 */
+	if (spaceres != 0) {
+		error = xfs_trans_reserve_quota_nblks(tp, target_dp, spaceres,
+				0, false);
+		if (error == -EDQUOT || error == -ENOSPC) {
+			if (!retried) {
+				xfs_trans_cancel(tp);
+				xfs_blockgc_free_quota(target_dp, 0);
+				retried = true;
+				goto retry;
+			}
+
+			nospace_error = error;
+			spaceres = 0;
+			error = 0;
+		}
+		if (error)
+			goto out_trans_cancel;
+	}
+
+	/*
 	 * Check for expected errors before we dirty the transaction
 	 * so we can return an error without a transaction abort.
 	 *
@@ -3442,6 +3458,8 @@ out_trans_cancel:
 out_release_wip:
 	if (wip)
 		xfs_irele(wip);
+	if (error == -ENOSPC && nospace_error)
+		error = nospace_error;
 	return error;
 }
 
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 09269f478df9..bcc3c18c8080 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -372,7 +372,7 @@ int
 xfs_ioc_attr_list(
 	struct xfs_inode		*dp,
 	void __user			*ubuf,
-	int				bufsize,
+	size_t				bufsize,
 	int				flags,
 	struct xfs_attrlist_cursor __user *ucursor)
 {
@@ -1545,7 +1545,7 @@ xfs_ioc_getbmap(
 
 	if (bmx.bmv_count < 2)
 		return -EINVAL;
-	if (bmx.bmv_count > ULONG_MAX / recsize)
+	if (bmx.bmv_count >= INT_MAX / recsize)
 		return -ENOMEM;
 
 	buf = kvzalloc(bmx.bmv_count * sizeof(*buf), GFP_KERNEL);
diff --git a/fs/xfs/xfs_ioctl.h b/fs/xfs/xfs_ioctl.h
index 28453a6d4461..845d3bcab74b 100644
--- a/fs/xfs/xfs_ioctl.h
+++ b/fs/xfs/xfs_ioctl.h
@@ -38,8 +38,9 @@ xfs_readlink_by_handle(
 int xfs_ioc_attrmulti_one(struct file *parfilp, struct inode *inode,
 		uint32_t opcode, void __user *uname, void __user *value,
 		uint32_t *len, uint32_t flags);
-int xfs_ioc_attr_list(struct xfs_inode *dp, void __user *ubuf, int bufsize,
-	int flags, struct xfs_attrlist_cursor __user *ucursor);
+int xfs_ioc_attr_list(struct xfs_inode *dp, void __user *ubuf,
+		      size_t bufsize, int flags,
+		      struct xfs_attrlist_cursor __user *ucursor);
 
 extern struct dentry *
 xfs_handle_to_dentry(
diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index 09a8fba84ff9..cb9105d667db 100644
--- a/fs/xfs/xfs_linux.h
+++ b/fs/xfs/xfs_linux.h
@@ -197,8 +197,6 @@ static inline uint64_t howmany_64(uint64_t x, uint32_t y)
 
 int xfs_rw_bdev(struct block_device *bdev, sector_t sector, unsigned int count,
 		char *data, unsigned int op);
-void xfs_flush_bdev_async(struct bio *bio, struct block_device *bdev,
-		struct completion *done);
 
 #define ASSERT_ALWAYS(expr)	\
 	(likely(expr) ? (void)0 : assfail(NULL, #expr, __FILE__, __LINE__))
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index f6cd2d4aa770..0fb7d05ca308 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -487,7 +487,10 @@ out_error:
  * Run all the pending iclog callbacks and wake log force waiters and iclog
  * space waiters so they can process the newly set shutdown state. We really
  * don't care what order we process callbacks here because the log is shut down
- * and so state cannot change on disk anymore.
+ * and so state cannot change on disk anymore. However, we cannot wake waiters
+ * until the callbacks have been processed because we may be in unmount and
+ * we must ensure that all AIL operations the callbacks perform have completed
+ * before we tear down the AIL.
  *
  * We avoid processing actively referenced iclogs so that we don't run callbacks
  * while the iclog owner might still be preparing the iclog for IO submssion.
@@ -501,7 +504,6 @@ xlog_state_shutdown_callbacks(
 	struct xlog_in_core	*iclog;
 	LIST_HEAD(cb_list);
 
-	spin_lock(&log->l_icloglock);
 	iclog = log->l_iclog;
 	do {
 		if (atomic_read(&iclog->ic_refcnt)) {
@@ -509,26 +511,22 @@ xlog_state_shutdown_callbacks(
 			continue;
 		}
 		list_splice_init(&iclog->ic_callbacks, &cb_list);
+		spin_unlock(&log->l_icloglock);
+
+		xlog_cil_process_committed(&cb_list);
+
+		spin_lock(&log->l_icloglock);
 		wake_up_all(&iclog->ic_write_wait);
 		wake_up_all(&iclog->ic_force_wait);
 	} while ((iclog = iclog->ic_next) != log->l_iclog);
 
 	wake_up_all(&log->l_flush_wait);
-	spin_unlock(&log->l_icloglock);
-
-	xlog_cil_process_committed(&cb_list);
 }
 
 /*
  * Flush iclog to disk if this is the last reference to the given iclog and the
  * it is in the WANT_SYNC state.
  *
- * If the caller passes in a non-zero @old_tail_lsn and the current log tail
- * does not match, there may be metadata on disk that must be persisted before
- * this iclog is written.  To satisfy that requirement, set the
- * XLOG_ICL_NEED_FLUSH flag as a condition for writing this iclog with the new
- * log tail value.
- *
  * If XLOG_ICL_NEED_FUA is already set on the iclog, we need to ensure that the
  * log tail is updated correctly. NEED_FUA indicates that the iclog will be
  * written to stable storage, and implies that a commit record is contained
@@ -545,12 +543,10 @@ xlog_state_shutdown_callbacks(
  * always capture the tail lsn on the iclog on the first NEED_FUA release
  * regardless of the number of active reference counts on this iclog.
  */
-
 int
 xlog_state_release_iclog(
 	struct xlog		*log,
-	struct xlog_in_core	*iclog,
-	xfs_lsn_t		old_tail_lsn)
+	struct xlog_in_core	*iclog)
 {
 	xfs_lsn_t		tail_lsn;
 	bool			last_ref;
@@ -561,18 +557,14 @@ xlog_state_release_iclog(
 	/*
 	 * Grabbing the current log tail needs to be atomic w.r.t. the writing
 	 * of the tail LSN into the iclog so we guarantee that the log tail does
-	 * not move between deciding if a cache flush is required and writing
-	 * the LSN into the iclog below.
+	 * not move between the first time we know that the iclog needs to be
+	 * made stable and when we eventually submit it.
 	 */
-	if (old_tail_lsn || iclog->ic_state == XLOG_STATE_WANT_SYNC) {
+	if ((iclog->ic_state == XLOG_STATE_WANT_SYNC ||
+	     (iclog->ic_flags & XLOG_ICL_NEED_FUA)) &&
+	    !iclog->ic_header.h_tail_lsn) {
 		tail_lsn = xlog_assign_tail_lsn(log->l_mp);
-
-		if (old_tail_lsn && tail_lsn != old_tail_lsn)
-			iclog->ic_flags |= XLOG_ICL_NEED_FLUSH;
-
-		if ((iclog->ic_flags & XLOG_ICL_NEED_FUA) &&
-		    !iclog->ic_header.h_tail_lsn)
-			iclog->ic_header.h_tail_lsn = cpu_to_be64(tail_lsn);
+		iclog->ic_header.h_tail_lsn = cpu_to_be64(tail_lsn);
 	}
 
 	last_ref = atomic_dec_and_test(&iclog->ic_refcnt);
@@ -583,11 +575,8 @@ xlog_state_release_iclog(
 		 * pending iclog callbacks that were waiting on the release of
 		 * this iclog.
 		 */
-		if (last_ref) {
-			spin_unlock(&log->l_icloglock);
+		if (last_ref)
 			xlog_state_shutdown_callbacks(log);
-			spin_lock(&log->l_icloglock);
-		}
 		return -EIO;
 	}
 
@@ -600,8 +589,6 @@ xlog_state_release_iclog(
 	}
 
 	iclog->ic_state = XLOG_STATE_SYNCING;
-	if (!iclog->ic_header.h_tail_lsn)
-		iclog->ic_header.h_tail_lsn = cpu_to_be64(tail_lsn);
 	xlog_verify_tail_lsn(log, iclog);
 	trace_xlog_iclog_syncing(iclog, _RET_IP_);
 
@@ -874,7 +861,7 @@ xlog_force_iclog(
 	iclog->ic_flags |= XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA;
 	if (iclog->ic_state == XLOG_STATE_ACTIVE)
 		xlog_state_switch_iclogs(iclog->ic_log, iclog, 0);
-	return xlog_state_release_iclog(iclog->ic_log, iclog, 0);
+	return xlog_state_release_iclog(iclog->ic_log, iclog);
 }
 
 /*
@@ -2412,7 +2399,7 @@ xlog_write_copy_finish(
 		ASSERT(iclog->ic_state == XLOG_STATE_WANT_SYNC ||
 			xlog_is_shutdown(log));
 release_iclog:
-	error = xlog_state_release_iclog(log, iclog, 0);
+	error = xlog_state_release_iclog(log, iclog);
 	spin_unlock(&log->l_icloglock);
 	return error;
 }
@@ -2629,7 +2616,7 @@ next_lv:
 
 	spin_lock(&log->l_icloglock);
 	xlog_state_finish_copy(log, iclog, record_cnt, data_cnt);
-	error = xlog_state_release_iclog(log, iclog, 0);
+	error = xlog_state_release_iclog(log, iclog);
 	spin_unlock(&log->l_icloglock);
 
 	return error;
@@ -3053,7 +3040,7 @@ restart:
 		 * reference to the iclog.
 		 */
 		if (!atomic_add_unless(&iclog->ic_refcnt, -1, 1))
-			error = xlog_state_release_iclog(log, iclog, 0);
+			error = xlog_state_release_iclog(log, iclog);
 		spin_unlock(&log->l_icloglock);
 		if (error)
 			return error;
@@ -3904,7 +3891,10 @@ xlog_force_shutdown(
 	wake_up_all(&log->l_cilp->xc_start_wait);
 	wake_up_all(&log->l_cilp->xc_commit_wait);
 	spin_unlock(&log->l_cilp->xc_push_lock);
+
+	spin_lock(&log->l_icloglock);
 	xlog_state_shutdown_callbacks(log);
+	spin_unlock(&log->l_icloglock);
 
 	return log_error;
 }
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index b59cc9c0961c..eafe30843ff0 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -681,11 +681,21 @@ xlog_cil_set_ctx_write_state(
 		 * The LSN we need to pass to the log items on transaction
 		 * commit is the LSN reported by the first log vector write, not
 		 * the commit lsn. If we use the commit record lsn then we can
-		 * move the tail beyond the grant write head.
+		 * move the grant write head beyond the tail LSN and overwrite
+		 * it.
 		 */
 		ctx->start_lsn = lsn;
 		wake_up_all(&cil->xc_start_wait);
 		spin_unlock(&cil->xc_push_lock);
+
+		/*
+		 * Make sure the metadata we are about to overwrite in the log
+		 * has been flushed to stable storage before this iclog is
+		 * issued.
+		 */
+		spin_lock(&cil->xc_log->l_icloglock);
+		iclog->ic_flags |= XLOG_ICL_NEED_FLUSH;
+		spin_unlock(&cil->xc_log->l_icloglock);
 		return;
 	}
 
@@ -864,10 +874,7 @@ xlog_cil_push_work(
 	struct xfs_trans_header thdr;
 	struct xfs_log_iovec	lhdr;
 	struct xfs_log_vec	lvhdr = { NULL };
-	xfs_lsn_t		preflush_tail_lsn;
 	xfs_csn_t		push_seq;
-	struct bio		bio;
-	DECLARE_COMPLETION_ONSTACK(bdev_flush);
 	bool			push_commit_stable;
 
 	new_ctx = xlog_cil_ctx_alloc();
@@ -938,23 +945,6 @@ xlog_cil_push_work(
 	spin_unlock(&cil->xc_push_lock);
 
 	/*
-	 * The CIL is stable at this point - nothing new will be added to it
-	 * because we hold the flush lock exclusively. Hence we can now issue
-	 * a cache flush to ensure all the completed metadata in the journal we
-	 * are about to overwrite is on stable storage.
-	 *
-	 * Because we are issuing this cache flush before we've written the
-	 * tail lsn to the iclog, we can have metadata IO completions move the
-	 * tail forwards between the completion of this flush and the iclog
-	 * being written. In this case, we need to re-issue the cache flush
-	 * before the iclog write. To detect whether the log tail moves, sample
-	 * the tail LSN *before* we issue the flush.
-	 */
-	preflush_tail_lsn = atomic64_read(&log->l_tail_lsn);
-	xfs_flush_bdev_async(&bio, log->l_mp->m_ddev_targp->bt_bdev,
-				&bdev_flush);
-
-	/*
 	 * Pull all the log vectors off the items in the CIL, and remove the
 	 * items from the CIL. We don't need the CIL lock here because it's only
 	 * needed on the transaction commit side which is currently locked out
@@ -1030,12 +1020,6 @@ xlog_cil_push_work(
 	lvhdr.lv_iovecp = &lhdr;
 	lvhdr.lv_next = ctx->lv_chain;
 
-	/*
-	 * Before we format and submit the first iclog, we have to ensure that
-	 * the metadata writeback ordering cache flush is complete.
-	 */
-	wait_for_completion(&bdev_flush);
-
 	error = xlog_cil_write_chain(ctx, &lvhdr);
 	if (error)
 		goto out_abort_free_ticket;
@@ -1094,7 +1078,7 @@ xlog_cil_push_work(
 	if (push_commit_stable &&
 	    ctx->commit_iclog->ic_state == XLOG_STATE_ACTIVE)
 		xlog_state_switch_iclogs(log, ctx->commit_iclog, 0);
-	xlog_state_release_iclog(log, ctx->commit_iclog, preflush_tail_lsn);
+	xlog_state_release_iclog(log, ctx->commit_iclog);
 
 	/* Not safe to reference ctx now! */
 
@@ -1115,7 +1099,7 @@ out_abort_free_ticket:
 		return;
 	}
 	spin_lock(&log->l_icloglock);
-	xlog_state_release_iclog(log, ctx->commit_iclog, 0);
+	xlog_state_release_iclog(log, ctx->commit_iclog);
 	/* Not safe to reference ctx now! */
 	spin_unlock(&log->l_icloglock);
 }
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index 844fbeec3545..f3d68ca39f45 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -524,8 +524,7 @@ void	xfs_log_ticket_regrant(struct xlog *log, struct xlog_ticket *ticket);
 
 void xlog_state_switch_iclogs(struct xlog *log, struct xlog_in_core *iclog,
 		int eventual_size);
-int xlog_state_release_iclog(struct xlog *log, struct xlog_in_core *iclog,
-		xfs_lsn_t log_tail_lsn);
+int xlog_state_release_iclog(struct xlog *log, struct xlog_in_core *iclog);
 
 /*
  * When we crack an atomic LSN, we sample it first so that the value will not
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 10562ecbd9ea..581aeb288b32 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -27,7 +27,7 @@
 #include "xfs_buf_item.h"
 #include "xfs_ag.h"
 #include "xfs_quota.h"
-
+#include "xfs_reflink.h"
 
 #define BLK_AVG(blk1, blk2)	((blk1+blk2) >> 1)
 
@@ -3502,6 +3502,28 @@ xlog_recover_finish(
 
 	xlog_recover_process_iunlinks(log);
 	xlog_recover_check_summary(log);
+
+	/*
+	 * Recover any CoW staging blocks that are still referenced by the
+	 * ondisk refcount metadata.  During mount there cannot be any live
+	 * staging extents as we have not permitted any user modifications.
+	 * Therefore, it is safe to free them all right now, even on a
+	 * read-only mount.
+	 */
+	error = xfs_reflink_recover_cow(log->l_mp);
+	if (error) {
+		xfs_alert(log->l_mp,
+	"Failed to recover leftover CoW staging extents, err %d.",
+				error);
+		/*
+		 * If we get an error here, make sure the log is shut down
+		 * but return zero so that any log items committed since the
+		 * end of intents processing can be pushed through the CIL
+		 * and AIL.
+		 */
+		xfs_force_shutdown(log->l_mp, SHUTDOWN_LOG_IO_ERROR);
+	}
+
 	return 0;
 }
 
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 06dac09eddbd..76056de83971 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -922,15 +922,6 @@ xfs_mountfs(
 			xfs_warn(mp,
 	"Unable to allocate reserve blocks. Continuing without reserve pool.");
 
-		/* Recover any CoW blocks that never got remapped. */
-		error = xfs_reflink_recover_cow(mp);
-		if (error) {
-			xfs_err(mp,
-	"Error %d recovering leftover CoW allocations.", error);
-			xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
-			goto out_quota;
-		}
-
 		/* Reserve AG blocks for future btree expansion. */
 		error = xfs_fs_reserve_ag_blocks(mp);
 		if (error && error != -ENOSPC)
@@ -941,7 +932,6 @@ xfs_mountfs(
 
  out_agresv:
 	xfs_fs_unreserve_ag_blocks(mp);
- out_quota:
 	xfs_qm_unmount_quotas(mp);
  out_rtunmount:
 	xfs_rtunmount_inodes(mp);
@@ -1142,7 +1132,7 @@ xfs_mod_fdblocks(
 	 * problems (i.e. transaction abort, pagecache discards, etc.) than
 	 * slightly premature -ENOSPC.
 	 */
-	set_aside = mp->m_alloc_set_aside + atomic64_read(&mp->m_allocbt_blks);
+	set_aside = xfs_fdblocks_unavailable(mp);
 	percpu_counter_add_batch(&mp->m_fdblocks, delta, batch);
 	if (__percpu_counter_compare(&mp->m_fdblocks, set_aside,
 				     XFS_FDBLOCKS_BATCH) >= 0) {
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index e091f3b3fa15..86564295fce6 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -478,6 +478,21 @@ extern void	xfs_unmountfs(xfs_mount_t *);
  */
 #define XFS_FDBLOCKS_BATCH	1024
 
+/*
+ * Estimate the amount of free space that is not available to userspace and is
+ * not explicitly reserved from the incore fdblocks.  This includes:
+ *
+ * - The minimum number of blocks needed to support splitting a bmap btree
+ * - The blocks currently in use by the freespace btrees because they record
+ *   the actual blocks that will fill per-AG metadata space reservations
+ */
+static inline uint64_t
+xfs_fdblocks_unavailable(
+	struct xfs_mount	*mp)
+{
+	return mp->m_alloc_set_aside + atomic64_read(&mp->m_allocbt_blks);
+}
+
 extern int	xfs_mod_fdblocks(struct xfs_mount *mp, int64_t delta,
 				 bool reserved);
 extern int	xfs_mod_frextents(struct xfs_mount *mp, int64_t delta);
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 76355f293488..36832e4bc803 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -749,7 +749,10 @@ xfs_reflink_end_cow(
 }
 
 /*
- * Free leftover CoW reservations that didn't get cleaned out.
+ * Free all CoW staging blocks that are still referenced by the ondisk refcount
+ * metadata.  The ondisk metadata does not track which inode created the
+ * staging extent, so callers must ensure that there are no cached inodes with
+ * live CoW staging extents.
  */
 int
 xfs_reflink_recover_cow(
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index e8d19916ba99..5410bf0ab426 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1742,15 +1742,6 @@ xfs_remount_rw(
 	 */
 	xfs_restore_resvblks(mp);
 	xfs_log_work_queue(mp);
-
-	/* Recover any CoW blocks that never got remapped. */
-	error = xfs_reflink_recover_cow(mp);
-	if (error) {
-		xfs_err(mp,
-			"Error %d recovering leftover CoW allocations.", error);
-		xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
-		return error;
-	}
 	xfs_blockgc_start(mp);
 
 	/* Create the per-AG metadata reservation pool .*/
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 67dec11e34c7..95c183072e7a 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -1201,3 +1201,89 @@ out_cancel:
 	xfs_trans_cancel(tp);
 	return error;
 }
+
+/*
+ * Allocate an transaction, lock and join the directory and child inodes to it,
+ * and reserve quota for a directory update.  If there isn't sufficient space,
+ * @dblocks will be set to zero for a reservationless directory update and
+ * @nospace_error will be set to a negative errno describing the space
+ * constraint we hit.
+ *
+ * The caller must ensure that the on-disk dquots attached to this inode have
+ * already been allocated and initialized.  The ILOCKs will be dropped when the
+ * transaction is committed or cancelled.
+ */
+int
+xfs_trans_alloc_dir(
+	struct xfs_inode	*dp,
+	struct xfs_trans_res	*resv,
+	struct xfs_inode	*ip,
+	unsigned int		*dblocks,
+	struct xfs_trans	**tpp,
+	int			*nospace_error)
+{
+	struct xfs_trans	*tp;
+	struct xfs_mount	*mp = ip->i_mount;
+	unsigned int		resblks;
+	bool			retried = false;
+	int			error;
+
+retry:
+	*nospace_error = 0;
+	resblks = *dblocks;
+	error = xfs_trans_alloc(mp, resv, resblks, 0, 0, &tp);
+	if (error == -ENOSPC) {
+		*nospace_error = error;
+		resblks = 0;
+		error = xfs_trans_alloc(mp, resv, resblks, 0, 0, &tp);
+	}
+	if (error)
+		return error;
+
+	xfs_lock_two_inodes(dp, XFS_ILOCK_EXCL, ip, XFS_ILOCK_EXCL);
+
+	xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+
+	error = xfs_qm_dqattach_locked(dp, false);
+	if (error) {
+		/* Caller should have allocated the dquots! */
+		ASSERT(error != -ENOENT);
+		goto out_cancel;
+	}
+
+	error = xfs_qm_dqattach_locked(ip, false);
+	if (error) {
+		/* Caller should have allocated the dquots! */
+		ASSERT(error != -ENOENT);
+		goto out_cancel;
+	}
+
+	if (resblks == 0)
+		goto done;
+
+	error = xfs_trans_reserve_quota_nblks(tp, dp, resblks, 0, false);
+	if (error == -EDQUOT || error == -ENOSPC) {
+		if (!retried) {
+			xfs_trans_cancel(tp);
+			xfs_blockgc_free_quota(dp, 0);
+			retried = true;
+			goto retry;
+		}
+
+		*nospace_error = error;
+		resblks = 0;
+		error = 0;
+	}
+	if (error)
+		goto out_cancel;
+
+done:
+	*tpp = tp;
+	*dblocks = resblks;
+	return 0;
+
+out_cancel:
+	xfs_trans_cancel(tp);
+	return error;
+}
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 50da47f23a07..faba74d4c702 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -265,6 +265,9 @@ int xfs_trans_alloc_icreate(struct xfs_mount *mp, struct xfs_trans_res *resv,
 int xfs_trans_alloc_ichange(struct xfs_inode *ip, struct xfs_dquot *udqp,
 		struct xfs_dquot *gdqp, struct xfs_dquot *pdqp, bool force,
 		struct xfs_trans **tpp);
+int xfs_trans_alloc_dir(struct xfs_inode *dp, struct xfs_trans_res *resv,
+		struct xfs_inode *ip, unsigned int *dblocks,
+		struct xfs_trans **tpp, int *nospace_error);
 
 static inline void
 xfs_trans_set_context(
diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c
index 3872ce671411..955c457e585a 100644
--- a/fs/xfs/xfs_trans_dquot.c
+++ b/fs/xfs/xfs_trans_dquot.c
@@ -603,7 +603,6 @@ xfs_dqresv_check(
 			return QUOTA_NL_ISOFTLONGWARN;
 		}
 
-		res->warnings++;
 		return QUOTA_NL_ISOFTWARN;
 	}
 
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index ecf564d150b3..f8feaed0b54d 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -723,13 +723,12 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from)
 	struct inode *inode = file_inode(iocb->ki_filp);
 	struct zonefs_inode_info *zi = ZONEFS_I(inode);
 	struct block_device *bdev = inode->i_sb->s_bdev;
-	unsigned int max;
+	unsigned int max = bdev_max_zone_append_sectors(bdev);
 	struct bio *bio;
 	ssize_t size;
 	int nr_pages;
 	ssize_t ret;
 
-	max = queue_max_zone_append_sectors(bdev_get_queue(bdev));
 	max = ALIGN_DOWN(max << SECTOR_SHIFT, inode->i_sb->s_blocksize);
 	iov_iter_truncate(from, max);
 
diff --git a/include/acpi/apei.h b/include/acpi/apei.h
index 680f80960c3d..a6ac2e8b72da 100644
--- a/include/acpi/apei.h
+++ b/include/acpi/apei.h
@@ -27,14 +27,16 @@ extern int hest_disable;
 extern int erst_disable;
 #ifdef CONFIG_ACPI_APEI_GHES
 extern bool ghes_disable;
+void __init ghes_init(void);
 #else
 #define ghes_disable 1
+static inline void ghes_init(void) { }
 #endif
 
 #ifdef CONFIG_ACPI_APEI
 void __init acpi_hest_init(void);
 #else
-static inline void acpi_hest_init(void) { return; }
+static inline void acpi_hest_init(void) { }
 #endif
 
 typedef int (*apei_hest_func_t)(struct acpi_hest_header *hest_hdr, void *data);
diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h
index bc159a9b4a73..6b14414b9ec1 100644
--- a/include/acpi/cppc_acpi.h
+++ b/include/acpi/cppc_acpi.h
@@ -17,7 +17,7 @@
 #include <acpi/pcc.h>
 #include <acpi/processor.h>
 
-/* Support CPPCv2 and CPPCv3  */
+/* CPPCv2 and CPPCv3 support */
 #define CPPC_V2_REV	2
 #define CPPC_V3_REV	3
 #define CPPC_V2_NUM_ENT	21
diff --git a/include/asm-generic/bitops/atomic.h b/include/asm-generic/bitops/atomic.h
index 3096f086b5a3..71ab4ba9c25d 100644
--- a/include/asm-generic/bitops/atomic.h
+++ b/include/asm-generic/bitops/atomic.h
@@ -39,9 +39,6 @@ arch_test_and_set_bit(unsigned int nr, volatile unsigned long *p)
 	unsigned long mask = BIT_MASK(nr);
 
 	p += BIT_WORD(nr);
-	if (READ_ONCE(*p) & mask)
-		return 1;
-
 	old = arch_atomic_long_fetch_or(mask, (atomic_long_t *)p);
 	return !!(old & mask);
 }
@@ -53,9 +50,6 @@ arch_test_and_clear_bit(unsigned int nr, volatile unsigned long *p)
 	unsigned long mask = BIT_MASK(nr);
 
 	p += BIT_WORD(nr);
-	if (!(READ_ONCE(*p) & mask))
-		return 0;
-
 	old = arch_atomic_long_fetch_andnot(mask, (atomic_long_t *)p);
 	return !!(old & mask);
 }
diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index 7ce93aaf69f8..98954dda5734 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -1125,9 +1125,7 @@ static inline void memcpy_toio(volatile void __iomem *addr, const void *buffer,
 }
 #endif
 
-#ifndef CONFIG_GENERIC_DEVMEM_IS_ALLOWED
 extern int devmem_is_allowed(unsigned long pfn);
-#endif
 
 #endif /* __KERNEL__ */
 
diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index d16302d3eb59..72f1e2a8c167 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -114,7 +114,7 @@ static inline bool memory_contains(void *begin, void *end, void *virt,
 /**
  * memory_intersects - checks if the region occupied by an object intersects
  *                     with another memory region
- * @begin: virtual address of the beginning of the memory regien
+ * @begin: virtual address of the beginning of the memory region
  * @end: virtual address of the end of the memory region
  * @virt: virtual address of the memory object
  * @size: size of the memory object
@@ -127,7 +127,10 @@ static inline bool memory_intersects(void *begin, void *end, void *virt,
 {
 	void *vend = virt + size;
 
-	return (virt >= begin && virt < end) || (vend >= begin && vend < end);
+	if (virt < end && vend > begin)
+		return true;
+
+	return false;
 }
 
 /**
diff --git a/include/crypto/internal/blake2s.h b/include/crypto/internal/blake2s.h
index 52363eee2b20..506d56530ca9 100644
--- a/include/crypto/internal/blake2s.h
+++ b/include/crypto/internal/blake2s.h
@@ -8,7 +8,6 @@
 #define _CRYPTO_INTERNAL_BLAKE2S_H
 
 #include <crypto/blake2s.h>
-#include <crypto/internal/hash.h>
 #include <linux/string.h>
 
 void blake2s_compress_generic(struct blake2s_state *state, const u8 *block,
@@ -19,111 +18,4 @@ void blake2s_compress(struct blake2s_state *state, const u8 *block,
 
 bool blake2s_selftest(void);
 
-static inline void blake2s_set_lastblock(struct blake2s_state *state)
-{
-	state->f[0] = -1;
-}
-
-/* Helper functions for BLAKE2s shared by the library and shash APIs */
-
-static __always_inline void
-__blake2s_update(struct blake2s_state *state, const u8 *in, size_t inlen,
-		 bool force_generic)
-{
-	const size_t fill = BLAKE2S_BLOCK_SIZE - state->buflen;
-
-	if (unlikely(!inlen))
-		return;
-	if (inlen > fill) {
-		memcpy(state->buf + state->buflen, in, fill);
-		if (force_generic)
-			blake2s_compress_generic(state, state->buf, 1,
-						 BLAKE2S_BLOCK_SIZE);
-		else
-			blake2s_compress(state, state->buf, 1,
-					 BLAKE2S_BLOCK_SIZE);
-		state->buflen = 0;
-		in += fill;
-		inlen -= fill;
-	}
-	if (inlen > BLAKE2S_BLOCK_SIZE) {
-		const size_t nblocks = DIV_ROUND_UP(inlen, BLAKE2S_BLOCK_SIZE);
-		/* Hash one less (full) block than strictly possible */
-		if (force_generic)
-			blake2s_compress_generic(state, in, nblocks - 1,
-						 BLAKE2S_BLOCK_SIZE);
-		else
-			blake2s_compress(state, in, nblocks - 1,
-					 BLAKE2S_BLOCK_SIZE);
-		in += BLAKE2S_BLOCK_SIZE * (nblocks - 1);
-		inlen -= BLAKE2S_BLOCK_SIZE * (nblocks - 1);
-	}
-	memcpy(state->buf + state->buflen, in, inlen);
-	state->buflen += inlen;
-}
-
-static __always_inline void
-__blake2s_final(struct blake2s_state *state, u8 *out, bool force_generic)
-{
-	blake2s_set_lastblock(state);
-	memset(state->buf + state->buflen, 0,
-	       BLAKE2S_BLOCK_SIZE - state->buflen); /* Padding */
-	if (force_generic)
-		blake2s_compress_generic(state, state->buf, 1, state->buflen);
-	else
-		blake2s_compress(state, state->buf, 1, state->buflen);
-	cpu_to_le32_array(state->h, ARRAY_SIZE(state->h));
-	memcpy(out, state->h, state->outlen);
-}
-
-/* Helper functions for shash implementations of BLAKE2s */
-
-struct blake2s_tfm_ctx {
-	u8 key[BLAKE2S_KEY_SIZE];
-	unsigned int keylen;
-};
-
-static inline int crypto_blake2s_setkey(struct crypto_shash *tfm,
-					const u8 *key, unsigned int keylen)
-{
-	struct blake2s_tfm_ctx *tctx = crypto_shash_ctx(tfm);
-
-	if (keylen == 0 || keylen > BLAKE2S_KEY_SIZE)
-		return -EINVAL;
-
-	memcpy(tctx->key, key, keylen);
-	tctx->keylen = keylen;
-
-	return 0;
-}
-
-static inline int crypto_blake2s_init(struct shash_desc *desc)
-{
-	const struct blake2s_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
-	struct blake2s_state *state = shash_desc_ctx(desc);
-	unsigned int outlen = crypto_shash_digestsize(desc->tfm);
-
-	__blake2s_init(state, outlen, tctx->key, tctx->keylen);
-	return 0;
-}
-
-static inline int crypto_blake2s_update(struct shash_desc *desc,
-					const u8 *in, unsigned int inlen,
-					bool force_generic)
-{
-	struct blake2s_state *state = shash_desc_ctx(desc);
-
-	__blake2s_update(state, in, inlen, force_generic);
-	return 0;
-}
-
-static inline int crypto_blake2s_final(struct shash_desc *desc, u8 *out,
-				       bool force_generic)
-{
-	struct blake2s_state *state = shash_desc_ctx(desc);
-
-	__blake2s_final(state, out, force_generic);
-	return 0;
-}
-
 #endif /* _CRYPTO_INTERNAL_BLAKE2S_H */
diff --git a/include/drm/drm_bridge.h b/include/drm/drm_bridge.h
index 46bdfa48c413..1648ce265cba 100644
--- a/include/drm/drm_bridge.h
+++ b/include/drm/drm_bridge.h
@@ -914,4 +914,17 @@ struct drm_bridge *devm_drm_panel_bridge_add_typed(struct device *dev,
 struct drm_connector *drm_panel_bridge_connector(struct drm_bridge *bridge);
 #endif
 
+#if defined(CONFIG_OF) && defined(CONFIG_DRM_PANEL_BRIDGE)
+struct drm_bridge *devm_drm_of_get_bridge(struct device *dev, struct device_node *node,
+					  u32 port, u32 endpoint);
+#else
+static inline struct drm_bridge *devm_drm_of_get_bridge(struct device *dev,
+							struct device_node *node,
+							u32 port,
+							u32 endpoint)
+{
+	return ERR_PTR(-ENODEV);
+}
+#endif
+
 #endif
diff --git a/include/drm/drm_gem_shmem_helper.h b/include/drm/drm_gem_shmem_helper.h
index 434328d8a0d9..311d66c9cf4b 100644
--- a/include/drm/drm_gem_shmem_helper.h
+++ b/include/drm/drm_gem_shmem_helper.h
@@ -107,16 +107,17 @@ struct drm_gem_shmem_object {
 	container_of(obj, struct drm_gem_shmem_object, base)
 
 struct drm_gem_shmem_object *drm_gem_shmem_create(struct drm_device *dev, size_t size);
-void drm_gem_shmem_free_object(struct drm_gem_object *obj);
+void drm_gem_shmem_free(struct drm_gem_shmem_object *shmem);
 
 int drm_gem_shmem_get_pages(struct drm_gem_shmem_object *shmem);
 void drm_gem_shmem_put_pages(struct drm_gem_shmem_object *shmem);
-int drm_gem_shmem_pin(struct drm_gem_object *obj);
-void drm_gem_shmem_unpin(struct drm_gem_object *obj);
-int drm_gem_shmem_vmap(struct drm_gem_object *obj, struct dma_buf_map *map);
-void drm_gem_shmem_vunmap(struct drm_gem_object *obj, struct dma_buf_map *map);
+int drm_gem_shmem_pin(struct drm_gem_shmem_object *shmem);
+void drm_gem_shmem_unpin(struct drm_gem_shmem_object *shmem);
+int drm_gem_shmem_vmap(struct drm_gem_shmem_object *shmem, struct dma_buf_map *map);
+void drm_gem_shmem_vunmap(struct drm_gem_shmem_object *shmem, struct dma_buf_map *map);
+int drm_gem_shmem_mmap(struct drm_gem_shmem_object *shmem, struct vm_area_struct *vma);
 
-int drm_gem_shmem_madvise(struct drm_gem_object *obj, int madv);
+int drm_gem_shmem_madvise(struct drm_gem_shmem_object *shmem, int madv);
 
 static inline bool drm_gem_shmem_is_purgeable(struct drm_gem_shmem_object *shmem)
 {
@@ -125,29 +126,156 @@ static inline bool drm_gem_shmem_is_purgeable(struct drm_gem_shmem_object *shmem
 		!shmem->base.dma_buf && !shmem->base.import_attach;
 }
 
-void drm_gem_shmem_purge_locked(struct drm_gem_object *obj);
-bool drm_gem_shmem_purge(struct drm_gem_object *obj);
+void drm_gem_shmem_purge_locked(struct drm_gem_shmem_object *shmem);
+bool drm_gem_shmem_purge(struct drm_gem_shmem_object *shmem);
 
-struct drm_gem_shmem_object *
-drm_gem_shmem_create_with_handle(struct drm_file *file_priv,
-				 struct drm_device *dev, size_t size,
-				 uint32_t *handle);
+struct sg_table *drm_gem_shmem_get_sg_table(struct drm_gem_shmem_object *shmem);
+struct sg_table *drm_gem_shmem_get_pages_sgt(struct drm_gem_shmem_object *shmem);
 
-int drm_gem_shmem_dumb_create(struct drm_file *file, struct drm_device *dev,
-			      struct drm_mode_create_dumb *args);
+void drm_gem_shmem_print_info(const struct drm_gem_shmem_object *shmem,
+			      struct drm_printer *p, unsigned int indent);
+
+/*
+ * GEM object functions
+ */
+
+/**
+ * drm_gem_shmem_object_free - GEM object function for drm_gem_shmem_free()
+ * @obj: GEM object to free
+ *
+ * This function wraps drm_gem_shmem_free(). Drivers that employ the shmem helpers
+ * should use it as their &drm_gem_object_funcs.free handler.
+ */
+static inline void drm_gem_shmem_object_free(struct drm_gem_object *obj)
+{
+	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
+
+	drm_gem_shmem_free(shmem);
+}
+
+/**
+ * drm_gem_shmem_object_print_info() - Print &drm_gem_shmem_object info for debugfs
+ * @p: DRM printer
+ * @indent: Tab indentation level
+ * @obj: GEM object
+ *
+ * This function wraps drm_gem_shmem_print_info(). Drivers that employ the shmem helpers should
+ * use this function as their &drm_gem_object_funcs.print_info handler.
+ */
+static inline void drm_gem_shmem_object_print_info(struct drm_printer *p, unsigned int indent,
+						   const struct drm_gem_object *obj)
+{
+	const struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
+
+	drm_gem_shmem_print_info(shmem, p, indent);
+}
+
+/**
+ * drm_gem_shmem_object_pin - GEM object function for drm_gem_shmem_pin()
+ * @obj: GEM object
+ *
+ * This function wraps drm_gem_shmem_pin(). Drivers that employ the shmem helpers should
+ * use it as their &drm_gem_object_funcs.pin handler.
+ */
+static inline int drm_gem_shmem_object_pin(struct drm_gem_object *obj)
+{
+	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
+
+	return drm_gem_shmem_pin(shmem);
+}
+
+/**
+ * drm_gem_shmem_object_unpin - GEM object function for drm_gem_shmem_unpin()
+ * @obj: GEM object
+ *
+ * This function wraps drm_gem_shmem_unpin(). Drivers that employ the shmem helpers should
+ * use it as their &drm_gem_object_funcs.unpin handler.
+ */
+static inline void drm_gem_shmem_object_unpin(struct drm_gem_object *obj)
+{
+	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
+
+	drm_gem_shmem_unpin(shmem);
+}
 
-int drm_gem_shmem_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma);
+/**
+ * drm_gem_shmem_object_get_sg_table - GEM object function for drm_gem_shmem_get_sg_table()
+ * @obj: GEM object
+ *
+ * This function wraps drm_gem_shmem_get_sg_table(). Drivers that employ the shmem helpers should
+ * use it as their &drm_gem_object_funcs.get_sg_table handler.
+ *
+ * Returns:
+ * A pointer to the scatter/gather table of pinned pages or NULL on failure.
+ */
+static inline struct sg_table *drm_gem_shmem_object_get_sg_table(struct drm_gem_object *obj)
+{
+	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
+
+	return drm_gem_shmem_get_sg_table(shmem);
+}
+
+/*
+ * drm_gem_shmem_object_vmap - GEM object function for drm_gem_shmem_vmap()
+ * @obj: GEM object
+ * @map: Returns the kernel virtual address of the SHMEM GEM object's backing store.
+ *
+ * This function wraps drm_gem_shmem_vmap(). Drivers that employ the shmem helpers should
+ * use it as their &drm_gem_object_funcs.vmap handler.
+ *
+ * Returns:
+ * 0 on success or a negative error code on failure.
+ */
+static inline int drm_gem_shmem_object_vmap(struct drm_gem_object *obj, struct dma_buf_map *map)
+{
+	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
+
+	return drm_gem_shmem_vmap(shmem, map);
+}
+
+/*
+ * drm_gem_shmem_object_vunmap - GEM object function for drm_gem_shmem_vunmap()
+ * @obj: GEM object
+ * @map: Kernel virtual address where the SHMEM GEM object was mapped
+ *
+ * This function wraps drm_gem_shmem_vunmap(). Drivers that employ the shmem helpers should
+ * use it as their &drm_gem_object_funcs.vunmap handler.
+ */
+static inline void drm_gem_shmem_object_vunmap(struct drm_gem_object *obj, struct dma_buf_map *map)
+{
+	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
+
+	drm_gem_shmem_vunmap(shmem, map);
+}
+
+/**
+ * drm_gem_shmem_object_mmap - GEM object function for drm_gem_shmem_mmap()
+ * @obj: GEM object
+ * @vma: VMA for the area to be mapped
+ *
+ * This function wraps drm_gem_shmem_mmap(). Drivers that employ the shmem helpers should
+ * use it as their &drm_gem_object_funcs.mmap handler.
+ *
+ * Returns:
+ * 0 on success or a negative error code on failure.
+ */
+static inline int drm_gem_shmem_object_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
+{
+	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
+
+	return drm_gem_shmem_mmap(shmem, vma);
+}
 
-void drm_gem_shmem_print_info(struct drm_printer *p, unsigned int indent,
-			      const struct drm_gem_object *obj);
+/*
+ * Driver ops
+ */
 
-struct sg_table *drm_gem_shmem_get_sg_table(struct drm_gem_object *obj);
 struct drm_gem_object *
 drm_gem_shmem_prime_import_sg_table(struct drm_device *dev,
 				    struct dma_buf_attachment *attach,
 				    struct sg_table *sgt);
-
-struct sg_table *drm_gem_shmem_get_pages_sgt(struct drm_gem_object *obj);
+int drm_gem_shmem_dumb_create(struct drm_file *file, struct drm_device *dev,
+			      struct drm_mode_create_dumb *args);
 
 /**
  * DRM_GEM_SHMEM_DRIVER_OPS - Default shmem GEM operations
diff --git a/include/dt-bindings/clock/qcom,gcc-msm8939.h b/include/dt-bindings/clock/qcom,gcc-msm8939.h
index 0634467c4ce5..2d545ed0d35a 100644
--- a/include/dt-bindings/clock/qcom,gcc-msm8939.h
+++ b/include/dt-bindings/clock/qcom,gcc-msm8939.h
@@ -192,6 +192,7 @@
 #define GCC_VENUS0_CORE0_VCODEC0_CLK		183
 #define GCC_VENUS0_CORE1_VCODEC0_CLK		184
 #define GCC_OXILI_TIMER_CLK			185
+#define SYSTEM_MM_NOC_BFDCD_CLK_SRC		186
 
 /* Indexes for GDSCs */
 #define BIMC_GDSC				0
diff --git a/include/linux/acpi_viot.h b/include/linux/acpi_viot.h
index 1eb8ee5b0e5f..a5a122431563 100644
--- a/include/linux/acpi_viot.h
+++ b/include/linux/acpi_viot.h
@@ -6,9 +6,11 @@
 #include <linux/acpi.h>
 
 #ifdef CONFIG_ACPI_VIOT
+void __init acpi_viot_early_init(void);
 void __init acpi_viot_init(void);
 int viot_iommu_configure(struct device *dev);
 #else
+static inline void acpi_viot_early_init(void) {}
 static inline void acpi_viot_init(void) {}
 static inline int viot_iommu_configure(struct device *dev)
 {
diff --git a/include/linux/arm_sdei.h b/include/linux/arm_sdei.h
index 0a241c5c911d..14dc461b0e82 100644
--- a/include/linux/arm_sdei.h
+++ b/include/linux/arm_sdei.h
@@ -46,9 +46,11 @@ int sdei_unregister_ghes(struct ghes *ghes);
 /* For use by arch code when CPU hotplug notifiers are not appropriate. */
 int sdei_mask_local_cpu(void);
 int sdei_unmask_local_cpu(void);
+void __init sdei_init(void);
 #else
 static inline int sdei_mask_local_cpu(void) { return 0; }
 static inline int sdei_unmask_local_cpu(void) { return 0; }
+static inline void sdei_init(void) { }
 #endif /* CONFIG_ARM_SDE_INTERFACE */
 
 
diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h
index 4e035aca6f7e..6093fa6db260 100644
--- a/include/linux/bitfield.h
+++ b/include/linux/bitfield.h
@@ -41,6 +41,22 @@
 
 #define __bf_shf(x) (__builtin_ffsll(x) - 1)
 
+#define __scalar_type_to_unsigned_cases(type)				\
+		unsigned type:	(unsigned type)0,			\
+		signed type:	(unsigned type)0
+
+#define __unsigned_scalar_typeof(x) typeof(				\
+		_Generic((x),						\
+			char:	(unsigned char)0,			\
+			__scalar_type_to_unsigned_cases(char),		\
+			__scalar_type_to_unsigned_cases(short),		\
+			__scalar_type_to_unsigned_cases(int),		\
+			__scalar_type_to_unsigned_cases(long),		\
+			__scalar_type_to_unsigned_cases(long long),	\
+			default: (x)))
+
+#define __bf_cast_unsigned(type, x)	((__unsigned_scalar_typeof(type))(x))
+
 #define __BF_FIELD_CHECK(_mask, _reg, _val, _pfx)			\
 	({								\
 		BUILD_BUG_ON_MSG(!__builtin_constant_p(_mask),		\
@@ -49,7 +65,8 @@
 		BUILD_BUG_ON_MSG(__builtin_constant_p(_val) ?		\
 				 ~((_mask) >> __bf_shf(_mask)) & (_val) : 0, \
 				 _pfx "value too large for the field"); \
-		BUILD_BUG_ON_MSG((_mask) > (typeof(_reg))~0ull,		\
+		BUILD_BUG_ON_MSG(__bf_cast_unsigned(_mask, _mask) >	\
+				 __bf_cast_unsigned(_reg, ~0ull),	\
 				 _pfx "type of reg too small for mask"); \
 		__BUILD_BUG_ON_NOT_POWER_OF_2((_mask) +			\
 					      (1ULL << __bf_shf(_mask))); \
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 17c92c0f15b2..36ce3d0fb9f3 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -294,7 +294,8 @@ enum {
 	BIO_TRACE_COMPLETION,	/* bio_endio() should trace the final completion
 				 * of this bio. */
 	BIO_CGROUP_ACCT,	/* has been accounted to a cgroup */
-	BIO_TRACKED,		/* set if bio goes through the rq_qos path */
+	BIO_QOS_THROTTLED,	/* bio went through rq_qos throttle path */
+	BIO_QOS_MERGED,		/* but went through rq_qos merge path */
 	BIO_REMAPPED,
 	BIO_ZONE_WRITE_LOCKED,	/* Owns a zoned device zone write lock */
 	BIO_PERCPU_CACHE,	/* can participate in per-cpu alloc cache */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index aebe67ed7a73..67344dfe07a7 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -261,8 +261,6 @@ static inline unsigned short req_get_ioprio(struct request *req)
 
 #include <linux/elevator.h>
 
-struct blk_queue_ctx;
-
 struct bio_vec;
 
 enum blk_eh_timer_return {
@@ -1389,6 +1387,17 @@ static inline unsigned int queue_max_zone_append_sectors(const struct request_qu
 	return min(l->max_zone_append_sectors, l->max_sectors);
 }
 
+static inline unsigned int
+bdev_max_zone_append_sectors(struct block_device *bdev)
+{
+	return queue_max_zone_append_sectors(bdev_get_queue(bdev));
+}
+
+static inline unsigned int bdev_max_segments(struct block_device *bdev)
+{
+	return queue_max_segments(bdev_get_queue(bdev));
+}
+
 static inline unsigned queue_logical_block_size(const struct request_queue *q)
 {
 	int retval = 512;
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index bb766a0b9b51..818cd594e922 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -533,6 +533,12 @@ bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size)
 	aux->ctx_field_size = size;
 }
 
+static inline bool bpf_pseudo_func(const struct bpf_insn *insn)
+{
+	return insn->code == (BPF_LD | BPF_IMM | BPF_DW) &&
+	       insn->src_reg == BPF_PSEUDO_FUNC;
+}
+
 struct bpf_prog_ops {
 	int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr,
 			union bpf_attr __user *uattr);
diff --git a/include/linux/bpfptr.h b/include/linux/bpfptr.h
index 546e27fc6d46..ee28d2b0a309 100644
--- a/include/linux/bpfptr.h
+++ b/include/linux/bpfptr.h
@@ -48,7 +48,9 @@ static inline void bpfptr_add(bpfptr_t *bpfptr, size_t val)
 static inline int copy_from_bpfptr_offset(void *dst, bpfptr_t src,
 					  size_t offset, size_t size)
 {
-	return copy_from_sockptr_offset(dst, (sockptr_t) src, offset, size);
+	if (!bpfptr_is_kernel(src))
+		return copy_from_user(dst, src.user + offset, size);
+	return copy_from_kernel_nofault(dst, src.kernel + offset, size);
 }
 
 static inline int copy_from_bpfptr(void *dst, bpfptr_t src, size_t size)
@@ -77,7 +79,9 @@ static inline void *kvmemdup_bpfptr(bpfptr_t src, size_t len)
 
 static inline long strncpy_from_bpfptr(char *dst, bpfptr_t src, size_t count)
 {
-	return strncpy_from_sockptr(dst, (sockptr_t) src, count);
+	if (bpfptr_is_kernel(src))
+		return strncpy_from_kernel_nofault(dst, src.kernel, count);
+	return strncpy_from_user(dst, src.user, count);
 }
 
 #endif /* _LINUX_BPFPTR_H */
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 36f33685c8c0..25b4263d66d7 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -117,7 +117,6 @@ static __always_inline int test_clear_buffer_##name(struct buffer_head *bh) \
  * of the form "mark_buffer_foo()".  These are higher-level functions which
  * do something in addition to setting a b_state bit.
  */
-BUFFER_FNS(Uptodate, uptodate)
 BUFFER_FNS(Dirty, dirty)
 TAS_BUFFER_FNS(Dirty, dirty)
 BUFFER_FNS(Lock, locked)
@@ -135,6 +134,41 @@ BUFFER_FNS(Meta, meta)
 BUFFER_FNS(Prio, prio)
 BUFFER_FNS(Defer_Completion, defer_completion)
 
+static __always_inline void set_buffer_uptodate(struct buffer_head *bh)
+{
+	/*
+	 * If somebody else already set this uptodate, they will
+	 * have done the memory barrier, and a reader will thus
+	 * see *some* valid buffer state.
+	 *
+	 * Any other serialization (with IO errors or whatever that
+	 * might clear the bit) has to come from other state (eg BH_Lock).
+	 */
+	if (test_bit(BH_Uptodate, &bh->b_state))
+		return;
+
+	/*
+	 * make it consistent with folio_mark_uptodate
+	 * pairs with smp_load_acquire in buffer_uptodate
+	 */
+	smp_mb__before_atomic();
+	set_bit(BH_Uptodate, &bh->b_state);
+}
+
+static __always_inline void clear_buffer_uptodate(struct buffer_head *bh)
+{
+	clear_bit(BH_Uptodate, &bh->b_state);
+}
+
+static __always_inline int buffer_uptodate(const struct buffer_head *bh)
+{
+	/*
+	 * make it consistent with folio_test_uptodate
+	 * pairs with smp_mb__before_atomic in set_buffer_uptodate
+	 */
+	return (smp_load_acquire(&bh->b_state) & (1UL << BH_Uptodate)) != 0;
+}
+
 #define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)
 
 /* If we *know* page->private refers to buffer_heads */
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index db2e147e069f..cd8b8bd5ec4d 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -264,7 +264,8 @@ struct css_set {
 	 * List of csets participating in the on-going migration either as
 	 * source or destination.  Protected by cgroup_mutex.
 	 */
-	struct list_head mg_preload_node;
+	struct list_head mg_src_preload_node;
+	struct list_head mg_dst_preload_node;
 	struct list_head mg_node;
 
 	/*
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index bd2b881c6b63..b9d5f9c373a0 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -144,3 +144,11 @@
 #else
 #define __diag_GCC_8(s)
 #endif
+
+/*
+ * Prior to 9.1, -Wno-alloc-size-larger-than (and therefore the "alloc_size"
+ * attribute) do not work, and must be disabled.
+ */
+#if GCC_VERSION < 90100
+#undef __alloc_size__
+#endif
diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h
index e6ec63403965..3de06a8fae73 100644
--- a/include/linux/compiler_attributes.h
+++ b/include/linux/compiler_attributes.h
@@ -34,6 +34,15 @@
 #define __aligned_largest               __attribute__((__aligned__))
 
 /*
+ * Note: do not use this directly. Instead, use __alloc_size() since it is conditionally
+ * available and includes other attributes.
+ *
+ *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-alloc_005fsize-function-attribute
+ * clang: https://clang.llvm.org/docs/AttributeReference.html#alloc-size
+ */
+#define __alloc_size__(x, ...)		__attribute__((__alloc_size__(x, ## __VA_ARGS__)))
+
+/*
  * Note: users of __always_inline currently do not write "inline" themselves,
  * which seems to be required by gcc to apply the attribute according
  * to its docs (and also "warning: always_inline function might not be
@@ -153,6 +162,7 @@
 
 /*
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-malloc-function-attribute
+ * clang: https://clang.llvm.org/docs/AttributeReference.html#malloc
  */
 #define __malloc                        __attribute__((__malloc__))
 
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index b6ff83a714ca..4f2203c4a257 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -250,6 +250,18 @@ struct ftrace_likely_data {
 # define __cficanonical
 #endif
 
+/*
+ * Any place that could be marked with the "alloc_size" attribute is also
+ * a place to be marked with the "malloc" attribute. Do this as part of the
+ * __alloc_size macro to avoid redundant attributes and to avoid missing a
+ * __malloc marking.
+ */
+#ifdef __alloc_size__
+# define __alloc_size(x, ...)	__alloc_size__(x, ## __VA_ARGS__) __malloc
+#else
+# define __alloc_size(x, ...)	__malloc
+#endif
+
 #ifndef asm_volatile_goto
 #define asm_volatile_goto(x...) asm goto(x)
 #endif
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index eb3394f5b109..6102a21a01d9 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -68,6 +68,8 @@ extern ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr,
 extern ssize_t cpu_show_mmio_stale_data(struct device *dev,
 					struct device_attribute *attr,
 					char *buf);
+extern ssize_t cpu_show_retbleed(struct device *dev,
+				 struct device_attribute *attr, char *buf);
 
 extern __printf(4, 5)
 struct device *cpu_device_create(struct device *parent, void *drvdata,
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 1e7399fc69c0..054e654f06de 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -1045,4 +1045,22 @@ cpumap_print_list_to_buf(char *buf, const struct cpumask *mask,
 	[0] =  1UL							\
 } }
 
+/*
+ * Provide a valid theoretical max size for cpumap and cpulist sysfs files
+ * to avoid breaking userspace which may allocate a buffer based on the size
+ * reported by e.g. fstat.
+ *
+ * for cpumap NR_CPUS * 9/32 - 1 should be an exact length.
+ *
+ * For cpulist 7 is (ceil(log10(NR_CPUS)) + 1) allowing for NR_CPUS to be up
+ * to 2 orders of magnitude larger than 8192. And then we divide by 2 to
+ * cover a worst-case of every other cpu being on one of two nodes for a
+ * very large NR_CPUS.
+ *
+ *  Use PAGE_SIZE as a minimum for smaller configurations.
+ */
+#define CPUMAP_FILE_MAX_BYTES  ((((NR_CPUS * 9)/32 - 1) > PAGE_SIZE) \
+					? (NR_CPUS * 9)/32 - 1 : PAGE_SIZE)
+#define CPULIST_FILE_MAX_BYTES  (((NR_CPUS * 7)/2 > PAGE_SIZE) ? (NR_CPUS * 7)/2 : PAGE_SIZE)
+
 #endif /* __LINUX_CPUMASK_H */
diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h
index c869f1e73d75..f60674692d36 100644
--- a/include/linux/debugfs.h
+++ b/include/linux/debugfs.h
@@ -91,6 +91,8 @@ struct dentry *debugfs_create_automount(const char *name,
 void debugfs_remove(struct dentry *dentry);
 #define debugfs_remove_recursive debugfs_remove
 
+void debugfs_lookup_and_remove(const char *name, struct dentry *parent);
+
 const struct file_operations *debugfs_real_fops(const struct file *filp);
 
 int debugfs_file_get(struct dentry *dentry);
@@ -225,6 +227,10 @@ static inline void debugfs_remove(struct dentry *dentry)
 static inline void debugfs_remove_recursive(struct dentry *dentry)
 { }
 
+static inline void debugfs_lookup_and_remove(const char *name,
+					     struct dentry *parent)
+{ }
+
 const struct file_operations *debugfs_real_fops(const struct file *filp);
 
 static inline int debugfs_file_get(struct dentry *dentry)
diff --git a/include/linux/dim.h b/include/linux/dim.h
index b698266d0035..6c5733981563 100644
--- a/include/linux/dim.h
+++ b/include/linux/dim.h
@@ -21,7 +21,7 @@
  * We consider 10% difference as significant.
  */
 #define IS_SIGNIFICANT_DIFF(val, ref) \
-	(((100UL * abs((val) - (ref))) / (ref)) > 10)
+	((ref) && (((100UL * abs((val) - (ref))) / (ref)) > 10))
 
 /*
  * Calculate the gap between two values.
diff --git a/include/linux/fbcon.h b/include/linux/fbcon.h
index ff5596dd30f8..2382dec6d6ab 100644
--- a/include/linux/fbcon.h
+++ b/include/linux/fbcon.h
@@ -15,6 +15,8 @@ void fbcon_new_modelist(struct fb_info *info);
 void fbcon_get_requirement(struct fb_info *info,
 			   struct fb_blit_caps *caps);
 void fbcon_fb_blanked(struct fb_info *info, int blank);
+int  fbcon_modechange_possible(struct fb_info *info,
+			       struct fb_var_screeninfo *var);
 void fbcon_update_vcs(struct fb_info *info, bool all);
 void fbcon_remap_all(struct fb_info *info);
 int fbcon_set_con2fb_map_ioctl(void __user *argp);
@@ -33,6 +35,8 @@ static inline void fbcon_new_modelist(struct fb_info *info) {}
 static inline void fbcon_get_requirement(struct fb_info *info,
 					 struct fb_blit_caps *caps) {}
 static inline void fbcon_fb_blanked(struct fb_info *info, int blank) {}
+static inline int  fbcon_modechange_possible(struct fb_info *info,
+				struct fb_var_screeninfo *var) { return 0; }
 static inline void fbcon_update_vcs(struct fb_info *info, bool all) {}
 static inline void fbcon_remap_all(struct fb_info *info) {}
 static inline int fbcon_set_con2fb_map_ioctl(void __user *argp) { return 0; }
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 1faebe1cd0ed..22c1d935e22d 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -167,6 +167,7 @@ long hugetlb_unreserve_pages(struct inode *inode, long start, long end,
 						long freed);
 bool isolate_huge_page(struct page *page, struct list_head *list);
 int get_hwpoison_huge_page(struct page *page, bool *hugetlb);
+int get_huge_page_for_hwpoison(unsigned long pfn, int flags);
 void putback_active_hugepage(struct page *page);
 void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason);
 void free_huge_page(struct page *page);
@@ -362,6 +363,11 @@ static inline int get_hwpoison_huge_page(struct page *page, bool *hugetlb)
 	return 0;
 }
 
+static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags)
+{
+	return 0;
+}
+
 static inline void putback_active_hugepage(struct page *page)
 {
 }
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 694264503119..00ed7c17698d 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1023,6 +1023,8 @@ struct ieee80211_tpc_report_ie {
 #define IEEE80211_ADDBA_EXT_FRAG_LEVEL_MASK	GENMASK(2, 1)
 #define IEEE80211_ADDBA_EXT_FRAG_LEVEL_SHIFT	1
 #define IEEE80211_ADDBA_EXT_NO_FRAG		BIT(0)
+#define IEEE80211_ADDBA_EXT_BUF_SIZE_MASK	GENMASK(7, 5)
+#define IEEE80211_ADDBA_EXT_BUF_SIZE_SHIFT	10
 
 struct ieee80211_addba_ext_ie {
 	u8 data;
@@ -1697,10 +1699,12 @@ struct ieee80211_ht_operation {
  * A-MPDU buffer sizes
  * According to HT size varies from 8 to 64 frames
  * HE adds the ability to have up to 256 frames.
+ * EHT adds the ability to have up to 1K frames.
  */
 #define IEEE80211_MIN_AMPDU_BUF		0x8
 #define IEEE80211_MAX_AMPDU_BUF_HT	0x40
-#define IEEE80211_MAX_AMPDU_BUF		0x100
+#define IEEE80211_MAX_AMPDU_BUF_HE	0x100
+#define IEEE80211_MAX_AMPDU_BUF_EHT	0x400
 
 
 /* Spatial Multiplexing Power Save Modes (for capability) */
diff --git a/include/linux/iio/common/cros_ec_sensors_core.h b/include/linux/iio/common/cros_ec_sensors_core.h
index c582e1a14232..7b5dbd749995 100644
--- a/include/linux/iio/common/cros_ec_sensors_core.h
+++ b/include/linux/iio/common/cros_ec_sensors_core.h
@@ -95,8 +95,11 @@ int cros_ec_sensors_read_cmd(struct iio_dev *indio_dev, unsigned long scan_mask,
 struct platform_device;
 int cros_ec_sensors_core_init(struct platform_device *pdev,
 			      struct iio_dev *indio_dev, bool physical_device,
-			      cros_ec_sensors_capture_t trigger_capture,
-			      cros_ec_sensorhub_push_data_cb_t push_data);
+			      cros_ec_sensors_capture_t trigger_capture);
+
+int cros_ec_sensors_core_register(struct device *dev,
+				  struct iio_dev *indio_dev,
+				  cros_ec_sensorhub_push_data_cb_t push_data);
 
 irqreturn_t cros_ec_sensors_capture(int irq, void *p);
 int cros_ec_sensors_push_data(struct iio_dev *indio_dev,
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 05a65eb155f7..81da7107e3bd 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -196,7 +196,6 @@
 #define ecap_dis(e)		(((e) >> 27) & 0x1)
 #define ecap_nest(e)		(((e) >> 26) & 0x1)
 #define ecap_mts(e)		(((e) >> 25) & 0x1)
-#define ecap_ecs(e)		(((e) >> 24) & 0x1)
 #define ecap_iotlb_offset(e) 	((((e) >> 8) & 0x3ff) * 16)
 #define ecap_max_iotlb_offset(e) (ecap_iotlb_offset(e) + 16)
 #define ecap_coherent(e)	((e) & 0x1)
@@ -264,7 +263,6 @@
 #define DMA_GSTS_CFIS (((u32)1) << 23)
 
 /* DMA_RTADDR_REG */
-#define DMA_RTADDR_RTT (((u64)1) << 11)
 #define DMA_RTADDR_SMT (((u64)1) << 10)
 
 /* CCMD_REG */
@@ -594,6 +592,7 @@ struct intel_iommu {
 #ifdef CONFIG_INTEL_IOMMU
 	unsigned long 	*domain_ids; /* bitmap of domains */
 	struct dmar_domain ***domains; /* ptr to domains */
+	unsigned long	*copied_tables; /* bitmap of copied tables */
 	spinlock_t	lock; /* protect context, domain ids */
 	struct root_entry *root_entry; /* virtual address */
 
@@ -713,6 +712,11 @@ static inline int first_pte_in_page(struct dma_pte *pte)
 	return !((unsigned long)pte & ~VTD_PAGE_MASK);
 }
 
+static inline bool context_present(struct context_entry *context)
+{
+	return (context->lo & 1);
+}
+
 extern struct dmar_drhd_unit * dmar_find_matched_drhd_unit(struct pci_dev *dev);
 extern int dmar_find_matched_atsr_unit(struct pci_dev *dev);
 
@@ -806,7 +810,6 @@ static inline void intel_iommu_debugfs_init(void) {}
 #endif /* CONFIG_INTEL_IOMMU_DEBUGFS */
 
 extern const struct attribute_group *intel_iommu_groups[];
-bool context_present(struct context_entry *context);
 struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus,
 					 u8 devfn, int alloc);
 
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 86af6f0a00a2..ca98aeadcc80 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -74,17 +74,22 @@ struct io_pgtable_cfg {
 	 *	to support up to 35 bits PA where the bit32, bit33 and bit34 are
 	 *	encoded in the bit9, bit4 and bit5 of the PTE respectively.
 	 *
+	 * IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT: (ARM v7s format) MediaTek IOMMUs
+	 *	extend the translation table base support up to 35 bits PA, the
+	 *	encoding format is same with IO_PGTABLE_QUIRK_ARM_MTK_EXT.
+	 *
 	 * IO_PGTABLE_QUIRK_ARM_TTBR1: (ARM LPAE format) Configure the table
 	 *	for use in the upper half of a split address space.
 	 *
 	 * IO_PGTABLE_QUIRK_ARM_OUTER_WBWA: Override the outer-cacheability
 	 *	attributes set in the TCR for a non-coherent page-table walker.
 	 */
-	#define IO_PGTABLE_QUIRK_ARM_NS		BIT(0)
-	#define IO_PGTABLE_QUIRK_NO_PERMS	BIT(1)
-	#define IO_PGTABLE_QUIRK_ARM_MTK_EXT	BIT(3)
-	#define IO_PGTABLE_QUIRK_ARM_TTBR1	BIT(5)
-	#define IO_PGTABLE_QUIRK_ARM_OUTER_WBWA	BIT(6)
+	#define IO_PGTABLE_QUIRK_ARM_NS			BIT(0)
+	#define IO_PGTABLE_QUIRK_NO_PERMS		BIT(1)
+	#define IO_PGTABLE_QUIRK_ARM_MTK_EXT		BIT(3)
+	#define IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT	BIT(4)
+	#define IO_PGTABLE_QUIRK_ARM_TTBR1		BIT(5)
+	#define IO_PGTABLE_QUIRK_ARM_OUTER_WBWA		BIT(6)
 	unsigned long			quirks;
 	unsigned long			pgsize_bitmap;
 	unsigned int			ias;
diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h
index 3f53bc27a19b..3d088a88f832 100644
--- a/include/linux/ioprio.h
+++ b/include/linux/ioprio.h
@@ -11,7 +11,7 @@
 /*
  * Default IO priority.
  */
-#define IOPRIO_DEFAULT	IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_BE_NORM)
+#define IOPRIO_DEFAULT	IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0)
 
 /*
  * Check that a priority value has a valid class.
diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h
index 600c10da321a..747f40e0c326 100644
--- a/include/linux/irqflags.h
+++ b/include/linux/irqflags.h
@@ -20,13 +20,13 @@
 #ifdef CONFIG_PROVE_LOCKING
   extern void lockdep_softirqs_on(unsigned long ip);
   extern void lockdep_softirqs_off(unsigned long ip);
-  extern void lockdep_hardirqs_on_prepare(unsigned long ip);
+  extern void lockdep_hardirqs_on_prepare(void);
   extern void lockdep_hardirqs_on(unsigned long ip);
   extern void lockdep_hardirqs_off(unsigned long ip);
 #else
   static inline void lockdep_softirqs_on(unsigned long ip) { }
   static inline void lockdep_softirqs_off(unsigned long ip) { }
-  static inline void lockdep_hardirqs_on_prepare(unsigned long ip) { }
+  static inline void lockdep_hardirqs_on_prepare(void) { }
   static inline void lockdep_hardirqs_on(unsigned long ip) { }
   static inline void lockdep_hardirqs_off(unsigned long ip) { }
 #endif
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index 33be67c2f7ff..cf042d41c87b 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -452,6 +452,12 @@ static inline int kexec_crash_loaded(void) { return 0; }
 #define kexec_in_progress false
 #endif /* CONFIG_KEXEC_CORE */
 
+#ifdef CONFIG_KEXEC_SIG
+void set_kexec_sig_enforced(void);
+#else
+static inline void set_kexec_sig_enforced(void) {}
+#endif
+
 #endif /* !defined(__ASSEBMLY__) */
 
 #endif /* LINUX_KEXEC_H */
diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h
index 86249476b57f..0b35a41440ff 100644
--- a/include/linux/kfifo.h
+++ b/include/linux/kfifo.h
@@ -688,7 +688,7 @@ __kfifo_uint_must_check_helper( \
  * writer, you don't need extra locking to use these macro.
  */
 #define	kfifo_to_user(fifo, to, len, copied) \
-__kfifo_uint_must_check_helper( \
+__kfifo_int_must_check_helper( \
 ({ \
 	typeof((fifo) + 1) __tmp = (fifo); \
 	void __user *__to = (to); \
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 926f60499c34..725f8f13adb5 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -436,7 +436,7 @@ static __always_inline void guest_state_enter_irqoff(void)
 {
 	instrumentation_begin();
 	trace_hardirqs_on_prepare();
-	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+	lockdep_hardirqs_on_prepare();
 	instrumentation_end();
 
 	guest_context_enter_irqoff();
@@ -1233,7 +1233,7 @@ static inline void kvm_arch_end_assignment(struct kvm *kvm)
 {
 }
 
-static inline bool kvm_arch_has_assigned_device(struct kvm *kvm)
+static __always_inline bool kvm_arch_has_assigned_device(struct kvm *kvm)
 {
 	return false;
 }
@@ -1912,6 +1912,8 @@ static inline long kvm_arch_vcpu_async_ioctl(struct file *filp,
 void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
 					    unsigned long start, unsigned long end);
 
+void kvm_arch_guest_memory_reclaimed(struct kvm *kvm);
+
 #ifdef CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE
 int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu);
 #else
diff --git a/include/linux/list.h b/include/linux/list.h
index a119dd1990d4..d206ae93c06d 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -578,6 +578,16 @@ static inline void list_splice_tail_init(struct list_head *list,
 	for (pos = (head)->next; !list_is_head(pos, (head)); pos = pos->next)
 
 /**
+ * list_for_each_rcu - Iterate over a list in an RCU-safe fashion
+ * @pos:	the &struct list_head to use as a loop cursor.
+ * @head:	the head for your list.
+ */
+#define list_for_each_rcu(pos, head)		  \
+	for (pos = rcu_dereference((head)->next); \
+	     !list_is_head(pos, (head)); \
+	     pos = rcu_dereference(pos->next))
+
+/**
  * list_for_each_continue - continue iteration over a list
  * @pos:	the &struct list_head to use as a loop cursor.
  * @head:	the head for your list.
diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h
index a98309c0121c..bed63156b052 100644
--- a/include/linux/lockd/xdr.h
+++ b/include/linux/lockd/xdr.h
@@ -41,6 +41,8 @@ struct nlm_lock {
 	struct nfs_fh		fh;
 	struct xdr_netobj	oh;
 	u32			svid;
+	u64			lock_start;
+	u64			lock_len;
 	struct file_lock	fl;
 };
 
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 9fe165beb0f9..aa0ecfc6cdb4 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -192,7 +192,7 @@ static inline void
 lockdep_init_map_waits(struct lockdep_map *lock, const char *name,
 		       struct lock_class_key *key, int subclass, u8 inner, u8 outer)
 {
-	lockdep_init_map_type(lock, name, key, subclass, inner, LD_WAIT_INV, LD_LOCK_NORMAL);
+	lockdep_init_map_type(lock, name, key, subclass, inner, outer, LD_LOCK_NORMAL);
 }
 
 static inline void
@@ -215,24 +215,28 @@ static inline void lockdep_init_map(struct lockdep_map *lock, const char *name,
  * or they are too narrow (they suffer from a false class-split):
  */
 #define lockdep_set_class(lock, key)				\
-	lockdep_init_map_waits(&(lock)->dep_map, #key, key, 0,	\
-			       (lock)->dep_map.wait_type_inner,	\
-			       (lock)->dep_map.wait_type_outer)
+	lockdep_init_map_type(&(lock)->dep_map, #key, key, 0,	\
+			      (lock)->dep_map.wait_type_inner,	\
+			      (lock)->dep_map.wait_type_outer,	\
+			      (lock)->dep_map.lock_type)
 
 #define lockdep_set_class_and_name(lock, key, name)		\
-	lockdep_init_map_waits(&(lock)->dep_map, name, key, 0,	\
-			       (lock)->dep_map.wait_type_inner,	\
-			       (lock)->dep_map.wait_type_outer)
+	lockdep_init_map_type(&(lock)->dep_map, name, key, 0,	\
+			      (lock)->dep_map.wait_type_inner,	\
+			      (lock)->dep_map.wait_type_outer,	\
+			      (lock)->dep_map.lock_type)
 
 #define lockdep_set_class_and_subclass(lock, key, sub)		\
-	lockdep_init_map_waits(&(lock)->dep_map, #key, key, sub,\
-			       (lock)->dep_map.wait_type_inner,	\
-			       (lock)->dep_map.wait_type_outer)
+	lockdep_init_map_type(&(lock)->dep_map, #key, key, sub,	\
+			      (lock)->dep_map.wait_type_inner,	\
+			      (lock)->dep_map.wait_type_outer,	\
+			      (lock)->dep_map.lock_type)
 
 #define lockdep_set_subclass(lock, sub)					\
-	lockdep_init_map_waits(&(lock)->dep_map, #lock, (lock)->dep_map.key, sub,\
-			       (lock)->dep_map.wait_type_inner,		\
-			       (lock)->dep_map.wait_type_outer)
+	lockdep_init_map_type(&(lock)->dep_map, #lock, (lock)->dep_map.key, sub,\
+			      (lock)->dep_map.wait_type_inner,		\
+			      (lock)->dep_map.wait_type_outer,		\
+			      (lock)->dep_map.lock_type)
 
 #define lockdep_set_novalidate_class(lock) \
 	lockdep_set_class_and_name(lock, &__lockdep_no_validate__, #lock)
diff --git a/include/linux/mbcache.h b/include/linux/mbcache.h
index 20f1e3ff6013..8eca7f25c432 100644
--- a/include/linux/mbcache.h
+++ b/include/linux/mbcache.h
@@ -30,15 +30,23 @@ void mb_cache_destroy(struct mb_cache *cache);
 int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key,
 			  u64 value, bool reusable);
 void __mb_cache_entry_free(struct mb_cache_entry *entry);
+void mb_cache_entry_wait_unused(struct mb_cache_entry *entry);
 static inline int mb_cache_entry_put(struct mb_cache *cache,
 				     struct mb_cache_entry *entry)
 {
-	if (!atomic_dec_and_test(&entry->e_refcnt))
+	unsigned int cnt = atomic_dec_return(&entry->e_refcnt);
+
+	if (cnt > 0) {
+		if (cnt <= 3)
+			wake_up_var(&entry->e_refcnt);
 		return 0;
+	}
 	__mb_cache_entry_free(entry);
 	return 1;
 }
 
+struct mb_cache_entry *mb_cache_entry_delete_or_get(struct mb_cache *cache,
+						    u32 key, u64 value);
 void mb_cache_entry_delete(struct mb_cache *cache, u32 key, u64 value);
 struct mb_cache_entry *mb_cache_entry_get(struct mb_cache *cache, u32 key,
 					  u64 value);
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index d35439db047c..4f189b17dafc 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -966,19 +966,30 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg,
 
 static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
 {
-	return READ_ONCE(memcg->vmstats.state[idx]);
+	long x = READ_ONCE(memcg->vmstats.state[idx]);
+#ifdef CONFIG_SMP
+	if (x < 0)
+		x = 0;
+#endif
+	return x;
 }
 
 static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
 					      enum node_stat_item idx)
 {
 	struct mem_cgroup_per_node *pn;
+	long x;
 
 	if (mem_cgroup_disabled())
 		return node_page_state(lruvec_pgdat(lruvec), idx);
 
 	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
-	return READ_ONCE(pn->lruvec_stats.state[idx]);
+	x = READ_ONCE(pn->lruvec_stats.state[idx]);
+#ifdef CONFIG_SMP
+	if (x < 0)
+		x = 0;
+#endif
+	return x;
 }
 
 static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
diff --git a/include/linux/memregion.h b/include/linux/memregion.h
index e11595256cac..c04c4fd2e209 100644
--- a/include/linux/memregion.h
+++ b/include/linux/memregion.h
@@ -16,7 +16,7 @@ static inline int memregion_alloc(gfp_t gfp)
 {
 	return -ENOMEM;
 }
-void memregion_free(int id)
+static inline void memregion_free(int id)
 {
 }
 #endif
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index c0e9d35889e8..a8bc588fe7aa 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -73,16 +73,6 @@ struct dev_pagemap_ops {
 	void (*page_free)(struct page *page);
 
 	/*
-	 * Transition the refcount in struct dev_pagemap to the dead state.
-	 */
-	void (*kill)(struct dev_pagemap *pgmap);
-
-	/*
-	 * Wait for refcount in struct dev_pagemap to be idle and reap it.
-	 */
-	void (*cleanup)(struct dev_pagemap *pgmap);
-
-	/*
 	 * Used for private (un-addressable) device memory only.  Must migrate
 	 * the page back to a CPU accessible page.
 	 */
@@ -95,8 +85,7 @@ struct dev_pagemap_ops {
  * struct dev_pagemap - metadata for ZONE_DEVICE mappings
  * @altmap: pre-allocated/reserved memory for vmemmap allocations
  * @ref: reference count that pins the devm_memremap_pages() mapping
- * @internal_ref: internal reference if @ref is not provided by the caller
- * @done: completion for @internal_ref
+ * @done: completion for @ref
  * @type: memory type: see MEMORY_* in memory_hotplug.h
  * @flags: PGMAP_* flags to specify defailed behavior
  * @ops: method table
@@ -109,8 +98,7 @@ struct dev_pagemap_ops {
  */
 struct dev_pagemap {
 	struct vmem_altmap altmap;
-	struct percpu_ref *ref;
-	struct percpu_ref internal_ref;
+	struct percpu_ref ref;
 	struct completion done;
 	enum memory_type type;
 	unsigned int flags;
@@ -191,7 +179,7 @@ static inline unsigned long memremap_compat_align(void)
 static inline void put_dev_pagemap(struct dev_pagemap *pgmap)
 {
 	if (pgmap)
-		percpu_ref_put(pgmap->ref);
+		percpu_ref_put(&pgmap->ref);
 }
 
 #endif /* _LINUX_MEMREMAP_H_ */
diff --git a/include/linux/mfd/t7l66xb.h b/include/linux/mfd/t7l66xb.h
index 69632c1b07bd..ae3e7a5c5219 100644
--- a/include/linux/mfd/t7l66xb.h
+++ b/include/linux/mfd/t7l66xb.h
@@ -12,7 +12,6 @@
 
 struct t7l66xb_platform_data {
 	int (*enable)(struct platform_device *dev);
-	int (*disable)(struct platform_device *dev);
 	int (*suspend)(struct platform_device *dev);
 	int (*resume)(struct platform_device *dev);
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index f17d2101af7a..4c678de4608d 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -759,6 +759,7 @@ struct mlx5_core_dev {
 	enum mlx5_device_state	state;
 	/* sync interface state */
 	struct mutex		intf_state_mutex;
+	struct lock_class_key	lock_key;
 	unsigned long		intf_state;
 	struct mlx5_priv	priv;
 	struct mlx5_profile	profile;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 85205adcdd0d..e4e1817bb3b8 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3132,6 +3132,14 @@ extern int sysctl_memory_failure_recovery;
 extern void shake_page(struct page *p);
 extern atomic_long_t num_poisoned_pages __read_mostly;
 extern int soft_offline_page(unsigned long pfn, int flags);
+#ifdef CONFIG_MEMORY_FAILURE
+extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags);
+#else
+static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags)
+{
+	return 0;
+}
+#endif
 
 
 /*
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b2b2d04bca53..2d6e74ac689e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -626,9 +626,23 @@ extern int sysctl_devconf_inherit_init_net;
  */
 static inline bool net_has_fallback_tunnels(const struct net *net)
 {
-	return !IS_ENABLED(CONFIG_SYSCTL) ||
-	       !sysctl_fb_tunnels_only_for_init_net ||
-	       (net == &init_net && sysctl_fb_tunnels_only_for_init_net == 1);
+#if IS_ENABLED(CONFIG_SYSCTL)
+	int fb_tunnels_only_for_init_net = READ_ONCE(sysctl_fb_tunnels_only_for_init_net);
+
+	return !fb_tunnels_only_for_init_net ||
+		(net_eq(net, &init_net) && fb_tunnels_only_for_init_net == 1);
+#else
+	return true;
+#endif
+}
+
+static inline int net_inherit_devconf(void)
+{
+#if IS_ENABLED(CONFIG_SYSCTL)
+	return READ_ONCE(sysctl_devconf_inherit_init_net);
+#else
+	return 0;
+#endif
 }
 
 static inline int netdev_queue_numa_node_read(const struct netdev_queue *q)
@@ -1646,7 +1660,7 @@ enum netdev_priv_flags {
 	IFF_FAILOVER_SLAVE		= 1<<28,
 	IFF_L3MDEV_RX_HANDLER		= 1<<29,
 	IFF_LIVE_RENAME_OK		= 1<<30,
-	IFF_TX_SKB_NO_LINEAR		= 1<<31,
+	IFF_TX_SKB_NO_LINEAR		= BIT_ULL(31),
 };
 
 #define IFF_802_1Q_VLAN			IFF_802_1Q_VLAN
diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h
index 10a01978bc0d..bde9db771ae4 100644
--- a/include/linux/netfilter_bridge/ebtables.h
+++ b/include/linux/netfilter_bridge/ebtables.h
@@ -94,10 +94,6 @@ struct ebt_table {
 	struct ebt_replace_kernel *table;
 	unsigned int valid_hooks;
 	rwlock_t lock;
-	/* e.g. could be the table explicitly only allows certain
-	 * matches, targets, ... 0 == let it in */
-	int (*check)(const struct ebt_table_info *info,
-	   unsigned int valid_hooks);
 	/* the data used by the kernel */
 	struct ebt_table_info *private;
 	struct nf_hook_ops *ops;
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 66b6cc24ab8c..5ddc30405f7f 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -103,6 +103,7 @@ struct nfs_open_dir_context {
 	__be32	verf[NFS_DIR_VERIFIER_SIZE];
 	__u64 dir_cookie;
 	__u64 dup_cookie;
+	pgoff_t page_index;
 	signed char duped;
 };
 
@@ -154,36 +155,40 @@ struct nfs_inode {
 	unsigned long		attrtimeo_timestamp;
 
 	unsigned long		attr_gencount;
-	/* "Generation counter" for the attribute cache. This is
-	 * bumped whenever we update the metadata on the
-	 * server.
-	 */
-	unsigned long		cache_change_attribute;
 
 	struct rb_root		access_cache;
 	struct list_head	access_cache_entry_lru;
 	struct list_head	access_cache_inode_lru;
 
-	/*
-	 * This is the cookie verifier used for NFSv3 readdir
-	 * operations
-	 */
-	__be32			cookieverf[NFS_DIR_VERIFIER_SIZE];
-
-	atomic_long_t		nrequests;
-	struct nfs_mds_commit_info commit_info;
+	union {
+		/* Directory */
+		struct {
+			/* "Generation counter" for the attribute cache.
+			 * This is bumped whenever we update the metadata
+			 * on the server.
+			 */
+			unsigned long	cache_change_attribute;
+			/*
+			 * This is the cookie verifier used for NFSv3 readdir
+			 * operations
+			 */
+			__be32		cookieverf[NFS_DIR_VERIFIER_SIZE];
+			/* Readers: in-flight sillydelete RPC calls */
+			/* Writers: rmdir */
+			struct rw_semaphore	rmdir_sem;
+		};
+		/* Regular file */
+		struct {
+			atomic_long_t	nrequests;
+			atomic_long_t	redirtied_pages;
+			struct nfs_mds_commit_info commit_info;
+			struct mutex	commit_mutex;
+		};
+	};
 
 	/* Open contexts for shared mmap writes */
 	struct list_head	open_files;
 
-	/* Readers: in-flight sillydelete RPC calls */
-	/* Writers: rmdir */
-	struct rw_semaphore	rmdir_sem;
-	struct mutex		commit_mutex;
-
-	/* track last access to cached pages */
-	unsigned long		page_index;
-
 #if IS_ENABLED(CONFIG_NFS_V4)
 	struct nfs4_cached_acl	*nfs4_acl;
         /* NFSv4 state */
@@ -272,6 +277,7 @@ struct nfs4_copy_state {
 #define NFS_INO_INVALIDATING	(3)		/* inode is being invalidated */
 #define NFS_INO_FSCACHE		(5)		/* inode can be cached by FS-Cache */
 #define NFS_INO_FSCACHE_LOCK	(6)		/* FS-Cache cookie management lock */
+#define NFS_INO_FORCE_READDIR	(7)		/* force readdirplus */
 #define NFS_INO_LAYOUTCOMMIT	(9)		/* layoutcommit required */
 #define NFS_INO_LAYOUTCOMMITTING (10)		/* layoutcommit inflight */
 #define NFS_INO_LAYOUTSTATS	(11)		/* layoutstats inflight */
@@ -587,7 +593,9 @@ bool nfs_commit_end(struct nfs_mds_commit_info *cinfo);
 static inline int
 nfs_have_writebacks(struct inode *inode)
 {
-	return atomic_long_read(&NFS_I(inode)->nrequests) != 0;
+	if (S_ISREG(inode->i_mode))
+		return atomic_long_read(&NFS_I(inode)->nrequests) != 0;
+	return 0;
 }
 
 /*
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index 750c7f395ca9..f700ff2df074 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -122,6 +122,8 @@ int watchdog_nmi_probe(void);
 int watchdog_nmi_enable(unsigned int cpu);
 void watchdog_nmi_disable(unsigned int cpu);
 
+void lockup_detector_reconfigure(void);
+
 /**
  * touch_nmi_watchdog - restart NMI watchdog timeout.
  *
diff --git a/include/linux/objtool.h b/include/linux/objtool.h
index 7e72d975cb76..a2042c418686 100644
--- a/include/linux/objtool.h
+++ b/include/linux/objtool.h
@@ -32,11 +32,16 @@ struct unwind_hint {
  *
  * UNWIND_HINT_FUNC: Generate the unwind metadata of a callable function.
  * Useful for code which doesn't have an ELF function annotation.
+ *
+ * UNWIND_HINT_ENTRY: machine entry without stack, SYSCALL/SYSENTER etc.
  */
 #define UNWIND_HINT_TYPE_CALL		0
 #define UNWIND_HINT_TYPE_REGS		1
 #define UNWIND_HINT_TYPE_REGS_PARTIAL	2
 #define UNWIND_HINT_TYPE_FUNC		3
+#define UNWIND_HINT_TYPE_ENTRY		4
+#define UNWIND_HINT_TYPE_SAVE		5
+#define UNWIND_HINT_TYPE_RESTORE	6
 
 #ifdef CONFIG_STACK_VALIDATION
 
@@ -99,7 +104,7 @@ struct unwind_hint {
  * the debuginfo as necessary.  It will also warn if it sees any
  * inconsistencies.
  */
-.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0
+.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 end=0
 .Lunwind_hint_ip_\@:
 	.pushsection .discard.unwind_hints
 		/* struct unwind_hint */
@@ -129,7 +134,7 @@ struct unwind_hint {
 #define STACK_FRAME_NON_STANDARD(func)
 #else
 #define ANNOTATE_INTRA_FUNCTION_CALL
-.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0
+.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 end=0
 .endm
 .macro STACK_FRAME_NON_STANDARD func:req
 .endm
diff --git a/include/linux/of_device.h b/include/linux/of_device.h
index 1d7992a02e36..1a803e4335d3 100644
--- a/include/linux/of_device.h
+++ b/include/linux/of_device.h
@@ -101,8 +101,9 @@ static inline struct device_node *of_cpu_device_node_get(int cpu)
 }
 
 static inline int of_dma_configure_id(struct device *dev,
-				   struct device_node *np,
-				   bool force_dma)
+				      struct device_node *np,
+				      bool force_dma,
+				      const u32 *id)
 {
 	return 0;
 }
diff --git a/include/linux/once_lite.h b/include/linux/once_lite.h
index 861e606b820f..b7bce4983638 100644
--- a/include/linux/once_lite.h
+++ b/include/linux/once_lite.h
@@ -9,15 +9,27 @@
  */
 #define DO_ONCE_LITE(func, ...)						\
 	DO_ONCE_LITE_IF(true, func, ##__VA_ARGS__)
-#define DO_ONCE_LITE_IF(condition, func, ...)				\
+
+#define __ONCE_LITE_IF(condition)					\
 	({								\
 		static bool __section(".data.once") __already_done;	\
-		bool __ret_do_once = !!(condition);			\
+		bool __ret_cond = !!(condition);			\
+		bool __ret_once = false;				\
 									\
-		if (unlikely(__ret_do_once && !__already_done)) {	\
+		if (unlikely(__ret_cond && !__already_done)) {		\
 			__already_done = true;				\
-			func(__VA_ARGS__);				\
+			__ret_once = true;				\
 		}							\
+		unlikely(__ret_once);					\
+	})
+
+#define DO_ONCE_LITE_IF(condition, func, ...)				\
+	({								\
+		bool __ret_do_once = !!(condition);			\
+									\
+		if (__ONCE_LITE_IF(__ret_do_once))			\
+			func(__VA_ARGS__);				\
+									\
 		unlikely(__ret_do_once);				\
 	})
 
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index aff5489b0726..f0558e2a9359 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -60,6 +60,8 @@
 #define PCI_CLASS_BRIDGE_EISA		0x0602
 #define PCI_CLASS_BRIDGE_MC		0x0603
 #define PCI_CLASS_BRIDGE_PCI		0x0604
+#define PCI_CLASS_BRIDGE_PCI_NORMAL		0x060400
+#define PCI_CLASS_BRIDGE_PCI_SUBTRACTIVE	0x060401
 #define PCI_CLASS_BRIDGE_PCMCIA		0x0605
 #define PCI_CLASS_BRIDGE_NUBUS		0x0606
 #define PCI_CLASS_BRIDGE_CARDBUS	0x0607
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 339ba28eac1f..cb8552dec644 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -573,6 +573,10 @@ struct macsec_ops;
  * @mdix: Current crossover
  * @mdix_ctrl: User setting of crossover
  * @interrupts: Flag interrupts have been enabled
+ * @irq_suspended: Flag indicating PHY is suspended and therefore interrupt
+ *                 handling shall be postponed until PHY has resumed
+ * @irq_rerun: Flag indicating interrupts occurred while PHY was suspended,
+ *             requiring a rerun of the interrupt handler after resume
  * @interface: enum phy_interface_t value
  * @skb: Netlink message for cable diagnostics
  * @nest: Netlink nest used for cable diagnostics
@@ -627,6 +631,8 @@ struct phy_device {
 
 	/* Interrupts are enabled */
 	unsigned interrupts:1;
+	unsigned irq_suspended:1;
+	unsigned irq_rerun:1;
 
 	enum phy_state state;
 
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index c0b6ec6bf65b..18dcca51829e 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -229,6 +229,15 @@ static inline bool pipe_buf_try_steal(struct pipe_inode_info *pipe,
 	return buf->ops->try_steal(pipe, buf);
 }
 
+static inline void pipe_discard_from(struct pipe_inode_info *pipe,
+		unsigned int old_head)
+{
+	unsigned int mask = pipe->ring_size - 1;
+
+	while (pipe->head > old_head)
+		pipe_buf_release(pipe, &pipe->bufs[--pipe->head & mask]);
+}
+
 /* Differs from PIPE_BUF in that PIPE_SIZE is the length of the actual
    memory allocation, whereas PIPE_BUF makes atomicity guarantees.  */
 #define PIPE_SIZE		PAGE_SIZE
diff --git a/include/linux/platform_data/x86/pmc_atom.h b/include/linux/platform_data/x86/pmc_atom.h
index 022bcea9edec..99a9b09dc839 100644
--- a/include/linux/platform_data/x86/pmc_atom.h
+++ b/include/linux/platform_data/x86/pmc_atom.h
@@ -7,6 +7,8 @@
 #ifndef PMC_ATOM_H
 #define PMC_ATOM_H
 
+#include <linux/bits.h>
+
 /* ValleyView Power Control Unit PCI Device ID */
 #define	PCI_DEVICE_ID_VLV_PMC	0x0F1C
 /* CherryTrail Power Control Unit PCI Device ID */
@@ -139,9 +141,9 @@
 #define	ACPI_MMIO_REG_LEN	0x100
 
 #define	PM1_CNT			0x4
-#define	SLEEP_TYPE_MASK		0xFFFFECFF
+#define	SLEEP_TYPE_MASK		GENMASK(12, 10)
 #define	SLEEP_TYPE_S5		0x1C00
-#define	SLEEP_ENABLE		0x2000
+#define	SLEEP_ENABLE		BIT(13)
 
 extern int pmc_atom_read(int offset, u32 *value);
 extern int pmc_atom_write(int offset, u32 value);
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 016de5776b6d..90eaff8b78fc 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -58,7 +58,7 @@ extern void pm_runtime_get_suppliers(struct device *dev);
 extern void pm_runtime_put_suppliers(struct device *dev);
 extern void pm_runtime_new_link(struct device *dev);
 extern void pm_runtime_drop_link(struct device_link *link);
-extern void pm_runtime_release_supplier(struct device_link *link, bool check_idle);
+extern void pm_runtime_release_supplier(struct device_link *link);
 
 extern int devm_pm_runtime_enable(struct device *dev);
 
@@ -284,8 +284,7 @@ static inline void pm_runtime_get_suppliers(struct device *dev) {}
 static inline void pm_runtime_put_suppliers(struct device *dev) {}
 static inline void pm_runtime_new_link(struct device *dev) {}
 static inline void pm_runtime_drop_link(struct device_link *link) {}
-static inline void pm_runtime_release_supplier(struct device_link *link,
-					       bool check_idle) {}
+static inline void pm_runtime_release_supplier(struct device_link *link) {}
 
 #endif /* !CONFIG_PM */
 
diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h
index 812a4d751163..4df0bf0a0864 100644
--- a/include/linux/qed/qed_eth_if.h
+++ b/include/linux/qed/qed_eth_if.h
@@ -145,12 +145,6 @@ struct qed_filter_mcast_params {
 	unsigned char mac[64][ETH_ALEN];
 };
 
-union qed_filter_type_params {
-	enum qed_filter_rx_mode_type accept_flags;
-	struct qed_filter_ucast_params ucast;
-	struct qed_filter_mcast_params mcast;
-};
-
 enum qed_filter_type {
 	QED_FILTER_TYPE_UCAST,
 	QED_FILTER_TYPE_MCAST,
@@ -158,11 +152,6 @@ enum qed_filter_type {
 	QED_MAX_FILTER_TYPES,
 };
 
-struct qed_filter_params {
-	enum qed_filter_type type;
-	union qed_filter_type_params filter;
-};
-
 struct qed_tunn_params {
 	u16 vxlan_port;
 	u8 update_vxlan_port;
@@ -314,8 +303,14 @@ struct qed_eth_ops {
 
 	int (*q_tx_stop)(struct qed_dev *cdev, u8 rss_id, void *handle);
 
-	int (*filter_config)(struct qed_dev *cdev,
-			     struct qed_filter_params *params);
+	int (*filter_config_rx_mode)(struct qed_dev *cdev,
+				     enum qed_filter_rx_mode_type type);
+
+	int (*filter_config_ucast)(struct qed_dev *cdev,
+				   struct qed_filter_ucast_params *params);
+
+	int (*filter_config_mcast)(struct qed_dev *cdev,
+				   struct qed_filter_mcast_params *params);
 
 	int (*fastpath_stop)(struct qed_dev *cdev);
 
diff --git a/include/linux/reset.h b/include/linux/reset.h
index db0e6115a2f6..7bb583737528 100644
--- a/include/linux/reset.h
+++ b/include/linux/reset.h
@@ -711,7 +711,7 @@ static inline int __must_check
 devm_reset_control_bulk_get_optional_exclusive(struct device *dev, int num_rstcs,
 					       struct reset_control_bulk_data *rstcs)
 {
-	return __devm_reset_control_bulk_get(dev, num_rstcs, rstcs, true, false, true);
+	return __devm_reset_control_bulk_get(dev, num_rstcs, rstcs, false, true, true);
 }
 
 /**
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index c976cc6de257..c29d9c13378b 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -39,12 +39,15 @@ struct anon_vma {
 	atomic_t refcount;
 
 	/*
-	 * Count of child anon_vmas and VMAs which points to this anon_vma.
+	 * Count of child anon_vmas. Equals to the count of all anon_vmas that
+	 * have ->parent pointing to this one, including itself.
 	 *
 	 * This counter is used for making decision about reusing anon_vma
 	 * instead of forking new one. See comments in function anon_vma_clone.
 	 */
-	unsigned degree;
+	unsigned long num_children;
+	/* Count of VMAs whose ->anon_vma pointer points to this object. */
+	unsigned long num_active_vmas;
 
 	struct anon_vma *parent;	/* Parent of this anon_vma */
 
diff --git a/include/linux/rtsx_usb.h b/include/linux/rtsx_usb.h
index 159729cffd8e..3247ed8e9ff0 100644
--- a/include/linux/rtsx_usb.h
+++ b/include/linux/rtsx_usb.h
@@ -54,8 +54,6 @@ struct rtsx_ucr {
 	struct usb_device	*pusb_dev;
 	struct usb_interface	*pusb_intf;
 	struct usb_sg_request	current_sg;
-	unsigned char		*iobuf;
-	dma_addr_t		iobuf_dma;
 
 	struct timer_list	sg_timer;
 	struct mutex		dev_mutex;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ad7ff332a0ac..dcba347cbffa 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1797,7 +1797,7 @@ current_restore_flags(unsigned long orig_flags, unsigned long flags)
 }
 
 extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
-extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed);
+extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_effective_cpus);
 #ifdef CONFIG_SMP
 extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask);
 extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask);
diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h
index e5af028c08b4..994c25640e15 100644
--- a/include/linux/sched/rt.h
+++ b/include/linux/sched/rt.h
@@ -39,20 +39,12 @@ static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *p)
 }
 extern void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task);
 extern void rt_mutex_adjust_pi(struct task_struct *p);
-static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
-{
-	return tsk->pi_blocked_on != NULL;
-}
 #else
 static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
 {
 	return NULL;
 }
 # define rt_mutex_adjust_pi(p)		do { } while (0)
-static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
-{
-	return false;
-}
 #endif
 
 extern void normalize_rt_tasks(void);
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 8db25fcc1eba..caae8e045160 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -81,7 +81,7 @@ static inline void exit_thread(struct task_struct *tsk)
 extern void do_group_exit(int);
 
 extern void exit_files(struct task_struct *);
-extern void exit_itimers(struct signal_struct *);
+extern void exit_itimers(struct task_struct *);
 
 extern pid_t kernel_clone(struct kernel_clone_args *kargs);
 struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node);
diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h
index d10150587d81..1009b6b5ce40 100644
--- a/include/linux/sched/task_stack.h
+++ b/include/linux/sched/task_stack.h
@@ -16,7 +16,7 @@
  * try_get_task_stack() instead.  task_stack_page will return a pointer
  * that could get freed out from under you.
  */
-static inline void *task_stack_page(const struct task_struct *task)
+static __always_inline void *task_stack_page(const struct task_struct *task)
 {
 	return task->stack;
 }
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 8f0f778b7c91..63a04a65e310 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -74,6 +74,7 @@ struct sched_domain_shared {
 	atomic_t	ref;
 	atomic_t	nr_busy_cpus;
 	int		has_idle_cores;
+	int		nr_idle_scan;
 };
 
 struct sched_domain {
diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h
index 5733890df64f..0b429111f85e 100644
--- a/include/linux/seq_file.h
+++ b/include/linux/seq_file.h
@@ -261,6 +261,10 @@ extern struct list_head *seq_list_start_head(struct list_head *head,
 extern struct list_head *seq_list_next(void *v, struct list_head *head,
 		loff_t *ppos);
 
+extern struct list_head *seq_list_start_rcu(struct list_head *head, loff_t pos);
+extern struct list_head *seq_list_start_head_rcu(struct list_head *head, loff_t pos);
+extern struct list_head *seq_list_next_rcu(void *v, struct list_head *head, loff_t *ppos);
+
 /*
  * Helpers for iteration over hlist_head-s in seq_files
  */
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 8c32935e1059..6d07b5f9e3b8 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -388,6 +388,11 @@ static const bool earlycon_acpi_spcr_enable EARLYCON_USED_OR_UNUSED;
 static inline int setup_earlycon(char *buf) { return 0; }
 #endif
 
+static inline bool uart_console_enabled(struct uart_port *port)
+{
+	return uart_console(port) && (port->cons->flags & CON_ENABLED);
+}
+
 struct uart_port *uart_get_console(struct uart_port *ports, int nr,
 				   struct console *c);
 int uart_parse_earlycon(char *p, unsigned char *iotype, resource_size_t *addr,
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index c575ef812c82..c6d80a8b522c 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -304,6 +304,41 @@ struct sk_buff_head {
 
 struct sk_buff;
 
+/* The reason of skb drop, which is used in kfree_skb_reason().
+ * en...maybe they should be splited by group?
+ *
+ * Each item here should also be in 'TRACE_SKB_DROP_REASON', which is
+ * used to translate the reason to string.
+ */
+enum skb_drop_reason {
+	SKB_DROP_REASON_NOT_SPECIFIED,	/* drop reason is not specified */
+	SKB_DROP_REASON_NO_SOCKET,	/* socket not found */
+	SKB_DROP_REASON_PKT_TOO_SMALL,	/* packet size is too small */
+	SKB_DROP_REASON_TCP_CSUM,	/* TCP checksum error */
+	SKB_DROP_REASON_SOCKET_FILTER,	/* dropped by socket filter */
+	SKB_DROP_REASON_UDP_CSUM,	/* UDP checksum error */
+	SKB_DROP_REASON_NETFILTER_DROP,	/* dropped by netfilter */
+	SKB_DROP_REASON_OTHERHOST,	/* packet don't belong to current
+					 * host (interface is in promisc
+					 * mode)
+					 */
+	SKB_DROP_REASON_IP_CSUM,	/* IP checksum error */
+	SKB_DROP_REASON_IP_INHDR,	/* there is something wrong with
+					 * IP header (see
+					 * IPSTATS_MIB_INHDRERRORS)
+					 */
+	SKB_DROP_REASON_IP_RPFILTER,	/* IP rpfilter validate failed.
+					 * see the document for rp_filter
+					 * in ip-sysctl.rst for more
+					 * information
+					 */
+	SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST, /* destination address of L2
+						  * is multicast, but L3 is
+						  * unicast.
+						  */
+	SKB_DROP_REASON_MAX,
+};
+
 /* To allow 64K frame to be packed as single skb without frag_list we
  * require 64K/PAGE_SIZE pages plus 1 additional page to allow for
  * buffers which do not start on a page boundary.
@@ -1074,8 +1109,18 @@ static inline bool skb_unref(struct sk_buff *skb)
 	return true;
 }
 
+void kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason);
+
+/**
+ *	kfree_skb - free an sk_buff with 'NOT_SPECIFIED' reason
+ *	@skb: buffer to free
+ */
+static inline void kfree_skb(struct sk_buff *skb)
+{
+	kfree_skb_reason(skb, SKB_DROP_REASON_NOT_SPECIFIED);
+}
+
 void skb_release_head_state(struct sk_buff *skb);
-void kfree_skb(struct sk_buff *skb);
 void kfree_skb_list(struct sk_buff *segs);
 void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt);
 void skb_tx_error(struct sk_buff *skb);
@@ -2188,6 +2233,22 @@ static inline unsigned int skb_pagelen(const struct sk_buff *skb)
 	return skb_headlen(skb) + __skb_pagelen(skb);
 }
 
+static inline void __skb_fill_page_desc_noacc(struct skb_shared_info *shinfo,
+					      int i, struct page *page,
+					      int off, int size)
+{
+	skb_frag_t *frag = &shinfo->frags[i];
+
+	/*
+	 * Propagate page pfmemalloc to the skb if we can. The problem is
+	 * that not all callers have unique ownership of the page but rely
+	 * on page_is_pfmemalloc doing the right thing(tm).
+	 */
+	frag->bv_page		  = page;
+	frag->bv_offset		  = off;
+	skb_frag_size_set(frag, size);
+}
+
 /**
  * __skb_fill_page_desc - initialise a paged fragment in an skb
  * @skb: buffer containing fragment to be initialised
@@ -2204,17 +2265,7 @@ static inline unsigned int skb_pagelen(const struct sk_buff *skb)
 static inline void __skb_fill_page_desc(struct sk_buff *skb, int i,
 					struct page *page, int off, int size)
 {
-	skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
-
-	/*
-	 * Propagate page pfmemalloc to the skb if we can. The problem is
-	 * that not all callers have unique ownership of the page but rely
-	 * on page_is_pfmemalloc doing the right thing(tm).
-	 */
-	frag->bv_page		  = page;
-	frag->bv_offset		  = off;
-	skb_frag_size_set(frag, size);
-
+	__skb_fill_page_desc_noacc(skb_shinfo(skb), i, page, off, size);
 	page = compound_head(page);
 	if (page_is_pfmemalloc(page))
 		skb->pfmemalloc	= true;
@@ -2241,6 +2292,27 @@ static inline void skb_fill_page_desc(struct sk_buff *skb, int i,
 	skb_shinfo(skb)->nr_frags = i + 1;
 }
 
+/**
+ * skb_fill_page_desc_noacc - initialise a paged fragment in an skb
+ * @skb: buffer containing fragment to be initialised
+ * @i: paged fragment index to initialise
+ * @page: the page to use for this fragment
+ * @off: the offset to the data with @page
+ * @size: the length of the data
+ *
+ * Variant of skb_fill_page_desc() which does not deal with
+ * pfmemalloc, if page is not owned by us.
+ */
+static inline void skb_fill_page_desc_noacc(struct sk_buff *skb, int i,
+					    struct page *page, int off,
+					    int size)
+{
+	struct skb_shared_info *shinfo = skb_shinfo(skb);
+
+	__skb_fill_page_desc_noacc(shinfo, i, page, off, size);
+	shinfo->nr_frags = i + 1;
+}
+
 void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
 		     int size, unsigned int truesize);
 
@@ -2284,6 +2356,14 @@ static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset)
 
 #endif /* NET_SKBUFF_DATA_USES_OFFSET */
 
+static inline void skb_assert_len(struct sk_buff *skb)
+{
+#ifdef CONFIG_DEBUG_NET
+	if (WARN_ONCE(!skb->len, "%s\n", __func__))
+		DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false);
+#endif /* CONFIG_DEBUG_NET */
+}
+
 /*
  *	Add data to an sk_buff
  */
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 73bedd128d52..0c742cdf413c 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -283,7 +283,8 @@ static inline void sk_msg_sg_copy_clear(struct sk_msg *msg, u32 start)
 
 static inline struct sk_psock *sk_psock(const struct sock *sk)
 {
-	return rcu_dereference_sk_user_data(sk);
+	return __rcu_dereference_sk_user_data_with_flags(sk,
+							 SK_USER_DATA_PSOCK);
 }
 
 static inline void sk_psock_set_state(struct sk_psock *psock,
diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 76ce3f3ac0f2..bf6f0decb3f6 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -646,9 +646,6 @@ struct sdw_slave_ops {
  * @dev_num: Current Device Number, values can be 0 or dev_num_sticky
  * @dev_num_sticky: one-time static Device Number assigned by Bus
  * @probed: boolean tracking driver state
- * @probe_complete: completion utility to control potential races
- * on startup between driver probe/initialization and SoundWire
- * Slave state changes/implementation-defined interrupts
  * @enumeration_complete: completion utility to control potential races
  * on startup between device enumeration and read/write access to the
  * Slave device
@@ -663,6 +660,7 @@ struct sdw_slave_ops {
  * for a Slave happens for the first time after enumeration
  * @is_mockup_device: status flag used to squelch errors in the command/control
  * protocol for SoundWire mockup devices
+ * @sdw_dev_lock: mutex used to protect callbacks/remove races
  */
 struct sdw_slave {
 	struct sdw_slave_id id;
@@ -680,12 +678,12 @@ struct sdw_slave {
 	u16 dev_num;
 	u16 dev_num_sticky;
 	bool probed;
-	struct completion probe_complete;
 	struct completion enumeration_complete;
 	struct completion initialization_complete;
 	u32 unattach_request;
 	bool first_interrupt_done;
 	bool is_mockup_device;
+	struct mutex sdw_dev_lock; /* protect callbacks/remove races */
 };
 
 #define dev_to_sdw_dev(_dev) container_of(_dev, struct sdw_slave, dev)
diff --git a/include/linux/stddef.h b/include/linux/stddef.h
index 998a4ba28eba..31fdbb784c24 100644
--- a/include/linux/stddef.h
+++ b/include/linux/stddef.h
@@ -36,4 +36,65 @@ enum {
 #define offsetofend(TYPE, MEMBER) \
 	(offsetof(TYPE, MEMBER)	+ sizeof_field(TYPE, MEMBER))
 
+/**
+ * struct_group() - Wrap a set of declarations in a mirrored struct
+ *
+ * @NAME: The identifier name of the mirrored sub-struct
+ * @MEMBERS: The member declarations for the mirrored structs
+ *
+ * Used to create an anonymous union of two structs with identical
+ * layout and size: one anonymous and one named. The former can be
+ * used normally without sub-struct naming, and the latter can be
+ * used to reason about the start, end, and size of the group of
+ * struct members.
+ */
+#define struct_group(NAME, MEMBERS...)	\
+	__struct_group(/* no tag */, NAME, /* no attrs */, MEMBERS)
+
+/**
+ * struct_group_attr() - Create a struct_group() with trailing attributes
+ *
+ * @NAME: The identifier name of the mirrored sub-struct
+ * @ATTRS: Any struct attributes to apply
+ * @MEMBERS: The member declarations for the mirrored structs
+ *
+ * Used to create an anonymous union of two structs with identical
+ * layout and size: one anonymous and one named. The former can be
+ * used normally without sub-struct naming, and the latter can be
+ * used to reason about the start, end, and size of the group of
+ * struct members. Includes structure attributes argument.
+ */
+#define struct_group_attr(NAME, ATTRS, MEMBERS...) \
+	__struct_group(/* no tag */, NAME, ATTRS, MEMBERS)
+
+/**
+ * struct_group_tagged() - Create a struct_group with a reusable tag
+ *
+ * @TAG: The tag name for the named sub-struct
+ * @NAME: The identifier name of the mirrored sub-struct
+ * @MEMBERS: The member declarations for the mirrored structs
+ *
+ * Used to create an anonymous union of two structs with identical
+ * layout and size: one anonymous and one named. The former can be
+ * used normally without sub-struct naming, and the latter can be
+ * used to reason about the start, end, and size of the group of
+ * struct members. Includes struct tag argument for the named copy,
+ * so the specified layout can be reused later.
+ */
+#define struct_group_tagged(TAG, NAME, MEMBERS...) \
+	__struct_group(TAG, NAME, /* no attrs */, MEMBERS)
+
+/**
+ * DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union
+ *
+ * @TYPE: The type of each flexible array element
+ * @NAME: The name of the flexible array member
+ *
+ * In order to have a flexible array member in a union or alone in a
+ * struct, it needs to be wrapped in an anonymous struct with at least 1
+ * named member, but that member can be empty.
+ */
+#define DECLARE_FLEX_ARRAY(TYPE, NAME) \
+	__DECLARE_FLEX_ARRAY(TYPE, NAME)
+
 #endif
diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 4417f667c757..3a2c714d6b62 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -405,8 +405,8 @@ static inline int xdr_stream_encode_item_absent(struct xdr_stream *xdr)
  */
 static inline __be32 *xdr_encode_bool(__be32 *p, u32 n)
 {
-	*p = n ? xdr_one : xdr_zero;
-	return p++;
+	*p++ = n ? xdr_one : xdr_zero;
+	return p;
 }
 
 /**
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 1fa2b69c6fc3..fa372b4c2313 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -38,9 +38,16 @@ struct ctl_table_header;
 struct ctl_dir;
 
 /* Keep the same order as in fs/proc/proc_sysctl.c */
-#define SYSCTL_ZERO	((void *)&sysctl_vals[0])
-#define SYSCTL_ONE	((void *)&sysctl_vals[1])
-#define SYSCTL_INT_MAX	((void *)&sysctl_vals[2])
+#define SYSCTL_NEG_ONE			((void *)&sysctl_vals[0])
+#define SYSCTL_ZERO			((void *)&sysctl_vals[1])
+#define SYSCTL_ONE			((void *)&sysctl_vals[2])
+#define SYSCTL_TWO			((void *)&sysctl_vals[3])
+#define SYSCTL_FOUR			((void *)&sysctl_vals[4])
+#define SYSCTL_ONE_HUNDRED		((void *)&sysctl_vals[5])
+#define SYSCTL_TWO_HUNDRED		((void *)&sysctl_vals[6])
+#define SYSCTL_ONE_THOUSAND		((void *)&sysctl_vals[7])
+#define SYSCTL_THREE_THOUSAND		((void *)&sysctl_vals[8])
+#define SYSCTL_INT_MAX			((void *)&sysctl_vals[9])
 
 extern const int sysctl_vals[];
 
diff --git a/include/linux/sysfb.h b/include/linux/sysfb.h
index b0dcfa26d07b..8ba8b5be5567 100644
--- a/include/linux/sysfb.h
+++ b/include/linux/sysfb.h
@@ -55,6 +55,18 @@ struct efifb_dmi_info {
 	int flags;
 };
 
+#ifdef CONFIG_SYSFB
+
+void sysfb_disable(void);
+
+#else /* CONFIG_SYSFB */
+
+static inline void sysfb_disable(void)
+{
+}
+
+#endif /* CONFIG_SYSFB */
+
 #ifdef CONFIG_EFI
 
 extern struct efifb_dmi_info efifb_dmi_list[];
@@ -72,8 +84,8 @@ static inline void sysfb_apply_efi_quirks(struct platform_device *pd)
 
 bool sysfb_parse_mode(const struct screen_info *si,
 		      struct simplefb_platform_data *mode);
-int sysfb_create_simplefb(const struct screen_info *si,
-			  const struct simplefb_platform_data *mode);
+struct platform_device *sysfb_create_simplefb(const struct screen_info *si,
+					      const struct simplefb_platform_data *mode);
 
 #else /* CONFIG_SYSFB_SIMPLE */
 
@@ -83,10 +95,10 @@ static inline bool sysfb_parse_mode(const struct screen_info *si,
 	return false;
 }
 
-static inline int sysfb_create_simplefb(const struct screen_info *si,
-					 const struct simplefb_platform_data *mode)
+static inline struct platform_device *sysfb_create_simplefb(const struct screen_info *si,
+							    const struct simplefb_platform_data *mode)
 {
-	return -EINVAL;
+	return ERR_PTR(-EINVAL);
 }
 
 #endif /* CONFIG_SYSFB_SIMPLE */
diff --git a/include/linux/torture.h b/include/linux/torture.h
index 0910c5803f35..24f58e50a94b 100644
--- a/include/linux/torture.h
+++ b/include/linux/torture.h
@@ -47,6 +47,14 @@ do {										\
 } while (0)
 void verbose_torout_sleep(void);
 
+#define torture_init_error(firsterr)						\
+({										\
+	int ___firsterr = (firsterr);						\
+										\
+	WARN_ONCE(!IS_MODULE(CONFIG_RCU_TORTURE_TEST) && ___firsterr < 0, "Torture-test initialization failed with error code %d\n", ___firsterr); \
+	___firsterr < 0;								\
+})
+
 /* Definitions for online/offline exerciser. */
 #ifdef CONFIG_HOTPLUG_CPU
 int torture_num_online_cpus(void);
diff --git a/include/linux/tpm_eventlog.h b/include/linux/tpm_eventlog.h
index 739ba9a03ec1..20c0ff54b7a0 100644
--- a/include/linux/tpm_eventlog.h
+++ b/include/linux/tpm_eventlog.h
@@ -157,7 +157,7 @@ struct tcg_algorithm_info {
  * Return: size of the event on success, 0 on failure
  */
 
-static inline int __calc_tpm2_event_size(struct tcg_pcr_event2_head *event,
+static __always_inline int __calc_tpm2_event_size(struct tcg_pcr_event2_head *event,
 					 struct tcg_pcr_event *event_header,
 					 bool do_mapping)
 {
diff --git a/include/linux/tty_flip.h b/include/linux/tty_flip.h
index 32284992b31a..1fb727b7b969 100644
--- a/include/linux/tty_flip.h
+++ b/include/linux/tty_flip.h
@@ -17,7 +17,6 @@ extern int tty_insert_flip_string_fixed_flag(struct tty_port *port,
 extern int tty_prepare_flip_string(struct tty_port *port,
 		unsigned char **chars, size_t size);
 extern void tty_flip_buffer_push(struct tty_port *port);
-void tty_schedule_flip(struct tty_port *port);
 int __tty_insert_flip_char(struct tty_port *port, unsigned char ch, char flag);
 
 static inline int tty_insert_flip_char(struct tty_port *port,
diff --git a/include/linux/uacce.h b/include/linux/uacce.h
index 48e319f40275..9ce88c28b0a8 100644
--- a/include/linux/uacce.h
+++ b/include/linux/uacce.h
@@ -70,6 +70,7 @@ enum uacce_q_state {
  * @wait: wait queue head
  * @list: index into uacce queues list
  * @qfrs: pointer of qfr regions
+ * @mutex: protects queue state
  * @state: queue state machine
  * @pasid: pasid associated to the mm
  * @handle: iommu_sva handle returned by iommu_sva_bind_device()
@@ -80,6 +81,7 @@ struct uacce_queue {
 	wait_queue_head_t wait;
 	struct list_head list;
 	struct uacce_qfile_region *qfrs[UACCE_MAX_REGION];
+	struct mutex mutex;
 	enum uacce_q_state state;
 	u32 pasid;
 	struct iommu_sva *handle;
@@ -97,9 +99,9 @@ struct uacce_queue {
  * @dev_id: id of the uacce device
  * @cdev: cdev of the uacce
  * @dev: dev of the uacce
+ * @mutex: protects uacce operation
  * @priv: private pointer of the uacce
  * @queues: list of queues
- * @queues_lock: lock for queues list
  * @inode: core vfs
  */
 struct uacce_device {
@@ -113,9 +115,9 @@ struct uacce_device {
 	u32 dev_id;
 	struct cdev *cdev;
 	struct device dev;
+	struct mutex mutex;
 	void *priv;
 	struct list_head queues;
-	struct mutex queues_lock;
 	struct inode *inode;
 };
 
diff --git a/include/linux/udp.h b/include/linux/udp.h
index ae66dadd8543..0727276e7538 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -75,6 +75,7 @@ struct udp_sock {
 	 * For encapsulation sockets.
 	 */
 	int (*encap_rcv)(struct sock *sk, struct sk_buff *skb);
+	void (*encap_err_rcv)(struct sock *sk, struct sk_buff *skb, unsigned int udp_offset);
 	int (*encap_err_lookup)(struct sock *sk, struct sk_buff *skb);
 	void (*encap_destroy)(struct sock *sk);
 
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 7ccaa76a9a96..da1329b85329 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -575,6 +575,7 @@ struct usb3_lpm_parameters {
  * @devaddr: device address, XHCI: assigned by HW, others: same as devnum
  * @can_submit: URBs may be submitted
  * @persist_enabled:  USB_PERSIST enabled for this device
+ * @reset_in_progress: the device is being reset
  * @have_langid: whether string_langid is valid
  * @authorized: policy has said we can use it;
  *	(user space) policy determines if we authorize this device to be
@@ -661,6 +662,7 @@ struct usb_device {
 
 	unsigned can_submit:1;
 	unsigned persist_enabled:1;
+	unsigned reset_in_progress:1;
 	unsigned have_langid:1;
 	unsigned authorized:1;
 	unsigned authenticated:1;
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index 2c1fc9212cf2..98d1921f02b1 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -66,6 +66,7 @@
 
 struct giveback_urb_bh {
 	bool running;
+	bool high_prio;
 	spinlock_t lock;
 	struct list_head  head;
 	struct tasklet_struct bh;
diff --git a/include/linux/usb/typec_dp.h b/include/linux/usb/typec_dp.h
index cfb916cccd31..8d09c2f0a9b8 100644
--- a/include/linux/usb/typec_dp.h
+++ b/include/linux/usb/typec_dp.h
@@ -73,6 +73,11 @@ enum {
 #define DP_CAP_USB			BIT(7)
 #define DP_CAP_DFP_D_PIN_ASSIGN(_cap_)	(((_cap_) & GENMASK(15, 8)) >> 8)
 #define DP_CAP_UFP_D_PIN_ASSIGN(_cap_)	(((_cap_) & GENMASK(23, 16)) >> 16)
+/* Get pin assignment taking plug & receptacle into consideration */
+#define DP_CAP_PIN_ASSIGN_UFP_D(_cap_) ((_cap_ & DP_CAP_RECEPTACLE) ? \
+			DP_CAP_UFP_D_PIN_ASSIGN(_cap_) : DP_CAP_DFP_D_PIN_ASSIGN(_cap_))
+#define DP_CAP_PIN_ASSIGN_DFP_D(_cap_) ((_cap_ & DP_CAP_RECEPTACLE) ? \
+			DP_CAP_DFP_D_PIN_ASSIGN(_cap_) : DP_CAP_UFP_D_PIN_ASSIGN(_cap_))
 
 /* DisplayPort Status Update VDO bits */
 #define DP_STATUS_CONNECTION(_status_)	((_status_) & 3)
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 4fe9e885bbfa..5535be1012a2 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -159,6 +159,11 @@ void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask,
 		int node, const void *caller);
 void *vmalloc_no_huge(unsigned long size);
 
+extern void *__vmalloc_array(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2);
+extern void *vmalloc_array(size_t n, size_t size) __alloc_size(1, 2);
+extern void *__vcalloc(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2);
+extern void *vcalloc(size_t n, size_t size) __alloc_size(1, 2);
+
 extern void vfree(const void *addr);
 extern void vfree_atomic(const void *addr);
 
diff --git a/include/linux/wait.h b/include/linux/wait.h
index d22cf2985b8f..21044562aab7 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -544,10 +544,11 @@ do {										\
 										\
 	hrtimer_init_sleeper_on_stack(&__t, CLOCK_MONOTONIC,			\
 				      HRTIMER_MODE_REL);			\
-	if ((timeout) != KTIME_MAX)						\
-		hrtimer_start_range_ns(&__t.timer, timeout,			\
-				       current->timer_slack_ns,			\
-				       HRTIMER_MODE_REL);			\
+	if ((timeout) != KTIME_MAX) {						\
+		hrtimer_set_expires_range_ns(&__t.timer, timeout,		\
+					current->timer_slack_ns);		\
+		hrtimer_sleeper_start_expires(&__t, HRTIMER_MODE_REL);		\
+	}									\
 										\
 	__ret = ___wait_event(wq_head, condition, state, 0, 0,			\
 		if (!__t.task) {						\
diff --git a/include/net/9p/9p.h b/include/net/9p/9p.h
index 03614de86942..6d0615140dbc 100644
--- a/include/net/9p/9p.h
+++ b/include/net/9p/9p.h
@@ -32,13 +32,13 @@
  */
 
 enum p9_debug_flags {
-	P9_DEBUG_ERROR = 	(1<<0),
-	P9_DEBUG_9P = 		(1<<2),
+	P9_DEBUG_ERROR =	(1<<0),
+	P9_DEBUG_9P =		(1<<2),
 	P9_DEBUG_VFS =		(1<<3),
 	P9_DEBUG_CONV =		(1<<4),
 	P9_DEBUG_MUX =		(1<<5),
 	P9_DEBUG_TRANS =	(1<<6),
-	P9_DEBUG_SLABS =      	(1<<7),
+	P9_DEBUG_SLABS =	(1<<7),
 	P9_DEBUG_FCALL =	(1<<8),
 	P9_DEBUG_FID =		(1<<9),
 	P9_DEBUG_PKT =		(1<<10),
@@ -317,8 +317,8 @@ enum p9_qid_t {
 };
 
 /* 9P Magic Numbers */
-#define P9_NOTAG	(u16)(~0)
-#define P9_NOFID	(u32)(~0)
+#define P9_NOTAG	((u16)(~0))
+#define P9_NOFID	((u32)(~0))
 #define P9_MAXWELEM	16
 
 /* Minimal header size: size[4] type[1] tag[2] */
diff --git a/include/net/9p/client.h b/include/net/9p/client.h
index e1c308d8d288..7060de84c559 100644
--- a/include/net/9p/client.h
+++ b/include/net/9p/client.h
@@ -23,7 +23,7 @@
  * @p9_proto_2000L: 9P2000.L extension
  */
 
-enum p9_proto_versions{
+enum p9_proto_versions {
 	p9_proto_legacy,
 	p9_proto_2000u,
 	p9_proto_2000L,
@@ -78,7 +78,7 @@ enum p9_req_status_t {
 struct p9_req_t {
 	int status;
 	int t_err;
-	struct kref refcount;
+	refcount_t refcount;
 	wait_queue_head_t wq;
 	struct p9_fcall tc;
 	struct p9_fcall rc;
@@ -219,36 +219,40 @@ struct p9_stat_dotl *p9_client_getattr_dotl(struct p9_fid *fid,
 							u64 request_mask);
 
 int p9_client_mknod_dotl(struct p9_fid *oldfid, const char *name, int mode,
-			dev_t rdev, kgid_t gid, struct p9_qid *);
+			dev_t rdev, kgid_t gid, struct p9_qid *qid);
 int p9_client_mkdir_dotl(struct p9_fid *fid, const char *name, int mode,
-				kgid_t gid, struct p9_qid *);
+				kgid_t gid, struct p9_qid *qid);
 int p9_client_lock_dotl(struct p9_fid *fid, struct p9_flock *flock, u8 *status);
 int p9_client_getlock_dotl(struct p9_fid *fid, struct p9_getlock *fl);
 void p9_fcall_fini(struct p9_fcall *fc);
-struct p9_req_t *p9_tag_lookup(struct p9_client *, u16);
+struct p9_req_t *p9_tag_lookup(struct p9_client *c, u16 tag);
 
 static inline void p9_req_get(struct p9_req_t *r)
 {
-	kref_get(&r->refcount);
+	refcount_inc(&r->refcount);
 }
 
 static inline int p9_req_try_get(struct p9_req_t *r)
 {
-	return kref_get_unless_zero(&r->refcount);
+	return refcount_inc_not_zero(&r->refcount);
 }
 
-int p9_req_put(struct p9_req_t *r);
+int p9_req_put(struct p9_client *c, struct p9_req_t *r);
 
 void p9_client_cb(struct p9_client *c, struct p9_req_t *req, int status);
 
-int p9_parse_header(struct p9_fcall *, int32_t *, int8_t *, int16_t *, int);
-int p9stat_read(struct p9_client *, char *, int, struct p9_wstat *);
-void p9stat_free(struct p9_wstat *);
+int p9_parse_header(struct p9_fcall *pdu, int32_t *size, int8_t *type,
+		    int16_t *tag, int rewind);
+int p9stat_read(struct p9_client *clnt, char *buf, int len,
+		struct p9_wstat *st);
+void p9stat_free(struct p9_wstat *stbuf);
 
 int p9_is_proto_dotu(struct p9_client *clnt);
 int p9_is_proto_dotl(struct p9_client *clnt);
-struct p9_fid *p9_client_xattrwalk(struct p9_fid *, const char *, u64 *);
-int p9_client_xattrcreate(struct p9_fid *, const char *, u64, int);
+struct p9_fid *p9_client_xattrwalk(struct p9_fid *file_fid,
+				   const char *attr_name, u64 *attr_size);
+int p9_client_xattrcreate(struct p9_fid *fid, const char *name,
+			  u64 attr_size, int flags);
 int p9_client_readlink(struct p9_fid *fid, char **target);
 
 int p9_client_init(void);
diff --git a/include/net/9p/transport.h b/include/net/9p/transport.h
index 3eb4261b2958..721597611625 100644
--- a/include/net/9p/transport.h
+++ b/include/net/9p/transport.h
@@ -40,14 +40,16 @@ struct p9_trans_module {
 	int maxsize;		/* max message size of transport */
 	int def;		/* this transport should be default */
 	struct module *owner;
-	int (*create)(struct p9_client *, const char *, char *);
-	void (*close) (struct p9_client *);
-	int (*request) (struct p9_client *, struct p9_req_t *req);
-	int (*cancel) (struct p9_client *, struct p9_req_t *req);
-	int (*cancelled)(struct p9_client *, struct p9_req_t *req);
-	int (*zc_request)(struct p9_client *, struct p9_req_t *,
-			  struct iov_iter *, struct iov_iter *, int , int, int);
-	int (*show_options)(struct seq_file *, struct p9_client *);
+	int (*create)(struct p9_client *client,
+		      const char *devname, char *args);
+	void (*close)(struct p9_client *client);
+	int (*request)(struct p9_client *client, struct p9_req_t *req);
+	int (*cancel)(struct p9_client *client, struct p9_req_t *req);
+	int (*cancelled)(struct p9_client *client, struct p9_req_t *req);
+	int (*zc_request)(struct p9_client *client, struct p9_req_t *req,
+			  struct iov_iter *uidata, struct iov_iter *uodata,
+			  int inlen, int outlen, int in_hdr_len);
+	int (*show_options)(struct seq_file *m, struct p9_client *client);
 };
 
 void v9fs_register_trans(struct p9_trans_module *m);
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 59940e230b78..53627afab104 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -403,6 +403,9 @@ static inline bool ip6_ignore_linkdown(const struct net_device *dev)
 {
 	const struct inet6_dev *idev = __in6_dev_get(dev);
 
+	if (unlikely(!idev))
+		return true;
+
 	return !!idev->cnf.ignore_routes_with_linkdown;
 }
 
diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index 3fecc4a411a1..355835639ae5 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -422,6 +422,71 @@ out:
 	return NULL;
 }
 
+/* Shall not be called with lock_sock held */
+static inline struct sk_buff *bt_skb_sendmsg(struct sock *sk,
+					     struct msghdr *msg,
+					     size_t len, size_t mtu,
+					     size_t headroom, size_t tailroom)
+{
+	struct sk_buff *skb;
+	size_t size = min_t(size_t, len, mtu);
+	int err;
+
+	skb = bt_skb_send_alloc(sk, size + headroom + tailroom,
+				msg->msg_flags & MSG_DONTWAIT, &err);
+	if (!skb)
+		return ERR_PTR(err);
+
+	skb_reserve(skb, headroom);
+	skb_tailroom_reserve(skb, mtu, tailroom);
+
+	if (!copy_from_iter_full(skb_put(skb, size), size, &msg->msg_iter)) {
+		kfree_skb(skb);
+		return ERR_PTR(-EFAULT);
+	}
+
+	skb->priority = sk->sk_priority;
+
+	return skb;
+}
+
+/* Similar to bt_skb_sendmsg but can split the msg into multiple fragments
+ * accourding to the MTU.
+ */
+static inline struct sk_buff *bt_skb_sendmmsg(struct sock *sk,
+					      struct msghdr *msg,
+					      size_t len, size_t mtu,
+					      size_t headroom, size_t tailroom)
+{
+	struct sk_buff *skb, **frag;
+
+	skb = bt_skb_sendmsg(sk, msg, len, mtu, headroom, tailroom);
+	if (IS_ERR_OR_NULL(skb))
+		return skb;
+
+	len -= skb->len;
+	if (!len)
+		return skb;
+
+	/* Add remaining data over MTU as continuation fragments */
+	frag = &skb_shinfo(skb)->frag_list;
+	while (len) {
+		struct sk_buff *tmp;
+
+		tmp = bt_skb_sendmsg(sk, msg, len, mtu, headroom, tailroom);
+		if (IS_ERR(tmp)) {
+			return skb;
+		}
+
+		len -= tmp->len;
+
+		*frag = tmp;
+		frag = &(*frag)->next;
+	}
+
+	return skb;
+}
+
 int bt_to_errno(u16 code);
 
 void hci_sock_set_flag(struct sock *sk, int nr);
diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 3c4f550e5a8b..2f766e3437ce 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -847,6 +847,7 @@ enum {
 };
 
 void l2cap_chan_hold(struct l2cap_chan *c);
+struct l2cap_chan *l2cap_chan_hold_unless_zero(struct l2cap_chan *c);
 void l2cap_chan_put(struct l2cap_chan *c);
 
 static inline void l2cap_chan_lock(struct l2cap_chan *chan)
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index 40296ed976a9..3459a04a3d61 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -33,7 +33,7 @@ extern unsigned int sysctl_net_busy_poll __read_mostly;
 
 static inline bool net_busy_loop_on(void)
 {
-	return sysctl_net_busy_poll;
+	return READ_ONCE(sysctl_net_busy_poll);
 }
 
 static inline bool sk_can_busy_loop(const struct sock *sk)
diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index 81b965953036..56f1286583d3 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -103,15 +103,24 @@ struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
 			  const int dif);
 
 int inet6_hash(struct sock *sk);
-#endif /* IS_ENABLED(CONFIG_IPV6) */
 
-#define INET6_MATCH(__sk, __net, __saddr, __daddr, __ports, __dif, __sdif) \
-	(((__sk)->sk_portpair == (__ports))			&&	\
-	 ((__sk)->sk_family == AF_INET6)			&&	\
-	 ipv6_addr_equal(&(__sk)->sk_v6_daddr, (__saddr))		&&	\
-	 ipv6_addr_equal(&(__sk)->sk_v6_rcv_saddr, (__daddr))	&&	\
-	 (((__sk)->sk_bound_dev_if == (__dif))	||			\
-	  ((__sk)->sk_bound_dev_if == (__sdif)))		&&	\
-	 net_eq(sock_net(__sk), (__net)))
+static inline bool inet6_match(struct net *net, const struct sock *sk,
+			       const struct in6_addr *saddr,
+			       const struct in6_addr *daddr,
+			       const __portpair ports,
+			       const int dif, const int sdif)
+{
+	if (!net_eq(sock_net(sk), net) ||
+	    sk->sk_family != AF_INET6 ||
+	    sk->sk_portpair != ports ||
+	    !ipv6_addr_equal(&sk->sk_v6_daddr, saddr) ||
+	    !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
+		return false;
+
+	/* READ_ONCE() paired with WRITE_ONCE() in sock_bindtoindex_locked() */
+	return inet_sk_bound_dev_eq(net, READ_ONCE(sk->sk_bound_dev_if), dif,
+				    sdif);
+}
+#endif /* IS_ENABLED(CONFIG_IPV6) */
 
 #endif /* _INET6_HASHTABLES_H */
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index fa6a87246a7b..695ed45841f0 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -315,7 +315,7 @@ void inet_csk_update_fastreuse(struct inet_bind_bucket *tb,
 
 struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu);
 
-#define TCP_PINGPONG_THRESH	3
+#define TCP_PINGPONG_THRESH	1
 
 static inline void inet_csk_enter_pingpong_mode(struct sock *sk)
 {
@@ -332,14 +332,6 @@ static inline bool inet_csk_in_pingpong_mode(struct sock *sk)
 	return inet_csk(sk)->icsk_ack.pingpong >= TCP_PINGPONG_THRESH;
 }
 
-static inline void inet_csk_inc_pingpong_cnt(struct sock *sk)
-{
-	struct inet_connection_sock *icsk = inet_csk(sk);
-
-	if (icsk->icsk_ack.pingpong < U8_MAX)
-		icsk->icsk_ack.pingpong++;
-}
-
 static inline bool inet_csk_has_ulp(struct sock *sk)
 {
 	return inet_sk(sk)->is_icsk && !!inet_csk(sk)->icsk_ulp_ops;
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 98e1ec1a14f0..53c22b64e972 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -203,17 +203,6 @@ static inline void inet_ehash_locks_free(struct inet_hashinfo *hashinfo)
 	hashinfo->ehash_locks = NULL;
 }
 
-static inline bool inet_sk_bound_dev_eq(struct net *net, int bound_dev_if,
-					int dif, int sdif)
-{
-#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
-	return inet_bound_dev_eq(!!net->ipv4.sysctl_tcp_l3mdev_accept,
-				 bound_dev_if, dif, sdif);
-#else
-	return inet_bound_dev_eq(true, bound_dev_if, dif, sdif);
-#endif
-}
-
 struct inet_bind_bucket *
 inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net,
 			struct inet_bind_hashbucket *head,
@@ -295,7 +284,6 @@ static inline struct sock *inet_lookup_listener(struct net *net,
 	((__force __portpair)(((__u32)(__dport) << 16) | (__force __u32)(__be16)(__sport)))
 #endif
 
-#if (BITS_PER_LONG == 64)
 #ifdef __BIG_ENDIAN
 #define INET_ADDR_COOKIE(__name, __saddr, __daddr) \
 	const __addrpair __name = (__force __addrpair) ( \
@@ -307,24 +295,20 @@ static inline struct sock *inet_lookup_listener(struct net *net,
 				   (((__force __u64)(__be32)(__daddr)) << 32) | \
 				   ((__force __u64)(__be32)(__saddr)))
 #endif /* __BIG_ENDIAN */
-#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif, __sdif) \
-	(((__sk)->sk_portpair == (__ports))			&&	\
-	 ((__sk)->sk_addrpair == (__cookie))			&&	\
-	 (((__sk)->sk_bound_dev_if == (__dif))			||	\
-	  ((__sk)->sk_bound_dev_if == (__sdif)))		&&	\
-	 net_eq(sock_net(__sk), (__net)))
-#else /* 32-bit arch */
-#define INET_ADDR_COOKIE(__name, __saddr, __daddr) \
-	const int __name __deprecated __attribute__((unused))
-
-#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif, __sdif) \
-	(((__sk)->sk_portpair == (__ports))		&&		\
-	 ((__sk)->sk_daddr	== (__saddr))		&&		\
-	 ((__sk)->sk_rcv_saddr	== (__daddr))		&&		\
-	 (((__sk)->sk_bound_dev_if == (__dif))		||		\
-	  ((__sk)->sk_bound_dev_if == (__sdif)))	&&		\
-	 net_eq(sock_net(__sk), (__net)))
-#endif /* 64-bit arch */
+
+static inline bool INET_MATCH(struct net *net, const struct sock *sk,
+			      const __addrpair cookie, const __portpair ports,
+			      int dif, int sdif)
+{
+	if (!net_eq(sock_net(sk), net) ||
+	    sk->sk_portpair != ports ||
+	    sk->sk_addrpair != cookie)
+	        return false;
+
+	/* READ_ONCE() paired with WRITE_ONCE() in sock_bindtoindex_locked() */
+	return inet_sk_bound_dev_eq(net, READ_ONCE(sk->sk_bound_dev_if), dif,
+				    sdif);
+}
 
 /* Sockets in TCP_CLOSE state are _always_ taken out of the hash, so we need
  * not check it for lookups anymore, thanks Alexey. -DaveM
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index d81b7f85819e..2c2b41ea7f81 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -107,7 +107,8 @@ static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk)
 
 static inline u32 inet_request_mark(const struct sock *sk, struct sk_buff *skb)
 {
-	if (!sk->sk_mark && sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept)
+	if (!sk->sk_mark &&
+	    READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept))
 		return skb->mark;
 
 	return sk->sk_mark;
@@ -116,14 +117,15 @@ static inline u32 inet_request_mark(const struct sock *sk, struct sk_buff *skb)
 static inline int inet_request_bound_dev_if(const struct sock *sk,
 					    struct sk_buff *skb)
 {
+	int bound_dev_if = READ_ONCE(sk->sk_bound_dev_if);
 #ifdef CONFIG_NET_L3_MASTER_DEV
 	struct net *net = sock_net(sk);
 
-	if (!sk->sk_bound_dev_if && net->ipv4.sysctl_tcp_l3mdev_accept)
+	if (!bound_dev_if && READ_ONCE(net->ipv4.sysctl_tcp_l3mdev_accept))
 		return l3mdev_master_ifindex_by_index(net, skb->skb_iif);
 #endif
 
-	return sk->sk_bound_dev_if;
+	return bound_dev_if;
 }
 
 static inline int inet_sk_bound_l3mdev(const struct sock *sk)
@@ -131,7 +133,7 @@ static inline int inet_sk_bound_l3mdev(const struct sock *sk)
 #ifdef CONFIG_NET_L3_MASTER_DEV
 	struct net *net = sock_net(sk);
 
-	if (!net->ipv4.sysctl_tcp_l3mdev_accept)
+	if (!READ_ONCE(net->ipv4.sysctl_tcp_l3mdev_accept))
 		return l3mdev_master_ifindex_by_index(net,
 						      sk->sk_bound_dev_if);
 #endif
@@ -147,6 +149,17 @@ static inline bool inet_bound_dev_eq(bool l3mdev_accept, int bound_dev_if,
 	return bound_dev_if == dif || bound_dev_if == sdif;
 }
 
+static inline bool inet_sk_bound_dev_eq(struct net *net, int bound_dev_if,
+					int dif, int sdif)
+{
+#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
+	return inet_bound_dev_eq(!!READ_ONCE(net->ipv4.sysctl_tcp_l3mdev_accept),
+				 bound_dev_if, dif, sdif);
+#else
+	return inet_bound_dev_eq(true, bound_dev_if, dif, sdif);
+#endif
+}
+
 struct inet_cork {
 	unsigned int		flags;
 	__be32			addr;
@@ -373,7 +386,7 @@ static inline bool inet_get_convert_csum(struct sock *sk)
 static inline bool inet_can_nonlocal_bind(struct net *net,
 					  struct inet_sock *inet)
 {
-	return net->ipv4.sysctl_ip_nonlocal_bind ||
+	return READ_ONCE(net->ipv4.sysctl_ip_nonlocal_bind) ||
 		inet->freebind || inet->transparent;
 }
 
diff --git a/include/net/ip.h b/include/net/ip.h
index a77a9e1c6c04..8462ced0c21e 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -352,7 +352,7 @@ static inline bool sysctl_dev_name_is_allowed(const char *name)
 
 static inline bool inet_port_requires_bind_service(struct net *net, unsigned short port)
 {
-	return port < net->ipv4.sysctl_ip_prot_sock;
+	return port < READ_ONCE(net->ipv4.sysctl_ip_prot_sock);
 }
 
 #else
@@ -379,7 +379,7 @@ void ipfrag_init(void);
 void ip_static_sysctl_init(void);
 
 #define IP4_REPLY_MARK(net, mark) \
-	((net)->ipv4.sysctl_fwmark_reflect ? (mark) : 0)
+	(READ_ONCE((net)->ipv4.sysctl_fwmark_reflect) ? (mark) : 0)
 
 static inline bool ip_is_fragment(const struct iphdr *iph)
 {
@@ -441,7 +441,7 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst,
 	struct net *net = dev_net(dst->dev);
 	unsigned int mtu;
 
-	if (net->ipv4.sysctl_ip_fwd_use_pmtu ||
+	if (READ_ONCE(net->ipv4.sysctl_ip_fwd_use_pmtu) ||
 	    ip_mtu_locked(dst) ||
 	    !forwarding) {
 		mtu = rt->rt_pmtu;
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index 9f927c44087d..aaa518e777e9 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -266,6 +266,7 @@ void flow_offload_refresh(struct nf_flowtable *flow_table,
 
 struct flow_offload_tuple_rhash *flow_offload_lookup(struct nf_flowtable *flow_table,
 						     struct flow_offload_tuple *tuple);
+void nf_flow_table_gc_run(struct nf_flowtable *flow_table);
 void nf_flow_table_gc_cleanup(struct nf_flowtable *flowtable,
 			      struct net_device *dev);
 void nf_flow_table_cleanup(struct net_device *dev);
@@ -302,6 +303,8 @@ void nf_flow_offload_stats(struct nf_flowtable *flowtable,
 			   struct flow_offload *flow);
 
 void nf_flow_table_offload_flush(struct nf_flowtable *flowtable);
+void nf_flow_table_offload_flush_cleanup(struct nf_flowtable *flowtable);
+
 int nf_flow_table_offload_setup(struct nf_flowtable *flowtable,
 				struct net_device *dev,
 				enum flow_block_command cmd);
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 2af1c2c64128..53746494eb84 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -21,13 +21,19 @@ struct module;
 
 #define NFT_JUMP_STACK_SIZE	16
 
+enum {
+	NFT_PKTINFO_L4PROTO	= (1 << 0),
+	NFT_PKTINFO_INNER	= (1 << 1),
+};
+
 struct nft_pktinfo {
 	struct sk_buff			*skb;
 	const struct nf_hook_state	*state;
-	bool				tprot_set;
+	u8				flags;
 	u8				tprot;
 	u16				fragoff;
 	unsigned int			thoff;
+	unsigned int			inneroff;
 };
 
 static inline struct sock *nft_sk(const struct nft_pktinfo *pkt)
@@ -75,7 +81,7 @@ static inline void nft_set_pktinfo(struct nft_pktinfo *pkt,
 
 static inline void nft_set_pktinfo_unspec(struct nft_pktinfo *pkt)
 {
-	pkt->tprot_set = false;
+	pkt->flags = 0;
 	pkt->tprot = 0;
 	pkt->thoff = 0;
 	pkt->fragoff = 0;
@@ -187,13 +193,18 @@ struct nft_ctx {
 	bool				report;
 };
 
+enum nft_data_desc_flags {
+	NFT_DATA_DESC_SETELEM	= (1 << 0),
+};
+
 struct nft_data_desc {
 	enum nft_data_types		type;
+	unsigned int			size;
 	unsigned int			len;
+	unsigned int			flags;
 };
 
-int nft_data_init(const struct nft_ctx *ctx,
-		  struct nft_data *data, unsigned int size,
+int nft_data_init(const struct nft_ctx *ctx, struct nft_data *data,
 		  struct nft_data_desc *desc, const struct nlattr *nla);
 void nft_data_hold(const struct nft_data *data, enum nft_data_types type);
 void nft_data_release(const struct nft_data *data, enum nft_data_types type);
@@ -636,18 +647,22 @@ static inline void nft_set_ext_prepare(struct nft_set_ext_tmpl *tmpl)
 	tmpl->len = sizeof(struct nft_set_ext);
 }
 
-static inline void nft_set_ext_add_length(struct nft_set_ext_tmpl *tmpl, u8 id,
-					  unsigned int len)
+static inline int nft_set_ext_add_length(struct nft_set_ext_tmpl *tmpl, u8 id,
+					 unsigned int len)
 {
 	tmpl->len	 = ALIGN(tmpl->len, nft_set_ext_types[id].align);
-	BUG_ON(tmpl->len > U8_MAX);
+	if (tmpl->len > U8_MAX)
+		return -EINVAL;
+
 	tmpl->offset[id] = tmpl->len;
 	tmpl->len	+= nft_set_ext_types[id].len + len;
+
+	return 0;
 }
 
-static inline void nft_set_ext_add(struct nft_set_ext_tmpl *tmpl, u8 id)
+static inline int nft_set_ext_add(struct nft_set_ext_tmpl *tmpl, u8 id)
 {
-	nft_set_ext_add_length(tmpl, id, 0);
+	return nft_set_ext_add_length(tmpl, id, 0);
 }
 
 static inline void nft_set_ext_init(struct nft_set_ext *ext,
@@ -1585,6 +1600,7 @@ struct nftables_pernet {
 	struct list_head	module_list;
 	struct list_head	notify_list;
 	struct mutex		commit_mutex;
+	u64			table_handle;
 	unsigned int		base_seq;
 	u8			validate_state;
 };
diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h
index 0fa5a6d98a00..9dfa11d4224d 100644
--- a/include/net/netfilter/nf_tables_core.h
+++ b/include/net/netfilter/nf_tables_core.h
@@ -40,6 +40,14 @@ struct nft_cmp_fast_expr {
 	bool			inv;
 };
 
+struct nft_cmp16_fast_expr {
+	struct nft_data		data;
+	struct nft_data		mask;
+	u8			sreg;
+	u8			len;
+	bool			inv;
+};
+
 struct nft_immediate_expr {
 	struct nft_data		data;
 	u8			dreg;
@@ -57,6 +65,7 @@ static inline u32 nft_cmp_fast_mask(unsigned int len)
 }
 
 extern const struct nft_expr_ops nft_cmp_fast_ops;
+extern const struct nft_expr_ops nft_cmp16_fast_ops;
 
 struct nft_payload {
 	enum nft_payload_bases	base:8;
diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h
index eb4c094cd54d..c4a6147b0ef8 100644
--- a/include/net/netfilter/nf_tables_ipv4.h
+++ b/include/net/netfilter/nf_tables_ipv4.h
@@ -10,7 +10,7 @@ static inline void nft_set_pktinfo_ipv4(struct nft_pktinfo *pkt)
 	struct iphdr *ip;
 
 	ip = ip_hdr(pkt->skb);
-	pkt->tprot_set = true;
+	pkt->flags = NFT_PKTINFO_L4PROTO;
 	pkt->tprot = ip->protocol;
 	pkt->thoff = ip_hdrlen(pkt->skb);
 	pkt->fragoff = ntohs(ip->frag_off) & IP_OFFSET;
@@ -36,7 +36,7 @@ static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt)
 	else if (len < thoff)
 		return -1;
 
-	pkt->tprot_set = true;
+	pkt->flags = NFT_PKTINFO_L4PROTO;
 	pkt->tprot = iph->protocol;
 	pkt->thoff = thoff;
 	pkt->fragoff = ntohs(iph->frag_off) & IP_OFFSET;
@@ -71,7 +71,7 @@ static inline int nft_set_pktinfo_ipv4_ingress(struct nft_pktinfo *pkt)
 		goto inhdr_error;
 	}
 
-	pkt->tprot_set = true;
+	pkt->flags = NFT_PKTINFO_L4PROTO;
 	pkt->tprot = iph->protocol;
 	pkt->thoff = thoff;
 	pkt->fragoff = ntohs(iph->frag_off) & IP_OFFSET;
@@ -82,4 +82,5 @@ inhdr_error:
 	__IP_INC_STATS(nft_net(pkt), IPSTATS_MIB_INHDRERRORS);
 	return -1;
 }
+
 #endif
diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h
index 7595e02b00ba..ec7eaeaf4f04 100644
--- a/include/net/netfilter/nf_tables_ipv6.h
+++ b/include/net/netfilter/nf_tables_ipv6.h
@@ -18,7 +18,7 @@ static inline void nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt)
 		return;
 	}
 
-	pkt->tprot_set = true;
+	pkt->flags = NFT_PKTINFO_L4PROTO;
 	pkt->tprot = protohdr;
 	pkt->thoff = thoff;
 	pkt->fragoff = frag_off;
@@ -50,7 +50,7 @@ static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt)
 	if (protohdr < 0)
 		return -1;
 
-	pkt->tprot_set = true;
+	pkt->flags = NFT_PKTINFO_L4PROTO;
 	pkt->tprot = protohdr;
 	pkt->thoff = thoff;
 	pkt->fragoff = frag_off;
@@ -96,7 +96,7 @@ static inline int nft_set_pktinfo_ipv6_ingress(struct nft_pktinfo *pkt)
 	if (protohdr < 0)
 		goto inhdr_error;
 
-	pkt->tprot_set = true;
+	pkt->flags = NFT_PKTINFO_L4PROTO;
 	pkt->tprot = protohdr;
 	pkt->thoff = thoff;
 	pkt->fragoff = frag_off;
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 6c5b2efc4f17..d60a10cfc382 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -74,7 +74,6 @@ struct netns_ipv4 {
 	struct sock		*mc_autojoin_sk;
 
 	struct inet_peer_base	*peers;
-	struct sock  * __percpu	*tcp_sk;
 	struct fqdir		*fqdir;
 
 	u8 sysctl_icmp_echo_ignore_all;
diff --git a/include/net/raw.h b/include/net/raw.h
index 8ad8df594853..c51a635671a7 100644
--- a/include/net/raw.h
+++ b/include/net/raw.h
@@ -75,7 +75,7 @@ static inline bool raw_sk_bound_dev_eq(struct net *net, int bound_dev_if,
 				       int dif, int sdif)
 {
 #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
-	return inet_bound_dev_eq(!!net->ipv4.sysctl_raw_l3mdev_accept,
+	return inet_bound_dev_eq(READ_ONCE(net->ipv4.sysctl_raw_l3mdev_accept),
 				 bound_dev_if, dif, sdif);
 #else
 	return inet_bound_dev_eq(true, bound_dev_if, dif, sdif);
diff --git a/include/net/route.h b/include/net/route.h
index 2551f3f03b37..30610101ea14 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -360,7 +360,7 @@ static inline int ip4_dst_hoplimit(const struct dst_entry *dst)
 	struct net *net = dev_net(dst->dev);
 
 	if (hoplimit == 0)
-		hoplimit = net->ipv4.sysctl_ip_default_ttl;
+		hoplimit = READ_ONCE(net->ipv4.sysctl_ip_default_ttl);
 	return hoplimit;
 }
 
diff --git a/include/net/sock.h b/include/net/sock.h
index 7d49196a3880..cb1a1bb64ed8 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -161,9 +161,6 @@ typedef __u64 __bitwise __addrpair;
  *	for struct sock and struct inet_timewait_sock.
  */
 struct sock_common {
-	/* skc_daddr and skc_rcv_saddr must be grouped on a 8 bytes aligned
-	 * address on 64bit arches : cf INET_MATCH()
-	 */
 	union {
 		__addrpair	skc_addrpair;
 		struct {
@@ -546,14 +543,26 @@ enum sk_pacing {
 	SK_PACING_FQ		= 2,
 };
 
-/* Pointer stored in sk_user_data might not be suitable for copying
- * when cloning the socket. For instance, it can point to a reference
- * counted object. sk_user_data bottom bit is set if pointer must not
- * be copied.
+/* flag bits in sk_user_data
+ *
+ * - SK_USER_DATA_NOCOPY:      Pointer stored in sk_user_data might
+ *   not be suitable for copying when cloning the socket. For instance,
+ *   it can point to a reference counted object. sk_user_data bottom
+ *   bit is set if pointer must not be copied.
+ *
+ * - SK_USER_DATA_BPF:         Mark whether sk_user_data field is
+ *   managed/owned by a BPF reuseport array. This bit should be set
+ *   when sk_user_data's sk is added to the bpf's reuseport_array.
+ *
+ * - SK_USER_DATA_PSOCK:       Mark whether pointer stored in
+ *   sk_user_data points to psock type. This bit should be set
+ *   when sk_user_data is assigned to a psock object.
  */
 #define SK_USER_DATA_NOCOPY	1UL
-#define SK_USER_DATA_BPF	2UL	/* Managed by BPF */
-#define SK_USER_DATA_PTRMASK	~(SK_USER_DATA_NOCOPY | SK_USER_DATA_BPF)
+#define SK_USER_DATA_BPF	2UL
+#define SK_USER_DATA_PSOCK	4UL
+#define SK_USER_DATA_PTRMASK	~(SK_USER_DATA_NOCOPY | SK_USER_DATA_BPF |\
+				  SK_USER_DATA_PSOCK)
 
 /**
  * sk_user_data_is_nocopy - Test if sk_user_data pointer must not be copied
@@ -566,24 +575,40 @@ static inline bool sk_user_data_is_nocopy(const struct sock *sk)
 
 #define __sk_user_data(sk) ((*((void __rcu **)&(sk)->sk_user_data)))
 
+/**
+ * __rcu_dereference_sk_user_data_with_flags - return the pointer
+ * only if argument flags all has been set in sk_user_data. Otherwise
+ * return NULL
+ *
+ * @sk: socket
+ * @flags: flag bits
+ */
+static inline void *
+__rcu_dereference_sk_user_data_with_flags(const struct sock *sk,
+					  uintptr_t flags)
+{
+	uintptr_t sk_user_data = (uintptr_t)rcu_dereference(__sk_user_data(sk));
+
+	WARN_ON_ONCE(flags & SK_USER_DATA_PTRMASK);
+
+	if ((sk_user_data & flags) == flags)
+		return (void *)(sk_user_data & SK_USER_DATA_PTRMASK);
+	return NULL;
+}
+
 #define rcu_dereference_sk_user_data(sk)				\
+	__rcu_dereference_sk_user_data_with_flags(sk, 0)
+#define __rcu_assign_sk_user_data_with_flags(sk, ptr, flags)		\
 ({									\
-	void *__tmp = rcu_dereference(__sk_user_data((sk)));		\
-	(void *)((uintptr_t)__tmp & SK_USER_DATA_PTRMASK);		\
-})
-#define rcu_assign_sk_user_data(sk, ptr)				\
-({									\
-	uintptr_t __tmp = (uintptr_t)(ptr);				\
-	WARN_ON_ONCE(__tmp & ~SK_USER_DATA_PTRMASK);			\
-	rcu_assign_pointer(__sk_user_data((sk)), __tmp);		\
-})
-#define rcu_assign_sk_user_data_nocopy(sk, ptr)				\
-({									\
-	uintptr_t __tmp = (uintptr_t)(ptr);				\
-	WARN_ON_ONCE(__tmp & ~SK_USER_DATA_PTRMASK);			\
+	uintptr_t __tmp1 = (uintptr_t)(ptr),				\
+		  __tmp2 = (uintptr_t)(flags);				\
+	WARN_ON_ONCE(__tmp1 & ~SK_USER_DATA_PTRMASK);			\
+	WARN_ON_ONCE(__tmp2 & SK_USER_DATA_PTRMASK);			\
 	rcu_assign_pointer(__sk_user_data((sk)),			\
-			   __tmp | SK_USER_DATA_NOCOPY);		\
+			   __tmp1 | __tmp2);				\
 })
+#define rcu_assign_sk_user_data(sk, ptr)				\
+	__rcu_assign_sk_user_data_with_flags(sk, ptr, 0)
 
 /*
  * SK_CAN_REUSE and SK_NO_REUSE on a socket mean that the socket is OK
@@ -1484,7 +1509,7 @@ void __sk_mem_reclaim(struct sock *sk, int amount);
 /* sysctl_mem values are in pages, we convert them in SK_MEM_QUANTUM units */
 static inline long sk_prot_mem_limits(const struct sock *sk, int index)
 {
-	long val = sk->sk_prot->sysctl_mem[index];
+	long val = READ_ONCE(sk->sk_prot->sysctl_mem[index]);
 
 #if PAGE_SIZE > SK_MEM_QUANTUM
 	val <<= PAGE_SHIFT - SK_MEM_QUANTUM_SHIFT;
@@ -1507,19 +1532,23 @@ static inline bool sk_has_account(struct sock *sk)
 
 static inline bool sk_wmem_schedule(struct sock *sk, int size)
 {
+	int delta;
+
 	if (!sk_has_account(sk))
 		return true;
-	return size <= sk->sk_forward_alloc ||
-		__sk_mem_schedule(sk, size, SK_MEM_SEND);
+	delta = size - sk->sk_forward_alloc;
+	return delta <= 0 || __sk_mem_schedule(sk, delta, SK_MEM_SEND);
 }
 
 static inline bool
 sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size)
 {
+	int delta;
+
 	if (!sk_has_account(sk))
 		return true;
-	return size <= sk->sk_forward_alloc ||
-		__sk_mem_schedule(sk, size, SK_MEM_RECV) ||
+	delta = size - sk->sk_forward_alloc;
+	return delta <= 0 || __sk_mem_schedule(sk, delta, SK_MEM_RECV) ||
 		skb_pfmemalloc(skb);
 }
 
@@ -2765,18 +2794,18 @@ static inline int sk_get_wmem0(const struct sock *sk, const struct proto *proto)
 {
 	/* Does this proto have per netns sysctl_wmem ? */
 	if (proto->sysctl_wmem_offset)
-		return *(int *)((void *)sock_net(sk) + proto->sysctl_wmem_offset);
+		return READ_ONCE(*(int *)((void *)sock_net(sk) + proto->sysctl_wmem_offset));
 
-	return *proto->sysctl_wmem;
+	return READ_ONCE(*proto->sysctl_wmem);
 }
 
 static inline int sk_get_rmem0(const struct sock *sk, const struct proto *proto)
 {
 	/* Does this proto have per netns sysctl_rmem ? */
 	if (proto->sysctl_rmem_offset)
-		return *(int *)((void *)sock_net(sk) + proto->sysctl_rmem_offset);
+		return READ_ONCE(*(int *)((void *)sock_net(sk) + proto->sysctl_rmem_offset));
 
-	return *proto->sysctl_rmem;
+	return READ_ONCE(*proto->sysctl_rmem);
 }
 
 /* Default TCP Small queue budget is ~1 ms of data (1sec >> 10)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 3b97db2d438f..d3646645cb9e 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -571,6 +571,8 @@ __u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mss);
 #endif
 /* tcp_output.c */
 
+void tcp_skb_entail(struct sock *sk, struct sk_buff *skb);
+void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb);
 void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss,
 			       int nonagle);
 int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs);
@@ -1390,8 +1392,8 @@ static inline void tcp_slow_start_after_idle_check(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 	s32 delta;
 
-	if (!sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle || tp->packets_out ||
-	    ca_ops->cong_control)
+	if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle) ||
+	    tp->packets_out || ca_ops->cong_control)
 		return;
 	delta = tcp_jiffies32 - tp->lsndtime;
 	if (delta > inet_csk(sk)->icsk_rto)
@@ -1406,7 +1408,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space,
 
 static inline int tcp_win_from_space(const struct sock *sk, int space)
 {
-	int tcp_adv_win_scale = sock_net(sk)->ipv4.sysctl_tcp_adv_win_scale;
+	int tcp_adv_win_scale = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_adv_win_scale);
 
 	return tcp_adv_win_scale <= 0 ?
 		(space>>(-tcp_adv_win_scale)) :
@@ -1469,21 +1471,24 @@ static inline int keepalive_intvl_when(const struct tcp_sock *tp)
 {
 	struct net *net = sock_net((struct sock *)tp);
 
-	return tp->keepalive_intvl ? : net->ipv4.sysctl_tcp_keepalive_intvl;
+	return tp->keepalive_intvl ? :
+		READ_ONCE(net->ipv4.sysctl_tcp_keepalive_intvl);
 }
 
 static inline int keepalive_time_when(const struct tcp_sock *tp)
 {
 	struct net *net = sock_net((struct sock *)tp);
 
-	return tp->keepalive_time ? : net->ipv4.sysctl_tcp_keepalive_time;
+	return tp->keepalive_time ? :
+		READ_ONCE(net->ipv4.sysctl_tcp_keepalive_time);
 }
 
 static inline int keepalive_probes(const struct tcp_sock *tp)
 {
 	struct net *net = sock_net((struct sock *)tp);
 
-	return tp->keepalive_probes ? : net->ipv4.sysctl_tcp_keepalive_probes;
+	return tp->keepalive_probes ? :
+		READ_ONCE(net->ipv4.sysctl_tcp_keepalive_probes);
 }
 
 static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp)
@@ -1496,7 +1501,8 @@ static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp)
 
 static inline int tcp_fin_time(const struct sock *sk)
 {
-	int fin_timeout = tcp_sk(sk)->linger2 ? : sock_net(sk)->ipv4.sysctl_tcp_fin_timeout;
+	int fin_timeout = tcp_sk(sk)->linger2 ? :
+		READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fin_timeout);
 	const int rto = inet_csk(sk)->icsk_rto;
 
 	if (fin_timeout < (rto << 2) - (rto >> 1))
@@ -1990,7 +1996,7 @@ void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr);
 static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp)
 {
 	struct net *net = sock_net((struct sock *)tp);
-	return tp->notsent_lowat ?: net->ipv4.sysctl_tcp_notsent_lowat;
+	return tp->notsent_lowat ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat);
 }
 
 bool tcp_stream_memory_free(const struct sock *sk, int wake);
diff --git a/include/net/tls.h b/include/net/tls.h
index 1fffb206f09f..bf3d63a52788 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -707,7 +707,7 @@ int tls_sw_fallback_init(struct sock *sk,
 			 struct tls_crypto_info *crypto_info);
 
 #ifdef CONFIG_TLS_DEVICE
-void tls_device_init(void);
+int tls_device_init(void);
 void tls_device_cleanup(void);
 void tls_device_sk_destruct(struct sock *sk);
 int tls_set_device_offload(struct sock *sk, struct tls_context *ctx);
@@ -727,7 +727,7 @@ static inline bool tls_is_sk_rx_device_offloaded(struct sock *sk)
 	return tls_get_ctx(sk)->rx_conf == TLS_HW;
 }
 #else
-static inline void tls_device_init(void) {}
+static inline int tls_device_init(void) { return 0; }
 static inline void tls_device_cleanup(void) {}
 
 static inline int
diff --git a/include/net/udp.h b/include/net/udp.h
index 909ecf447e0f..438b1b01a56c 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -262,7 +262,7 @@ static inline bool udp_sk_bound_dev_eq(struct net *net, int bound_dev_if,
 				       int dif, int sdif)
 {
 #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
-	return inet_bound_dev_eq(!!net->ipv4.sysctl_udp_l3mdev_accept,
+	return inet_bound_dev_eq(!!READ_ONCE(net->ipv4.sysctl_udp_l3mdev_accept),
 				 bound_dev_if, dif, sdif);
 #else
 	return inet_bound_dev_eq(true, bound_dev_if, dif, sdif);
diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index afc7ce713657..72394f441dad 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -67,6 +67,9 @@ static inline int udp_sock_create(struct net *net,
 typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb);
 typedef int (*udp_tunnel_encap_err_lookup_t)(struct sock *sk,
 					     struct sk_buff *skb);
+typedef void (*udp_tunnel_encap_err_rcv_t)(struct sock *sk,
+					   struct sk_buff *skb,
+					   unsigned int udp_offset);
 typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk);
 typedef struct sk_buff *(*udp_tunnel_gro_receive_t)(struct sock *sk,
 						    struct list_head *head,
@@ -80,6 +83,7 @@ struct udp_tunnel_sock_cfg {
 	__u8  encap_type;
 	udp_tunnel_encap_rcv_t encap_rcv;
 	udp_tunnel_encap_err_lookup_t encap_err_lookup;
+	udp_tunnel_encap_err_rcv_t encap_err_rcv;
 	udp_tunnel_encap_destroy_t encap_destroy;
 	udp_tunnel_gro_receive_t gro_receive;
 	udp_tunnel_gro_complete_t gro_complete;
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 65242172e41c..73030094c6e6 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1190,6 +1190,8 @@ int __xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk);
 
 static inline int xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk)
 {
+	if (!sk_fullsock(osk))
+		return 0;
 	sk->sk_policy[0] = NULL;
 	sk->sk_policy[1] = NULL;
 	if (unlikely(osk->sk_policy[0] || osk->sk_policy[1]))
diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h
index 6ad01d7de480..a071f6ffd7fa 100644
--- a/include/scsi/libiscsi.h
+++ b/include/scsi/libiscsi.h
@@ -400,7 +400,7 @@ extern int iscsi_host_add(struct Scsi_Host *shost, struct device *pdev);
 extern struct Scsi_Host *iscsi_host_alloc(struct scsi_host_template *sht,
 					  int dd_data_size,
 					  bool xmit_can_sleep);
-extern void iscsi_host_remove(struct Scsi_Host *shost);
+extern void iscsi_host_remove(struct Scsi_Host *shost, bool is_shutdown);
 extern void iscsi_host_free(struct Scsi_Host *shost);
 extern int iscsi_target_alloc(struct scsi_target *starget);
 extern int iscsi_host_get_max_scsi_cmds(struct Scsi_Host *shost,
diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h
index 3ecf9702287b..0f2f149ad916 100644
--- a/include/scsi/scsi_transport_iscsi.h
+++ b/include/scsi/scsi_transport_iscsi.h
@@ -441,6 +441,7 @@ extern struct iscsi_cls_session *iscsi_create_session(struct Scsi_Host *shost,
 						struct iscsi_transport *t,
 						int dd_size,
 						unsigned int target_id);
+extern void iscsi_force_destroy_session(struct iscsi_cls_session *session);
 extern void iscsi_remove_session(struct iscsi_cls_session *session);
 extern void iscsi_free_session(struct iscsi_cls_session *session);
 extern struct iscsi_cls_conn *iscsi_create_conn(struct iscsi_cls_session *sess,
diff --git a/include/soc/at91/sama7-ddr.h b/include/soc/at91/sama7-ddr.h
index f6542584ca13..f203f34dba12 100644
--- a/include/soc/at91/sama7-ddr.h
+++ b/include/soc/at91/sama7-ddr.h
@@ -11,8 +11,6 @@
 #ifndef __SAMA7_DDR_H__
 #define __SAMA7_DDR_H__
 
-#ifdef CONFIG_SOC_SAMA7
-
 /* DDR3PHY */
 #define DDR3PHY_PIR				(0x04)		/* DDR3PHY PHY Initialization Register	*/
 #define	DDR3PHY_PIR_DLLBYP		(1 << 17)	/* DLL Bypass */
@@ -40,6 +38,14 @@
 #define		DDR3PHY_DSGCR_ODTPDD_ODT0	(1 << 20)	/* ODT[0] Power Down Driver */
 
 #define DDR3PHY_ZQ0SR0				(0x188)		/* ZQ status register 0 */
+#define DDR3PHY_ZQ0SR0_PDO_OFF			(0)		/* Pull-down output impedance select offset */
+#define DDR3PHY_ZQ0SR0_PUO_OFF			(5)		/* Pull-up output impedance select offset */
+#define DDR3PHY_ZQ0SR0_PDODT_OFF		(10)		/* Pull-down on-die termination impedance select offset */
+#define DDR3PHY_ZQ0SRO_PUODT_OFF		(15)		/* Pull-up on-die termination impedance select offset */
+
+#define	DDR3PHY_DX0DLLCR			(0x1CC)		/* DDR3PHY DATX8 DLL Control Register */
+#define	DDR3PHY_DX1DLLCR			(0x20C)		/* DDR3PHY DATX8 DLL Control Register */
+#define		DDR3PHY_DXDLLCR_DLLDIS		(1 << 31)	/* DLL Disable */
 
 /* UDDRC */
 #define UDDRC_STAT				(0x04)		/* UDDRC Operating Mode Status Register */
@@ -75,6 +81,4 @@
 #define UDDRC_PCTRL_3				(0x6A0)		/* UDDRC Port 3 Control Register */
 #define UDDRC_PCTRL_4				(0x750)		/* UDDRC Port 4 Control Register */
 
-#endif /* CONFIG_SOC_SAMA7 */
-
 #endif /* __SAMA7_DDR_H__ */
diff --git a/include/sound/control.h b/include/sound/control.h
index 985c51a8fb74..a1fc7e0a47d9 100644
--- a/include/sound/control.h
+++ b/include/sound/control.h
@@ -109,7 +109,7 @@ struct snd_ctl_file {
 	int preferred_subdevice[SND_CTL_SUBDEV_ITEMS];
 	wait_queue_head_t change_sleep;
 	spinlock_t read_lock;
-	struct fasync_struct *fasync;
+	struct snd_fasync *fasync;
 	int subscribed;			/* read interface is activated */
 	struct list_head events;	/* waiting events for read */
 };
diff --git a/include/sound/core.h b/include/sound/core.h
index 6d4cc49584c6..39cee40ac22e 100644
--- a/include/sound/core.h
+++ b/include/sound/core.h
@@ -501,4 +501,12 @@ snd_pci_quirk_lookup_id(u16 vendor, u16 device,
 }
 #endif
 
+/* async signal helpers */
+struct snd_fasync;
+
+int snd_fasync_helper(int fd, struct file *file, int on,
+		      struct snd_fasync **fasyncp);
+void snd_kill_fasync(struct snd_fasync *fasync, int signal, int poll);
+void snd_fasync_free(struct snd_fasync *fasync);
+
 #endif /* __SOUND_CORE_H */
diff --git a/include/trace/bpf_probe.h b/include/trace/bpf_probe.h
index a23be89119aa..04939b2d2f19 100644
--- a/include/trace/bpf_probe.h
+++ b/include/trace/bpf_probe.h
@@ -21,6 +21,22 @@
 #undef __get_bitmask
 #define __get_bitmask(field) (char *)__get_dynamic_array(field)
 
+#undef __get_rel_dynamic_array
+#define __get_rel_dynamic_array(field)	\
+		((void *)(&__entry->__rel_loc_##field) +	\
+		 sizeof(__entry->__rel_loc_##field) +		\
+		 (__entry->__rel_loc_##field & 0xffff))
+
+#undef __get_rel_dynamic_array_len
+#define __get_rel_dynamic_array_len(field)	\
+		((__entry->__rel_loc_##field >> 16) & 0xffff)
+
+#undef __get_rel_str
+#define __get_rel_str(field) ((char *)__get_rel_dynamic_array(field))
+
+#undef __get_rel_bitmask
+#define __get_rel_bitmask(field) (char *)__get_rel_dynamic_array(field)
+
 #undef __perf_count
 #define __perf_count(c)	(c)
 
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index 9e92f22eb086..485a1d3034a4 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -9,29 +9,63 @@
 #include <linux/netdevice.h>
 #include <linux/tracepoint.h>
 
+#define TRACE_SKB_DROP_REASON					\
+	EM(SKB_DROP_REASON_NOT_SPECIFIED, NOT_SPECIFIED)	\
+	EM(SKB_DROP_REASON_NO_SOCKET, NO_SOCKET)		\
+	EM(SKB_DROP_REASON_PKT_TOO_SMALL, PKT_TOO_SMALL)	\
+	EM(SKB_DROP_REASON_TCP_CSUM, TCP_CSUM)			\
+	EM(SKB_DROP_REASON_SOCKET_FILTER, SOCKET_FILTER)	\
+	EM(SKB_DROP_REASON_UDP_CSUM, UDP_CSUM)			\
+	EM(SKB_DROP_REASON_NETFILTER_DROP, NETFILTER_DROP)	\
+	EM(SKB_DROP_REASON_OTHERHOST, OTHERHOST)		\
+	EM(SKB_DROP_REASON_IP_CSUM, IP_CSUM)			\
+	EM(SKB_DROP_REASON_IP_INHDR, IP_INHDR)			\
+	EM(SKB_DROP_REASON_IP_RPFILTER, IP_RPFILTER)		\
+	EM(SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST,		\
+	   UNICAST_IN_L2_MULTICAST)				\
+	EMe(SKB_DROP_REASON_MAX, MAX)
+
+#undef EM
+#undef EMe
+
+#define EM(a, b)	TRACE_DEFINE_ENUM(a);
+#define EMe(a, b)	TRACE_DEFINE_ENUM(a);
+
+TRACE_SKB_DROP_REASON
+
+#undef EM
+#undef EMe
+#define EM(a, b)	{ a, #b },
+#define EMe(a, b)	{ a, #b }
+
 /*
  * Tracepoint for free an sk_buff:
  */
 TRACE_EVENT(kfree_skb,
 
-	TP_PROTO(struct sk_buff *skb, void *location),
+	TP_PROTO(struct sk_buff *skb, void *location,
+		 enum skb_drop_reason reason),
 
-	TP_ARGS(skb, location),
+	TP_ARGS(skb, location, reason),
 
 	TP_STRUCT__entry(
-		__field(	void *,		skbaddr		)
-		__field(	void *,		location	)
-		__field(	unsigned short,	protocol	)
+		__field(void *,		skbaddr)
+		__field(void *,		location)
+		__field(unsigned short,	protocol)
+		__field(enum skb_drop_reason,	reason)
 	),
 
 	TP_fast_assign(
 		__entry->skbaddr = skb;
 		__entry->location = location;
 		__entry->protocol = ntohs(skb->protocol);
+		__entry->reason = reason;
 	),
 
-	TP_printk("skbaddr=%p protocol=%u location=%p",
-		__entry->skbaddr, __entry->protocol, __entry->location)
+	TP_printk("skbaddr=%p protocol=%u location=%p reason: %s",
+		  __entry->skbaddr, __entry->protocol, __entry->location,
+		  __print_symbolic(__entry->reason,
+				   TRACE_SKB_DROP_REASON))
 );
 
 TRACE_EVENT(consume_skb,
diff --git a/include/trace/events/sock.h b/include/trace/events/sock.h
index 12c315782766..777ee6cbe933 100644
--- a/include/trace/events/sock.h
+++ b/include/trace/events/sock.h
@@ -98,7 +98,7 @@ TRACE_EVENT(sock_exceed_buf_limit,
 
 	TP_STRUCT__entry(
 		__array(char, name, 32)
-		__field(long *, sysctl_mem)
+		__array(long, sysctl_mem, 3)
 		__field(long, allocated)
 		__field(int, sysctl_rmem)
 		__field(int, rmem_alloc)
@@ -110,7 +110,9 @@ TRACE_EVENT(sock_exceed_buf_limit,
 
 	TP_fast_assign(
 		strncpy(__entry->name, prot->name, 32);
-		__entry->sysctl_mem = prot->sysctl_mem;
+		__entry->sysctl_mem[0] = READ_ONCE(prot->sysctl_mem[0]);
+		__entry->sysctl_mem[1] = READ_ONCE(prot->sysctl_mem[1]);
+		__entry->sysctl_mem[2] = READ_ONCE(prot->sysctl_mem[2]);
 		__entry->allocated = allocated;
 		__entry->sysctl_rmem = sk_get_rmem0(sk, prot);
 		__entry->rmem_alloc = atomic_read(&sk->sk_rmem_alloc);
diff --git a/include/trace/events/spmi.h b/include/trace/events/spmi.h
index 8b60efe18ba6..a6819fd85cdf 100644
--- a/include/trace/events/spmi.h
+++ b/include/trace/events/spmi.h
@@ -21,15 +21,15 @@ TRACE_EVENT(spmi_write_begin,
 		__field		( u8,         sid       )
 		__field		( u16,        addr      )
 		__field		( u8,         len       )
-		__dynamic_array	( u8,   buf,  len + 1   )
+		__dynamic_array	( u8,   buf,  len       )
 	),
 
 	TP_fast_assign(
 		__entry->opcode = opcode;
 		__entry->sid    = sid;
 		__entry->addr   = addr;
-		__entry->len    = len + 1;
-		memcpy(__get_dynamic_array(buf), buf, len + 1);
+		__entry->len    = len;
+		memcpy(__get_dynamic_array(buf), buf, len);
 	),
 
 	TP_printk("opc=%d sid=%02d addr=0x%04x len=%d buf=0x[%*phD]",
@@ -92,7 +92,7 @@ TRACE_EVENT(spmi_read_end,
 		__field		( u16,        addr      )
 		__field		( int,        ret       )
 		__field		( u8,         len       )
-		__dynamic_array	( u8,   buf,  len + 1   )
+		__dynamic_array	( u8,   buf,  len       )
 	),
 
 	TP_fast_assign(
@@ -100,8 +100,8 @@ TRACE_EVENT(spmi_read_end,
 		__entry->sid    = sid;
 		__entry->addr   = addr;
 		__entry->ret    = ret;
-		__entry->len    = len + 1;
-		memcpy(__get_dynamic_array(buf), buf, len + 1);
+		__entry->len    = len;
+		memcpy(__get_dynamic_array(buf), buf, len);
 	),
 
 	TP_printk("opc=%d sid=%02d addr=0x%04x ret=%d len=%02d buf=0x[%*phD]",
diff --git a/include/trace/perf.h b/include/trace/perf.h
index dbc6c74defc3..5d48c46a3008 100644
--- a/include/trace/perf.h
+++ b/include/trace/perf.h
@@ -21,6 +21,23 @@
 #undef __get_bitmask
 #define __get_bitmask(field) (char *)__get_dynamic_array(field)
 
+#undef __get_rel_dynamic_array
+#define __get_rel_dynamic_array(field)	\
+		((void *)__entry +					\
+		 offsetof(typeof(*__entry), __rel_loc_##field) +	\
+		 sizeof(__entry->__rel_loc_##field) +			\
+		 (__entry->__rel_loc_##field & 0xffff))
+
+#undef __get_rel_dynamic_array_len
+#define __get_rel_dynamic_array_len(field)	\
+		((__entry->__rel_loc_##field >> 16) & 0xffff)
+
+#undef __get_rel_str
+#define __get_rel_str(field) ((char *)__get_rel_dynamic_array(field))
+
+#undef __get_rel_bitmask
+#define __get_rel_bitmask(field) (char *)__get_rel_dynamic_array(field)
+
 #undef __perf_count
 #define __perf_count(c)	(__count = (c))
 
diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h
index 08810a463880..a77b690709cc 100644
--- a/include/trace/trace_events.h
+++ b/include/trace/trace_events.h
@@ -108,6 +108,18 @@ TRACE_MAKE_SYSTEM_STR();
 #undef __bitmask
 #define __bitmask(item, nr_bits) __dynamic_array(char, item, -1)
 
+#undef __rel_dynamic_array
+#define __rel_dynamic_array(type, item, len) u32 __rel_loc_##item;
+
+#undef __rel_string
+#define __rel_string(item, src) __rel_dynamic_array(char, item, -1)
+
+#undef __rel_string_len
+#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1)
+
+#undef __rel_bitmask
+#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(char, item, -1)
+
 #undef TP_STRUCT__entry
 #define TP_STRUCT__entry(args...) args
 
@@ -116,7 +128,7 @@ TRACE_MAKE_SYSTEM_STR();
 	struct trace_event_raw_##name {					\
 		struct trace_entry	ent;				\
 		tstruct							\
-		char			__data[0];			\
+		char			__data[];			\
 	};								\
 									\
 	static struct trace_event_class event_class_##name;
@@ -200,11 +212,23 @@ TRACE_MAKE_SYSTEM_STR();
 #undef __string
 #define __string(item, src) __dynamic_array(char, item, -1)
 
+#undef __bitmask
+#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1)
+
 #undef __string_len
 #define __string_len(item, src, len) __dynamic_array(char, item, -1)
 
-#undef __bitmask
-#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1)
+#undef __rel_dynamic_array
+#define __rel_dynamic_array(type, item, len)	u32 item;
+
+#undef __rel_string
+#define __rel_string(item, src) __rel_dynamic_array(char, item, -1)
+
+#undef __rel_string_len
+#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1)
+
+#undef __rel_bitmask
+#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, -1)
 
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
@@ -293,6 +317,20 @@ TRACE_MAKE_SYSTEM_STR();
 #undef __get_str
 #define __get_str(field) ((char *)__get_dynamic_array(field))
 
+#undef __get_rel_dynamic_array
+#define __get_rel_dynamic_array(field)					\
+		((void *)__entry + 					\
+		 offsetof(typeof(*__entry), __rel_loc_##field) +	\
+		 sizeof(__entry->__rel_loc_##field) +			\
+		 (__entry->__rel_loc_##field & 0xffff))
+
+#undef __get_rel_dynamic_array_len
+#define __get_rel_dynamic_array_len(field)	\
+		((__entry->__rel_loc_##field >> 16) & 0xffff)
+
+#undef __get_rel_str
+#define __get_rel_str(field) ((char *)__get_rel_dynamic_array(field))
+
 #undef __get_bitmask
 #define __get_bitmask(field)						\
 	({								\
@@ -302,6 +340,15 @@ TRACE_MAKE_SYSTEM_STR();
 		trace_print_bitmask_seq(p, __bitmask, __bitmask_size);	\
 	})
 
+#undef __get_rel_bitmask
+#define __get_rel_bitmask(field)						\
+	({								\
+		void *__bitmask = __get_rel_dynamic_array(field);		\
+		unsigned int __bitmask_size;				\
+		__bitmask_size = __get_rel_dynamic_array_len(field);	\
+		trace_print_bitmask_seq(p, __bitmask, __bitmask_size);	\
+	})
+
 #undef __print_flags
 #define __print_flags(flag, delim, flag_array...)			\
 	({								\
@@ -432,16 +479,18 @@ static struct trace_event_functions trace_event_type_funcs_##call = {	\
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
+#define ALIGN_STRUCTFIELD(type) ((int)(offsetof(struct {char a; type b;}, b)))
+
 #undef __field_ext
 #define __field_ext(_type, _item, _filter_type) {			\
 	.type = #_type, .name = #_item,					\
-	.size = sizeof(_type), .align = __alignof__(_type),		\
+	.size = sizeof(_type), .align = ALIGN_STRUCTFIELD(_type),	\
 	.is_signed = is_signed_type(_type), .filter_type = _filter_type },
 
 #undef __field_struct_ext
 #define __field_struct_ext(_type, _item, _filter_type) {		\
 	.type = #_type, .name = #_item,					\
-	.size = sizeof(_type), .align = __alignof__(_type),		\
+	.size = sizeof(_type), .align = ALIGN_STRUCTFIELD(_type),	\
 	0, .filter_type = _filter_type },
 
 #undef __field
@@ -453,7 +502,7 @@ static struct trace_event_functions trace_event_type_funcs_##call = {	\
 #undef __array
 #define __array(_type, _item, _len) {					\
 	.type = #_type"["__stringify(_len)"]", .name = #_item,		\
-	.size = sizeof(_type[_len]), .align = __alignof__(_type),	\
+	.size = sizeof(_type[_len]), .align = ALIGN_STRUCTFIELD(_type),	\
 	.is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER },
 
 #undef __dynamic_array
@@ -471,6 +520,21 @@ static struct trace_event_functions trace_event_type_funcs_##call = {	\
 #undef __bitmask
 #define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1)
 
+#undef __rel_dynamic_array
+#define __rel_dynamic_array(_type, _item, _len) {			\
+	.type = "__rel_loc " #_type "[]", .name = #_item,		\
+	.size = 4, .align = 4,						\
+	.is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER },
+
+#undef __rel_string
+#define __rel_string(item, src) __rel_dynamic_array(char, item, -1)
+
+#undef __rel_string_len
+#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1)
+
+#undef __rel_bitmask
+#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, -1)
+
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, func, print)	\
 static struct trace_event_fields trace_event_fields_##call[] = {	\
@@ -519,6 +583,22 @@ static struct trace_event_fields trace_event_fields_##call[] = {	\
 #undef __string_len
 #define __string_len(item, src, len) __dynamic_array(char, item, (len) + 1)
 
+#undef __rel_dynamic_array
+#define __rel_dynamic_array(type, item, len)				\
+	__item_length = (len) * sizeof(type);				\
+	__data_offsets->item = __data_size +				\
+			       offsetof(typeof(*entry), __data) -	\
+			       offsetof(typeof(*entry), __rel_loc_##item) -	\
+			       sizeof(u32);				\
+	__data_offsets->item |= __item_length << 16;			\
+	__data_size += __item_length;
+
+#undef __rel_string
+#define __rel_string(item, src) __rel_dynamic_array(char, item,			\
+		    strlen((src) ? (const char *)(src) : "(null)") + 1)
+
+#undef __rel_string_len
+#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, (len) + 1)
 /*
  * __bitmask_size_in_bytes_raw is the number of bytes needed to hold
  * num_possible_cpus().
@@ -542,6 +622,10 @@ static struct trace_event_fields trace_event_fields_##call[] = {	\
 #define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item,	\
 					 __bitmask_size_in_longs(nr_bits))
 
+#undef __rel_bitmask
+#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item,	\
+					 __bitmask_size_in_longs(nr_bits))
+
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
 static inline notrace int trace_event_get_offsets_##call(		\
@@ -706,6 +790,37 @@ static inline notrace int trace_event_get_offsets_##call(		\
 #define __assign_bitmask(dst, src, nr_bits)					\
 	memcpy(__get_bitmask(dst), (src), __bitmask_size_in_bytes(nr_bits))
 
+#undef __rel_dynamic_array
+#define __rel_dynamic_array(type, item, len)				\
+	__entry->__rel_loc_##item = __data_offsets.item;
+
+#undef __rel_string
+#define __rel_string(item, src) __rel_dynamic_array(char, item, -1)
+
+#undef __rel_string_len
+#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1)
+
+#undef __assign_rel_str
+#define __assign_rel_str(dst, src)					\
+	strcpy(__get_rel_str(dst), (src) ? (const char *)(src) : "(null)");
+
+#undef __assign_rel_str_len
+#define __assign_rel_str_len(dst, src, len)				\
+	do {								\
+		memcpy(__get_rel_str(dst), (src), (len));		\
+		__get_rel_str(dst)[len] = '\0';				\
+	} while (0)
+
+#undef __rel_bitmask
+#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, -1)
+
+#undef __get_rel_bitmask
+#define __get_rel_bitmask(field) (char *)__get_rel_dynamic_array(field)
+
+#undef __assign_rel_bitmask
+#define __assign_rel_bitmask(dst, src, nr_bits)					\
+	memcpy(__get_rel_bitmask(dst), (src), __bitmask_size_in_bytes(nr_bits))
+
 #undef TP_fast_assign
 #define TP_fast_assign(args...) args
 
@@ -770,6 +885,10 @@ static inline void ftrace_test_probe_##call(void)			\
 #undef __get_dynamic_array_len
 #undef __get_str
 #undef __get_bitmask
+#undef __get_rel_dynamic_array
+#undef __get_rel_dynamic_array_len
+#undef __get_rel_str
+#undef __get_rel_bitmask
 #undef __print_array
 #undef __print_hex_dump
 
diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index 28c4c4034487..e17b2635cad3 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -1363,11 +1363,11 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier)
 #define AMD_FMT_MOD_PIPE_MASK 0x7
 
 #define AMD_FMT_MOD_SET(field, value) \
-	((uint64_t)(value) << AMD_FMT_MOD_##field##_SHIFT)
+	((__u64)(value) << AMD_FMT_MOD_##field##_SHIFT)
 #define AMD_FMT_MOD_GET(field, value) \
 	(((value) >> AMD_FMT_MOD_##field##_SHIFT) & AMD_FMT_MOD_##field##_MASK)
 #define AMD_FMT_MOD_CLEAR(field) \
-	(~((uint64_t)AMD_FMT_MOD_##field##_MASK << AMD_FMT_MOD_##field##_SHIFT))
+	(~((__u64)AMD_FMT_MOD_##field##_MASK << AMD_FMT_MOD_##field##_SHIFT))
 
 /* Amphion tiled layout */
 
diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h
index e1c4c732aaba..5416f1f1a77a 100644
--- a/include/uapi/linux/btrfs_tree.h
+++ b/include/uapi/linux/btrfs_tree.h
@@ -146,7 +146,9 @@
 
 /*
  * dir items are the name -> inode pointers in a directory.  There is one
- * for every name in a directory.
+ * for every name in a directory.  BTRFS_DIR_LOG_ITEM_KEY is no longer used
+ * but it's still defined here for documentation purposes and to help avoid
+ * having its numerical value reused in the future.
  */
 #define BTRFS_DIR_LOG_ITEM_KEY  60
 #define BTRFS_DIR_LOG_INDEX_KEY 72
diff --git a/include/uapi/linux/can/error.h b/include/uapi/linux/can/error.h
index 34633283de64..a1000cb63063 100644
--- a/include/uapi/linux/can/error.h
+++ b/include/uapi/linux/can/error.h
@@ -120,6 +120,9 @@
 #define CAN_ERR_TRX_CANL_SHORT_TO_GND  0x70 /* 0111 0000 */
 #define CAN_ERR_TRX_CANL_SHORT_TO_CANH 0x80 /* 1000 0000 */
 
-/* controller specific additional information / data[5..7] */
+/* data[5] is reserved (do not use) */
+
+/* TX error counter / data[6] */
+/* RX error counter / data[7] */
 
 #endif /* _UAPI_CAN_ERROR_H */
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index e94d1fa554cb..07871c8a0601 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -753,11 +753,13 @@ enum nft_dynset_attributes {
  * @NFT_PAYLOAD_LL_HEADER: link layer header
  * @NFT_PAYLOAD_NETWORK_HEADER: network header
  * @NFT_PAYLOAD_TRANSPORT_HEADER: transport header
+ * @NFT_PAYLOAD_INNER_HEADER: inner header / payload
  */
 enum nft_payload_bases {
 	NFT_PAYLOAD_LL_HEADER,
 	NFT_PAYLOAD_NETWORK_HEADER,
 	NFT_PAYLOAD_TRANSPORT_HEADER,
+	NFT_PAYLOAD_INNER_HEADER,
 };
 
 /**
diff --git a/include/uapi/linux/netfilter/xt_IDLETIMER.h b/include/uapi/linux/netfilter/xt_IDLETIMER.h
index 49ddcdc61c09..7bfb31a66fc9 100644
--- a/include/uapi/linux/netfilter/xt_IDLETIMER.h
+++ b/include/uapi/linux/netfilter/xt_IDLETIMER.h
@@ -1,6 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
 /*
- * linux/include/linux/netfilter/xt_IDLETIMER.h
- *
  * Header file for Xtables timer target module.
  *
  * Copyright (C) 2004, 2010 Nokia Corporation
@@ -10,20 +9,6 @@
  * by Luciano Coelho <luciano.coelho@nokia.com>
  *
  * Contact: Luciano Coelho <luciano.coelho@nokia.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
  */
 
 #ifndef _XT_IDLETIMER_H
diff --git a/include/uapi/linux/omap3isp.h b/include/uapi/linux/omap3isp.h
index 87b55755f4ff..d9db7ad43890 100644
--- a/include/uapi/linux/omap3isp.h
+++ b/include/uapi/linux/omap3isp.h
@@ -162,6 +162,7 @@ struct omap3isp_h3a_aewb_config {
  * struct omap3isp_stat_data - Statistic data sent to or received from user
  * @ts: Timestamp of returned framestats.
  * @buf: Pointer to pass to user.
+ * @buf_size: Size of buffer.
  * @frame_number: Frame number of requested stats.
  * @cur_frame: Current frame number being processed.
  * @config_counter: Number of the configuration associated with the data.
@@ -176,10 +177,12 @@ struct omap3isp_stat_data {
 	struct timeval ts;
 #endif
 	void __user *buf;
-	__u32 buf_size;
-	__u16 frame_number;
-	__u16 cur_frame;
-	__u16 config_counter;
+	__struct_group(/* no tag */, frame, /* no attrs */,
+		__u32 buf_size;
+		__u16 frame_number;
+		__u16 cur_frame;
+		__u16 config_counter;
+	);
 };
 
 #ifdef __KERNEL__
@@ -189,10 +192,12 @@ struct omap3isp_stat_data_time32 {
 		__s32	tv_usec;
 	} ts;
 	__u32 buf;
-	__u32 buf_size;
-	__u16 frame_number;
-	__u16 cur_frame;
-	__u16 config_counter;
+	__struct_group(/* no tag */, frame, /* no attrs */,
+		__u32 buf_size;
+		__u16 frame_number;
+		__u16 cur_frame;
+		__u16 config_counter;
+	);
 };
 #endif
 
diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h
index ee8220f8dcf5..7837ba4fe728 100644
--- a/include/uapi/linux/stddef.h
+++ b/include/uapi/linux/stddef.h
@@ -1,6 +1,47 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_STDDEF_H
+#define _UAPI_LINUX_STDDEF_H
+
 #include <linux/compiler_types.h>
 
 #ifndef __always_inline
 #define __always_inline inline
 #endif
+
+/**
+ * __struct_group() - Create a mirrored named and anonyomous struct
+ *
+ * @TAG: The tag name for the named sub-struct (usually empty)
+ * @NAME: The identifier name of the mirrored sub-struct
+ * @ATTRS: Any struct attributes (usually empty)
+ * @MEMBERS: The member declarations for the mirrored structs
+ *
+ * Used to create an anonymous union of two structs with identical layout
+ * and size: one anonymous and one named. The former's members can be used
+ * normally without sub-struct naming, and the latter can be used to
+ * reason about the start, end, and size of the group of struct members.
+ * The named struct can also be explicitly tagged for layer reuse, as well
+ * as both having struct attributes appended.
+ */
+#define __struct_group(TAG, NAME, ATTRS, MEMBERS...) \
+	union { \
+		struct { MEMBERS } ATTRS; \
+		struct TAG { MEMBERS } ATTRS NAME; \
+	}
+
+/**
+ * __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union
+ *
+ * @TYPE: The type of each flexible array element
+ * @NAME: The name of the flexible array member
+ *
+ * In order to have a flexible array member in a union or alone in a
+ * struct, it needs to be wrapped in an anonymous struct with at least 1
+ * named member, but that member can be empty.
+ */
+#define __DECLARE_FLEX_ARRAY(TYPE, NAME)	\
+	struct { \
+		struct { } __empty_ ## NAME; \
+		TYPE NAME[]; \
+	}
+#endif
diff --git a/include/video/of_display_timing.h b/include/video/of_display_timing.h
index e1126a74882a..eff166fdd81b 100644
--- a/include/video/of_display_timing.h
+++ b/include/video/of_display_timing.h
@@ -8,6 +8,8 @@
 #ifndef __LINUX_OF_DISPLAY_TIMING_H
 #define __LINUX_OF_DISPLAY_TIMING_H
 
+#include <linux/errno.h>
+
 struct device_node;
 struct display_timing;
 struct display_timings;
diff --git a/init/main.c b/init/main.c
index cf79b5a766cb..649d9e4201a8 100644
--- a/init/main.c
+++ b/init/main.c
@@ -100,6 +100,7 @@
 #include <linux/kcsan.h>
 #include <linux/init_syscalls.h>
 #include <linux/stackdepot.h>
+#include <linux/randomize_kstack.h>
 #include <net/net_namespace.h>
 
 #include <asm/io.h>
diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c
index 60739d5e3373..c428312938e9 100644
--- a/kernel/audit_fsnotify.c
+++ b/kernel/audit_fsnotify.c
@@ -102,6 +102,7 @@ struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, char *pa
 
 	ret = fsnotify_add_inode_mark(&audit_mark->mark, inode, true);
 	if (ret < 0) {
+		audit_mark->path = NULL;
 		fsnotify_put_mark(&audit_mark->mark);
 		audit_mark = ERR_PTR(ret);
 	}
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 447def540544..88014cd31b28 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -620,6 +620,11 @@ static int bpf_iter_init_array_map(void *priv_data,
 		seq_info->percpu_value_buf = value_buf;
 	}
 
+	/* bpf_iter_attach_map() acquires a map uref, and the uref may be
+	 * released before or in the middle of iterating map elements, so
+	 * acquire an extra map uref for iterator.
+	 */
+	bpf_map_inc_with_uref(map);
 	seq_info->map = map;
 	return 0;
 }
@@ -628,6 +633,7 @@ static void bpf_iter_fini_array_map(void *priv_data)
 {
 	struct bpf_iter_seq_array_map_info *seq_info = priv_data;
 
+	bpf_map_put_with_uref(seq_info->map);
 	kfree(seq_info->percpu_value_buf);
 }
 
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index fe053ffd8932..eb3e787a3a97 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -668,6 +668,62 @@ static struct bpf_prog_list *find_detach_entry(struct list_head *progs,
 }
 
 /**
+ * purge_effective_progs() - After compute_effective_progs fails to alloc new
+ *                           cgrp->bpf.inactive table we can recover by
+ *                           recomputing the array in place.
+ *
+ * @cgrp: The cgroup which descendants to travers
+ * @prog: A program to detach or NULL
+ * @link: A link to detach or NULL
+ * @atype: Type of detach operation
+ */
+static void purge_effective_progs(struct cgroup *cgrp, struct bpf_prog *prog,
+				  struct bpf_cgroup_link *link,
+				  enum cgroup_bpf_attach_type atype)
+{
+	struct cgroup_subsys_state *css;
+	struct bpf_prog_array *progs;
+	struct bpf_prog_list *pl;
+	struct list_head *head;
+	struct cgroup *cg;
+	int pos;
+
+	/* recompute effective prog array in place */
+	css_for_each_descendant_pre(css, &cgrp->self) {
+		struct cgroup *desc = container_of(css, struct cgroup, self);
+
+		if (percpu_ref_is_zero(&desc->bpf.refcnt))
+			continue;
+
+		/* find position of link or prog in effective progs array */
+		for (pos = 0, cg = desc; cg; cg = cgroup_parent(cg)) {
+			if (pos && !(cg->bpf.flags[atype] & BPF_F_ALLOW_MULTI))
+				continue;
+
+			head = &cg->bpf.progs[atype];
+			list_for_each_entry(pl, head, node) {
+				if (!prog_list_prog(pl))
+					continue;
+				if (pl->prog == prog && pl->link == link)
+					goto found;
+				pos++;
+			}
+		}
+
+		/* no link or prog match, skip the cgroup of this layer */
+		continue;
+found:
+		progs = rcu_dereference_protected(
+				desc->bpf.effective[atype],
+				lockdep_is_held(&cgroup_mutex));
+
+		/* Remove the program from the array */
+		WARN_ONCE(bpf_prog_array_delete_safe_at(progs, pos),
+			  "Failed to purge a prog from array at index %d", pos);
+	}
+}
+
+/**
  * __cgroup_bpf_detach() - Detach the program or link from a cgroup, and
  *                         propagate the change to descendants
  * @cgrp: The cgroup which descendants to traverse
@@ -686,7 +742,6 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
 	struct bpf_prog_list *pl;
 	struct list_head *progs;
 	u32 flags;
-	int err;
 
 	atype = to_cgroup_bpf_attach_type(type);
 	if (atype < 0)
@@ -708,9 +763,12 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
 	pl->prog = NULL;
 	pl->link = NULL;
 
-	err = update_effective_progs(cgrp, atype);
-	if (err)
-		goto cleanup;
+	if (update_effective_progs(cgrp, atype)) {
+		/* if update effective array failed replace the prog with a dummy prog*/
+		pl->prog = old_prog;
+		pl->link = link;
+		purge_effective_progs(cgrp, old_prog, link, atype);
+	}
 
 	/* now can actually delete it from this cgroup list */
 	list_del(&pl->node);
@@ -722,12 +780,6 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
 		bpf_prog_put(old_prog);
 	static_branch_dec(&cgroup_bpf_enabled_key[atype]);
 	return 0;
-
-cleanup:
-	/* restore back prog or link */
-	pl->prog = old_prog;
-	pl->link = link;
-	return err;
 }
 
 /* Must be called with cgroup_mutex held to avoid races. */
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 48eb9c329da6..4ce500eac2ef 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -66,11 +66,13 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns
 {
 	u8 *ptr = NULL;
 
-	if (k >= SKF_NET_OFF)
+	if (k >= SKF_NET_OFF) {
 		ptr = skb_network_header(skb) + k - SKF_NET_OFF;
-	else if (k >= SKF_LL_OFF)
+	} else if (k >= SKF_LL_OFF) {
+		if (unlikely(!skb_mac_header_was_set(skb)))
+			return NULL;
 		ptr = skb_mac_header(skb) + k - SKF_LL_OFF;
-
+	}
 	if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb))
 		return ptr;
 
@@ -389,6 +391,13 @@ static int bpf_adj_branches(struct bpf_prog *prog, u32 pos, s32 end_old,
 			i = end_new;
 			insn = prog->insnsi + end_old;
 		}
+		if (bpf_pseudo_func(insn)) {
+			ret = bpf_adj_delta_to_imm(insn, pos, end_old,
+						   end_new, i, probe_pass);
+			if (ret)
+				return ret;
+			continue;
+		}
 		code = insn->code;
 		if ((BPF_CLASS(code) != BPF_JMP &&
 		     BPF_CLASS(code) != BPF_JMP32) ||
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 32471ba02708..47eebb88695e 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -291,12 +291,8 @@ static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key,
 	struct htab_elem *l;
 
 	if (node) {
-		u32 key_size = htab->map.key_size;
-
 		l = container_of(node, struct htab_elem, lru_node);
-		memcpy(l->key, key, key_size);
-		check_and_init_map_value(&htab->map,
-					 l->key + round_up(key_size, 8));
+		memcpy(l->key, key, htab->map.key_size);
 		return l;
 	}
 
@@ -2023,6 +2019,7 @@ static int bpf_iter_init_hash_map(void *priv_data,
 		seq_info->percpu_value_buf = value_buf;
 	}
 
+	bpf_map_inc_with_uref(map);
 	seq_info->map = map;
 	seq_info->htab = container_of(map, struct bpf_htab, map);
 	return 0;
@@ -2032,6 +2029,7 @@ static void bpf_iter_fini_hash_map(void *priv_data)
 {
 	struct bpf_iter_seq_hash_map_info *seq_info = priv_data;
 
+	bpf_map_put_with_uref(seq_info->map);
 	kfree(seq_info->percpu_value_buf);
 }
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 48e02a725563..99ce46f51889 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -4785,7 +4785,7 @@ syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	switch (func_id) {
 	case BPF_FUNC_sys_bpf:
-		return &bpf_sys_bpf_proto;
+		return !perfmon_capable() ? NULL : &bpf_sys_bpf_proto;
 	case BPF_FUNC_btf_find_by_name_kind:
 		return &bpf_btf_find_by_name_kind_proto;
 	case BPF_FUNC_sys_close:
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 25ee8d9572c6..5c9ebcbf6f5f 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -240,12 +240,6 @@ static bool bpf_pseudo_kfunc_call(const struct bpf_insn *insn)
 	       insn->src_reg == BPF_PSEUDO_KFUNC_CALL;
 }
 
-static bool bpf_pseudo_func(const struct bpf_insn *insn)
-{
-	return insn->code == (BPF_LD | BPF_IMM | BPF_DW) &&
-	       insn->src_reg == BPF_PSEUDO_FUNC;
-}
-
 struct bpf_call_arg_meta {
 	struct bpf_map *map_ptr;
 	bool raw_mode;
@@ -1333,6 +1327,21 @@ static void __reg_bound_offset(struct bpf_reg_state *reg)
 	reg->var_off = tnum_or(tnum_clear_subreg(var64_off), var32_off);
 }
 
+static void reg_bounds_sync(struct bpf_reg_state *reg)
+{
+	/* We might have learned new bounds from the var_off. */
+	__update_reg_bounds(reg);
+	/* We might have learned something about the sign bit. */
+	__reg_deduce_bounds(reg);
+	/* We might have learned some bits from the bounds. */
+	__reg_bound_offset(reg);
+	/* Intersecting with the old var_off might have improved our bounds
+	 * slightly, e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc),
+	 * then new var_off is (0; 0x7f...fc) which improves our umax.
+	 */
+	__update_reg_bounds(reg);
+}
+
 static bool __reg32_bound_s64(s32 a)
 {
 	return a >= 0 && a <= S32_MAX;
@@ -1374,16 +1383,8 @@ static void __reg_combine_32_into_64(struct bpf_reg_state *reg)
 		 * so they do not impact tnum bounds calculation.
 		 */
 		__mark_reg64_unbounded(reg);
-		__update_reg_bounds(reg);
 	}
-
-	/* Intersecting with the old var_off might have improved our bounds
-	 * slightly.  e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc),
-	 * then new var_off is (0; 0x7f...fc) which improves our umax.
-	 */
-	__reg_deduce_bounds(reg);
-	__reg_bound_offset(reg);
-	__update_reg_bounds(reg);
+	reg_bounds_sync(reg);
 }
 
 static bool __reg64_bound_s32(s64 a)
@@ -1399,7 +1400,6 @@ static bool __reg64_bound_u32(u64 a)
 static void __reg_combine_64_into_32(struct bpf_reg_state *reg)
 {
 	__mark_reg32_unbounded(reg);
-
 	if (__reg64_bound_s32(reg->smin_value) && __reg64_bound_s32(reg->smax_value)) {
 		reg->s32_min_value = (s32)reg->smin_value;
 		reg->s32_max_value = (s32)reg->smax_value;
@@ -1408,14 +1408,7 @@ static void __reg_combine_64_into_32(struct bpf_reg_state *reg)
 		reg->u32_min_value = (u32)reg->umin_value;
 		reg->u32_max_value = (u32)reg->umax_value;
 	}
-
-	/* Intersecting with the old var_off might have improved our bounds
-	 * slightly.  e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc),
-	 * then new var_off is (0; 0x7f...fc) which improves our umax.
-	 */
-	__reg_deduce_bounds(reg);
-	__reg_bound_offset(reg);
-	__update_reg_bounds(reg);
+	reg_bounds_sync(reg);
 }
 
 /* Mark a register as having a completely unknown (scalar) value. */
@@ -1789,16 +1782,10 @@ static int add_subprog_and_kfunc(struct bpf_verifier_env *env)
 			return -EPERM;
 		}
 
-		if (bpf_pseudo_func(insn)) {
-			ret = add_subprog(env, i + insn->imm + 1);
-			if (ret >= 0)
-				/* remember subprog */
-				insn[1].imm = ret;
-		} else if (bpf_pseudo_call(insn)) {
+		if (bpf_pseudo_func(insn) || bpf_pseudo_call(insn))
 			ret = add_subprog(env, i + insn->imm + 1);
-		} else {
+		else
 			ret = add_kfunc_call(env, insn->imm);
-		}
 
 		if (ret < 0)
 			return ret;
@@ -6054,9 +6041,7 @@ static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type,
 	ret_reg->s32_max_value = meta->msize_max_value;
 	ret_reg->smin_value = -MAX_ERRNO;
 	ret_reg->s32_min_value = -MAX_ERRNO;
-	__reg_deduce_bounds(ret_reg);
-	__reg_bound_offset(ret_reg);
-	__update_reg_bounds(ret_reg);
+	reg_bounds_sync(ret_reg);
 }
 
 static int
@@ -6111,8 +6096,7 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
 	struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx];
 	struct bpf_reg_state *regs = cur_regs(env), *reg;
 	struct bpf_map *map = meta->map_ptr;
-	struct tnum range;
-	u64 val;
+	u64 val, max;
 	int err;
 
 	if (func_id != BPF_FUNC_tail_call)
@@ -6122,10 +6106,11 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
 		return -EINVAL;
 	}
 
-	range = tnum_range(0, map->max_entries - 1);
 	reg = &regs[BPF_REG_3];
+	val = reg->var_off.value;
+	max = map->max_entries;
 
-	if (!register_is_const(reg) || !tnum_in(range, reg->var_off)) {
+	if (!(register_is_const(reg) && val < max)) {
 		bpf_map_key_store(aux, BPF_MAP_KEY_POISON);
 		return 0;
 	}
@@ -6133,8 +6118,6 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
 	err = mark_chain_precision(env, BPF_REG_3);
 	if (err)
 		return err;
-
-	val = reg->var_off.value;
 	if (bpf_map_key_unseen(aux))
 		bpf_map_key_store(aux, val);
 	else if (!bpf_map_key_poisoned(aux) &&
@@ -7216,11 +7199,7 @@ reject:
 
 	if (!check_reg_sane_offset(env, dst_reg, ptr_reg->type))
 		return -EINVAL;
-
-	__update_reg_bounds(dst_reg);
-	__reg_deduce_bounds(dst_reg);
-	__reg_bound_offset(dst_reg);
-
+	reg_bounds_sync(dst_reg);
 	if (sanitize_check_bounds(env, insn, dst_reg) < 0)
 		return -EACCES;
 	if (sanitize_needed(opcode)) {
@@ -7958,10 +7937,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 	/* ALU32 ops are zero extended into 64bit register */
 	if (alu32)
 		zext_32_to_64(dst_reg);
-
-	__update_reg_bounds(dst_reg);
-	__reg_deduce_bounds(dst_reg);
-	__reg_bound_offset(dst_reg);
+	reg_bounds_sync(dst_reg);
 	return 0;
 }
 
@@ -8150,10 +8126,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 							 insn->dst_reg);
 				}
 				zext_32_to_64(dst_reg);
-
-				__update_reg_bounds(dst_reg);
-				__reg_deduce_bounds(dst_reg);
-				__reg_bound_offset(dst_reg);
+				reg_bounds_sync(dst_reg);
 			}
 		} else {
 			/* case: R = imm
@@ -8591,26 +8564,33 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg,
 		return;
 
 	switch (opcode) {
+	/* JEQ/JNE comparison doesn't change the register equivalence.
+	 *
+	 * r1 = r2;
+	 * if (r1 == 42) goto label;
+	 * ...
+	 * label: // here both r1 and r2 are known to be 42.
+	 *
+	 * Hence when marking register as known preserve it's ID.
+	 */
 	case BPF_JEQ:
+		if (is_jmp32) {
+			__mark_reg32_known(true_reg, val32);
+			true_32off = tnum_subreg(true_reg->var_off);
+		} else {
+			___mark_reg_known(true_reg, val);
+			true_64off = true_reg->var_off;
+		}
+		break;
 	case BPF_JNE:
-	{
-		struct bpf_reg_state *reg =
-			opcode == BPF_JEQ ? true_reg : false_reg;
-
-		/* JEQ/JNE comparison doesn't change the register equivalence.
-		 * r1 = r2;
-		 * if (r1 == 42) goto label;
-		 * ...
-		 * label: // here both r1 and r2 are known to be 42.
-		 *
-		 * Hence when marking register as known preserve it's ID.
-		 */
-		if (is_jmp32)
-			__mark_reg32_known(reg, val32);
-		else
-			___mark_reg_known(reg, val);
+		if (is_jmp32) {
+			__mark_reg32_known(false_reg, val32);
+			false_32off = tnum_subreg(false_reg->var_off);
+		} else {
+			___mark_reg_known(false_reg, val);
+			false_64off = false_reg->var_off;
+		}
 		break;
-	}
 	case BPF_JSET:
 		if (is_jmp32) {
 			false_32off = tnum_and(false_32off, tnum_const(~val32));
@@ -8749,21 +8729,8 @@ static void __reg_combine_min_max(struct bpf_reg_state *src_reg,
 							dst_reg->smax_value);
 	src_reg->var_off = dst_reg->var_off = tnum_intersect(src_reg->var_off,
 							     dst_reg->var_off);
-	/* We might have learned new bounds from the var_off. */
-	__update_reg_bounds(src_reg);
-	__update_reg_bounds(dst_reg);
-	/* We might have learned something about the sign bit. */
-	__reg_deduce_bounds(src_reg);
-	__reg_deduce_bounds(dst_reg);
-	/* We might have learned some bits from the bounds. */
-	__reg_bound_offset(src_reg);
-	__reg_bound_offset(dst_reg);
-	/* Intersecting with the old var_off might have improved our bounds
-	 * slightly.  e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc),
-	 * then new var_off is (0; 0x7f...fc) which improves our umax.
-	 */
-	__update_reg_bounds(src_reg);
-	__update_reg_bounds(dst_reg);
+	reg_bounds_sync(src_reg);
+	reg_bounds_sync(dst_reg);
 }
 
 static void reg_combine_min_max(struct bpf_reg_state *true_src,
@@ -9241,7 +9208,8 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
 
 	if (insn->src_reg == BPF_PSEUDO_FUNC) {
 		struct bpf_prog_aux *aux = env->prog->aux;
-		u32 subprogno = insn[1].imm;
+		u32 subprogno = find_subprog(env,
+					     env->insn_idx + insn->imm + 1);
 
 		if (!aux->func_info) {
 			verbose(env, "missing btf func_info\n");
@@ -12411,14 +12379,9 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		return 0;
 
 	for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
-		if (bpf_pseudo_func(insn)) {
-			env->insn_aux_data[i].call_imm = insn->imm;
-			/* subprog is encoded in insn[1].imm */
+		if (!bpf_pseudo_func(insn) && !bpf_pseudo_call(insn))
 			continue;
-		}
 
-		if (!bpf_pseudo_call(insn))
-			continue;
 		/* Upon error here we cannot fall back to interpreter but
 		 * need a hard reject of the program. Thus -EFAULT is
 		 * propagated in any case.
@@ -12439,6 +12402,12 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		env->insn_aux_data[i].call_imm = insn->imm;
 		/* point imm to __bpf_call_base+1 from JITs point of view */
 		insn->imm = 1;
+		if (bpf_pseudo_func(insn))
+			/* jit (e.g. x86_64) may emit fewer instructions
+			 * if it learns a u32 imm is the same as a u64 imm.
+			 * Force a non zero here.
+			 */
+			insn[1].imm = 1;
 	}
 
 	err = bpf_prog_alloc_jited_linfo(prog);
@@ -12474,6 +12443,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		/* Below members will be freed only at prog->aux */
 		func[i]->aux->btf = prog->aux->btf;
 		func[i]->aux->func_info = prog->aux->func_info;
+		func[i]->aux->func_info_cnt = prog->aux->func_info_cnt;
 		func[i]->aux->poke_tab = prog->aux->poke_tab;
 		func[i]->aux->size_poke_tab = prog->aux->size_poke_tab;
 
@@ -12486,9 +12456,6 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 				poke->aux = func[i]->aux;
 		}
 
-		/* Use bpf_prog_F_tag to indicate functions in stack traces.
-		 * Long term would need debug info to populate names
-		 */
 		func[i]->aux->name[0] = 'F';
 		func[i]->aux->stack_depth = env->subprog_info[i].stack_depth;
 		func[i]->jit_requested = 1;
@@ -12522,7 +12489,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		insn = func[i]->insnsi;
 		for (j = 0; j < func[i]->len; j++, insn++) {
 			if (bpf_pseudo_func(insn)) {
-				subprog = insn[1].imm;
+				subprog = insn->off;
 				insn[0].imm = (u32)(long)func[subprog]->bpf_func;
 				insn[1].imm = ((u64)(long)func[subprog]->bpf_func) >> 32;
 				continue;
@@ -12574,7 +12541,8 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 	for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
 		if (bpf_pseudo_func(insn)) {
 			insn[0].imm = env->insn_aux_data[i].call_imm;
-			insn[1].imm = find_subprog(env, i + insn[0].imm + 1);
+			insn[1].imm = insn->off;
+			insn->off = 0;
 			continue;
 		}
 		if (!bpf_pseudo_call(insn))
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 58900dc92ac9..ee8b3d80f19e 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -59,6 +59,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
 	int retval = 0;
 
 	mutex_lock(&cgroup_mutex);
+	cpus_read_lock();
 	percpu_down_write(&cgroup_threadgroup_rwsem);
 	for_each_root(root) {
 		struct cgroup *from_cgrp;
@@ -75,6 +76,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
 			break;
 	}
 	percpu_up_write(&cgroup_threadgroup_rwsem);
+	cpus_read_unlock();
 	mutex_unlock(&cgroup_mutex);
 
 	return retval;
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index de8b4fa1e1fd..75c3881af078 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -764,7 +764,8 @@ struct css_set init_css_set = {
 	.task_iters		= LIST_HEAD_INIT(init_css_set.task_iters),
 	.threaded_csets		= LIST_HEAD_INIT(init_css_set.threaded_csets),
 	.cgrp_links		= LIST_HEAD_INIT(init_css_set.cgrp_links),
-	.mg_preload_node	= LIST_HEAD_INIT(init_css_set.mg_preload_node),
+	.mg_src_preload_node	= LIST_HEAD_INIT(init_css_set.mg_src_preload_node),
+	.mg_dst_preload_node	= LIST_HEAD_INIT(init_css_set.mg_dst_preload_node),
 	.mg_node		= LIST_HEAD_INIT(init_css_set.mg_node),
 
 	/*
@@ -1239,7 +1240,8 @@ static struct css_set *find_css_set(struct css_set *old_cset,
 	INIT_LIST_HEAD(&cset->threaded_csets);
 	INIT_HLIST_NODE(&cset->hlist);
 	INIT_LIST_HEAD(&cset->cgrp_links);
-	INIT_LIST_HEAD(&cset->mg_preload_node);
+	INIT_LIST_HEAD(&cset->mg_src_preload_node);
+	INIT_LIST_HEAD(&cset->mg_dst_preload_node);
 	INIT_LIST_HEAD(&cset->mg_node);
 
 	/* Copy the set of subsystem state objects generated in
@@ -1808,6 +1810,7 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
 
 		if (ss->css_rstat_flush) {
 			list_del_rcu(&css->rstat_css_node);
+			synchronize_rcu();
 			list_add_rcu(&css->rstat_css_node,
 				     &dcgrp->rstat_css_list);
 		}
@@ -2343,6 +2346,47 @@ int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
 EXPORT_SYMBOL_GPL(task_cgroup_path);
 
 /**
+ * cgroup_attach_lock - Lock for ->attach()
+ * @lock_threadgroup: whether to down_write cgroup_threadgroup_rwsem
+ *
+ * cgroup migration sometimes needs to stabilize threadgroups against forks and
+ * exits by write-locking cgroup_threadgroup_rwsem. However, some ->attach()
+ * implementations (e.g. cpuset), also need to disable CPU hotplug.
+ * Unfortunately, letting ->attach() operations acquire cpus_read_lock() can
+ * lead to deadlocks.
+ *
+ * Bringing up a CPU may involve creating and destroying tasks which requires
+ * read-locking threadgroup_rwsem, so threadgroup_rwsem nests inside
+ * cpus_read_lock(). If we call an ->attach() which acquires the cpus lock while
+ * write-locking threadgroup_rwsem, the locking order is reversed and we end up
+ * waiting for an on-going CPU hotplug operation which in turn is waiting for
+ * the threadgroup_rwsem to be released to create new tasks. For more details:
+ *
+ *   http://lkml.kernel.org/r/20220711174629.uehfmqegcwn2lqzu@wubuntu
+ *
+ * Resolve the situation by always acquiring cpus_read_lock() before optionally
+ * write-locking cgroup_threadgroup_rwsem. This allows ->attach() to assume that
+ * CPU hotplug is disabled on entry.
+ */
+static void cgroup_attach_lock(bool lock_threadgroup)
+{
+	cpus_read_lock();
+	if (lock_threadgroup)
+		percpu_down_write(&cgroup_threadgroup_rwsem);
+}
+
+/**
+ * cgroup_attach_unlock - Undo cgroup_attach_lock()
+ * @lock_threadgroup: whether to up_write cgroup_threadgroup_rwsem
+ */
+static void cgroup_attach_unlock(bool lock_threadgroup)
+{
+	if (lock_threadgroup)
+		percpu_up_write(&cgroup_threadgroup_rwsem);
+	cpus_read_unlock();
+}
+
+/**
  * cgroup_migrate_add_task - add a migration target task to a migration context
  * @task: target task
  * @mgctx: target migration context
@@ -2596,21 +2640,27 @@ int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp)
  */
 void cgroup_migrate_finish(struct cgroup_mgctx *mgctx)
 {
-	LIST_HEAD(preloaded);
 	struct css_set *cset, *tmp_cset;
 
 	lockdep_assert_held(&cgroup_mutex);
 
 	spin_lock_irq(&css_set_lock);
 
-	list_splice_tail_init(&mgctx->preloaded_src_csets, &preloaded);
-	list_splice_tail_init(&mgctx->preloaded_dst_csets, &preloaded);
+	list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_src_csets,
+				 mg_src_preload_node) {
+		cset->mg_src_cgrp = NULL;
+		cset->mg_dst_cgrp = NULL;
+		cset->mg_dst_cset = NULL;
+		list_del_init(&cset->mg_src_preload_node);
+		put_css_set_locked(cset);
+	}
 
-	list_for_each_entry_safe(cset, tmp_cset, &preloaded, mg_preload_node) {
+	list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_dst_csets,
+				 mg_dst_preload_node) {
 		cset->mg_src_cgrp = NULL;
 		cset->mg_dst_cgrp = NULL;
 		cset->mg_dst_cset = NULL;
-		list_del_init(&cset->mg_preload_node);
+		list_del_init(&cset->mg_dst_preload_node);
 		put_css_set_locked(cset);
 	}
 
@@ -2652,7 +2702,7 @@ void cgroup_migrate_add_src(struct css_set *src_cset,
 
 	src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root);
 
-	if (!list_empty(&src_cset->mg_preload_node))
+	if (!list_empty(&src_cset->mg_src_preload_node))
 		return;
 
 	WARN_ON(src_cset->mg_src_cgrp);
@@ -2663,7 +2713,7 @@ void cgroup_migrate_add_src(struct css_set *src_cset,
 	src_cset->mg_src_cgrp = src_cgrp;
 	src_cset->mg_dst_cgrp = dst_cgrp;
 	get_css_set(src_cset);
-	list_add_tail(&src_cset->mg_preload_node, &mgctx->preloaded_src_csets);
+	list_add_tail(&src_cset->mg_src_preload_node, &mgctx->preloaded_src_csets);
 }
 
 /**
@@ -2688,7 +2738,7 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx)
 
 	/* look up the dst cset for each src cset and link it to src */
 	list_for_each_entry_safe(src_cset, tmp_cset, &mgctx->preloaded_src_csets,
-				 mg_preload_node) {
+				 mg_src_preload_node) {
 		struct css_set *dst_cset;
 		struct cgroup_subsys *ss;
 		int ssid;
@@ -2707,7 +2757,7 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx)
 		if (src_cset == dst_cset) {
 			src_cset->mg_src_cgrp = NULL;
 			src_cset->mg_dst_cgrp = NULL;
-			list_del_init(&src_cset->mg_preload_node);
+			list_del_init(&src_cset->mg_src_preload_node);
 			put_css_set(src_cset);
 			put_css_set(dst_cset);
 			continue;
@@ -2715,8 +2765,8 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx)
 
 		src_cset->mg_dst_cset = dst_cset;
 
-		if (list_empty(&dst_cset->mg_preload_node))
-			list_add_tail(&dst_cset->mg_preload_node,
+		if (list_empty(&dst_cset->mg_dst_preload_node))
+			list_add_tail(&dst_cset->mg_dst_preload_node,
 				      &mgctx->preloaded_dst_csets);
 		else
 			put_css_set(dst_cset);
@@ -2812,8 +2862,7 @@ int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader,
 }
 
 struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup,
-					     bool *locked)
-	__acquires(&cgroup_threadgroup_rwsem)
+					     bool *threadgroup_locked)
 {
 	struct task_struct *tsk;
 	pid_t pid;
@@ -2830,12 +2879,8 @@ struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup,
 	 * Therefore, we can skip the global lock.
 	 */
 	lockdep_assert_held(&cgroup_mutex);
-	if (pid || threadgroup) {
-		percpu_down_write(&cgroup_threadgroup_rwsem);
-		*locked = true;
-	} else {
-		*locked = false;
-	}
+	*threadgroup_locked = pid || threadgroup;
+	cgroup_attach_lock(*threadgroup_locked);
 
 	rcu_read_lock();
 	if (pid) {
@@ -2866,17 +2911,14 @@ struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup,
 	goto out_unlock_rcu;
 
 out_unlock_threadgroup:
-	if (*locked) {
-		percpu_up_write(&cgroup_threadgroup_rwsem);
-		*locked = false;
-	}
+	cgroup_attach_unlock(*threadgroup_locked);
+	*threadgroup_locked = false;
 out_unlock_rcu:
 	rcu_read_unlock();
 	return tsk;
 }
 
-void cgroup_procs_write_finish(struct task_struct *task, bool locked)
-	__releases(&cgroup_threadgroup_rwsem)
+void cgroup_procs_write_finish(struct task_struct *task, bool threadgroup_locked)
 {
 	struct cgroup_subsys *ss;
 	int ssid;
@@ -2884,8 +2926,8 @@ void cgroup_procs_write_finish(struct task_struct *task, bool locked)
 	/* release reference from cgroup_procs_write_start() */
 	put_task_struct(task);
 
-	if (locked)
-		percpu_up_write(&cgroup_threadgroup_rwsem);
+	cgroup_attach_unlock(threadgroup_locked);
+
 	for_each_subsys(ss, ssid)
 		if (ss->post_attach)
 			ss->post_attach();
@@ -2940,12 +2982,11 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 	struct cgroup_subsys_state *d_css;
 	struct cgroup *dsct;
 	struct css_set *src_cset;
+	bool has_tasks;
 	int ret;
 
 	lockdep_assert_held(&cgroup_mutex);
 
-	percpu_down_write(&cgroup_threadgroup_rwsem);
-
 	/* look up all csses currently attached to @cgrp's subtree */
 	spin_lock_irq(&css_set_lock);
 	cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) {
@@ -2956,13 +2997,23 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 	}
 	spin_unlock_irq(&css_set_lock);
 
+	/*
+	 * We need to write-lock threadgroup_rwsem while migrating tasks.
+	 * However, if there are no source csets for @cgrp, changing its
+	 * controllers isn't gonna produce any task migrations and the
+	 * write-locking can be skipped safely.
+	 */
+	has_tasks = !list_empty(&mgctx.preloaded_src_csets);
+	cgroup_attach_lock(has_tasks);
+
 	/* NULL dst indicates self on default hierarchy */
 	ret = cgroup_migrate_prepare_dst(&mgctx);
 	if (ret)
 		goto out_finish;
 
 	spin_lock_irq(&css_set_lock);
-	list_for_each_entry(src_cset, &mgctx.preloaded_src_csets, mg_preload_node) {
+	list_for_each_entry(src_cset, &mgctx.preloaded_src_csets,
+			    mg_src_preload_node) {
 		struct task_struct *task, *ntask;
 
 		/* all tasks in src_csets need to be migrated */
@@ -2974,7 +3025,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 	ret = cgroup_migrate_execute(&mgctx);
 out_finish:
 	cgroup_migrate_finish(&mgctx);
-	percpu_up_write(&cgroup_threadgroup_rwsem);
+	cgroup_attach_unlock(has_tasks);
 	return ret;
 }
 
@@ -4922,13 +4973,13 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
 	struct task_struct *task;
 	const struct cred *saved_cred;
 	ssize_t ret;
-	bool locked;
+	bool threadgroup_locked;
 
 	dst_cgrp = cgroup_kn_lock_live(of->kn, false);
 	if (!dst_cgrp)
 		return -ENODEV;
 
-	task = cgroup_procs_write_start(buf, threadgroup, &locked);
+	task = cgroup_procs_write_start(buf, threadgroup, &threadgroup_locked);
 	ret = PTR_ERR_OR_ZERO(task);
 	if (ret)
 		goto out_unlock;
@@ -4954,7 +5005,7 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
 	ret = cgroup_attach_task(dst_cgrp, task, threadgroup);
 
 out_finish:
-	cgroup_procs_write_finish(task, locked);
+	cgroup_procs_write_finish(task, threadgroup_locked);
 out_unlock:
 	cgroup_kn_unlock(of->kn);
 
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 31f94c6ea0a5..3213d3c8ea0a 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -2199,7 +2199,7 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
 		goto out_unlock;
 
 	cgroup_taskset_for_each(task, css, tset) {
-		ret = task_can_attach(task, cs->cpus_allowed);
+		ret = task_can_attach(task, cs->effective_cpus);
 		if (ret)
 			goto out_unlock;
 		ret = security_task_setscheduler(task);
@@ -2249,7 +2249,7 @@ static void cpuset_attach(struct cgroup_taskset *tset)
 	cgroup_taskset_first(tset, &css);
 	cs = css_cs(css);
 
-	cpus_read_lock();
+	lockdep_assert_cpus_held();	/* see cgroup_attach_lock() */
 	percpu_down_write(&cpuset_rwsem);
 
 	guarantee_online_mems(cs, &cpuset_attach_nodemask_to);
@@ -2303,7 +2303,6 @@ static void cpuset_attach(struct cgroup_taskset *tset)
 		wake_up(&cpuset_attach_wq);
 
 	percpu_up_write(&cpuset_rwsem);
-	cpus_read_unlock();
 }
 
 /* The various types of files and directories in a cpuset file system */
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 2ee5419649ed..018f140aaaf4 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -435,7 +435,10 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size
 	}
 }
 
-#define slot_addr(start, idx)	((start) + ((idx) << IO_TLB_SHIFT))
+static inline phys_addr_t slot_addr(phys_addr_t start, phys_addr_t idx)
+{
+	return start + (idx << IO_TLB_SHIFT);
+}
 
 /*
  * Carefully handle integer overflow which can occur when boundary_mask == ~0UL.
@@ -551,7 +554,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
 	int index;
 	phys_addr_t tlb_addr;
 
-	if (!mem)
+	if (!mem || !mem->nslabs)
 		panic("Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer");
 
 	if (mem_encrypt_active())
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index d5a61d565ad5..998bdb7b8bf7 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -124,7 +124,7 @@ static __always_inline void __exit_to_user_mode(void)
 {
 	instrumentation_begin();
 	trace_hardirqs_on_prepare();
-	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+	lockdep_hardirqs_on_prepare();
 	instrumentation_end();
 
 	user_enter_irqoff();
@@ -412,7 +412,7 @@ noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state)
 			instrumentation_begin();
 			/* Tell the tracer that IRET will enable interrupts */
 			trace_hardirqs_on_prepare();
-			lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+			lockdep_hardirqs_on_prepare();
 			instrumentation_end();
 			rcu_irq_exit();
 			lockdep_hardirqs_on(CALLER_ADDR0);
@@ -465,7 +465,7 @@ void noinstr irqentry_nmi_exit(struct pt_regs *regs, irqentry_state_t irq_state)
 	ftrace_nmi_exit();
 	if (irq_state.lockdep) {
 		trace_hardirqs_on_prepare();
-		lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+		lockdep_hardirqs_on_prepare();
 	}
 	instrumentation_end();
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index d7e05d937560..c6c7a4d80573 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6355,10 +6355,10 @@ again:
 
 		if (!atomic_inc_not_zero(&event->rb->mmap_count)) {
 			/*
-			 * Raced against perf_mmap_close() through
-			 * perf_event_set_output(). Try again, hope for better
-			 * luck.
+			 * Raced against perf_mmap_close(); remove the
+			 * event and try again.
 			 */
+			ring_buffer_attach(event, NULL);
 			mutex_unlock(&event->mmap_mutex);
 			goto again;
 		}
@@ -11892,14 +11892,25 @@ err_size:
 	goto out;
 }
 
+static void mutex_lock_double(struct mutex *a, struct mutex *b)
+{
+	if (b < a)
+		swap(a, b);
+
+	mutex_lock(a);
+	mutex_lock_nested(b, SINGLE_DEPTH_NESTING);
+}
+
 static int
 perf_event_set_output(struct perf_event *event, struct perf_event *output_event)
 {
 	struct perf_buffer *rb = NULL;
 	int ret = -EINVAL;
 
-	if (!output_event)
+	if (!output_event) {
+		mutex_lock(&event->mmap_mutex);
 		goto set;
+	}
 
 	/* don't allow circular references */
 	if (event == output_event)
@@ -11937,8 +11948,15 @@ perf_event_set_output(struct perf_event *event, struct perf_event *output_event)
 	    event->pmu != output_event->pmu)
 		goto out;
 
+	/*
+	 * Hold both mmap_mutex to serialize against perf_mmap_close().  Since
+	 * output_event is already on rb->event_list, and the list iteration
+	 * restarts after every removal, it is guaranteed this new event is
+	 * observed *OR* if output_event is already removed, it's guaranteed we
+	 * observe !rb->mmap_count.
+	 */
+	mutex_lock_double(&event->mmap_mutex, &output_event->mmap_mutex);
 set:
-	mutex_lock(&event->mmap_mutex);
 	/* Can't redirect output if we've got an active mmap() */
 	if (atomic_read(&event->mmap_count))
 		goto unlock;
@@ -11948,6 +11966,12 @@ set:
 		rb = ring_buffer_get(output_event);
 		if (!rb)
 			goto unlock;
+
+		/* did we race against perf_mmap_close() */
+		if (!atomic_read(&rb->mmap_count)) {
+			ring_buffer_put(rb);
+			goto unlock;
+		}
 	}
 
 	ring_buffer_attach(event, rb);
@@ -11955,20 +11979,13 @@ set:
 	ret = 0;
 unlock:
 	mutex_unlock(&event->mmap_mutex);
+	if (output_event)
+		mutex_unlock(&output_event->mmap_mutex);
 
 out:
 	return ret;
 }
 
-static void mutex_lock_double(struct mutex *a, struct mutex *b)
-{
-	if (b < a)
-		swap(a, b);
-
-	mutex_lock(a);
-	mutex_lock_nested(b, SINGLE_DEPTH_NESTING);
-}
-
 static int perf_event_set_clock(struct perf_event *event, clockid_t clk_id)
 {
 	bool nmi_safe = false;
diff --git a/kernel/exit.c b/kernel/exit.c
index 91a43e57a32e..aefe7445508d 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -796,7 +796,7 @@ void __noreturn do_exit(long code)
 
 #ifdef CONFIG_POSIX_TIMERS
 		hrtimer_cancel(&tsk->signal->real_timer);
-		exit_itimers(tsk->signal);
+		exit_itimers(tsk);
 #endif
 		if (tsk->mm)
 			setmax_mm_hiwater_rss(&tsk->signal->maxrss, tsk->mm);
diff --git a/kernel/fork.c b/kernel/fork.c
index 89475c994ca9..908ba3c93893 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1153,6 +1153,7 @@ void mmput_async(struct mm_struct *mm)
 		schedule_work(&mm->async_put_work);
 	}
 }
+EXPORT_SYMBOL_GPL(mmput_async);
 #endif
 
 /**
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index fbc54c2a7f23..00d58588ea95 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -82,6 +82,7 @@ config IRQ_FASTEOI_HIERARCHY_HANDLERS
 # Generic IRQ IPI support
 config GENERIC_IRQ_IPI
 	bool
+	depends on SMP
 	select IRQ_DOMAIN_HIERARCHY
 
 # Generic MSI interrupt support
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index a98bcfc4be7b..f3920374f71c 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -1516,7 +1516,8 @@ int irq_chip_request_resources_parent(struct irq_data *data)
 	if (data->chip->irq_request_resources)
 		return data->chip->irq_request_resources(data);
 
-	return -ENOSYS;
+	/* no error on missing optional irq_chip::irq_request_resources */
+	return 0;
 }
 EXPORT_SYMBOL_GPL(irq_chip_request_resources_parent);
 
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 4d8fc65cf38f..035e3038c4de 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -910,6 +910,8 @@ struct irq_desc *__irq_resolve_mapping(struct irq_domain *domain,
 			data = irq_domain_get_irq_data(domain, hwirq);
 			if (data && data->hwirq == hwirq)
 				desc = irq_data_to_desc(data);
+			if (irq && desc)
+				*irq = hwirq;
 		}
 
 		return desc;
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index e289e60ba3ad..f7a4fd4d243f 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -29,6 +29,15 @@
 #include <linux/vmalloc.h>
 #include "kexec_internal.h"
 
+#ifdef CONFIG_KEXEC_SIG
+static bool sig_enforce = IS_ENABLED(CONFIG_KEXEC_SIG_FORCE);
+
+void set_kexec_sig_enforced(void)
+{
+	sig_enforce = true;
+}
+#endif
+
 static int kexec_calculate_store_digests(struct kimage *image);
 
 /*
@@ -159,7 +168,7 @@ kimage_validate_signature(struct kimage *image)
 					   image->kernel_buf_len);
 	if (ret) {
 
-		if (IS_ENABLED(CONFIG_KEXEC_SIG_FORCE)) {
+		if (sig_enforce) {
 			pr_notice("Enforced kernel signature verification failed (%d).\n", ret);
 			return ret;
 		}
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 2ef90d15699f..9df585b9467e 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1559,7 +1559,9 @@ static int check_kprobe_address_safe(struct kprobe *p,
 	preempt_disable();
 
 	/* Ensure it is not in reserved area nor out of text */
-	if (!kernel_text_address((unsigned long) p->addr) ||
+	if (!(core_kernel_text((unsigned long) p->addr) ||
+	    is_module_text_address((unsigned long) p->addr)) ||
+	    in_gate_area_no_mm((unsigned long) p->addr) ||
 	    within_kprobe_blacklist((unsigned long) p->addr) ||
 	    jump_label_text_reserved(p->addr, p->addr) ||
 	    static_call_text_reserved(p->addr, p->addr) ||
@@ -1704,11 +1706,12 @@ static struct kprobe *__disable_kprobe(struct kprobe *p)
 		/* Try to disarm and disable this/parent probe */
 		if (p == orig_p || aggr_kprobe_disabled(orig_p)) {
 			/*
-			 * If kprobes_all_disarmed is set, orig_p
-			 * should have already been disarmed, so
-			 * skip unneed disarming process.
+			 * Don't be lazy here.  Even if 'kprobes_all_disarmed'
+			 * is false, 'orig_p' might not have been armed yet.
+			 * Note arm_all_kprobes() __tries__ to arm all kprobes
+			 * on the best effort basis.
 			 */
-			if (!kprobes_all_disarmed) {
+			if (!kprobes_all_disarmed && !kprobe_disabled(orig_p)) {
 				ret = disarm_kprobe(orig_p, true);
 				if (ret) {
 					p->flags &= ~KPROBE_FLAG_DISABLED;
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index a30702b847ba..e6a282bc1665 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -1368,7 +1368,7 @@ static struct lock_list *alloc_list_entry(void)
  */
 static int add_lock_to_list(struct lock_class *this,
 			    struct lock_class *links_to, struct list_head *head,
-			    unsigned long ip, u16 distance, u8 dep,
+			    u16 distance, u8 dep,
 			    const struct lock_trace *trace)
 {
 	struct lock_list *entry;
@@ -3121,19 +3121,15 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 	 * to the previous lock's dependency list:
 	 */
 	ret = add_lock_to_list(hlock_class(next), hlock_class(prev),
-			       &hlock_class(prev)->locks_after,
-			       next->acquire_ip, distance,
-			       calc_dep(prev, next),
-			       *trace);
+			       &hlock_class(prev)->locks_after, distance,
+			       calc_dep(prev, next), *trace);
 
 	if (!ret)
 		return 0;
 
 	ret = add_lock_to_list(hlock_class(prev), hlock_class(next),
-			       &hlock_class(next)->locks_before,
-			       next->acquire_ip, distance,
-			       calc_depb(prev, next),
-			       *trace);
+			       &hlock_class(next)->locks_before, distance,
+			       calc_depb(prev, next), *trace);
 	if (!ret)
 		return 0;
 
@@ -4224,14 +4220,13 @@ static void __trace_hardirqs_on_caller(void)
 
 /**
  * lockdep_hardirqs_on_prepare - Prepare for enabling interrupts
- * @ip:		Caller address
  *
  * Invoked before a possible transition to RCU idle from exit to user or
  * guest mode. This ensures that all RCU operations are done before RCU
  * stops watching. After the RCU transition lockdep_hardirqs_on() has to be
  * invoked to set the final state.
  */
-void lockdep_hardirqs_on_prepare(unsigned long ip)
+void lockdep_hardirqs_on_prepare(void)
 {
 	if (unlikely(!debug_locks))
 		return;
@@ -4828,8 +4823,7 @@ EXPORT_SYMBOL_GPL(__lockdep_no_validate__);
 
 static void
 print_lock_nested_lock_not_held(struct task_struct *curr,
-				struct held_lock *hlock,
-				unsigned long ip)
+				struct held_lock *hlock)
 {
 	if (!debug_locks_off())
 		return;
@@ -5005,7 +4999,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	chain_key = iterate_chain_key(chain_key, hlock_id(hlock));
 
 	if (nest_lock && !__lock_is_held(nest_lock, -1)) {
-		print_lock_nested_lock_not_held(curr, hlock, ip);
+		print_lock_nested_lock_not_held(curr, hlock);
 		return 0;
 	}
 
@@ -5202,9 +5196,10 @@ __lock_set_class(struct lockdep_map *lock, const char *name,
 		return 0;
 	}
 
-	lockdep_init_map_waits(lock, name, key, 0,
-			       lock->wait_type_inner,
-			       lock->wait_type_outer);
+	lockdep_init_map_type(lock, name, key, 0,
+			      lock->wait_type_inner,
+			      lock->wait_type_outer,
+			      lock->lock_type);
 	class = register_lock_class(lock, subclass, 0);
 	hlock->class_idx = class - lock_classes;
 
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index e63f740c2cc8..4cc73e6f8974 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -335,8 +335,6 @@ struct rwsem_waiter {
 	struct task_struct *task;
 	enum rwsem_waiter_type type;
 	unsigned long timeout;
-
-	/* Writer only, not initialized in reader */
 	bool handoff_set;
 };
 #define rwsem_first_waiter(sem) \
@@ -456,10 +454,12 @@ static void rwsem_mark_wake(struct rw_semaphore *sem,
 			 * to give up the lock), request a HANDOFF to
 			 * force the issue.
 			 */
-			if (!(oldcount & RWSEM_FLAG_HANDOFF) &&
-			    time_after(jiffies, waiter->timeout)) {
-				adjustment -= RWSEM_FLAG_HANDOFF;
-				lockevent_inc(rwsem_rlock_handoff);
+			if (time_after(jiffies, waiter->timeout)) {
+				if (!(oldcount & RWSEM_FLAG_HANDOFF)) {
+					adjustment -= RWSEM_FLAG_HANDOFF;
+					lockevent_inc(rwsem_rlock_handoff);
+				}
+				waiter->handoff_set = true;
 			}
 
 			atomic_long_add(-adjustment, &sem->count);
@@ -569,7 +569,7 @@ static void rwsem_mark_wake(struct rw_semaphore *sem,
 static inline bool rwsem_try_write_lock(struct rw_semaphore *sem,
 					struct rwsem_waiter *waiter)
 {
-	bool first = rwsem_first_waiter(sem) == waiter;
+	struct rwsem_waiter *first = rwsem_first_waiter(sem);
 	long count, new;
 
 	lockdep_assert_held(&sem->wait_lock);
@@ -579,11 +579,20 @@ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem,
 		bool has_handoff = !!(count & RWSEM_FLAG_HANDOFF);
 
 		if (has_handoff) {
-			if (!first)
+			/*
+			 * Honor handoff bit and yield only when the first
+			 * waiter is the one that set it. Otherwisee, we
+			 * still try to acquire the rwsem.
+			 */
+			if (first->handoff_set && (waiter != first))
 				return false;
 
-			/* First waiter inherits a previously set handoff bit */
-			waiter->handoff_set = true;
+			/*
+			 * First waiter can inherit a previously set handoff
+			 * bit and spin on rwsem if lock acquisition fails.
+			 */
+			if (waiter == first)
+				waiter->handoff_set = true;
 		}
 
 		new = count;
@@ -978,6 +987,7 @@ queue:
 	waiter.task = current;
 	waiter.type = RWSEM_WAITING_FOR_READ;
 	waiter.timeout = jiffies + RWSEM_WAIT_TIMEOUT;
+	waiter.handoff_set = false;
 
 	raw_spin_lock_irq(&sem->wait_lock);
 	if (list_empty(&sem->wait_list)) {
diff --git a/kernel/module.c b/kernel/module.c
index 83991c2d5af9..ef79f4dbda87 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2967,14 +2967,29 @@ static int elf_validity_check(struct load_info *info)
 	Elf_Shdr *shdr, *strhdr;
 	int err;
 
-	if (info->len < sizeof(*(info->hdr)))
-		return -ENOEXEC;
+	if (info->len < sizeof(*(info->hdr))) {
+		pr_err("Invalid ELF header len %lu\n", info->len);
+		goto no_exec;
+	}
 
-	if (memcmp(info->hdr->e_ident, ELFMAG, SELFMAG) != 0
-	    || info->hdr->e_type != ET_REL
-	    || !elf_check_arch(info->hdr)
-	    || info->hdr->e_shentsize != sizeof(Elf_Shdr))
-		return -ENOEXEC;
+	if (memcmp(info->hdr->e_ident, ELFMAG, SELFMAG) != 0) {
+		pr_err("Invalid ELF header magic: != %s\n", ELFMAG);
+		goto no_exec;
+	}
+	if (info->hdr->e_type != ET_REL) {
+		pr_err("Invalid ELF header type: %u != %u\n",
+		       info->hdr->e_type, ET_REL);
+		goto no_exec;
+	}
+	if (!elf_check_arch(info->hdr)) {
+		pr_err("Invalid architecture in ELF header: %u\n",
+		       info->hdr->e_machine);
+		goto no_exec;
+	}
+	if (info->hdr->e_shentsize != sizeof(Elf_Shdr)) {
+		pr_err("Invalid ELF section header size\n");
+		goto no_exec;
+	}
 
 	/*
 	 * e_shnum is 16 bits, and sizeof(Elf_Shdr) is
@@ -2983,8 +2998,10 @@ static int elf_validity_check(struct load_info *info)
 	 */
 	if (info->hdr->e_shoff >= info->len
 	    || (info->hdr->e_shnum * sizeof(Elf_Shdr) >
-		info->len - info->hdr->e_shoff))
-		return -ENOEXEC;
+		info->len - info->hdr->e_shoff)) {
+		pr_err("Invalid ELF section header overflow\n");
+		goto no_exec;
+	}
 
 	info->sechdrs = (void *)info->hdr + info->hdr->e_shoff;
 
@@ -2992,13 +3009,19 @@ static int elf_validity_check(struct load_info *info)
 	 * Verify if the section name table index is valid.
 	 */
 	if (info->hdr->e_shstrndx == SHN_UNDEF
-	    || info->hdr->e_shstrndx >= info->hdr->e_shnum)
-		return -ENOEXEC;
+	    || info->hdr->e_shstrndx >= info->hdr->e_shnum) {
+		pr_err("Invalid ELF section name index: %d || e_shstrndx (%d) >= e_shnum (%d)\n",
+		       info->hdr->e_shstrndx, info->hdr->e_shstrndx,
+		       info->hdr->e_shnum);
+		goto no_exec;
+	}
 
 	strhdr = &info->sechdrs[info->hdr->e_shstrndx];
 	err = validate_section_offset(info, strhdr);
-	if (err < 0)
+	if (err < 0) {
+		pr_err("Invalid ELF section hdr(type %u)\n", strhdr->sh_type);
 		return err;
+	}
 
 	/*
 	 * The section name table must be NUL-terminated, as required
@@ -3006,8 +3029,14 @@ static int elf_validity_check(struct load_info *info)
 	 * strings in the section safe.
 	 */
 	info->secstrings = (void *)info->hdr + strhdr->sh_offset;
-	if (info->secstrings[strhdr->sh_size - 1] != '\0')
-		return -ENOEXEC;
+	if (strhdr->sh_size == 0) {
+		pr_err("empty section name table\n");
+		goto no_exec;
+	}
+	if (info->secstrings[strhdr->sh_size - 1] != '\0') {
+		pr_err("ELF Spec violation: section name table isn't null terminated\n");
+		goto no_exec;
+	}
 
 	/*
 	 * The code assumes that section 0 has a length of zero and
@@ -3015,8 +3044,11 @@ static int elf_validity_check(struct load_info *info)
 	 */
 	if (info->sechdrs[0].sh_type != SHT_NULL
 	    || info->sechdrs[0].sh_size != 0
-	    || info->sechdrs[0].sh_addr != 0)
-		return -ENOEXEC;
+	    || info->sechdrs[0].sh_addr != 0) {
+		pr_err("ELF Spec violation: section 0 type(%d)!=SH_NULL or non-zero len or addr\n",
+		       info->sechdrs[0].sh_type);
+		goto no_exec;
+	}
 
 	for (i = 1; i < info->hdr->e_shnum; i++) {
 		shdr = &info->sechdrs[i];
@@ -3026,8 +3058,12 @@ static int elf_validity_check(struct load_info *info)
 			continue;
 		case SHT_SYMTAB:
 			if (shdr->sh_link == SHN_UNDEF
-			    || shdr->sh_link >= info->hdr->e_shnum)
-				return -ENOEXEC;
+			    || shdr->sh_link >= info->hdr->e_shnum) {
+				pr_err("Invalid ELF sh_link!=SHN_UNDEF(%d) or (sh_link(%d) >= hdr->e_shnum(%d)\n",
+				       shdr->sh_link, shdr->sh_link,
+				       info->hdr->e_shnum);
+				goto no_exec;
+			}
 			fallthrough;
 		default:
 			err = validate_section_offset(info, shdr);
@@ -3049,6 +3085,9 @@ static int elf_validity_check(struct load_info *info)
 	}
 
 	return 0;
+
+no_exec:
+	return -ENOEXEC;
 }
 
 #define COPY_CHUNK_SIZE (16*PAGE_SIZE)
@@ -3925,10 +3964,8 @@ static int load_module(struct load_info *info, const char __user *uargs,
 	 * sections.
 	 */
 	err = elf_validity_check(info);
-	if (err) {
-		pr_err("Module has invalid ELF structures\n");
+	if (err)
 		goto free_copy;
-	}
 
 	/*
 	 * Everything checks out, so set up the section info
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 740723bb3885..13cca2e2c2bc 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -26,6 +26,7 @@
 
 #include "power.h"
 
+static bool need_wait;
 
 static struct snapshot_data {
 	struct snapshot_handle handle;
@@ -78,7 +79,7 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 		 * Resuming.  We may need to wait for the image device to
 		 * appear.
 		 */
-		wait_for_device_probe();
+		need_wait = true;
 
 		data->swap = -1;
 		data->mode = O_WRONLY;
@@ -168,6 +169,11 @@ static ssize_t snapshot_write(struct file *filp, const char __user *buf,
 	ssize_t res;
 	loff_t pg_offp = *offp & ~PAGE_MASK;
 
+	if (need_wait) {
+		wait_for_device_probe();
+		need_wait = false;
+	}
+
 	lock_system_sleep();
 
 	data = filp->private_data;
@@ -244,6 +250,11 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 	loff_t size;
 	sector_t offset;
 
+	if (need_wait) {
+		wait_for_device_probe();
+		need_wait = false;
+	}
+
 	if (_IOC_TYPE(cmd) != SNAPSHOT_IOC_MAGIC)
 		return -ENOTTY;
 	if (_IOC_NR(cmd) > SNAPSHOT_IOC_MAXNR)
diff --git a/kernel/profile.c b/kernel/profile.c
index eb9c7f0f5ac5..0db1122855c0 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -109,6 +109,13 @@ int __ref profile_init(void)
 
 	/* only text is profiled */
 	prof_len = (_etext - _stext) >> prof_shift;
+
+	if (!prof_len) {
+		pr_warn("profiling shift: %u too large\n", prof_shift);
+		prof_on = 0;
+		return -EINVAL;
+	}
+
 	buffer_bytes = prof_len*sizeof(atomic_t);
 
 	if (!alloc_cpumask_var(&prof_cpu_mask, GFP_KERNEL))
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index f922937eb39a..d820ef615475 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -1991,6 +1991,19 @@ static int rcutorture_booster_init(unsigned int cpu)
 	if (boost_tasks[cpu] != NULL)
 		return 0;  /* Already created, nothing more to do. */
 
+	// Testing RCU priority boosting requires rcutorture do
+	// some serious abuse.  Counter this by running ksoftirqd
+	// at higher priority.
+	if (IS_BUILTIN(CONFIG_RCU_TORTURE_TEST)) {
+		struct sched_param sp;
+		struct task_struct *t;
+
+		t = per_cpu(ksoftirqd, cpu);
+		WARN_ON_ONCE(!t);
+		sp.sched_priority = 2;
+		sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
+	}
+
 	/* Don't allow time recalculation while creating a new task. */
 	mutex_lock(&boost_mutex);
 	rcu_torture_disable_rt_throttle();
@@ -2848,7 +2861,7 @@ rcu_torture_cleanup(void)
 		 rcutorture_seq_diff(gp_seq, start_gp_seq));
 	torture_stop_kthread(rcu_torture_stats, stats_task);
 	torture_stop_kthread(rcu_torture_fqs, fqs_task);
-	if (rcu_torture_can_boost())
+	if (rcu_torture_can_boost() && rcutor_hp >= 0)
 		cpuhp_remove_state(rcutor_hp);
 
 	/*
@@ -3066,7 +3079,7 @@ rcu_torture_init(void)
 	rcu_torture_write_types();
 	firsterr = torture_create_kthread(rcu_torture_writer, NULL,
 					  writer_task);
-	if (firsterr)
+	if (torture_init_error(firsterr))
 		goto unwind;
 	if (nfakewriters > 0) {
 		fakewriter_tasks = kcalloc(nfakewriters,
@@ -3081,7 +3094,7 @@ rcu_torture_init(void)
 	for (i = 0; i < nfakewriters; i++) {
 		firsterr = torture_create_kthread(rcu_torture_fakewriter,
 						  NULL, fakewriter_tasks[i]);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	reader_tasks = kcalloc(nrealreaders, sizeof(reader_tasks[0]),
@@ -3097,7 +3110,7 @@ rcu_torture_init(void)
 		rcu_torture_reader_mbchk[i].rtc_chkrdr = -1;
 		firsterr = torture_create_kthread(rcu_torture_reader, (void *)i,
 						  reader_tasks[i]);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	nrealnocbers = nocbs_nthreads;
@@ -3117,18 +3130,18 @@ rcu_torture_init(void)
 	}
 	for (i = 0; i < nrealnocbers; i++) {
 		firsterr = torture_create_kthread(rcu_nocb_toggle, NULL, nocb_tasks[i]);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	if (stat_interval > 0) {
 		firsterr = torture_create_kthread(rcu_torture_stats, NULL,
 						  stats_task);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	if (test_no_idle_hz && shuffle_interval > 0) {
 		firsterr = torture_shuffle_init(shuffle_interval * HZ);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	if (stutter < 0)
@@ -3138,7 +3151,7 @@ rcu_torture_init(void)
 
 		t = cur_ops->stall_dur ? cur_ops->stall_dur() : stutter * HZ;
 		firsterr = torture_stutter_init(stutter * HZ, t);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	if (fqs_duration < 0)
@@ -3147,7 +3160,7 @@ rcu_torture_init(void)
 		/* Create the fqs thread */
 		firsterr = torture_create_kthread(rcu_torture_fqs, NULL,
 						  fqs_task);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	if (test_boost_interval < 1)
@@ -3161,44 +3174,29 @@ rcu_torture_init(void)
 		firsterr = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "RCU_TORTURE",
 					     rcutorture_booster_init,
 					     rcutorture_booster_cleanup);
-		if (firsterr < 0)
-			goto unwind;
 		rcutor_hp = firsterr;
-
-		// Testing RCU priority boosting requires rcutorture do
-		// some serious abuse.  Counter this by running ksoftirqd
-		// at higher priority.
-		if (IS_BUILTIN(CONFIG_RCU_TORTURE_TEST)) {
-			for_each_online_cpu(cpu) {
-				struct sched_param sp;
-				struct task_struct *t;
-
-				t = per_cpu(ksoftirqd, cpu);
-				WARN_ON_ONCE(!t);
-				sp.sched_priority = 2;
-				sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
-			}
-		}
+		if (torture_init_error(firsterr))
+			goto unwind;
 	}
 	shutdown_jiffies = jiffies + shutdown_secs * HZ;
 	firsterr = torture_shutdown_init(shutdown_secs, rcu_torture_cleanup);
-	if (firsterr)
+	if (torture_init_error(firsterr))
 		goto unwind;
 	firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval,
 				      rcutorture_sync);
-	if (firsterr)
+	if (torture_init_error(firsterr))
 		goto unwind;
 	firsterr = rcu_torture_stall_init();
-	if (firsterr)
+	if (torture_init_error(firsterr))
 		goto unwind;
 	firsterr = rcu_torture_fwd_prog_init();
-	if (firsterr)
+	if (torture_init_error(firsterr))
 		goto unwind;
 	firsterr = rcu_torture_barrier_init();
-	if (firsterr)
+	if (torture_init_error(firsterr))
 		goto unwind;
 	firsterr = rcu_torture_read_exit_init();
-	if (firsterr)
+	if (torture_init_error(firsterr))
 		goto unwind;
 	if (object_debug)
 		rcu_test_debug_objects();
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b89ca5c83143..85be684687b0 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3714,7 +3714,7 @@ bool cpus_share_cache(int this_cpu, int that_cpu)
 	return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
 }
 
-static inline bool ttwu_queue_cond(int cpu, int wake_flags)
+static inline bool ttwu_queue_cond(struct task_struct *p, int cpu)
 {
 	/*
 	 * Do not complicate things with the async wake_list while the CPU is
@@ -3723,6 +3723,10 @@ static inline bool ttwu_queue_cond(int cpu, int wake_flags)
 	if (!cpu_active(cpu))
 		return false;
 
+	/* Ensure the task will still be allowed to run on the CPU. */
+	if (!cpumask_test_cpu(cpu, p->cpus_ptr))
+		return false;
+
 	/*
 	 * If the CPU does not share cache, then queue the task on the
 	 * remote rqs wakelist to avoid accessing remote data.
@@ -3730,13 +3734,21 @@ static inline bool ttwu_queue_cond(int cpu, int wake_flags)
 	if (!cpus_share_cache(smp_processor_id(), cpu))
 		return true;
 
+	if (cpu == smp_processor_id())
+		return false;
+
 	/*
-	 * If the task is descheduling and the only running task on the
-	 * CPU then use the wakelist to offload the task activation to
-	 * the soon-to-be-idle CPU as the current CPU is likely busy.
-	 * nr_running is checked to avoid unnecessary task stacking.
+	 * If the wakee cpu is idle, or the task is descheduling and the
+	 * only running task on the CPU, then use the wakelist to offload
+	 * the task activation to the idle (or soon-to-be-idle) CPU as
+	 * the current CPU is likely busy. nr_running is checked to
+	 * avoid unnecessary task stacking.
+	 *
+	 * Note that we can only get here with (wakee) p->on_rq=0,
+	 * p->on_cpu can be whatever, we've done the dequeue, so
+	 * the wakee has been accounted out of ->nr_running.
 	 */
-	if ((wake_flags & WF_ON_CPU) && cpu_rq(cpu)->nr_running <= 1)
+	if (!cpu_rq(cpu)->nr_running)
 		return true;
 
 	return false;
@@ -3744,10 +3756,7 @@ static inline bool ttwu_queue_cond(int cpu, int wake_flags)
 
 static bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
 {
-	if (sched_feat(TTWU_QUEUE) && ttwu_queue_cond(cpu, wake_flags)) {
-		if (WARN_ON_ONCE(cpu == smp_processor_id()))
-			return false;
-
+	if (sched_feat(TTWU_QUEUE) && ttwu_queue_cond(p, cpu)) {
 		sched_clock_cpu(cpu); /* Sync clocks across CPUs */
 		__ttwu_queue_wakelist(p, cpu, wake_flags);
 		return true;
@@ -4069,7 +4078,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 * scheduling.
 	 */
 	if (smp_load_acquire(&p->on_cpu) &&
-	    ttwu_queue_wakelist(p, task_cpu(p), wake_flags | WF_ON_CPU))
+	    ttwu_queue_wakelist(p, task_cpu(p), wake_flags))
 		goto unlock;
 
 	/*
@@ -4585,7 +4594,8 @@ static inline void prepare_task(struct task_struct *next)
 	 * Claim the task as running, we do this before switching to it
 	 * such that any running task will have this set.
 	 *
-	 * See the ttwu() WF_ON_CPU case and its ordering comment.
+	 * See the smp_load_acquire(&p->on_cpu) case in ttwu() and
+	 * its ordering comment.
 	 */
 	WRITE_ONCE(next->on_cpu, 1);
 #endif
@@ -6379,8 +6389,12 @@ static inline void sched_submit_work(struct task_struct *tsk)
 		preempt_enable_no_resched();
 	}
 
-	if (tsk_is_pi_blocked(tsk))
-		return;
+	/*
+	 * spinlock and rwlock must not flush block requests.  This will
+	 * deadlock if the callback attempts to acquire a lock which is
+	 * already acquired.
+	 */
+	SCHED_WARN_ON(current->__state & TASK_RTLOCK_WAIT);
 
 	/*
 	 * If we are going to sleep and we have plugged IO queued,
@@ -8737,7 +8751,7 @@ int cpuset_cpumask_can_shrink(const struct cpumask *cur,
 }
 
 int task_can_attach(struct task_struct *p,
-		    const struct cpumask *cs_cpus_allowed)
+		    const struct cpumask *cs_effective_cpus)
 {
 	int ret = 0;
 
@@ -8756,8 +8770,13 @@ int task_can_attach(struct task_struct *p,
 	}
 
 	if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span,
-					      cs_cpus_allowed))
-		ret = dl_task_can_attach(p, cs_cpus_allowed);
+					      cs_effective_cpus)) {
+		int cpu = cpumask_any_and(cpu_active_mask, cs_effective_cpus);
+
+		if (unlikely(cpu >= nr_cpu_ids))
+			return -EINVAL;
+		ret = dl_cpu_busy(cpu, p);
+	}
 
 out:
 	return ret;
@@ -9041,8 +9060,10 @@ static void cpuset_cpu_active(void)
 static int cpuset_cpu_inactive(unsigned int cpu)
 {
 	if (!cpuhp_tasks_frozen) {
-		if (dl_cpu_busy(cpu))
-			return -EBUSY;
+		int ret = dl_cpu_busy(cpu, NULL);
+
+		if (ret)
+			return ret;
 		cpuset_update_active_cpus();
 	} else {
 		num_cpus_frozen++;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index fffcb1aa77b7..147b757d162b 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1561,7 +1561,10 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 		 * the throttle.
 		 */
 		p->dl.dl_throttled = 0;
-		BUG_ON(!is_dl_boosted(&p->dl) || flags != ENQUEUE_REPLENISH);
+		if (!(flags & ENQUEUE_REPLENISH))
+			printk_deferred_once("sched: DL de-boosted task PID %d: REPLENISH flag missing\n",
+					     task_pid_nr(p));
+
 		return;
 	}
 
@@ -2861,41 +2864,6 @@ bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr)
 }
 
 #ifdef CONFIG_SMP
-int dl_task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed)
-{
-	unsigned long flags, cap;
-	unsigned int dest_cpu;
-	struct dl_bw *dl_b;
-	bool overflow;
-	int ret;
-
-	dest_cpu = cpumask_any_and(cpu_active_mask, cs_cpus_allowed);
-
-	rcu_read_lock_sched();
-	dl_b = dl_bw_of(dest_cpu);
-	raw_spin_lock_irqsave(&dl_b->lock, flags);
-	cap = dl_bw_capacity(dest_cpu);
-	overflow = __dl_overflow(dl_b, cap, 0, p->dl.dl_bw);
-	if (overflow) {
-		ret = -EBUSY;
-	} else {
-		/*
-		 * We reserve space for this task in the destination
-		 * root_domain, as we can't fail after this point.
-		 * We will free resources in the source root_domain
-		 * later on (see set_cpus_allowed_dl()).
-		 */
-		int cpus = dl_bw_cpus(dest_cpu);
-
-		__dl_add(dl_b, p->dl.dl_bw, cpus);
-		ret = 0;
-	}
-	raw_spin_unlock_irqrestore(&dl_b->lock, flags);
-	rcu_read_unlock_sched();
-
-	return ret;
-}
-
 int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur,
 				 const struct cpumask *trial)
 {
@@ -2917,7 +2885,7 @@ int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur,
 	return ret;
 }
 
-bool dl_cpu_busy(unsigned int cpu)
+int dl_cpu_busy(int cpu, struct task_struct *p)
 {
 	unsigned long flags, cap;
 	struct dl_bw *dl_b;
@@ -2927,11 +2895,22 @@ bool dl_cpu_busy(unsigned int cpu)
 	dl_b = dl_bw_of(cpu);
 	raw_spin_lock_irqsave(&dl_b->lock, flags);
 	cap = dl_bw_capacity(cpu);
-	overflow = __dl_overflow(dl_b, cap, 0, 0);
+	overflow = __dl_overflow(dl_b, cap, 0, p ? p->dl.dl_bw : 0);
+
+	if (!overflow && p) {
+		/*
+		 * We reserve space for this task in the destination
+		 * root_domain, as we can't fail after this point.
+		 * We will free resources in the source root_domain
+		 * later on (see set_cpus_allowed_dl()).
+		 */
+		__dl_add(dl_b, p->dl.dl_bw, dl_bw_cpus(cpu));
+	}
+
 	raw_spin_unlock_irqrestore(&dl_b->lock, flags);
 	rcu_read_unlock_sched();
 
-	return overflow;
+	return overflow ? -EBUSY : 0;
 }
 #endif
 
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 7a2d32d2025f..34c5ff3a0669 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -416,7 +416,7 @@ void update_sched_domain_debugfs(void)
 		char buf[32];
 
 		snprintf(buf, sizeof(buf), "cpu%d", cpu);
-		debugfs_remove(debugfs_lookup(buf, sd_dentry));
+		debugfs_lookup_and_remove(buf, sd_dentry);
 		d_cpu = debugfs_create_dir(buf, sd_dentry);
 
 		i = 0;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index fcbacc35d2b9..a853e4e9e3c3 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6280,6 +6280,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
 {
 	struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
 	int i, cpu, idle_cpu = -1, nr = INT_MAX;
+	struct sched_domain_shared *sd_share;
 	struct rq *this_rq = this_rq();
 	int this = smp_processor_id();
 	struct sched_domain *this_sd;
@@ -6319,6 +6320,17 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
 		time = cpu_clock(this);
 	}
 
+	if (sched_feat(SIS_UTIL)) {
+		sd_share = rcu_dereference(per_cpu(sd_llc_shared, target));
+		if (sd_share) {
+			/* because !--nr is the condition to stop scan */
+			nr = READ_ONCE(sd_share->nr_idle_scan) + 1;
+			/* overloaded LLC is unlikely to have idle cpu/core */
+			if (nr == 1)
+				return -1;
+		}
+	}
+
 	for_each_cpu_wrap(cpu, cpus, target + 1) {
 		if (has_idle_core) {
 			i = select_idle_core(p, cpu, cpus, &idle_cpu);
@@ -9166,6 +9178,77 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
 	return idlest;
 }
 
+static void update_idle_cpu_scan(struct lb_env *env,
+				 unsigned long sum_util)
+{
+	struct sched_domain_shared *sd_share;
+	int llc_weight, pct;
+	u64 x, y, tmp;
+	/*
+	 * Update the number of CPUs to scan in LLC domain, which could
+	 * be used as a hint in select_idle_cpu(). The update of sd_share
+	 * could be expensive because it is within a shared cache line.
+	 * So the write of this hint only occurs during periodic load
+	 * balancing, rather than CPU_NEWLY_IDLE, because the latter
+	 * can fire way more frequently than the former.
+	 */
+	if (!sched_feat(SIS_UTIL) || env->idle == CPU_NEWLY_IDLE)
+		return;
+
+	llc_weight = per_cpu(sd_llc_size, env->dst_cpu);
+	if (env->sd->span_weight != llc_weight)
+		return;
+
+	sd_share = rcu_dereference(per_cpu(sd_llc_shared, env->dst_cpu));
+	if (!sd_share)
+		return;
+
+	/*
+	 * The number of CPUs to search drops as sum_util increases, when
+	 * sum_util hits 85% or above, the scan stops.
+	 * The reason to choose 85% as the threshold is because this is the
+	 * imbalance_pct(117) when a LLC sched group is overloaded.
+	 *
+	 * let y = SCHED_CAPACITY_SCALE - p * x^2                       [1]
+	 * and y'= y / SCHED_CAPACITY_SCALE
+	 *
+	 * x is the ratio of sum_util compared to the CPU capacity:
+	 * x = sum_util / (llc_weight * SCHED_CAPACITY_SCALE)
+	 * y' is the ratio of CPUs to be scanned in the LLC domain,
+	 * and the number of CPUs to scan is calculated by:
+	 *
+	 * nr_scan = llc_weight * y'                                    [2]
+	 *
+	 * When x hits the threshold of overloaded, AKA, when
+	 * x = 100 / pct, y drops to 0. According to [1],
+	 * p should be SCHED_CAPACITY_SCALE * pct^2 / 10000
+	 *
+	 * Scale x by SCHED_CAPACITY_SCALE:
+	 * x' = sum_util / llc_weight;                                  [3]
+	 *
+	 * and finally [1] becomes:
+	 * y = SCHED_CAPACITY_SCALE -
+	 *     x'^2 * pct^2 / (10000 * SCHED_CAPACITY_SCALE)            [4]
+	 *
+	 */
+	/* equation [3] */
+	x = sum_util;
+	do_div(x, llc_weight);
+
+	/* equation [4] */
+	pct = env->sd->imbalance_pct;
+	tmp = x * x * pct * pct;
+	do_div(tmp, 10000 * SCHED_CAPACITY_SCALE);
+	tmp = min_t(long, tmp, SCHED_CAPACITY_SCALE);
+	y = SCHED_CAPACITY_SCALE - tmp;
+
+	/* equation [2] */
+	y *= llc_weight;
+	do_div(y, SCHED_CAPACITY_SCALE);
+	if ((int)y != sd_share->nr_idle_scan)
+		WRITE_ONCE(sd_share->nr_idle_scan, (int)y);
+}
+
 /**
  * update_sd_lb_stats - Update sched_domain's statistics for load balancing.
  * @env: The load balancing environment.
@@ -9178,6 +9261,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 	struct sched_group *sg = env->sd->groups;
 	struct sg_lb_stats *local = &sds->local_stat;
 	struct sg_lb_stats tmp_sgs;
+	unsigned long sum_util = 0;
 	int sg_status = 0;
 
 	do {
@@ -9210,6 +9294,7 @@ next_group:
 		sds->total_load += sgs->group_load;
 		sds->total_capacity += sgs->group_capacity;
 
+		sum_util += sgs->group_util;
 		sg = sg->next;
 	} while (sg != env->sd->groups);
 
@@ -9235,6 +9320,8 @@ next_group:
 		WRITE_ONCE(rd->overutilized, SG_OVERUTILIZED);
 		trace_sched_overutilized_tp(rd, SG_OVERUTILIZED);
 	}
+
+	update_idle_cpu_scan(env, sum_util);
 }
 
 #define NUMA_IMBALANCE_MIN 2
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 7f8dace0964c..c4947c1b5edb 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -55,7 +55,8 @@ SCHED_FEAT(TTWU_QUEUE, true)
 /*
  * When doing wakeups, attempt to limit superfluous scans of the LLC domain.
  */
-SCHED_FEAT(SIS_PROP, true)
+SCHED_FEAT(SIS_PROP, false)
+SCHED_FEAT(SIS_UTIL, true)
 
 /*
  * Issue a WARN when we do multiple update_rq_clock() calls
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index d17b0a5ce6ac..499a3e286cd0 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -105,7 +105,7 @@ void __cpuidle default_idle_call(void)
 		 * last -- this is very similar to the entry code.
 		 */
 		trace_hardirqs_on_prepare();
-		lockdep_hardirqs_on_prepare(_THIS_IP_);
+		lockdep_hardirqs_on_prepare();
 		rcu_idle_enter();
 		lockdep_hardirqs_on(_THIS_IP_);
 
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 8007d087a57f..f75dcd3537b8 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -444,7 +444,7 @@ static inline void rt_queue_push_tasks(struct rq *rq)
 #endif /* CONFIG_SMP */
 
 static void enqueue_top_rt_rq(struct rt_rq *rt_rq);
-static void dequeue_top_rt_rq(struct rt_rq *rt_rq);
+static void dequeue_top_rt_rq(struct rt_rq *rt_rq, unsigned int count);
 
 static inline int on_rt_rq(struct sched_rt_entity *rt_se)
 {
@@ -565,7 +565,7 @@ static void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
 	rt_se = rt_rq->tg->rt_se[cpu];
 
 	if (!rt_se) {
-		dequeue_top_rt_rq(rt_rq);
+		dequeue_top_rt_rq(rt_rq, rt_rq->rt_nr_running);
 		/* Kick cpufreq (see the comment in kernel/sched/sched.h). */
 		cpufreq_update_util(rq_of_rt_rq(rt_rq), 0);
 	}
@@ -651,7 +651,7 @@ static inline void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
 
 static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
 {
-	dequeue_top_rt_rq(rt_rq);
+	dequeue_top_rt_rq(rt_rq, rt_rq->rt_nr_running);
 }
 
 static inline int rt_rq_throttled(struct rt_rq *rt_rq)
@@ -1051,7 +1051,7 @@ static void update_curr_rt(struct rq *rq)
 }
 
 static void
-dequeue_top_rt_rq(struct rt_rq *rt_rq)
+dequeue_top_rt_rq(struct rt_rq *rt_rq, unsigned int count)
 {
 	struct rq *rq = rq_of_rt_rq(rt_rq);
 
@@ -1062,7 +1062,7 @@ dequeue_top_rt_rq(struct rt_rq *rt_rq)
 
 	BUG_ON(!rq->nr_running);
 
-	sub_nr_running(rq, rt_rq->rt_nr_running);
+	sub_nr_running(rq, count);
 	rt_rq->rt_queued = 0;
 
 }
@@ -1342,18 +1342,21 @@ static void __dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flag
 static void dequeue_rt_stack(struct sched_rt_entity *rt_se, unsigned int flags)
 {
 	struct sched_rt_entity *back = NULL;
+	unsigned int rt_nr_running;
 
 	for_each_sched_rt_entity(rt_se) {
 		rt_se->back = back;
 		back = rt_se;
 	}
 
-	dequeue_top_rt_rq(rt_rq_of_se(back));
+	rt_nr_running = rt_rq_of_se(back)->rt_nr_running;
 
 	for (rt_se = back; rt_se; rt_se = rt_se->back) {
 		if (on_rt_rq(rt_se))
 			__dequeue_rt_entity(rt_se, flags);
 	}
+
+	dequeue_top_rt_rq(rt_rq_of_se(back), rt_nr_running);
 }
 
 static void enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index fe8be2f8a47d..e49902898253 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -348,9 +348,8 @@ extern void __setparam_dl(struct task_struct *p, const struct sched_attr *attr);
 extern void __getparam_dl(struct task_struct *p, struct sched_attr *attr);
 extern bool __checkparam_dl(const struct sched_attr *attr);
 extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr);
-extern int  dl_task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed);
 extern int  dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
-extern bool dl_cpu_busy(unsigned int cpu);
+extern int  dl_cpu_busy(int cpu, struct task_struct *p);
 
 #ifdef CONFIG_CGROUP_SCHED
 
@@ -2053,7 +2052,6 @@ static inline int task_on_rq_migrating(struct task_struct *p)
 
 #define WF_SYNC     0x10 /* Waker goes to sleep after wakeup */
 #define WF_MIGRATED 0x20 /* Internal use, task got migrated */
-#define WF_ON_CPU   0x40 /* Wakee is on_cpu */
 
 #ifdef CONFIG_SMP
 static_assert(WF_EXEC == SD_BALANCE_EXEC);
diff --git a/kernel/signal.c b/kernel/signal.c
index d831f0aec56e..c7dbb19219b9 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2027,12 +2027,12 @@ bool do_notify_parent(struct task_struct *tsk, int sig)
 	bool autoreap = false;
 	u64 utime, stime;
 
-	BUG_ON(sig == -1);
+	WARN_ON_ONCE(sig == -1);
 
- 	/* do_notify_parent_cldstop should have been called instead.  */
- 	BUG_ON(task_is_stopped_or_traced(tsk));
+	/* do_notify_parent_cldstop should have been called instead.  */
+	WARN_ON_ONCE(task_is_stopped_or_traced(tsk));
 
-	BUG_ON(!tsk->ptrace &&
+	WARN_ON_ONCE(!tsk->ptrace &&
 	       (tsk->group_leader != tsk || !thread_group_empty(tsk)));
 
 	/* Wake up all pidfd waiters */
diff --git a/kernel/smp.c b/kernel/smp.c
index b68d63e965db..82825345432c 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -174,9 +174,9 @@ static int __init csdlock_debug(char *str)
 	if (val)
 		static_branch_enable(&csdlock_debug_enabled);
 
-	return 0;
+	return 1;
 }
-early_param("csdlock_debug", csdlock_debug);
+__setup("csdlock_debug=", csdlock_debug);
 
 static DEFINE_PER_CPU(call_single_data_t *, cur_csd);
 static DEFINE_PER_CPU(smp_call_func_t, cur_csd_func);
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index f43d89d92860..126380696f9c 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -276,6 +276,7 @@ COND_SYSCALL(landlock_restrict_self);
 
 /* mm/fadvise.c */
 COND_SYSCALL(fadvise64_64);
+COND_SYSCALL_COMPAT(fadvise64_64);
 
 /* mm/, CONFIG_MMU only */
 COND_SYSCALL(swapon);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 0586047f7323..23c08bf3db58 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -113,15 +113,9 @@
 static int sixty = 60;
 #endif
 
-static int __maybe_unused neg_one = -1;
-static int __maybe_unused two = 2;
-static int __maybe_unused four = 4;
 static unsigned long zero_ul;
 static unsigned long one_ul = 1;
 static unsigned long long_max = LONG_MAX;
-static int one_hundred = 100;
-static int two_hundred = 200;
-static int one_thousand = 1000;
 #ifdef CONFIG_PRINTK
 static int ten_thousand = 10000;
 #endif
@@ -566,14 +560,14 @@ static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp,
 		if (*negp) {
 			if (*lvalp > (unsigned long) INT_MAX + 1)
 				return -EINVAL;
-			*valp = -*lvalp;
+			WRITE_ONCE(*valp, -*lvalp);
 		} else {
 			if (*lvalp > (unsigned long) INT_MAX)
 				return -EINVAL;
-			*valp = *lvalp;
+			WRITE_ONCE(*valp, *lvalp);
 		}
 	} else {
-		int val = *valp;
+		int val = READ_ONCE(*valp);
 		if (val < 0) {
 			*negp = true;
 			*lvalp = -(unsigned long)val;
@@ -592,9 +586,9 @@ static int do_proc_douintvec_conv(unsigned long *lvalp,
 	if (write) {
 		if (*lvalp > UINT_MAX)
 			return -EINVAL;
-		*valp = *lvalp;
+		WRITE_ONCE(*valp, *lvalp);
 	} else {
-		unsigned int val = *valp;
+		unsigned int val = READ_ONCE(*valp);
 		*lvalp = (unsigned long)val;
 	}
 	return 0;
@@ -988,7 +982,7 @@ static int do_proc_dointvec_minmax_conv(bool *negp, unsigned long *lvalp,
 		if ((param->min && *param->min > tmp) ||
 		    (param->max && *param->max < tmp))
 			return -EINVAL;
-		*valp = tmp;
+		WRITE_ONCE(*valp, tmp);
 	}
 
 	return 0;
@@ -1054,7 +1048,7 @@ static int do_proc_douintvec_minmax_conv(unsigned long *lvalp,
 		    (param->max && *param->max < tmp))
 			return -ERANGE;
 
-		*valp = tmp;
+		WRITE_ONCE(*valp, tmp);
 	}
 
 	return 0;
@@ -1138,13 +1132,13 @@ int proc_dou8vec_minmax(struct ctl_table *table, int write,
 
 	tmp.maxlen = sizeof(val);
 	tmp.data = &val;
-	val = *data;
+	val = READ_ONCE(*data);
 	res = do_proc_douintvec(&tmp, write, buffer, lenp, ppos,
 				do_proc_douintvec_minmax_conv, &param);
 	if (res)
 		return res;
 	if (write)
-		*data = val;
+		WRITE_ONCE(*data, val);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(proc_dou8vec_minmax);
@@ -1281,9 +1275,9 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table,
 				err = -EINVAL;
 				break;
 			}
-			*i = val;
+			WRITE_ONCE(*i, val);
 		} else {
-			val = convdiv * (*i) / convmul;
+			val = convdiv * READ_ONCE(*i) / convmul;
 			if (!first)
 				proc_put_char(&buffer, &left, '\t');
 			proc_put_long(&buffer, &left, val, false);
@@ -1364,9 +1358,12 @@ static int do_proc_dointvec_jiffies_conv(bool *negp, unsigned long *lvalp,
 	if (write) {
 		if (*lvalp > INT_MAX / HZ)
 			return 1;
-		*valp = *negp ? -(*lvalp*HZ) : (*lvalp*HZ);
+		if (*negp)
+			WRITE_ONCE(*valp, -*lvalp * HZ);
+		else
+			WRITE_ONCE(*valp, *lvalp * HZ);
 	} else {
-		int val = *valp;
+		int val = READ_ONCE(*valp);
 		unsigned long lval;
 		if (val < 0) {
 			*negp = true;
@@ -1412,9 +1409,9 @@ static int do_proc_dointvec_ms_jiffies_conv(bool *negp, unsigned long *lvalp,
 
 		if (jif > INT_MAX)
 			return 1;
-		*valp = (int)jif;
+		WRITE_ONCE(*valp, (int)jif);
 	} else {
-		int val = *valp;
+		int val = READ_ONCE(*valp);
 		unsigned long lval;
 		if (val < 0) {
 			*negp = true;
@@ -1482,8 +1479,8 @@ int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write,
  * @ppos: the current position in the file
  *
  * Reads/writes up to table->maxlen/sizeof(unsigned int) integer
- * values from/to the user buffer, treated as an ASCII string. 
- * The values read are assumed to be in 1/1000 seconds, and 
+ * values from/to the user buffer, treated as an ASCII string.
+ * The values read are assumed to be in 1/1000 seconds, and
  * are converted into jiffies.
  *
  * Returns 0 on success.
@@ -1969,7 +1966,7 @@ static struct ctl_table kern_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &neg_one,
+		.extra1		= SYSCTL_NEG_ONE,
 		.extra2		= SYSCTL_ONE,
 	},
 #endif
@@ -2311,7 +2308,7 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax_sysadmin,
 		.extra1		= SYSCTL_ZERO,
-		.extra2		= &two,
+		.extra2		= SYSCTL_TWO,
 	},
 #endif
 	{
@@ -2571,7 +2568,7 @@ static struct ctl_table kern_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &neg_one,
+		.extra1		= SYSCTL_NEG_ONE,
 	},
 #endif
 #ifdef CONFIG_RT_MUTEXES
@@ -2633,7 +2630,7 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= perf_cpu_time_max_percent_handler,
 		.extra1		= SYSCTL_ZERO,
-		.extra2		= &one_hundred,
+		.extra2		= SYSCTL_ONE_HUNDRED,
 	},
 	{
 		.procname	= "perf_event_max_stack",
@@ -2651,7 +2648,7 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= perf_event_max_stack_handler,
 		.extra1		= SYSCTL_ZERO,
-		.extra2		= &one_thousand,
+		.extra2		= SYSCTL_ONE_THOUSAND,
 	},
 #endif
 	{
@@ -2682,7 +2679,7 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= bpf_unpriv_handler,
 		.extra1		= SYSCTL_ZERO,
-		.extra2		= &two,
+		.extra2		= SYSCTL_TWO,
 	},
 	{
 		.procname	= "bpf_stats_enabled",
@@ -2736,7 +2733,7 @@ static struct ctl_table vm_table[] = {
 		.mode		= 0644,
 		.proc_handler	= overcommit_policy_handler,
 		.extra1		= SYSCTL_ZERO,
-		.extra2		= &two,
+		.extra2		= SYSCTL_TWO,
 	},
 	{
 		.procname	= "panic_on_oom",
@@ -2745,7 +2742,7 @@ static struct ctl_table vm_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO,
-		.extra2		= &two,
+		.extra2		= SYSCTL_TWO,
 	},
 	{
 		.procname	= "oom_kill_allocating_task",
@@ -2790,7 +2787,7 @@ static struct ctl_table vm_table[] = {
 		.mode		= 0644,
 		.proc_handler	= dirty_background_ratio_handler,
 		.extra1		= SYSCTL_ZERO,
-		.extra2		= &one_hundred,
+		.extra2		= SYSCTL_ONE_HUNDRED,
 	},
 	{
 		.procname	= "dirty_background_bytes",
@@ -2807,7 +2804,7 @@ static struct ctl_table vm_table[] = {
 		.mode		= 0644,
 		.proc_handler	= dirty_ratio_handler,
 		.extra1		= SYSCTL_ZERO,
-		.extra2		= &one_hundred,
+		.extra2		= SYSCTL_ONE_HUNDRED,
 	},
 	{
 		.procname	= "dirty_bytes",
@@ -2847,8 +2844,19 @@ static struct ctl_table vm_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO,
-		.extra2		= &two_hundred,
+		.extra2		= SYSCTL_TWO_HUNDRED,
 	},
+#ifdef CONFIG_NUMA
+	{
+		.procname	= "numa_stat",
+		.data		= &sysctl_vm_numa_stat,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= sysctl_vm_numa_stat_handler,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+#endif
 #ifdef CONFIG_HUGETLB_PAGE
 	{
 		.procname	= "nr_hugepages",
@@ -2865,15 +2873,6 @@ static struct ctl_table vm_table[] = {
 		.mode           = 0644,
 		.proc_handler   = &hugetlb_mempolicy_sysctl_handler,
 	},
-	{
-		.procname		= "numa_stat",
-		.data			= &sysctl_vm_numa_stat,
-		.maxlen			= sizeof(int),
-		.mode			= 0644,
-		.proc_handler	= sysctl_vm_numa_stat_handler,
-		.extra1			= SYSCTL_ZERO,
-		.extra2			= SYSCTL_ONE,
-	},
 #endif
 	 {
 		.procname	= "hugetlb_shm_group",
@@ -2904,7 +2903,7 @@ static struct ctl_table vm_table[] = {
 		.mode		= 0200,
 		.proc_handler	= drop_caches_sysctl_handler,
 		.extra1		= SYSCTL_ONE,
-		.extra2		= &four,
+		.extra2		= SYSCTL_FOUR,
 	},
 #ifdef CONFIG_COMPACTION
 	{
@@ -2921,7 +2920,7 @@ static struct ctl_table vm_table[] = {
 		.mode		= 0644,
 		.proc_handler	= compaction_proactiveness_sysctl_handler,
 		.extra1		= SYSCTL_ZERO,
-		.extra2		= &one_hundred,
+		.extra2		= SYSCTL_ONE_HUNDRED,
 	},
 	{
 		.procname	= "extfrag_threshold",
@@ -2966,7 +2965,7 @@ static struct ctl_table vm_table[] = {
 		.mode		= 0644,
 		.proc_handler	= watermark_scale_factor_sysctl_handler,
 		.extra1		= SYSCTL_ONE,
-		.extra2		= &one_thousand,
+		.extra2		= SYSCTL_THREE_THOUSAND,
 	},
 	{
 		.procname	= "percpu_pagelist_high_fraction",
@@ -3045,7 +3044,7 @@ static struct ctl_table vm_table[] = {
 		.mode		= 0644,
 		.proc_handler	= sysctl_min_unmapped_ratio_sysctl_handler,
 		.extra1		= SYSCTL_ZERO,
-		.extra2		= &one_hundred,
+		.extra2		= SYSCTL_ONE_HUNDRED,
 	},
 	{
 		.procname	= "min_slab_ratio",
@@ -3054,7 +3053,7 @@ static struct ctl_table vm_table[] = {
 		.mode		= 0644,
 		.proc_handler	= sysctl_min_slab_ratio_sysctl_handler,
 		.extra1		= SYSCTL_ZERO,
-		.extra2		= &one_hundred,
+		.extra2		= SYSCTL_ONE_HUNDRED,
 	},
 #endif
 #ifdef CONFIG_SMP
@@ -3344,7 +3343,7 @@ static struct ctl_table fs_table[] = {
 		.mode		= 0600,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO,
-		.extra2		= &two,
+		.extra2		= SYSCTL_TWO,
 	},
 	{
 		.procname	= "protected_regular",
@@ -3353,7 +3352,7 @@ static struct ctl_table fs_table[] = {
 		.mode		= 0600,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO,
-		.extra2		= &two,
+		.extra2		= SYSCTL_TWO,
 	},
 	{
 		.procname	= "suid_dumpable",
@@ -3362,7 +3361,7 @@ static struct ctl_table fs_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax_coredump,
 		.extra1		= SYSCTL_ZERO,
-		.extra2		= &two,
+		.extra2		= SYSCTL_TWO,
 	},
 #if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE)
 	{
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 0ea8702eb516..23af5eca11b1 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -2311,6 +2311,7 @@ schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta,
 
 	return !t.task ? 0 : -EINTR;
 }
+EXPORT_SYMBOL_GPL(schedule_hrtimeout_range_clock);
 
 /**
  * schedule_hrtimeout_range - sleep until timeout
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 1cd10b102c51..5dead89308b7 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -1051,15 +1051,24 @@ retry_delete:
 }
 
 /*
- * This is called by do_exit or de_thread, only when there are no more
- * references to the shared signal_struct.
+ * This is called by do_exit or de_thread, only when nobody else can
+ * modify the signal->posix_timers list. Yet we need sighand->siglock
+ * to prevent the race with /proc/pid/timers.
  */
-void exit_itimers(struct signal_struct *sig)
+void exit_itimers(struct task_struct *tsk)
 {
+	struct list_head timers;
 	struct k_itimer *tmr;
 
-	while (!list_empty(&sig->posix_timers)) {
-		tmr = list_entry(sig->posix_timers.next, struct k_itimer, list);
+	if (list_empty(&tsk->signal->posix_timers))
+		return;
+
+	spin_lock_irq(&tsk->sighand->siglock);
+	list_replace_init(&tsk->signal->posix_timers, &timers);
+	spin_unlock_irq(&tsk->sighand->siglock);
+
+	while (!list_empty(&timers)) {
+		tmr = list_first_entry(&timers, struct k_itimer, list);
 		itimer_delete(tmr);
 	}
 }
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 871c912860ed..d6a0ff68df41 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -23,6 +23,7 @@
 #include <linux/pvclock_gtod.h>
 #include <linux/compiler.h>
 #include <linux/audit.h>
+#include <linux/random.h>
 
 #include "tick-internal.h"
 #include "ntp_internal.h"
@@ -1326,8 +1327,10 @@ out:
 	/* Signal hrtimers about time change */
 	clock_was_set(CLOCK_SET_WALL);
 
-	if (!ret)
+	if (!ret) {
 		audit_tk_injoffset(ts_delta);
+		add_device_randomness(ts, sizeof(*ts));
+	}
 
 	return ret;
 }
@@ -2413,6 +2416,7 @@ int do_adjtimex(struct __kernel_timex *txc)
 	ret = timekeeping_validate_timex(txc);
 	if (ret)
 		return ret;
+	add_device_randomness(txc, sizeof(*txc));
 
 	if (txc->modes & ADJ_SETOFFSET) {
 		struct timespec64 delta;
@@ -2430,6 +2434,7 @@ int do_adjtimex(struct __kernel_timex *txc)
 	audit_ntp_init(&ad);
 
 	ktime_get_real_ts64(&ts);
+	add_device_randomness(&ts, sizeof(ts));
 
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
 	write_seqcount_begin(&tk_core.seq);
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 6de5d4d63165..bedc5caceec7 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -47,6 +47,7 @@ obj-$(CONFIG_TRACING) += trace_output.o
 obj-$(CONFIG_TRACING) += trace_seq.o
 obj-$(CONFIG_TRACING) += trace_stat.o
 obj-$(CONFIG_TRACING) += trace_printk.o
+obj-$(CONFIG_TRACING) += 	pid_list.o
 obj-$(CONFIG_TRACING_MAP) += tracing_map.o
 obj-$(CONFIG_PREEMPTIRQ_DELAY_TEST) += preemptirq_delay_test.o
 obj-$(CONFIG_SYNTH_EVENT_GEN_TEST) += synth_event_gen_test.o
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index c42ff77eb6cc..eaa98e2b468f 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -1058,7 +1058,7 @@ static void blk_add_trace_rq_remap(void *ignore, struct request *rq, dev_t dev,
 	r.sector_from = cpu_to_be64(from);
 
 	__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
-			rq_data_dir(rq), 0, BLK_TA_REMAP, 0,
+			req_op(rq), rq->cmd_flags, BLK_TA_REMAP, 0,
 			sizeof(r), &r, blk_trace_request_get_cgid(rq));
 	rcu_read_unlock();
 }
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 53a1af21d25c..e10cf1b54812 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2901,6 +2901,16 @@ int ftrace_startup(struct ftrace_ops *ops, int command)
 
 	ftrace_startup_enable(command);
 
+	/*
+	 * If ftrace is in an undefined state, we just remove ops from list
+	 * to prevent the NULL pointer, instead of totally rolling it back and
+	 * free trampoline, because those actions could cause further damage.
+	 */
+	if (unlikely(ftrace_disabled)) {
+		__unregister_ftrace_function(ops);
+		return -ENODEV;
+	}
+
 	ops->flags &= ~FTRACE_OPS_FL_ADDING;
 
 	return 0;
@@ -7184,10 +7194,10 @@ static void clear_ftrace_pids(struct trace_array *tr, int type)
 	synchronize_rcu();
 
 	if ((type & TRACE_PIDS) && pid_list)
-		trace_free_pid_list(pid_list);
+		trace_pid_list_free(pid_list);
 
 	if ((type & TRACE_NO_PIDS) && no_pid_list)
-		trace_free_pid_list(no_pid_list);
+		trace_pid_list_free(no_pid_list);
 }
 
 void ftrace_clear_pids(struct trace_array *tr)
@@ -7428,7 +7438,7 @@ pid_write(struct file *filp, const char __user *ubuf,
 
 	if (filtered_pids) {
 		synchronize_rcu();
-		trace_free_pid_list(filtered_pids);
+		trace_pid_list_free(filtered_pids);
 	} else if (pid_list && !other_pids) {
 		/* Register a probe to set whether to ignore the tracing of a task */
 		register_trace_sched_switch(ftrace_filter_pid_sched_switch_probe, tr);
diff --git a/kernel/trace/pid_list.c b/kernel/trace/pid_list.c
new file mode 100644
index 000000000000..4483ef70b562
--- /dev/null
+++ b/kernel/trace/pid_list.c
@@ -0,0 +1,160 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 VMware Inc, Steven Rostedt <rostedt@goodmis.org>
+ */
+#include <linux/vmalloc.h>
+#include <linux/slab.h>
+#include "trace.h"
+
+/**
+ * trace_pid_list_is_set - test if the pid is set in the list
+ * @pid_list: The pid list to test
+ * @pid: The pid to to see if set in the list.
+ *
+ * Tests if @pid is is set in the @pid_list. This is usually called
+ * from the scheduler when a task is scheduled. Its pid is checked
+ * if it should be traced or not.
+ *
+ * Return true if the pid is in the list, false otherwise.
+ */
+bool trace_pid_list_is_set(struct trace_pid_list *pid_list, unsigned int pid)
+{
+	/*
+	 * If pid_max changed after filtered_pids was created, we
+	 * by default ignore all pids greater than the previous pid_max.
+	 */
+	if (pid >= pid_list->pid_max)
+		return false;
+
+	return test_bit(pid, pid_list->pids);
+}
+
+/**
+ * trace_pid_list_set - add a pid to the list
+ * @pid_list: The pid list to add the @pid to.
+ * @pid: The pid to add.
+ *
+ * Adds @pid to @pid_list. This is usually done explicitly by a user
+ * adding a task to be traced, or indirectly by the fork function
+ * when children should be traced and a task's pid is in the list.
+ *
+ * Return 0 on success, negative otherwise.
+ */
+int trace_pid_list_set(struct trace_pid_list *pid_list, unsigned int pid)
+{
+	/* Sorry, but we don't support pid_max changing after setting */
+	if (pid >= pid_list->pid_max)
+		return -EINVAL;
+
+	set_bit(pid, pid_list->pids);
+
+	return 0;
+}
+
+/**
+ * trace_pid_list_clear - remove a pid from the list
+ * @pid_list: The pid list to remove the @pid from.
+ * @pid: The pid to remove.
+ *
+ * Removes @pid from @pid_list. This is usually done explicitly by a user
+ * removing tasks from tracing, or indirectly by the exit function
+ * when a task that is set to be traced exits.
+ *
+ * Return 0 on success, negative otherwise.
+ */
+int trace_pid_list_clear(struct trace_pid_list *pid_list, unsigned int pid)
+{
+	/* Sorry, but we don't support pid_max changing after setting */
+	if (pid >= pid_list->pid_max)
+		return -EINVAL;
+
+	clear_bit(pid, pid_list->pids);
+
+	return 0;
+}
+
+/**
+ * trace_pid_list_next - return the next pid in the list
+ * @pid_list: The pid list to examine.
+ * @pid: The pid to start from
+ * @next: The pointer to place the pid that is set starting from @pid.
+ *
+ * Looks for the next consecutive pid that is in @pid_list starting
+ * at the pid specified by @pid. If one is set (including @pid), then
+ * that pid is placed into @next.
+ *
+ * Return 0 when a pid is found, -1 if there are no more pids included.
+ */
+int trace_pid_list_next(struct trace_pid_list *pid_list, unsigned int pid,
+			unsigned int *next)
+{
+	pid = find_next_bit(pid_list->pids, pid_list->pid_max, pid);
+
+	if (pid < pid_list->pid_max) {
+		*next = pid;
+		return 0;
+	}
+	return -1;
+}
+
+/**
+ * trace_pid_list_first - return the first pid in the list
+ * @pid_list: The pid list to examine.
+ * @pid: The pointer to place the pid first found pid that is set.
+ *
+ * Looks for the first pid that is set in @pid_list, and places it
+ * into @pid if found.
+ *
+ * Return 0 when a pid is found, -1 if there are no pids set.
+ */
+int trace_pid_list_first(struct trace_pid_list *pid_list, unsigned int *pid)
+{
+	unsigned int first;
+
+	first = find_first_bit(pid_list->pids, pid_list->pid_max);
+
+	if (first < pid_list->pid_max) {
+		*pid = first;
+		return 0;
+	}
+	return -1;
+}
+
+/**
+ * trace_pid_list_alloc - create a new pid_list
+ *
+ * Allocates a new pid_list to store pids into.
+ *
+ * Returns the pid_list on success, NULL otherwise.
+ */
+struct trace_pid_list *trace_pid_list_alloc(void)
+{
+	struct trace_pid_list *pid_list;
+
+	pid_list = kmalloc(sizeof(*pid_list), GFP_KERNEL);
+	if (!pid_list)
+		return NULL;
+
+	pid_list->pid_max = READ_ONCE(pid_max);
+
+	pid_list->pids = vzalloc((pid_list->pid_max + 7) >> 3);
+	if (!pid_list->pids) {
+		kfree(pid_list);
+		return NULL;
+	}
+	return pid_list;
+}
+
+/**
+ * trace_pid_list_free - Frees an allocated pid_list.
+ *
+ * Frees the memory for a pid_list that was allocated.
+ */
+void trace_pid_list_free(struct trace_pid_list *pid_list)
+{
+	if (!pid_list)
+		return;
+
+	vfree(pid_list->pids);
+	kfree(pid_list);
+}
diff --git a/kernel/trace/pid_list.h b/kernel/trace/pid_list.h
new file mode 100644
index 000000000000..80d0ecfe1536
--- /dev/null
+++ b/kernel/trace/pid_list.h
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Do not include this file directly. */
+
+#ifndef _TRACE_INTERNAL_PID_LIST_H
+#define _TRACE_INTERNAL_PID_LIST_H
+
+struct trace_pid_list {
+	int			pid_max;
+	unsigned long		*pids;
+};
+
+#endif /* _TRACE_INTERNAL_PID_LIST_H */
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 518ce39a878d..d93f9c59f50e 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -516,12 +516,6 @@ int call_filter_check_discard(struct trace_event_call *call, void *rec,
 	return 0;
 }
 
-void trace_free_pid_list(struct trace_pid_list *pid_list)
-{
-	vfree(pid_list->pids);
-	kfree(pid_list);
-}
-
 /**
  * trace_find_filtered_pid - check if a pid exists in a filtered_pid list
  * @filtered_pids: The list of pids to check
@@ -532,14 +526,7 @@ void trace_free_pid_list(struct trace_pid_list *pid_list)
 bool
 trace_find_filtered_pid(struct trace_pid_list *filtered_pids, pid_t search_pid)
 {
-	/*
-	 * If pid_max changed after filtered_pids was created, we
-	 * by default ignore all pids greater than the previous pid_max.
-	 */
-	if (search_pid >= filtered_pids->pid_max)
-		return false;
-
-	return test_bit(search_pid, filtered_pids->pids);
+	return trace_pid_list_is_set(filtered_pids, search_pid);
 }
 
 /**
@@ -596,15 +583,11 @@ void trace_filter_add_remove_task(struct trace_pid_list *pid_list,
 			return;
 	}
 
-	/* Sorry, but we don't support pid_max changing after setting */
-	if (task->pid >= pid_list->pid_max)
-		return;
-
 	/* "self" is set for forks, and NULL for exits */
 	if (self)
-		set_bit(task->pid, pid_list->pids);
+		trace_pid_list_set(pid_list, task->pid);
 	else
-		clear_bit(task->pid, pid_list->pids);
+		trace_pid_list_clear(pid_list, task->pid);
 }
 
 /**
@@ -621,18 +604,19 @@ void trace_filter_add_remove_task(struct trace_pid_list *pid_list,
  */
 void *trace_pid_next(struct trace_pid_list *pid_list, void *v, loff_t *pos)
 {
-	unsigned long pid = (unsigned long)v;
+	long pid = (unsigned long)v;
+	unsigned int next;
 
 	(*pos)++;
 
 	/* pid already is +1 of the actual previous bit */
-	pid = find_next_bit(pid_list->pids, pid_list->pid_max, pid);
+	if (trace_pid_list_next(pid_list, pid, &next) < 0)
+		return NULL;
 
-	/* Return pid + 1 to allow zero to be represented */
-	if (pid < pid_list->pid_max)
-		return (void *)(pid + 1);
+	pid = next;
 
-	return NULL;
+	/* Return pid + 1 to allow zero to be represented */
+	return (void *)(pid + 1);
 }
 
 /**
@@ -649,12 +633,14 @@ void *trace_pid_next(struct trace_pid_list *pid_list, void *v, loff_t *pos)
 void *trace_pid_start(struct trace_pid_list *pid_list, loff_t *pos)
 {
 	unsigned long pid;
+	unsigned int first;
 	loff_t l = 0;
 
-	pid = find_first_bit(pid_list->pids, pid_list->pid_max);
-	if (pid >= pid_list->pid_max)
+	if (trace_pid_list_first(pid_list, &first) < 0)
 		return NULL;
 
+	pid = first;
+
 	/* Return pid + 1 so that zero can be the exit value */
 	for (pid++; pid && l < *pos;
 	     pid = (unsigned long)trace_pid_next(pid_list, (void *)pid, &l))
@@ -690,7 +676,7 @@ int trace_pid_write(struct trace_pid_list *filtered_pids,
 	unsigned long val;
 	int nr_pids = 0;
 	ssize_t read = 0;
-	ssize_t ret = 0;
+	ssize_t ret;
 	loff_t pos;
 	pid_t pid;
 
@@ -703,55 +689,48 @@ int trace_pid_write(struct trace_pid_list *filtered_pids,
 	 * the user. If the operation fails, then the current list is
 	 * not modified.
 	 */
-	pid_list = kmalloc(sizeof(*pid_list), GFP_KERNEL);
+	pid_list = trace_pid_list_alloc();
 	if (!pid_list) {
 		trace_parser_put(&parser);
 		return -ENOMEM;
 	}
 
-	pid_list->pid_max = READ_ONCE(pid_max);
-
-	/* Only truncating will shrink pid_max */
-	if (filtered_pids && filtered_pids->pid_max > pid_list->pid_max)
-		pid_list->pid_max = filtered_pids->pid_max;
-
-	pid_list->pids = vzalloc((pid_list->pid_max + 7) >> 3);
-	if (!pid_list->pids) {
-		trace_parser_put(&parser);
-		kfree(pid_list);
-		return -ENOMEM;
-	}
-
 	if (filtered_pids) {
 		/* copy the current bits to the new max */
-		for_each_set_bit(pid, filtered_pids->pids,
-				 filtered_pids->pid_max) {
-			set_bit(pid, pid_list->pids);
+		ret = trace_pid_list_first(filtered_pids, &pid);
+		while (!ret) {
+			trace_pid_list_set(pid_list, pid);
+			ret = trace_pid_list_next(filtered_pids, pid + 1, &pid);
 			nr_pids++;
 		}
 	}
 
+	ret = 0;
 	while (cnt > 0) {
 
 		pos = 0;
 
 		ret = trace_get_user(&parser, ubuf, cnt, &pos);
-		if (ret < 0 || !trace_parser_loaded(&parser))
+		if (ret < 0)
 			break;
 
 		read += ret;
 		ubuf += ret;
 		cnt -= ret;
 
+		if (!trace_parser_loaded(&parser))
+			break;
+
 		ret = -EINVAL;
 		if (kstrtoul(parser.buffer, 0, &val))
 			break;
-		if (val >= pid_list->pid_max)
-			break;
 
 		pid = (pid_t)val;
 
-		set_bit(pid, pid_list->pids);
+		if (trace_pid_list_set(pid_list, pid) < 0) {
+			ret = -1;
+			break;
+		}
 		nr_pids++;
 
 		trace_parser_clear(&parser);
@@ -760,14 +739,13 @@ int trace_pid_write(struct trace_pid_list *filtered_pids,
 	trace_parser_put(&parser);
 
 	if (ret < 0) {
-		trace_free_pid_list(pid_list);
+		trace_pid_list_free(pid_list);
 		return ret;
 	}
 
 	if (!nr_pids) {
 		/* Cleared the list of pids */
-		trace_free_pid_list(pid_list);
-		read = ret;
+		trace_pid_list_free(pid_list);
 		pid_list = NULL;
 	}
 
@@ -9831,6 +9809,12 @@ void trace_init_global_iter(struct trace_iterator *iter)
 	/* Output in nanoseconds only if we are using a clock in nanoseconds. */
 	if (trace_clocks[iter->tr->clock_id].in_ns)
 		iter->iter_flags |= TRACE_FILE_TIME_IN_NS;
+
+	/* Can not use kmalloc for iter.temp and iter.fmt */
+	iter->temp = static_temp_buf;
+	iter->temp_size = STATIC_TEMP_BUF_SIZE;
+	iter->fmt = static_fmt_buf;
+	iter->fmt_size = STATIC_FMT_BUF_SIZE;
 }
 
 void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
@@ -9863,11 +9847,6 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 
 	/* Simulate the iterator */
 	trace_init_global_iter(&iter);
-	/* Can not use kmalloc for iter.temp and iter.fmt */
-	iter.temp = static_temp_buf;
-	iter.temp_size = STATIC_TEMP_BUF_SIZE;
-	iter.fmt = static_fmt_buf;
-	iter.fmt_size = STATIC_FMT_BUF_SIZE;
 
 	for_each_tracing_cpu(cpu) {
 		atomic_inc(&per_cpu_ptr(iter.array_buffer->data, cpu)->disabled);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 421374c304fc..28ea6c0be495 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -22,6 +22,8 @@
 #include <linux/ctype.h>
 #include <linux/once_lite.h>
 
+#include "pid_list.h"
+
 #ifdef CONFIG_FTRACE_SYSCALLS
 #include <asm/unistd.h>		/* For NR_SYSCALLS	     */
 #include <asm/syscall.h>	/* some archs define it here */
@@ -81,6 +83,9 @@ enum trace_type {
 #undef __dynamic_array
 #define __dynamic_array(type, item)	type	item[];
 
+#undef __rel_dynamic_array
+#define __rel_dynamic_array(type, item)	type	item[];
+
 #undef F_STRUCT
 #define F_STRUCT(args...)		args
 
@@ -191,10 +196,14 @@ struct trace_options {
 	struct trace_option_dentry	*topts;
 };
 
-struct trace_pid_list {
-	int				pid_max;
-	unsigned long			*pids;
-};
+struct trace_pid_list *trace_pid_list_alloc(void);
+void trace_pid_list_free(struct trace_pid_list *pid_list);
+bool trace_pid_list_is_set(struct trace_pid_list *pid_list, unsigned int pid);
+int trace_pid_list_set(struct trace_pid_list *pid_list, unsigned int pid);
+int trace_pid_list_clear(struct trace_pid_list *pid_list, unsigned int pid);
+int trace_pid_list_first(struct trace_pid_list *pid_list, unsigned int *pid);
+int trace_pid_list_next(struct trace_pid_list *pid_list, unsigned int pid,
+			unsigned int *next);
 
 enum {
 	TRACE_PIDS		= BIT(0),
diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c
index 928867f527e7..32688357c6da 100644
--- a/kernel/trace/trace_eprobe.c
+++ b/kernel/trace/trace_eprobe.c
@@ -226,6 +226,7 @@ static int trace_eprobe_tp_arg_update(struct trace_eprobe *ep, int i)
 	struct probe_arg *parg = &ep->tp.args[i];
 	struct ftrace_event_field *field;
 	struct list_head *head;
+	int ret = -ENOENT;
 
 	head = trace_get_fields(ep->event);
 	list_for_each_entry(field, head, link) {
@@ -235,9 +236,20 @@ static int trace_eprobe_tp_arg_update(struct trace_eprobe *ep, int i)
 			return 0;
 		}
 	}
+
+	/*
+	 * Argument not found on event. But allow for comm and COMM
+	 * to be used to get the current->comm.
+	 */
+	if (strcmp(parg->code->data, "COMM") == 0 ||
+	    strcmp(parg->code->data, "comm") == 0) {
+		parg->code->op = FETCH_OP_COMM;
+		ret = 0;
+	}
+
 	kfree(parg->code->data);
 	parg->code->data = NULL;
-	return -ENOENT;
+	return ret;
 }
 
 static int eprobe_event_define_fields(struct trace_event_call *event_call)
@@ -308,6 +320,24 @@ static unsigned long get_event_field(struct fetch_insn *code, void *rec)
 
 	addr = rec + field->offset;
 
+	if (is_string_field(field)) {
+		switch (field->filter_type) {
+		case FILTER_DYN_STRING:
+			val = (unsigned long)(rec + (*(unsigned int *)addr & 0xffff));
+			break;
+		case FILTER_STATIC_STRING:
+			val = (unsigned long)addr;
+			break;
+		case FILTER_PTR_STRING:
+			val = (unsigned long)(*(char *)addr);
+			break;
+		default:
+			WARN_ON_ONCE(1);
+			return 0;
+		}
+		return val;
+	}
+
 	switch (field->size) {
 	case 1:
 		if (field->is_signed)
@@ -339,16 +369,38 @@ static unsigned long get_event_field(struct fetch_insn *code, void *rec)
 
 static int get_eprobe_size(struct trace_probe *tp, void *rec)
 {
+	struct fetch_insn *code;
 	struct probe_arg *arg;
 	int i, len, ret = 0;
 
 	for (i = 0; i < tp->nr_args; i++) {
 		arg = tp->args + i;
-		if (unlikely(arg->dynamic)) {
+		if (arg->dynamic) {
 			unsigned long val;
 
-			val = get_event_field(arg->code, rec);
-			len = process_fetch_insn_bottom(arg->code + 1, val, NULL, NULL);
+			code = arg->code;
+ retry:
+			switch (code->op) {
+			case FETCH_OP_TP_ARG:
+				val = get_event_field(code, rec);
+				break;
+			case FETCH_OP_IMM:
+				val = code->immediate;
+				break;
+			case FETCH_OP_COMM:
+				val = (unsigned long)current->comm;
+				break;
+			case FETCH_OP_DATA:
+				val = (unsigned long)code->data;
+				break;
+			case FETCH_NOP_SYMBOL:	/* Ignore a place holder */
+				code++;
+				goto retry;
+			default:
+				continue;
+			}
+			code++;
+			len = process_fetch_insn_bottom(code, val, NULL, NULL);
 			if (len > 0)
 				ret += len;
 		}
@@ -366,8 +418,28 @@ process_fetch_insn(struct fetch_insn *code, void *rec, void *dest,
 {
 	unsigned long val;
 
-	val = get_event_field(code, rec);
-	return process_fetch_insn_bottom(code + 1, val, dest, base);
+ retry:
+	switch (code->op) {
+	case FETCH_OP_TP_ARG:
+		val = get_event_field(code, rec);
+		break;
+	case FETCH_OP_IMM:
+		val = code->immediate;
+		break;
+	case FETCH_OP_COMM:
+		val = (unsigned long)current->comm;
+		break;
+	case FETCH_OP_DATA:
+		val = (unsigned long)code->data;
+		break;
+	case FETCH_NOP_SYMBOL:	/* Ignore a place holder */
+		code++;
+		goto retry;
+	default:
+		return -EILSEQ;
+	}
+	code++;
+	return process_fetch_insn_bottom(code, val, dest, base);
 }
 NOKPROBE_SYMBOL(process_fetch_insn)
 
@@ -849,6 +921,10 @@ static int trace_eprobe_tp_update_arg(struct trace_eprobe *ep, const char *argv[
 	if (ep->tp.args[i].code->op == FETCH_OP_TP_ARG)
 		ret = trace_eprobe_tp_arg_update(ep, i);
 
+	/* Handle symbols "@" */
+	if (!ret)
+		ret = traceprobe_update_arg(&ep->tp.args[i]);
+
 	return ret;
 }
 
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index fba8cb77a73a..083f648e3265 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -157,7 +157,7 @@ static void perf_trace_event_unreg(struct perf_event *p_event)
 	int i;
 
 	if (--tp_event->perf_refcount > 0)
-		goto out;
+		return;
 
 	tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER, NULL);
 
@@ -176,8 +176,6 @@ static void perf_trace_event_unreg(struct perf_event *p_event)
 			perf_trace_buf[i] = NULL;
 		}
 	}
-out:
-	trace_event_put_ref(tp_event);
 }
 
 static int perf_trace_event_open(struct perf_event *p_event)
@@ -241,6 +239,7 @@ void perf_trace_destroy(struct perf_event *p_event)
 	mutex_lock(&event_mutex);
 	perf_trace_event_close(p_event);
 	perf_trace_event_unreg(p_event);
+	trace_event_put_ref(p_event->tp_event);
 	mutex_unlock(&event_mutex);
 }
 
@@ -292,6 +291,7 @@ void perf_kprobe_destroy(struct perf_event *p_event)
 	mutex_lock(&event_mutex);
 	perf_trace_event_close(p_event);
 	perf_trace_event_unreg(p_event);
+	trace_event_put_ref(p_event->tp_event);
 	mutex_unlock(&event_mutex);
 
 	destroy_local_trace_kprobe(p_event->tp_event);
@@ -347,6 +347,7 @@ void perf_uprobe_destroy(struct perf_event *p_event)
 	mutex_lock(&event_mutex);
 	perf_trace_event_close(p_event);
 	perf_trace_event_unreg(p_event);
+	trace_event_put_ref(p_event->tp_event);
 	mutex_unlock(&event_mutex);
 	destroy_local_trace_uprobe(p_event->tp_event);
 }
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index c072e8b9849c..c84c94334a60 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -176,6 +176,7 @@ static int trace_define_generic_fields(void)
 
 	__generic_field(int, CPU, FILTER_CPU);
 	__generic_field(int, cpu, FILTER_CPU);
+	__generic_field(int, common_cpu, FILTER_CPU);
 	__generic_field(char *, COMM, FILTER_COMM);
 	__generic_field(char *, comm, FILTER_COMM);
 
@@ -407,7 +408,14 @@ static void test_event_printk(struct trace_event_call *call)
 				a = strchr(fmt + i, '&');
 				if ((a && (a < r)) || test_field(r, call))
 					dereference_flags &= ~(1ULL << arg);
+			} else if ((r = strstr(fmt + i, "__get_dynamic_array(")) &&
+				   (!c || r < c)) {
+				dereference_flags &= ~(1ULL << arg);
+			} else if ((r = strstr(fmt + i, "__get_sockaddr(")) &&
+				   (!c || r < c)) {
+				dereference_flags &= ~(1ULL << arg);
 			}
+
 		next_arg:
 			i--;
 			arg++;
@@ -893,10 +901,10 @@ static void __ftrace_clear_event_pids(struct trace_array *tr, int type)
 	tracepoint_synchronize_unregister();
 
 	if ((type & TRACE_PIDS) && pid_list)
-		trace_free_pid_list(pid_list);
+		trace_pid_list_free(pid_list);
 
 	if ((type & TRACE_NO_PIDS) && no_pid_list)
-		trace_free_pid_list(no_pid_list);
+		trace_pid_list_free(no_pid_list);
 }
 
 static void ftrace_clear_event_pids(struct trace_array *tr, int type)
@@ -1975,7 +1983,7 @@ event_pid_write(struct file *filp, const char __user *ubuf,
 
 	if (filtered_pids) {
 		tracepoint_synchronize_unregister();
-		trace_free_pid_list(filtered_pids);
+		trace_pid_list_free(filtered_pids);
 	} else if (pid_list && !other_pids) {
 		register_pid_events(tr);
 	}
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 45a78e9c65c9..d5c7b9a37ed5 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -4056,6 +4056,8 @@ static int parse_var_defs(struct hist_trigger_data *hist_data)
 
 			s = kstrdup(field_str, GFP_KERNEL);
 			if (!s) {
+				kfree(hist_data->attrs->var_defs.name[n_vars]);
+				hist_data->attrs->var_defs.name[n_vars] = NULL;
 				ret = -ENOMEM;
 				goto free;
 			}
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 67c7979c40c0..106f9813841a 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -128,7 +128,8 @@ static bool check_user_trigger(struct trace_event_file *file)
 {
 	struct event_trigger_data *data;
 
-	list_for_each_entry_rcu(data, &file->triggers, list) {
+	list_for_each_entry_rcu(data, &file->triggers, list,
+				lockdep_is_held(&event_mutex)) {
 		if (data->flags & EVENT_TRIGGER_FL_PROBE)
 			continue;
 		return true;
diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c
index f4938040c228..1e130da1b742 100644
--- a/kernel/trace/trace_preemptirq.c
+++ b/kernel/trace/trace_preemptirq.c
@@ -46,7 +46,7 @@ void trace_hardirqs_on(void)
 		this_cpu_write(tracing_irq_cpu, 0);
 	}
 
-	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+	lockdep_hardirqs_on_prepare();
 	lockdep_hardirqs_on(CALLER_ADDR0);
 }
 EXPORT_SYMBOL(trace_hardirqs_on);
@@ -94,15 +94,15 @@ __visible void trace_hardirqs_on_caller(unsigned long caller_addr)
 		this_cpu_write(tracing_irq_cpu, 0);
 	}
 
-	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
-	lockdep_hardirqs_on(CALLER_ADDR0);
+	lockdep_hardirqs_on_prepare();
+	lockdep_hardirqs_on(caller_addr);
 }
 EXPORT_SYMBOL(trace_hardirqs_on_caller);
 NOKPROBE_SYMBOL(trace_hardirqs_on_caller);
 
 __visible void trace_hardirqs_off_caller(unsigned long caller_addr)
 {
-	lockdep_hardirqs_off(CALLER_ADDR0);
+	lockdep_hardirqs_off(caller_addr);
 
 	if (!this_cpu_read(tracing_irq_cpu)) {
 		this_cpu_write(tracing_irq_cpu, 1);
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index bb4605b60de7..2bbe4a7c6a2b 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -279,7 +279,14 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t,
 	int ret = 0;
 	int len;
 
-	if (strcmp(arg, "retval") == 0) {
+	if (flags & TPARG_FL_TPOINT) {
+		if (code->data)
+			return -EFAULT;
+		code->data = kstrdup(arg, GFP_KERNEL);
+		if (!code->data)
+			return -ENOMEM;
+		code->op = FETCH_OP_TP_ARG;
+	} else if (strcmp(arg, "retval") == 0) {
 		if (flags & TPARG_FL_RETURN) {
 			code->op = FETCH_OP_RETVAL;
 		} else {
@@ -303,7 +310,7 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t,
 			}
 		} else
 			goto inval_var;
-	} else if (strcmp(arg, "comm") == 0) {
+	} else if (strcmp(arg, "comm") == 0 || strcmp(arg, "COMM") == 0) {
 		code->op = FETCH_OP_COMM;
 #ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API
 	} else if (((flags & TPARG_FL_MASK) ==
@@ -319,13 +326,6 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t,
 		code->op = FETCH_OP_ARG;
 		code->param = (unsigned int)param - 1;
 #endif
-	} else if (flags & TPARG_FL_TPOINT) {
-		if (code->data)
-			return -EFAULT;
-		code->data = kstrdup(arg, GFP_KERNEL);
-		if (!code->data)
-			return -ENOMEM;
-		code->op = FETCH_OP_TP_ARG;
 	} else
 		goto inval_var;
 
@@ -380,6 +380,11 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
 		break;
 
 	case '%':	/* named register */
+		if (flags & TPARG_FL_TPOINT) {
+			/* eprobes do not handle registers */
+			trace_probe_log_err(offs, BAD_VAR);
+			break;
+		}
 		ret = regs_query_register_offset(arg + 1);
 		if (ret >= 0) {
 			code->op = FETCH_OP_REG;
@@ -613,9 +618,11 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
 
 	/*
 	 * Since $comm and immediate string can not be dereferenced,
-	 * we can find those by strcmp.
+	 * we can find those by strcmp. But ignore for eprobes.
 	 */
-	if (strcmp(arg, "$comm") == 0 || strncmp(arg, "\\\"", 2) == 0) {
+	if (!(flags & TPARG_FL_TPOINT) &&
+	    (strcmp(arg, "$comm") == 0 || strcmp(arg, "$COMM") == 0 ||
+	     strncmp(arg, "\\\"", 2) == 0)) {
 		/* The type of $comm must be "string", and not an array. */
 		if (parg->count || (t && strcmp(t, "string")))
 			goto out;
diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c
index b1ae7c9c3b47..1059ef6c3711 100644
--- a/kernel/watch_queue.c
+++ b/kernel/watch_queue.c
@@ -34,6 +34,27 @@ MODULE_LICENSE("GPL");
 #define WATCH_QUEUE_NOTE_SIZE 128
 #define WATCH_QUEUE_NOTES_PER_PAGE (PAGE_SIZE / WATCH_QUEUE_NOTE_SIZE)
 
+/*
+ * This must be called under the RCU read-lock, which makes
+ * sure that the wqueue still exists. It can then take the lock,
+ * and check that the wqueue hasn't been destroyed, which in
+ * turn makes sure that the notification pipe still exists.
+ */
+static inline bool lock_wqueue(struct watch_queue *wqueue)
+{
+	spin_lock_bh(&wqueue->lock);
+	if (unlikely(wqueue->defunct)) {
+		spin_unlock_bh(&wqueue->lock);
+		return false;
+	}
+	return true;
+}
+
+static inline void unlock_wqueue(struct watch_queue *wqueue)
+{
+	spin_unlock_bh(&wqueue->lock);
+}
+
 static void watch_queue_pipe_buf_release(struct pipe_inode_info *pipe,
 					 struct pipe_buffer *buf)
 {
@@ -69,6 +90,10 @@ static const struct pipe_buf_operations watch_queue_pipe_buf_ops = {
 
 /*
  * Post a notification to a watch queue.
+ *
+ * Must be called with the RCU lock for reading, and the
+ * watch_queue lock held, which guarantees that the pipe
+ * hasn't been released.
  */
 static bool post_one_notification(struct watch_queue *wqueue,
 				  struct watch_notification *n)
@@ -85,9 +110,6 @@ static bool post_one_notification(struct watch_queue *wqueue,
 
 	spin_lock_irq(&pipe->rd_wait.lock);
 
-	if (wqueue->defunct)
-		goto out;
-
 	mask = pipe->ring_size - 1;
 	head = pipe->head;
 	tail = pipe->tail;
@@ -203,7 +225,10 @@ void __post_watch_notification(struct watch_list *wlist,
 		if (security_post_notification(watch->cred, cred, n) < 0)
 			continue;
 
-		post_one_notification(wqueue, n);
+		if (lock_wqueue(wqueue)) {
+			post_one_notification(wqueue, n);
+			unlock_wqueue(wqueue);
+		}
 	}
 
 	rcu_read_unlock();
@@ -432,6 +457,33 @@ void init_watch(struct watch *watch, struct watch_queue *wqueue)
 	rcu_assign_pointer(watch->queue, wqueue);
 }
 
+static int add_one_watch(struct watch *watch, struct watch_list *wlist, struct watch_queue *wqueue)
+{
+	const struct cred *cred;
+	struct watch *w;
+
+	hlist_for_each_entry(w, &wlist->watchers, list_node) {
+		struct watch_queue *wq = rcu_access_pointer(w->queue);
+		if (wqueue == wq && watch->id == w->id)
+			return -EBUSY;
+	}
+
+	cred = current_cred();
+	if (atomic_inc_return(&cred->user->nr_watches) > task_rlimit(current, RLIMIT_NOFILE)) {
+		atomic_dec(&cred->user->nr_watches);
+		return -EAGAIN;
+	}
+
+	watch->cred = get_cred(cred);
+	rcu_assign_pointer(watch->watch_list, wlist);
+
+	kref_get(&wqueue->usage);
+	kref_get(&watch->usage);
+	hlist_add_head(&watch->queue_node, &wqueue->watches);
+	hlist_add_head_rcu(&watch->list_node, &wlist->watchers);
+	return 0;
+}
+
 /**
  * add_watch_to_object - Add a watch on an object to a watch list
  * @watch: The watch to add
@@ -446,33 +498,21 @@ void init_watch(struct watch *watch, struct watch_queue *wqueue)
  */
 int add_watch_to_object(struct watch *watch, struct watch_list *wlist)
 {
-	struct watch_queue *wqueue = rcu_access_pointer(watch->queue);
-	struct watch *w;
-
-	hlist_for_each_entry(w, &wlist->watchers, list_node) {
-		struct watch_queue *wq = rcu_access_pointer(w->queue);
-		if (wqueue == wq && watch->id == w->id)
-			return -EBUSY;
-	}
+	struct watch_queue *wqueue;
+	int ret = -ENOENT;
 
-	watch->cred = get_current_cred();
-	rcu_assign_pointer(watch->watch_list, wlist);
+	rcu_read_lock();
 
-	if (atomic_inc_return(&watch->cred->user->nr_watches) >
-	    task_rlimit(current, RLIMIT_NOFILE)) {
-		atomic_dec(&watch->cred->user->nr_watches);
-		put_cred(watch->cred);
-		return -EAGAIN;
+	wqueue = rcu_access_pointer(watch->queue);
+	if (lock_wqueue(wqueue)) {
+		spin_lock(&wlist->lock);
+		ret = add_one_watch(watch, wlist, wqueue);
+		spin_unlock(&wlist->lock);
+		unlock_wqueue(wqueue);
 	}
 
-	spin_lock_bh(&wqueue->lock);
-	kref_get(&wqueue->usage);
-	kref_get(&watch->usage);
-	hlist_add_head(&watch->queue_node, &wqueue->watches);
-	spin_unlock_bh(&wqueue->lock);
-
-	hlist_add_head(&watch->list_node, &wlist->watchers);
-	return 0;
+	rcu_read_unlock();
+	return ret;
 }
 EXPORT_SYMBOL(add_watch_to_object);
 
@@ -523,20 +563,15 @@ found:
 
 	wqueue = rcu_dereference(watch->queue);
 
-	/* We don't need the watch list lock for the next bit as RCU is
-	 * protecting *wqueue from deallocation.
-	 */
-	if (wqueue) {
+	if (lock_wqueue(wqueue)) {
 		post_one_notification(wqueue, &n.watch);
 
-		spin_lock_bh(&wqueue->lock);
-
 		if (!hlist_unhashed(&watch->queue_node)) {
 			hlist_del_init_rcu(&watch->queue_node);
 			put_watch(watch);
 		}
 
-		spin_unlock_bh(&wqueue->lock);
+		unlock_wqueue(wqueue);
 	}
 
 	if (wlist->release_watch) {
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index ad912511a0c0..1cfa269bd448 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -537,7 +537,7 @@ int lockup_detector_offline_cpu(unsigned int cpu)
 	return 0;
 }
 
-static void lockup_detector_reconfigure(void)
+static void __lockup_detector_reconfigure(void)
 {
 	cpus_read_lock();
 	watchdog_nmi_stop();
@@ -557,6 +557,13 @@ static void lockup_detector_reconfigure(void)
 	__lockup_detector_cleanup();
 }
 
+void lockup_detector_reconfigure(void)
+{
+	mutex_lock(&watchdog_mutex);
+	__lockup_detector_reconfigure();
+	mutex_unlock(&watchdog_mutex);
+}
+
 /*
  * Create the watchdog infrastructure and configure the detector(s).
  */
@@ -573,13 +580,13 @@ static __init void lockup_detector_setup(void)
 		return;
 
 	mutex_lock(&watchdog_mutex);
-	lockup_detector_reconfigure();
+	__lockup_detector_reconfigure();
 	softlockup_initialized = true;
 	mutex_unlock(&watchdog_mutex);
 }
 
 #else /* CONFIG_SOFTLOCKUP_DETECTOR */
-static void lockup_detector_reconfigure(void)
+static void __lockup_detector_reconfigure(void)
 {
 	cpus_read_lock();
 	watchdog_nmi_stop();
@@ -587,9 +594,13 @@ static void lockup_detector_reconfigure(void)
 	watchdog_nmi_start();
 	cpus_read_unlock();
 }
+void lockup_detector_reconfigure(void)
+{
+	__lockup_detector_reconfigure();
+}
 static inline void lockup_detector_setup(void)
 {
-	lockup_detector_reconfigure();
+	__lockup_detector_reconfigure();
 }
 #endif /* !CONFIG_SOFTLOCKUP_DETECTOR */
 
@@ -629,7 +640,7 @@ static void proc_watchdog_update(void)
 {
 	/* Remove impossible cpus to keep sysctl output clean. */
 	cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask);
-	lockup_detector_reconfigure();
+	__lockup_detector_reconfigure();
 }
 
 /*
diff --git a/lib/crypto/Kconfig b/lib/crypto/Kconfig
index 5056663c2aff..a29eff4f969e 100644
--- a/lib/crypto/Kconfig
+++ b/lib/crypto/Kconfig
@@ -33,7 +33,6 @@ config CRYPTO_ARCH_HAVE_LIB_CHACHA
 
 config CRYPTO_LIB_CHACHA_GENERIC
 	tristate
-	select XOR_BLOCKS
 	help
 	  This symbol can be depended upon by arch implementations of the
 	  ChaCha library interface that require the generic code as a
diff --git a/lib/crypto/blake2s-selftest.c b/lib/crypto/blake2s-selftest.c
index 409e4b728770..7d77dea15587 100644
--- a/lib/crypto/blake2s-selftest.c
+++ b/lib/crypto/blake2s-selftest.c
@@ -4,6 +4,8 @@
  */
 
 #include <crypto/internal/blake2s.h>
+#include <linux/kernel.h>
+#include <linux/random.h>
 #include <linux/string.h>
 
 /*
@@ -587,5 +589,44 @@ bool __init blake2s_selftest(void)
 		}
 	}
 
+	for (i = 0; i < 32; ++i) {
+		enum { TEST_ALIGNMENT = 16 };
+		u8 unaligned_block[BLAKE2S_BLOCK_SIZE + TEST_ALIGNMENT - 1]
+					__aligned(TEST_ALIGNMENT);
+		u8 blocks[BLAKE2S_BLOCK_SIZE * 2];
+		struct blake2s_state state1, state2;
+
+		get_random_bytes(blocks, sizeof(blocks));
+		get_random_bytes(&state, sizeof(state));
+
+#if defined(CONFIG_CRYPTO_LIB_BLAKE2S_GENERIC) && \
+    defined(CONFIG_CRYPTO_ARCH_HAVE_LIB_BLAKE2S)
+		memcpy(&state1, &state, sizeof(state1));
+		memcpy(&state2, &state, sizeof(state2));
+		blake2s_compress(&state1, blocks, 2, BLAKE2S_BLOCK_SIZE);
+		blake2s_compress_generic(&state2, blocks, 2, BLAKE2S_BLOCK_SIZE);
+		if (memcmp(&state1, &state2, sizeof(state1))) {
+			pr_err("blake2s random compress self-test %d: FAIL\n",
+			       i + 1);
+			success = false;
+		}
+#endif
+
+		memcpy(&state1, &state, sizeof(state1));
+		blake2s_compress(&state1, blocks, 1, BLAKE2S_BLOCK_SIZE);
+		for (l = 1; l < TEST_ALIGNMENT; ++l) {
+			memcpy(unaligned_block + l, blocks,
+			       BLAKE2S_BLOCK_SIZE);
+			memcpy(&state2, &state, sizeof(state2));
+			blake2s_compress(&state2, unaligned_block + l, 1,
+					 BLAKE2S_BLOCK_SIZE);
+			if (memcmp(&state1, &state2, sizeof(state1))) {
+				pr_err("blake2s random compress align %d self-test %d: FAIL\n",
+				       l, i + 1);
+				success = false;
+			}
+		}
+	}
+
 	return success;
 }
diff --git a/lib/crypto/blake2s.c b/lib/crypto/blake2s.c
index c71c09621c09..98e688c6d891 100644
--- a/lib/crypto/blake2s.c
+++ b/lib/crypto/blake2s.c
@@ -16,16 +16,44 @@
 #include <linux/init.h>
 #include <linux/bug.h>
 
+static inline void blake2s_set_lastblock(struct blake2s_state *state)
+{
+	state->f[0] = -1;
+}
+
 void blake2s_update(struct blake2s_state *state, const u8 *in, size_t inlen)
 {
-	__blake2s_update(state, in, inlen, false);
+	const size_t fill = BLAKE2S_BLOCK_SIZE - state->buflen;
+
+	if (unlikely(!inlen))
+		return;
+	if (inlen > fill) {
+		memcpy(state->buf + state->buflen, in, fill);
+		blake2s_compress(state, state->buf, 1, BLAKE2S_BLOCK_SIZE);
+		state->buflen = 0;
+		in += fill;
+		inlen -= fill;
+	}
+	if (inlen > BLAKE2S_BLOCK_SIZE) {
+		const size_t nblocks = DIV_ROUND_UP(inlen, BLAKE2S_BLOCK_SIZE);
+		blake2s_compress(state, in, nblocks - 1, BLAKE2S_BLOCK_SIZE);
+		in += BLAKE2S_BLOCK_SIZE * (nblocks - 1);
+		inlen -= BLAKE2S_BLOCK_SIZE * (nblocks - 1);
+	}
+	memcpy(state->buf + state->buflen, in, inlen);
+	state->buflen += inlen;
 }
 EXPORT_SYMBOL(blake2s_update);
 
 void blake2s_final(struct blake2s_state *state, u8 *out)
 {
 	WARN_ON(IS_ENABLED(DEBUG) && !out);
-	__blake2s_final(state, out, false);
+	blake2s_set_lastblock(state);
+	memset(state->buf + state->buflen, 0,
+	       BLAKE2S_BLOCK_SIZE - state->buflen); /* Padding */
+	blake2s_compress(state, state->buf, 1, state->buflen);
+	cpu_to_le32_array(state->h, ARRAY_SIZE(state->h));
+	memcpy(out, state->h, state->outlen);
 	memzero_explicit(state, sizeof(*state));
 }
 EXPORT_SYMBOL(blake2s_final);
@@ -38,12 +66,7 @@ static int __init blake2s_mod_init(void)
 	return 0;
 }
 
-static void __exit blake2s_mod_exit(void)
-{
-}
-
 module_init(blake2s_mod_init);
-module_exit(blake2s_mod_exit);
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("BLAKE2s hash function");
 MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>");
diff --git a/lib/idr.c b/lib/idr.c
index f4ab4f4aa3c7..7ecdfdb5309e 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -491,7 +491,8 @@ void ida_free(struct ida *ida, unsigned int id)
 	struct ida_bitmap *bitmap;
 	unsigned long flags;
 
-	BUG_ON((int)id < 0);
+	if ((int)id < 0)
+		return;
 
 	xas_lock_irqsave(&xas, flags);
 	bitmap = xas_load(&xas);
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 6cf2d66fb839..d0c3e939ee60 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -691,6 +691,7 @@ static size_t copy_mc_pipe_to_iter(const void *addr, size_t bytes,
 	struct pipe_inode_info *pipe = i->pipe;
 	unsigned int p_mask = pipe->ring_size - 1;
 	unsigned int i_head;
+	unsigned int valid = pipe->head;
 	size_t n, off, xfer = 0;
 
 	if (!sanity(i))
@@ -704,11 +705,17 @@ static size_t copy_mc_pipe_to_iter(const void *addr, size_t bytes,
 		rem = copy_mc_to_kernel(p + off, addr + xfer, chunk);
 		chunk -= rem;
 		kunmap_local(p);
-		i->head = i_head;
-		i->iov_offset = off + chunk;
-		xfer += chunk;
-		if (rem)
+		if (chunk) {
+			i->head = i_head;
+			i->iov_offset = off + chunk;
+			xfer += chunk;
+			valid = i_head + 1;
+		}
+		if (rem) {
+			pipe->bufs[i_head & p_mask].len -= rem;
+			pipe_discard_from(pipe, valid);
 			break;
+		}
 		n -= chunk;
 		off = 0;
 		i_head++;
diff --git a/lib/list_debug.c b/lib/list_debug.c
index 5d5424b51b74..413daa72a3d8 100644
--- a/lib/list_debug.c
+++ b/lib/list_debug.c
@@ -20,7 +20,11 @@
 bool __list_add_valid(struct list_head *new, struct list_head *prev,
 		      struct list_head *next)
 {
-	if (CHECK_DATA_CORRUPTION(next->prev != prev,
+	if (CHECK_DATA_CORRUPTION(prev == NULL,
+			"list_add corruption. prev is NULL.\n") ||
+	    CHECK_DATA_CORRUPTION(next == NULL,
+			"list_add corruption. next is NULL.\n") ||
+	    CHECK_DATA_CORRUPTION(next->prev != prev,
 			"list_add corruption. next->prev should be prev (%px), but was %px. (next=%px).\n",
 			prev, next->prev, next) ||
 	    CHECK_DATA_CORRUPTION(prev->next != next,
@@ -42,7 +46,11 @@ bool __list_del_entry_valid(struct list_head *entry)
 	prev = entry->prev;
 	next = entry->next;
 
-	if (CHECK_DATA_CORRUPTION(next == LIST_POISON1,
+	if (CHECK_DATA_CORRUPTION(next == NULL,
+			"list_del corruption, %px->next is NULL\n", entry) ||
+	    CHECK_DATA_CORRUPTION(prev == NULL,
+			"list_del corruption, %px->prev is NULL\n", entry) ||
+	    CHECK_DATA_CORRUPTION(next == LIST_POISON1,
 			"list_del corruption, %px->next is LIST_POISON1 (%px)\n",
 			entry, LIST_POISON1) ||
 	    CHECK_DATA_CORRUPTION(prev == LIST_POISON2,
diff --git a/lib/livepatch/test_klp_callbacks_busy.c b/lib/livepatch/test_klp_callbacks_busy.c
index 7ac845f65be5..133929e0ce8f 100644
--- a/lib/livepatch/test_klp_callbacks_busy.c
+++ b/lib/livepatch/test_klp_callbacks_busy.c
@@ -16,10 +16,12 @@ MODULE_PARM_DESC(block_transition, "block_transition (default=false)");
 
 static void busymod_work_func(struct work_struct *work);
 static DECLARE_WORK(work, busymod_work_func);
+static DECLARE_COMPLETION(busymod_work_started);
 
 static void busymod_work_func(struct work_struct *work)
 {
 	pr_info("%s enter\n", __func__);
+	complete(&busymod_work_started);
 
 	while (READ_ONCE(block_transition)) {
 		/*
@@ -37,6 +39,12 @@ static int test_klp_callbacks_busy_init(void)
 	pr_info("%s\n", __func__);
 	schedule_work(&work);
 
+	/*
+	 * To synchronize kernel messages, hold the init function from
+	 * exiting until the work function's entry message has printed.
+	 */
+	wait_for_completion(&busymod_work_started);
+
 	if (!block_transition) {
 		/*
 		 * Serialize output: print all messages from the work
diff --git a/lib/ratelimit.c b/lib/ratelimit.c
index e01a93f46f83..ce945c17980b 100644
--- a/lib/ratelimit.c
+++ b/lib/ratelimit.c
@@ -26,10 +26,16 @@
  */
 int ___ratelimit(struct ratelimit_state *rs, const char *func)
 {
+	/* Paired with WRITE_ONCE() in .proc_handler().
+	 * Changing two values seperately could be inconsistent
+	 * and some message could be lost.  (See: net_ratelimit_state).
+	 */
+	int interval = READ_ONCE(rs->interval);
+	int burst = READ_ONCE(rs->burst);
 	unsigned long flags;
 	int ret;
 
-	if (!rs->interval)
+	if (!interval)
 		return 1;
 
 	/*
@@ -44,7 +50,7 @@ int ___ratelimit(struct ratelimit_state *rs, const char *func)
 	if (!rs->begin)
 		rs->begin = jiffies;
 
-	if (time_is_before_jiffies(rs->begin + rs->interval)) {
+	if (time_is_before_jiffies(rs->begin + interval)) {
 		if (rs->missed) {
 			if (!(rs->flags & RATELIMIT_MSG_ON_RELEASE)) {
 				printk_deferred(KERN_WARNING
@@ -56,7 +62,7 @@ int ___ratelimit(struct ratelimit_state *rs, const char *func)
 		rs->begin   = jiffies;
 		rs->printed = 0;
 	}
-	if (rs->burst && rs->burst > rs->printed) {
+	if (burst && burst > rs->printed) {
 		rs->printed++;
 		ret = 1;
 	} else {
diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c
index 046ac6297c78..a2bb7738c373 100644
--- a/lib/smp_processor_id.c
+++ b/lib/smp_processor_id.c
@@ -47,9 +47,9 @@ unsigned int check_preemption_disabled(const char *what1, const char *what2)
 
 	printk("caller is %pS\n", __builtin_return_address(0));
 	dump_stack();
-	instrumentation_end();
 
 out_enable:
+	instrumentation_end();
 	preempt_enable_no_resched_notrace();
 out:
 	return this_cpu;
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index 68d125b409f2..84f5dd3b0fc7 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -8890,9 +8890,9 @@ static struct skb_segment_test skb_segment_tests[] __initconst = {
 		.build_skb = build_test_skb_linear_no_head_frag,
 		.features = NETIF_F_SG | NETIF_F_FRAGLIST |
 			    NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_GSO |
-			    NETIF_F_LLTX_BIT | NETIF_F_GRO |
+			    NETIF_F_LLTX | NETIF_F_GRO |
 			    NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM |
-			    NETIF_F_HW_VLAN_STAG_TX_BIT
+			    NETIF_F_HW_VLAN_STAG_TX
 	}
 };
 
diff --git a/lib/test_hmm.c b/lib/test_hmm.c
index ac794e354069..a89cb4281c9d 100644
--- a/lib/test_hmm.c
+++ b/lib/test_hmm.c
@@ -731,7 +731,7 @@ static int dmirror_exclusive(struct dmirror *dmirror,
 
 	mmap_read_lock(mm);
 	for (addr = start; addr < end; addr = next) {
-		unsigned long mapped;
+		unsigned long mapped = 0;
 		int i;
 
 		if (end < addr + (ARRAY_SIZE(pages) << PAGE_SHIFT))
@@ -740,7 +740,13 @@ static int dmirror_exclusive(struct dmirror *dmirror,
 			next = addr + (ARRAY_SIZE(pages) << PAGE_SHIFT);
 
 		ret = make_device_exclusive_range(mm, addr, next, pages, NULL);
-		mapped = dmirror_atomic_map(addr, next, pages, dmirror);
+		/*
+		 * Do dmirror_atomic_map() iff all pages are marked for
+		 * exclusive access to avoid accessing uninitialized
+		 * fields of pages.
+		 */
+		if (ret == (next - addr) >> PAGE_SHIFT)
+			mapped = dmirror_atomic_map(addr, next, pages, dmirror);
 		for (i = 0; i < ret; i++) {
 			if (pages[i]) {
 				unlock_page(pages[i]);
diff --git a/lib/test_kasan.c b/lib/test_kasan.c
index 8835e0784578..89f444cabd4a 100644
--- a/lib/test_kasan.c
+++ b/lib/test_kasan.c
@@ -125,6 +125,7 @@ static void kmalloc_oob_right(struct kunit *test)
 	ptr = kmalloc(size, GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
 
+	OPTIMIZER_HIDE_VAR(ptr);
 	/*
 	 * An unaligned access past the requested kmalloc size.
 	 * Only generic KASAN can precisely detect these.
@@ -153,6 +154,7 @@ static void kmalloc_oob_left(struct kunit *test)
 	ptr = kmalloc(size, GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
 
+	OPTIMIZER_HIDE_VAR(ptr);
 	KUNIT_EXPECT_KASAN_FAIL(test, *ptr = *(ptr - 1));
 	kfree(ptr);
 }
@@ -165,6 +167,7 @@ static void kmalloc_node_oob_right(struct kunit *test)
 	ptr = kmalloc_node(size, GFP_KERNEL, 0);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
 
+	OPTIMIZER_HIDE_VAR(ptr);
 	KUNIT_EXPECT_KASAN_FAIL(test, ptr[0] = ptr[size]);
 	kfree(ptr);
 }
@@ -185,6 +188,7 @@ static void kmalloc_pagealloc_oob_right(struct kunit *test)
 	ptr = kmalloc(size, GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
 
+	OPTIMIZER_HIDE_VAR(ptr);
 	KUNIT_EXPECT_KASAN_FAIL(test, ptr[size + OOB_TAG_OFF] = 0);
 
 	kfree(ptr);
@@ -265,6 +269,7 @@ static void kmalloc_large_oob_right(struct kunit *test)
 	ptr = kmalloc(size, GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
 
+	OPTIMIZER_HIDE_VAR(ptr);
 	KUNIT_EXPECT_KASAN_FAIL(test, ptr[size] = 0);
 	kfree(ptr);
 }
@@ -404,6 +409,8 @@ static void kmalloc_oob_16(struct kunit *test)
 	ptr2 = kmalloc(sizeof(*ptr2), GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr2);
 
+	OPTIMIZER_HIDE_VAR(ptr1);
+	OPTIMIZER_HIDE_VAR(ptr2);
 	KUNIT_EXPECT_KASAN_FAIL(test, *ptr1 = *ptr2);
 	kfree(ptr1);
 	kfree(ptr2);
@@ -712,6 +719,8 @@ static void ksize_unpoisons_memory(struct kunit *test)
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
 	real_size = ksize(ptr);
 
+	OPTIMIZER_HIDE_VAR(ptr);
+
 	/* This access shouldn't trigger a KASAN report. */
 	ptr[size] = 'x';
 
@@ -734,6 +743,7 @@ static void ksize_uaf(struct kunit *test)
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
 	kfree(ptr);
 
+	OPTIMIZER_HIDE_VAR(ptr);
 	KUNIT_EXPECT_KASAN_FAIL(test, ksize(ptr));
 	KUNIT_EXPECT_KASAN_FAIL(test, ((volatile char *)ptr)[0]);
 	KUNIT_EXPECT_KASAN_FAIL(test, ((volatile char *)ptr)[size]);
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 02c9d5c7276e..142e118ade87 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -258,10 +258,10 @@ void wb_wakeup_delayed(struct bdi_writeback *wb)
 	unsigned long timeout;
 
 	timeout = msecs_to_jiffies(dirty_writeback_interval * 10);
-	spin_lock_bh(&wb->work_lock);
+	spin_lock_irq(&wb->work_lock);
 	if (test_bit(WB_registered, &wb->state))
 		queue_delayed_work(bdi_wq, &wb->dwork, timeout);
-	spin_unlock_bh(&wb->work_lock);
+	spin_unlock_irq(&wb->work_lock);
 }
 
 static void wb_update_bandwidth_workfn(struct work_struct *work)
@@ -337,12 +337,12 @@ static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb);
 static void wb_shutdown(struct bdi_writeback *wb)
 {
 	/* Make sure nobody queues further work */
-	spin_lock_bh(&wb->work_lock);
+	spin_lock_irq(&wb->work_lock);
 	if (!test_and_clear_bit(WB_registered, &wb->state)) {
-		spin_unlock_bh(&wb->work_lock);
+		spin_unlock_irq(&wb->work_lock);
 		return;
 	}
-	spin_unlock_bh(&wb->work_lock);
+	spin_unlock_irq(&wb->work_lock);
 
 	cgwb_remove_from_bdi_list(wb);
 	/*
diff --git a/mm/bootmem_info.c b/mm/bootmem_info.c
index f03f42f426f6..8655492159a5 100644
--- a/mm/bootmem_info.c
+++ b/mm/bootmem_info.c
@@ -12,6 +12,7 @@
 #include <linux/memblock.h>
 #include <linux/bootmem_info.h>
 #include <linux/memory_hotplug.h>
+#include <linux/kmemleak.h>
 
 void get_page_bootmem(unsigned long info, struct page *page, unsigned long type)
 {
@@ -34,6 +35,7 @@ void put_page_bootmem(struct page *page)
 		ClearPagePrivate(page);
 		set_page_private(page, 0);
 		INIT_LIST_HEAD(&page->lru);
+		kmemleak_free_part(page_to_virt(page), PAGE_SIZE);
 		free_reserved_page(page);
 	}
 }
diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c
index 36624990b577..70a5cb977ed0 100644
--- a/mm/damon/dbgfs.c
+++ b/mm/damon/dbgfs.c
@@ -376,6 +376,9 @@ static int dbgfs_mk_context(char *name)
 		return -ENOENT;
 
 	new_dir = debugfs_create_dir(name, root);
+	/* Below check is required for a potential duplicated name case */
+	if (IS_ERR(new_dir))
+		return PTR_ERR(new_dir);
 	dbgfs_dirs[dbgfs_nr_ctxs] = new_dir;
 
 	new_ctx = dbgfs_new_ctx();
diff --git a/mm/filemap.c b/mm/filemap.c
index 00e391e75880..dbc461703ff4 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2090,7 +2090,11 @@ unsigned find_lock_entries(struct address_space *mapping, pgoff_t start,
 
 	rcu_read_lock();
 	while ((page = find_get_entry(&xas, end, XA_PRESENT))) {
+		unsigned long next_idx = xas.xa_index + 1;
+
 		if (!xa_is_value(page)) {
+			if (PageTransHuge(page))
+				next_idx = page->index + thp_nr_pages(page);
 			if (page->index < start)
 				goto put;
 			if (page->index + thp_nr_pages(page) - 1 > end)
@@ -2111,13 +2115,11 @@ unlock:
 put:
 		put_page(page);
 next:
-		if (!xa_is_value(page) && PageTransHuge(page)) {
-			unsigned int nr_pages = thp_nr_pages(page);
-
+		if (next_idx != xas.xa_index + 1) {
 			/* Final THP may cross MAX_LFS_FILESIZE on 32-bit */
-			xas_set(&xas, page->index + nr_pages);
-			if (xas.xa_index < nr_pages)
+			if (next_idx < xas.xa_index)
 				break;
+			xas_set(&xas, next_idx);
 		}
 	}
 	rcu_read_unlock();
diff --git a/mm/hmm.c b/mm/hmm.c
index bd56641c79d4..3af995c814a6 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -212,14 +212,6 @@ int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr,
 		unsigned long end, unsigned long hmm_pfns[], pmd_t pmd);
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
-static inline bool hmm_is_device_private_entry(struct hmm_range *range,
-		swp_entry_t entry)
-{
-	return is_device_private_entry(entry) &&
-		pfn_swap_entry_to_page(entry)->pgmap->owner ==
-		range->dev_private_owner;
-}
-
 static inline unsigned long pte_to_hmm_pfn_flags(struct hmm_range *range,
 						 pte_t pte)
 {
@@ -252,10 +244,12 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
 		swp_entry_t entry = pte_to_swp_entry(pte);
 
 		/*
-		 * Never fault in device private pages, but just report
-		 * the PFN even if not present.
+		 * Don't fault in device private pages owned by the caller,
+		 * just report the PFN.
 		 */
-		if (hmm_is_device_private_entry(range, entry)) {
+		if (is_device_private_entry(entry) &&
+		    pfn_swap_entry_to_page(entry)->pgmap->owner ==
+		    range->dev_private_owner) {
 			cpu_flags = HMM_PFN_VALID;
 			if (is_writable_device_private_entry(entry))
 				cpu_flags |= HMM_PFN_WRITE;
@@ -273,6 +267,9 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
 		if (!non_swap_entry(entry))
 			goto fault;
 
+		if (is_device_private_entry(entry))
+			goto fault;
+
 		if (is_device_exclusive_entry(entry))
 			goto fault;
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index e4c717b08cfe..d61b665c45d6 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5314,6 +5314,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 
 		page = alloc_huge_page(dst_vma, dst_addr, 0);
 		if (IS_ERR(page)) {
+			put_page(*pagep);
 			ret = -ENOMEM;
 			*pagep = NULL;
 			goto out;
@@ -5370,7 +5371,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 	if (!huge_pte_none(huge_ptep_get(dst_pte)))
 		goto out_release_unlock;
 
-	if (vm_shared) {
+	if (page_in_pagecache) {
 		page_dup_rmap(page, true);
 	} else {
 		ClearHPageRestoreReserve(page);
@@ -6290,6 +6291,16 @@ int get_hwpoison_huge_page(struct page *page, bool *hugetlb)
 	return ret;
 }
 
+int get_huge_page_for_hwpoison(unsigned long pfn, int flags)
+{
+	int ret;
+
+	spin_lock_irq(&hugetlb_lock);
+	ret = __get_huge_page_for_hwpoison(pfn, flags);
+	spin_unlock_irq(&hugetlb_lock);
+	return ret;
+}
+
 void putback_active_hugepage(struct page *page)
 {
 	spin_lock_irq(&hugetlb_lock);
diff --git a/mm/hwpoison-inject.c b/mm/hwpoison-inject.c
index aff4d27ec235..a1d6fc3c78b9 100644
--- a/mm/hwpoison-inject.c
+++ b/mm/hwpoison-inject.c
@@ -48,7 +48,8 @@ static int hwpoison_inject(void *data, u64 val)
 
 inject:
 	pr_info("Injecting memory failure at pfn %#lx\n", pfn);
-	return memory_failure(pfn, 0);
+	err = memory_failure(pfn, 0);
+	return (err == -EOPNOTSUPP) ? 0 : err;
 }
 
 static int hwpoison_unpoison(void *data, u64 val)
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 859303aae180..b78861b8e013 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1125,7 +1125,7 @@ EXPORT_SYMBOL(kmemleak_no_scan);
 void __ref kmemleak_alloc_phys(phys_addr_t phys, size_t size, int min_count,
 			       gfp_t gfp)
 {
-	if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn)
+	if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn)
 		kmemleak_alloc(__va(phys), size, min_count, gfp);
 }
 EXPORT_SYMBOL(kmemleak_alloc_phys);
@@ -1139,7 +1139,7 @@ EXPORT_SYMBOL(kmemleak_alloc_phys);
  */
 void __ref kmemleak_free_part_phys(phys_addr_t phys, size_t size)
 {
-	if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn)
+	if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn)
 		kmemleak_free_part(__va(phys), size);
 }
 EXPORT_SYMBOL(kmemleak_free_part_phys);
@@ -1151,7 +1151,7 @@ EXPORT_SYMBOL(kmemleak_free_part_phys);
  */
 void __ref kmemleak_not_leak_phys(phys_addr_t phys)
 {
-	if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn)
+	if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn)
 		kmemleak_not_leak(__va(phys));
 }
 EXPORT_SYMBOL(kmemleak_not_leak_phys);
@@ -1163,7 +1163,7 @@ EXPORT_SYMBOL(kmemleak_not_leak_phys);
  */
 void __ref kmemleak_ignore_phys(phys_addr_t phys)
 {
-	if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn)
+	if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn)
 		kmemleak_ignore(__va(phys));
 }
 EXPORT_SYMBOL(kmemleak_ignore_phys);
diff --git a/mm/madvise.c b/mm/madvise.c
index 8e5ca01a6cc0..882767d58c27 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -968,6 +968,8 @@ static int madvise_inject_error(int behavior,
 			pr_info("Injecting memory failure for pfn %#lx at process virtual address %#lx\n",
 				 pfn, start);
 			ret = memory_failure(pfn, MF_COUNT_INCREASED);
+			if (ret == -EOPNOTSUPP)
+				ret = 0;
 		}
 
 		if (ret)
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index c3ceb7436933..c71135edd0a1 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1418,59 +1418,115 @@ static int try_to_split_thp_page(struct page *page, const char *msg)
 	return 0;
 }
 
-static int memory_failure_hugetlb(unsigned long pfn, int flags)
+/*
+ * Called from hugetlb code with hugetlb_lock held.
+ *
+ * Return values:
+ *   0             - free hugepage
+ *   1             - in-use hugepage
+ *   2             - not a hugepage
+ *   -EBUSY        - the hugepage is busy (try to retry)
+ *   -EHWPOISON    - the hugepage is already hwpoisoned
+ */
+int __get_huge_page_for_hwpoison(unsigned long pfn, int flags)
+{
+	struct page *page = pfn_to_page(pfn);
+	struct page *head = compound_head(page);
+	int ret = 2;	/* fallback to normal page handling */
+	bool count_increased = false;
+
+	if (!PageHeadHuge(head))
+		goto out;
+
+	if (flags & MF_COUNT_INCREASED) {
+		ret = 1;
+		count_increased = true;
+	} else if (HPageFreed(head) || HPageMigratable(head)) {
+		ret = get_page_unless_zero(head);
+		if (ret)
+			count_increased = true;
+	} else {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	if (TestSetPageHWPoison(head)) {
+		ret = -EHWPOISON;
+		goto out;
+	}
+
+	return ret;
+out:
+	if (count_increased)
+		put_page(head);
+	return ret;
+}
+
+#ifdef CONFIG_HUGETLB_PAGE
+/*
+ * Taking refcount of hugetlb pages needs extra care about race conditions
+ * with basic operations like hugepage allocation/free/demotion.
+ * So some of prechecks for hwpoison (pinning, and testing/setting
+ * PageHWPoison) should be done in single hugetlb_lock range.
+ */
+static int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb)
 {
-	struct page *p = pfn_to_page(pfn);
-	struct page *head = compound_head(p);
 	int res;
+	struct page *p = pfn_to_page(pfn);
+	struct page *head;
 	unsigned long page_flags;
+	bool retry = true;
 
-	if (TestSetPageHWPoison(head)) {
-		pr_err("Memory failure: %#lx: already hardware poisoned\n",
-		       pfn);
-		res = -EHWPOISON;
-		if (flags & MF_ACTION_REQUIRED)
+	*hugetlb = 1;
+retry:
+	res = get_huge_page_for_hwpoison(pfn, flags);
+	if (res == 2) { /* fallback to normal page handling */
+		*hugetlb = 0;
+		return 0;
+	} else if (res == -EHWPOISON) {
+		pr_err("Memory failure: %#lx: already hardware poisoned\n", pfn);
+		if (flags & MF_ACTION_REQUIRED) {
+			head = compound_head(p);
 			res = kill_accessing_process(current, page_to_pfn(head), flags);
+		}
+		return res;
+	} else if (res == -EBUSY) {
+		if (retry) {
+			retry = false;
+			goto retry;
+		}
+		action_result(pfn, MF_MSG_UNKNOWN, MF_IGNORED);
 		return res;
 	}
 
-	num_poisoned_pages_inc();
+	head = compound_head(p);
+	lock_page(head);
 
-	if (!(flags & MF_COUNT_INCREASED)) {
-		res = get_hwpoison_page(p, flags);
-		if (!res) {
-			lock_page(head);
-			if (hwpoison_filter(p)) {
-				if (TestClearPageHWPoison(head))
-					num_poisoned_pages_dec();
-				unlock_page(head);
-				return 0;
-			}
-			unlock_page(head);
-			res = MF_FAILED;
-			if (__page_handle_poison(p)) {
-				page_ref_inc(p);
-				res = MF_RECOVERED;
-			}
-			action_result(pfn, MF_MSG_FREE_HUGE, res);
-			return res == MF_RECOVERED ? 0 : -EBUSY;
-		} else if (res < 0) {
-			action_result(pfn, MF_MSG_UNKNOWN, MF_IGNORED);
-			return -EBUSY;
-		}
+	if (hwpoison_filter(p)) {
+		ClearPageHWPoison(head);
+		res = -EOPNOTSUPP;
+		goto out;
 	}
 
-	lock_page(head);
-	page_flags = head->flags;
+	num_poisoned_pages_inc();
 
-	if (!PageHWPoison(head)) {
-		pr_err("Memory failure: %#lx: just unpoisoned\n", pfn);
-		num_poisoned_pages_dec();
+	/*
+	 * Handling free hugepage.  The possible race with hugepage allocation
+	 * or demotion can be prevented by PageHWPoison flag.
+	 */
+	if (res == 0) {
 		unlock_page(head);
-		put_page(head);
-		return 0;
+		res = MF_FAILED;
+		if (__page_handle_poison(p)) {
+			page_ref_inc(p);
+			res = MF_RECOVERED;
+		}
+		action_result(pfn, MF_MSG_FREE_HUGE, res);
+		return res == MF_RECOVERED ? 0 : -EBUSY;
 	}
 
+	page_flags = head->flags;
+
 	/*
 	 * TODO: hwpoison for pud-sized hugetlb doesn't work right now, so
 	 * simply disable it. In order to make it work properly, we need
@@ -1497,6 +1553,12 @@ out:
 	unlock_page(head);
 	return res;
 }
+#else
+static inline int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb)
+{
+	return 0;
+}
+#endif
 
 static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
 		struct dev_pagemap *pgmap)
@@ -1533,7 +1595,7 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
 		goto out;
 
 	if (hwpoison_filter(page)) {
-		rc = 0;
+		rc = -EOPNOTSUPP;
 		goto unlock;
 	}
 
@@ -1584,6 +1646,8 @@ out:
 	return rc;
 }
 
+static DEFINE_MUTEX(mf_mutex);
+
 /**
  * memory_failure - Handle memory failure of a page.
  * @pfn: Page Number of the corrupted page
@@ -1600,6 +1664,10 @@ out:
  *
  * Must run in process context (e.g. a work queue) with interrupts
  * enabled and no spinlocks hold.
+ *
+ * Return: 0 for successfully handled the memory error,
+ *         -EOPNOTSUPP for memory_filter() filtered the error event,
+ *         < 0(except -EOPNOTSUPP) on failure.
  */
 int memory_failure(unsigned long pfn, int flags)
 {
@@ -1610,7 +1678,7 @@ int memory_failure(unsigned long pfn, int flags)
 	int res = 0;
 	unsigned long page_flags;
 	bool retry = true;
-	static DEFINE_MUTEX(mf_mutex);
+	int hugetlb = 0;
 
 	if (!sysctl_memory_failure_recovery)
 		panic("Memory failure on page %lx", pfn);
@@ -1631,10 +1699,9 @@ int memory_failure(unsigned long pfn, int flags)
 	mutex_lock(&mf_mutex);
 
 try_again:
-	if (PageHuge(p)) {
-		res = memory_failure_hugetlb(pfn, flags);
+	res = try_memory_failure_hugetlb(pfn, flags, &hugetlb);
+	if (hugetlb)
 		goto unlock_mutex;
-	}
 
 	if (TestSetPageHWPoison(p)) {
 		pr_err("Memory failure: %#lx: already hardware poisoned\n",
@@ -1744,21 +1811,12 @@ try_again:
 	 */
 	page_flags = p->flags;
 
-	/*
-	 * unpoison always clear PG_hwpoison inside page lock
-	 */
-	if (!PageHWPoison(p)) {
-		pr_err("Memory failure: %#lx: just unpoisoned\n", pfn);
-		num_poisoned_pages_dec();
-		unlock_page(p);
-		put_page(p);
-		goto unlock_mutex;
-	}
 	if (hwpoison_filter(p)) {
 		if (TestClearPageHWPoison(p))
 			num_poisoned_pages_dec();
 		unlock_page(p);
 		put_page(p);
+		res = -EOPNOTSUPP;
 		goto unlock_mutex;
 	}
 
@@ -1934,6 +1992,7 @@ int unpoison_memory(unsigned long pfn)
 	struct page *page;
 	struct page *p;
 	int freeit = 0;
+	int ret = 0;
 	unsigned long flags = 0;
 	static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL,
 					DEFAULT_RATELIMIT_BURST);
@@ -1944,39 +2003,30 @@ int unpoison_memory(unsigned long pfn)
 	p = pfn_to_page(pfn);
 	page = compound_head(p);
 
+	mutex_lock(&mf_mutex);
+
 	if (!PageHWPoison(p)) {
 		unpoison_pr_info("Unpoison: Page was already unpoisoned %#lx\n",
 				 pfn, &unpoison_rs);
-		return 0;
+		goto unlock_mutex;
 	}
 
 	if (page_count(page) > 1) {
 		unpoison_pr_info("Unpoison: Someone grabs the hwpoison page %#lx\n",
 				 pfn, &unpoison_rs);
-		return 0;
+		goto unlock_mutex;
 	}
 
 	if (page_mapped(page)) {
 		unpoison_pr_info("Unpoison: Someone maps the hwpoison page %#lx\n",
 				 pfn, &unpoison_rs);
-		return 0;
+		goto unlock_mutex;
 	}
 
 	if (page_mapping(page)) {
 		unpoison_pr_info("Unpoison: the hwpoison page has non-NULL mapping %#lx\n",
 				 pfn, &unpoison_rs);
-		return 0;
-	}
-
-	/*
-	 * unpoison_memory() can encounter thp only when the thp is being
-	 * worked by memory_failure() and the page lock is not held yet.
-	 * In such case, we yield to memory_failure() and make unpoison fail.
-	 */
-	if (!PageHuge(page) && PageTransHuge(page)) {
-		unpoison_pr_info("Unpoison: Memory failure is now running on %#lx\n",
-				 pfn, &unpoison_rs);
-		return 0;
+		goto unlock_mutex;
 	}
 
 	if (!get_hwpoison_page(p, flags)) {
@@ -1984,29 +2034,23 @@ int unpoison_memory(unsigned long pfn)
 			num_poisoned_pages_dec();
 		unpoison_pr_info("Unpoison: Software-unpoisoned free page %#lx\n",
 				 pfn, &unpoison_rs);
-		return 0;
+		goto unlock_mutex;
 	}
 
-	lock_page(page);
-	/*
-	 * This test is racy because PG_hwpoison is set outside of page lock.
-	 * That's acceptable because that won't trigger kernel panic. Instead,
-	 * the PG_hwpoison page will be caught and isolated on the entrance to
-	 * the free buddy page pool.
-	 */
 	if (TestClearPageHWPoison(page)) {
 		unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n",
 				 pfn, &unpoison_rs);
 		num_poisoned_pages_dec();
 		freeit = 1;
 	}
-	unlock_page(page);
 
 	put_page(page);
 	if (freeit && !(pfn == my_zero_pfn(0) && page_count(p) == 1))
 		put_page(page);
 
-	return 0;
+unlock_mutex:
+	mutex_unlock(&mf_mutex);
+	return ret;
 }
 EXPORT_SYMBOL(unpoison_memory);
 
@@ -2187,9 +2231,12 @@ int soft_offline_page(unsigned long pfn, int flags)
 		return -EIO;
 	}
 
+	mutex_lock(&mf_mutex);
+
 	if (PageHWPoison(page)) {
 		pr_info("%s: %#lx page already poisoned\n", __func__, pfn);
 		put_ref_page(ref_page);
+		mutex_unlock(&mf_mutex);
 		return 0;
 	}
 
@@ -2208,5 +2255,7 @@ retry:
 		}
 	}
 
+	mutex_unlock(&mf_mutex);
+
 	return ret;
 }
diff --git a/mm/memory.c b/mm/memory.c
index 26d115ded4ab..a4d0f744a458 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4071,9 +4071,12 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
 		}
 	}
 
-	/* See comment in handle_pte_fault() */
+	/*
+	 * See comment in handle_pte_fault() for how this scenario happens, we
+	 * need to return NOPAGE so that we drop this page.
+	 */
 	if (pmd_devmap_trans_unstable(vmf->pmd))
-		return 0;
+		return VM_FAULT_NOPAGE;
 
 	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
 				      vmf->address, &vmf->ptl);
@@ -4491,6 +4494,19 @@ static vm_fault_t create_huge_pud(struct vm_fault *vmf)
 	defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
 	/* No support for anonymous transparent PUD pages yet */
 	if (vma_is_anonymous(vmf->vma))
+		return VM_FAULT_FALLBACK;
+	if (vmf->vma->vm_ops->huge_fault)
+		return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD);
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+	return VM_FAULT_FALLBACK;
+}
+
+static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud)
+{
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) &&			\
+	defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
+	/* No support for anonymous transparent PUD pages yet */
+	if (vma_is_anonymous(vmf->vma))
 		goto split;
 	if (vmf->vma->vm_ops->huge_fault) {
 		vm_fault_t ret = vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD);
@@ -4501,19 +4517,7 @@ static vm_fault_t create_huge_pud(struct vm_fault *vmf)
 split:
 	/* COW or write-notify not handled on PUD level: split pud.*/
 	__split_huge_pud(vmf->vma, vmf->pud, vmf->address);
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-	return VM_FAULT_FALLBACK;
-}
-
-static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud)
-{
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	/* No support for anonymous transparent PUD pages yet */
-	if (vma_is_anonymous(vmf->vma))
-		return VM_FAULT_FALLBACK;
-	if (vmf->vma->vm_ops->huge_fault)
-		return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD);
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE && CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
 	return VM_FAULT_FALLBACK;
 }
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index e75872035c76..4472be6f123d 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -347,7 +347,7 @@ static void mpol_rebind_preferred(struct mempolicy *pol,
  */
 static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask)
 {
-	if (!pol)
+	if (!pol || pol->mode == MPOL_LOCAL)
 		return;
 	if (!mpol_store_user_nodemask(pol) &&
 	    nodes_equal(pol->w.cpuset_mems_allowed, *newmask))
@@ -1389,7 +1389,7 @@ static int get_nodes(nodemask_t *nodes, const unsigned long __user *nmask,
 		unsigned long bits = min_t(unsigned long, maxnode, BITS_PER_LONG);
 		unsigned long t;
 
-		if (get_bitmap(&t, &nmask[maxnode / BITS_PER_LONG], bits))
+		if (get_bitmap(&t, &nmask[(maxnode - 1) / BITS_PER_LONG], bits))
 			return -EFAULT;
 
 		if (maxnode - bits >= MAX_NUMNODES) {
diff --git a/mm/memremap.c b/mm/memremap.c
index e77487375c8e..8d743cbc2964 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -112,30 +112,6 @@ static unsigned long pfn_next(unsigned long pfn)
 #define for_each_device_pfn(pfn, map, i) \
 	for (pfn = pfn_first(map, i); pfn < pfn_end(map, i); pfn = pfn_next(pfn))
 
-static void dev_pagemap_kill(struct dev_pagemap *pgmap)
-{
-	if (pgmap->ops && pgmap->ops->kill)
-		pgmap->ops->kill(pgmap);
-	else
-		percpu_ref_kill(pgmap->ref);
-}
-
-static void dev_pagemap_cleanup(struct dev_pagemap *pgmap)
-{
-	if (pgmap->ops && pgmap->ops->cleanup) {
-		pgmap->ops->cleanup(pgmap);
-	} else {
-		wait_for_completion(&pgmap->done);
-		percpu_ref_exit(pgmap->ref);
-	}
-	/*
-	 * Undo the pgmap ref assignment for the internal case as the
-	 * caller may re-enable the same pgmap.
-	 */
-	if (pgmap->ref == &pgmap->internal_ref)
-		pgmap->ref = NULL;
-}
-
 static void pageunmap_range(struct dev_pagemap *pgmap, int range_id)
 {
 	struct range *range = &pgmap->ranges[range_id];
@@ -167,14 +143,15 @@ void memunmap_pages(struct dev_pagemap *pgmap)
 	unsigned long pfn;
 	int i;
 
-	dev_pagemap_kill(pgmap);
+	percpu_ref_kill(&pgmap->ref);
 	for (i = 0; i < pgmap->nr_range; i++)
 		for_each_device_pfn(pfn, pgmap, i)
 			put_page(pfn_to_page(pfn));
-	dev_pagemap_cleanup(pgmap);
+	wait_for_completion(&pgmap->done);
 
 	for (i = 0; i < pgmap->nr_range; i++)
 		pageunmap_range(pgmap, i);
+	percpu_ref_exit(&pgmap->ref);
 
 	WARN_ONCE(pgmap->altmap.alloc, "failed to free all reserved pages\n");
 	devmap_managed_enable_put(pgmap);
@@ -188,8 +165,7 @@ static void devm_memremap_pages_release(void *data)
 
 static void dev_pagemap_percpu_release(struct percpu_ref *ref)
 {
-	struct dev_pagemap *pgmap =
-		container_of(ref, struct dev_pagemap, internal_ref);
+	struct dev_pagemap *pgmap = container_of(ref, struct dev_pagemap, ref);
 
 	complete(&pgmap->done);
 }
@@ -295,8 +271,8 @@ static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params,
 	memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
 				PHYS_PFN(range->start),
 				PHYS_PFN(range_len(range)), pgmap);
-	percpu_ref_get_many(pgmap->ref, pfn_end(pgmap, range_id)
-			- pfn_first(pgmap, range_id));
+	percpu_ref_get_many(&pgmap->ref,
+		pfn_end(pgmap, range_id) - pfn_first(pgmap, range_id));
 	return 0;
 
 err_add_memory:
@@ -362,22 +338,11 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 		break;
 	}
 
-	if (!pgmap->ref) {
-		if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup))
-			return ERR_PTR(-EINVAL);
-
-		init_completion(&pgmap->done);
-		error = percpu_ref_init(&pgmap->internal_ref,
-				dev_pagemap_percpu_release, 0, GFP_KERNEL);
-		if (error)
-			return ERR_PTR(error);
-		pgmap->ref = &pgmap->internal_ref;
-	} else {
-		if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) {
-			WARN(1, "Missing reference count teardown definition\n");
-			return ERR_PTR(-EINVAL);
-		}
-	}
+	init_completion(&pgmap->done);
+	error = percpu_ref_init(&pgmap->ref, dev_pagemap_percpu_release, 0,
+				GFP_KERNEL);
+	if (error)
+		return ERR_PTR(error);
 
 	devmap_managed_enable_get(pgmap);
 
@@ -486,7 +451,7 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
 	/* fall back to slow path lookup */
 	rcu_read_lock();
 	pgmap = xa_load(&pgmap_array, PHYS_PFN(phys));
-	if (pgmap && !percpu_ref_tryget_live(pgmap->ref))
+	if (pgmap && !percpu_ref_tryget_live(&pgmap->ref))
 		pgmap = NULL;
 	rcu_read_unlock();
 
diff --git a/mm/mmap.c b/mm/mmap.c
index 6bb553ed5c55..5c2c7651ca29 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1684,8 +1684,12 @@ int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot)
 	    pgprot_val(vm_pgprot_modify(vm_page_prot, vm_flags)))
 		return 0;
 
-	/* Do we need to track softdirty? */
-	if (IS_ENABLED(CONFIG_MEM_SOFT_DIRTY) && !(vm_flags & VM_SOFTDIRTY))
+	/*
+	 * Do we need to track softdirty? hugetlb does not support softdirty
+	 * tracking yet.
+	 */
+	if (IS_ENABLED(CONFIG_MEM_SOFT_DIRTY) && !(vm_flags & VM_SOFTDIRTY) &&
+	    !is_vm_hugetlb_page(vma))
 		return 1;
 
 	/* Specialty mapping? */
@@ -1878,7 +1882,6 @@ unmap_and_free_vma:
 
 	/* Undo any partial mapping done by a device driver. */
 	unmap_region(mm, vma, prev, vma->vm_start, vma->vm_end);
-	charged = 0;
 	if (vm_flags & VM_SHARED)
 		mapping_unmap_writable(file->f_mapping);
 free_vma:
@@ -2635,11 +2638,28 @@ static void unmap_region(struct mm_struct *mm,
 {
 	struct vm_area_struct *next = vma_next(mm, prev);
 	struct mmu_gather tlb;
+	struct vm_area_struct *cur_vma;
 
 	lru_add_drain();
 	tlb_gather_mmu(&tlb, mm);
 	update_hiwater_rss(mm);
 	unmap_vmas(&tlb, vma, start, end);
+
+	/*
+	 * Ensure we have no stale TLB entries by the time this mapping is
+	 * removed from the rmap.
+	 * Note that we don't have to worry about nested flushes here because
+	 * we're holding the mm semaphore for removing the mapping - so any
+	 * concurrent flush in this region has to be coming through the rmap,
+	 * and we synchronize against that using the rmap lock.
+	 */
+	for (cur_vma = vma; cur_vma; cur_vma = cur_vma->vm_next) {
+		if ((cur_vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) != 0) {
+			tlb_flush_mmu(&tlb);
+			break;
+		}
+	}
+
 	free_pgtables(&tlb, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS,
 				 next ? next->vm_start : USER_PGTABLES_CEILING);
 	tlb_finish_mmu(&tlb);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 4812a17b288c..8ca6617b2a72 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2755,6 +2755,7 @@ static void wb_inode_writeback_start(struct bdi_writeback *wb)
 
 static void wb_inode_writeback_end(struct bdi_writeback *wb)
 {
+	unsigned long flags;
 	atomic_dec(&wb->writeback_inodes);
 	/*
 	 * Make sure estimate of writeback throughput gets updated after
@@ -2763,7 +2764,10 @@ static void wb_inode_writeback_end(struct bdi_writeback *wb)
 	 * that if multiple inodes end writeback at a similar time, they get
 	 * batched into one bandwidth update.
 	 */
-	queue_delayed_work(bdi_wq, &wb->bw_dwork, BANDWIDTH_INTERVAL);
+	spin_lock_irqsave(&wb->work_lock, flags);
+	if (test_bit(WB_registered, &wb->state))
+		queue_delayed_work(bdi_wq, &wb->bw_dwork, BANDWIDTH_INTERVAL);
+	spin_unlock_irqrestore(&wb->work_lock, flags);
 }
 
 int test_clear_page_writeback(struct page *page)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a0b7afae59e9..61d7967897ce 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3928,11 +3928,15 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
 	 * need to be calculated.
 	 */
 	if (!order) {
-		long fast_free;
+		long usable_free;
+		long reserved;
 
-		fast_free = free_pages;
-		fast_free -= __zone_watermark_unusable_free(z, 0, alloc_flags);
-		if (fast_free > mark + z->lowmem_reserve[highest_zoneidx])
+		usable_free = free_pages;
+		reserved = __zone_watermark_unusable_free(z, 0, alloc_flags);
+
+		/* reserved may over estimate high-atomic reserves. */
+		usable_free -= min(usable_free, reserved);
+		if (usable_free > mark + z->lowmem_reserve[highest_zoneidx])
 			return true;
 	}
 
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 9b3db11a4d1d..fa7a3d21a751 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -110,7 +110,7 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
 	do {
 again:
 		next = pmd_addr_end(addr, end);
-		if (pmd_none(*pmd) || (!walk->vma && !walk->no_vma)) {
+		if (pmd_none(*pmd)) {
 			if (ops->pte_hole)
 				err = ops->pte_hole(addr, next, depth, walk);
 			if (err)
@@ -171,7 +171,7 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
 	do {
  again:
 		next = pud_addr_end(addr, end);
-		if (pud_none(*pud) || (!walk->vma && !walk->no_vma)) {
+		if (pud_none(*pud)) {
 			if (ops->pte_hole)
 				err = ops->pte_hole(addr, next, depth, walk);
 			if (err)
@@ -366,19 +366,19 @@ static int __walk_page_range(unsigned long start, unsigned long end,
 	struct vm_area_struct *vma = walk->vma;
 	const struct mm_walk_ops *ops = walk->ops;
 
-	if (vma && ops->pre_vma) {
+	if (ops->pre_vma) {
 		err = ops->pre_vma(start, end, walk);
 		if (err)
 			return err;
 	}
 
-	if (vma && is_vm_hugetlb_page(vma)) {
+	if (is_vm_hugetlb_page(vma)) {
 		if (ops->hugetlb_entry)
 			err = walk_hugetlb_range(start, end, walk);
 	} else
 		err = walk_pgd_range(start, end, walk);
 
-	if (vma && ops->post_vma)
+	if (ops->post_vma)
 		ops->post_vma(walk);
 
 	return err;
@@ -450,9 +450,13 @@ int walk_page_range(struct mm_struct *mm, unsigned long start,
 		if (!vma) { /* after the last vma */
 			walk.vma = NULL;
 			next = end;
+			if (ops->pte_hole)
+				err = ops->pte_hole(start, next, -1, &walk);
 		} else if (start < vma->vm_start) { /* outside vma */
 			walk.vma = NULL;
 			next = min(end, vma->vm_start);
+			if (ops->pte_hole)
+				err = ops->pte_hole(start, next, -1, &walk);
 		} else { /* inside vma */
 			walk.vma = vma;
 			next = min(end, vma->vm_end);
@@ -470,9 +474,8 @@ int walk_page_range(struct mm_struct *mm, unsigned long start,
 			}
 			if (err < 0)
 				break;
-		}
-		if (walk.vma || walk.ops->pte_hole)
 			err = __walk_page_range(start, next, &walk);
+		}
 		if (err)
 			break;
 	} while (start = next, start < end);
@@ -501,9 +504,9 @@ int walk_page_range_novma(struct mm_struct *mm, unsigned long start,
 	if (start >= end || !walk.mm)
 		return -EINVAL;
 
-	mmap_assert_locked(walk.mm);
+	mmap_assert_write_locked(walk.mm);
 
-	return __walk_page_range(start, end, &walk);
+	return walk_pgd_range(start, end, &walk);
 }
 
 int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops,
diff --git a/mm/ptdump.c b/mm/ptdump.c
index da751448d0e4..f84ea700662f 100644
--- a/mm/ptdump.c
+++ b/mm/ptdump.c
@@ -144,13 +144,13 @@ void ptdump_walk_pgd(struct ptdump_state *st, struct mm_struct *mm, pgd_t *pgd)
 {
 	const struct ptdump_range *range = st->range;
 
-	mmap_read_lock(mm);
+	mmap_write_lock(mm);
 	while (range->start != range->end) {
 		walk_page_range_novma(mm, range->start, range->end,
 				      &ptdump_ops, pgd, st);
 		range++;
 	}
-	mmap_read_unlock(mm);
+	mmap_write_unlock(mm);
 
 	/* Flush out the last page */
 	st->note_page(st, 0, -1, 0);
diff --git a/mm/rmap.c b/mm/rmap.c
index 3e340ee380cb..330b361a460e 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -90,7 +90,8 @@ static inline struct anon_vma *anon_vma_alloc(void)
 	anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL);
 	if (anon_vma) {
 		atomic_set(&anon_vma->refcount, 1);
-		anon_vma->degree = 1;	/* Reference for first vma */
+		anon_vma->num_children = 0;
+		anon_vma->num_active_vmas = 0;
 		anon_vma->parent = anon_vma;
 		/*
 		 * Initialise the anon_vma root to point to itself. If called
@@ -198,6 +199,7 @@ int __anon_vma_prepare(struct vm_area_struct *vma)
 		anon_vma = anon_vma_alloc();
 		if (unlikely(!anon_vma))
 			goto out_enomem_free_avc;
+		anon_vma->num_children++; /* self-parent link for new root */
 		allocated = anon_vma;
 	}
 
@@ -207,8 +209,7 @@ int __anon_vma_prepare(struct vm_area_struct *vma)
 	if (likely(!vma->anon_vma)) {
 		vma->anon_vma = anon_vma;
 		anon_vma_chain_link(vma, avc, anon_vma);
-		/* vma reference or self-parent link for new root */
-		anon_vma->degree++;
+		anon_vma->num_active_vmas++;
 		allocated = NULL;
 		avc = NULL;
 	}
@@ -293,19 +294,19 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src)
 		anon_vma_chain_link(dst, avc, anon_vma);
 
 		/*
-		 * Reuse existing anon_vma if its degree lower than two,
-		 * that means it has no vma and only one anon_vma child.
+		 * Reuse existing anon_vma if it has no vma and only one
+		 * anon_vma child.
 		 *
-		 * Do not chose parent anon_vma, otherwise first child
-		 * will always reuse it. Root anon_vma is never reused:
+		 * Root anon_vma is never reused:
 		 * it has self-parent reference and at least one child.
 		 */
 		if (!dst->anon_vma && src->anon_vma &&
-		    anon_vma != src->anon_vma && anon_vma->degree < 2)
+		    anon_vma->num_children < 2 &&
+		    anon_vma->num_active_vmas == 0)
 			dst->anon_vma = anon_vma;
 	}
 	if (dst->anon_vma)
-		dst->anon_vma->degree++;
+		dst->anon_vma->num_active_vmas++;
 	unlock_anon_vma_root(root);
 	return 0;
 
@@ -355,6 +356,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
 	anon_vma = anon_vma_alloc();
 	if (!anon_vma)
 		goto out_error;
+	anon_vma->num_active_vmas++;
 	avc = anon_vma_chain_alloc(GFP_KERNEL);
 	if (!avc)
 		goto out_error_free_anon_vma;
@@ -375,7 +377,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
 	vma->anon_vma = anon_vma;
 	anon_vma_lock_write(anon_vma);
 	anon_vma_chain_link(vma, avc, anon_vma);
-	anon_vma->parent->degree++;
+	anon_vma->parent->num_children++;
 	anon_vma_unlock_write(anon_vma);
 
 	return 0;
@@ -407,7 +409,7 @@ void unlink_anon_vmas(struct vm_area_struct *vma)
 		 * to free them outside the lock.
 		 */
 		if (RB_EMPTY_ROOT(&anon_vma->rb_root.rb_root)) {
-			anon_vma->parent->degree--;
+			anon_vma->parent->num_children--;
 			continue;
 		}
 
@@ -415,7 +417,7 @@ void unlink_anon_vmas(struct vm_area_struct *vma)
 		anon_vma_chain_free(avc);
 	}
 	if (vma->anon_vma) {
-		vma->anon_vma->degree--;
+		vma->anon_vma->num_active_vmas--;
 
 		/*
 		 * vma would still be needed after unlink, and anon_vma will be prepared
@@ -433,7 +435,8 @@ void unlink_anon_vmas(struct vm_area_struct *vma)
 	list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) {
 		struct anon_vma *anon_vma = avc->anon_vma;
 
-		VM_WARN_ON(anon_vma->degree);
+		VM_WARN_ON(anon_vma->num_children);
+		VM_WARN_ON(anon_vma->num_active_vmas);
 		put_anon_vma(anon_vma);
 
 		list_del(&avc->same_vma);
diff --git a/mm/secretmem.c b/mm/secretmem.c
index 5a62ef3bcfcf..14f49c0aa66e 100644
--- a/mm/secretmem.c
+++ b/mm/secretmem.c
@@ -55,22 +55,28 @@ static vm_fault_t secretmem_fault(struct vm_fault *vmf)
 	gfp_t gfp = vmf->gfp_mask;
 	unsigned long addr;
 	struct page *page;
+	vm_fault_t ret;
 	int err;
 
 	if (((loff_t)vmf->pgoff << PAGE_SHIFT) >= i_size_read(inode))
 		return vmf_error(-EINVAL);
 
+	filemap_invalidate_lock_shared(mapping);
+
 retry:
 	page = find_lock_page(mapping, offset);
 	if (!page) {
 		page = alloc_page(gfp | __GFP_ZERO);
-		if (!page)
-			return VM_FAULT_OOM;
+		if (!page) {
+			ret = VM_FAULT_OOM;
+			goto out;
+		}
 
 		err = set_direct_map_invalid_noflush(page);
 		if (err) {
 			put_page(page);
-			return vmf_error(err);
+			ret = vmf_error(err);
+			goto out;
 		}
 
 		__SetPageUptodate(page);
@@ -86,7 +92,8 @@ retry:
 			if (err == -EEXIST)
 				goto retry;
 
-			return vmf_error(err);
+			ret = vmf_error(err);
+			goto out;
 		}
 
 		addr = (unsigned long)page_address(page);
@@ -94,7 +101,11 @@ retry:
 	}
 
 	vmf->page = page;
-	return VM_FAULT_LOCKED;
+	ret = VM_FAULT_LOCKED;
+
+out:
+	filemap_invalidate_unlock_shared(mapping);
+	return ret;
 }
 
 static const struct vm_operations_struct secretmem_vm_ops = {
@@ -162,12 +173,20 @@ static int secretmem_setattr(struct user_namespace *mnt_userns,
 			     struct dentry *dentry, struct iattr *iattr)
 {
 	struct inode *inode = d_inode(dentry);
+	struct address_space *mapping = inode->i_mapping;
 	unsigned int ia_valid = iattr->ia_valid;
+	int ret;
+
+	filemap_invalidate_lock(mapping);
 
 	if ((ia_valid & ATTR_SIZE) && inode->i_size)
-		return -EINVAL;
+		ret = -EINVAL;
+	else
+		ret = simple_setattr(mnt_userns, dentry, iattr);
 
-	return simple_setattr(mnt_userns, dentry, iattr);
+	filemap_invalidate_unlock(mapping);
+
+	return ret;
 }
 
 static const struct inode_operations secretmem_iops = {
diff --git a/mm/slub.c b/mm/slub.c
index b75eebc0350e..519bbbad7b2f 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2935,6 +2935,7 @@ redo:
 
 	if (!freelist) {
 		c->page = NULL;
+		c->tid = next_tid(c->tid);
 		local_unlock_irqrestore(&s->cpu_slab->lock, flags);
 		stat(s, DEACTIVATE_BYPASS);
 		goto new_slab;
@@ -2967,6 +2968,7 @@ deactivate_slab:
 	freelist = c->freelist;
 	c->page = NULL;
 	c->freelist = NULL;
+	c->tid = next_tid(c->tid);
 	local_unlock_irqrestore(&s->cpu_slab->lock, flags);
 	deactivate_slab(s, page, freelist);
 
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index c9bab48856c6..3bbaf5f5353e 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -227,7 +227,10 @@ static int mcontinue_atomic_pte(struct mm_struct *dst_mm,
 	struct page *page;
 	int ret;
 
-	ret = shmem_getpage(inode, pgoff, &page, SGP_READ);
+	ret = shmem_getpage(inode, pgoff, &page, SGP_NOALLOC);
+	/* Our caller expects us to return -EFAULT if we failed to find page. */
+	if (ret == -ENOENT)
+		ret = -EFAULT;
 	if (ret)
 		goto out;
 	if (!page) {
diff --git a/mm/util.c b/mm/util.c
index 3073de05c2bd..ea04979f131e 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -698,6 +698,56 @@ static inline void *__page_rmapping(struct page *page)
 	return (void *)mapping;
 }
 
+/**
+ * __vmalloc_array - allocate memory for a virtually contiguous array.
+ * @n: number of elements.
+ * @size: element size.
+ * @flags: the type of memory to allocate (see kmalloc).
+ */
+void *__vmalloc_array(size_t n, size_t size, gfp_t flags)
+{
+	size_t bytes;
+
+	if (unlikely(check_mul_overflow(n, size, &bytes)))
+		return NULL;
+	return __vmalloc(bytes, flags);
+}
+EXPORT_SYMBOL(__vmalloc_array);
+
+/**
+ * vmalloc_array - allocate memory for a virtually contiguous array.
+ * @n: number of elements.
+ * @size: element size.
+ */
+void *vmalloc_array(size_t n, size_t size)
+{
+	return __vmalloc_array(n, size, GFP_KERNEL);
+}
+EXPORT_SYMBOL(vmalloc_array);
+
+/**
+ * __vcalloc - allocate and zero memory for a virtually contiguous array.
+ * @n: number of elements.
+ * @size: element size.
+ * @flags: the type of memory to allocate (see kmalloc).
+ */
+void *__vcalloc(size_t n, size_t size, gfp_t flags)
+{
+	return __vmalloc_array(n, size, flags | __GFP_ZERO);
+}
+EXPORT_SYMBOL(__vcalloc);
+
+/**
+ * vcalloc - allocate and zero memory for a virtually contiguous array.
+ * @n: number of elements.
+ * @size: element size.
+ */
+void *vcalloc(size_t n, size_t size)
+{
+	return __vmalloc_array(n, size, GFP_KERNEL | __GFP_ZERO);
+}
+EXPORT_SYMBOL(vcalloc);
+
 /* Neutral page->mapping pointer to address_space or anon_vma or other */
 void *page_rmapping(struct page *page)
 {
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 8602885c8a8e..a54535cbcf4c 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -250,7 +250,7 @@ bool vlan_dev_inherit_address(struct net_device *dev,
 	if (dev->addr_assign_type != NET_ADDR_STOLEN)
 		return false;
 
-	ether_addr_copy(dev->dev_addr, real_dev->dev_addr);
+	eth_hw_addr_set(dev, real_dev->dev_addr);
 	call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
 	return true;
 }
@@ -349,7 +349,7 @@ static int vlan_dev_set_mac_address(struct net_device *dev, void *p)
 		dev_uc_del(real_dev, dev->dev_addr);
 
 out:
-	ether_addr_copy(dev->dev_addr, addr->sa_data);
+	eth_hw_addr_set(dev, addr->sa_data);
 	return 0;
 }
 
@@ -586,7 +586,7 @@ static int vlan_dev_init(struct net_device *dev)
 	dev->dev_id = real_dev->dev_id;
 
 	if (is_zero_ether_addr(dev->dev_addr)) {
-		ether_addr_copy(dev->dev_addr, real_dev->dev_addr);
+		eth_hw_addr_set(dev, real_dev->dev_addr);
 		dev->addr_assign_type = NET_ADDR_STOLEN;
 	}
 	if (is_zero_ether_addr(dev->broadcast))
diff --git a/net/9p/client.c b/net/9p/client.c
index 7973267ec846..565aee6dfcc6 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -32,10 +32,9 @@
 
 #define DEFAULT_MSIZE (128 * 1024)
 
-/*
-  * Client Option Parsing (code inspired by NFS code)
-  *  - a little lazy - parse all client options
-  */
+/* Client Option Parsing (code inspired by NFS code)
+ *  - a little lazy - parse all client options
+ */
 
 enum {
 	Opt_msize,
@@ -89,20 +88,18 @@ int p9_show_client_options(struct seq_file *m, struct p9_client *clnt)
 }
 EXPORT_SYMBOL(p9_show_client_options);
 
-/*
- * Some error codes are taken directly from the server replies,
+/* Some error codes are taken directly from the server replies,
  * make sure they are valid.
  */
 static int safe_errno(int err)
 {
-	if ((err > 0) || (err < -MAX_ERRNO)) {
+	if (err > 0 || err < -MAX_ERRNO) {
 		p9_debug(P9_DEBUG_ERROR, "Invalid error code %d\n", err);
 		return -EPROTO;
 	}
 	return err;
 }
 
-
 /* Interpret mount option for protocol version */
 static int get_protocol_version(char *s)
 {
@@ -117,8 +114,9 @@ static int get_protocol_version(char *s)
 	} else if (!strcmp(s, "9p2000.L")) {
 		version = p9_proto_2000L;
 		p9_debug(P9_DEBUG_9P, "Protocol version: 9P2000.L\n");
-	} else
+	} else {
 		pr_info("Unknown protocol version %s\n", s);
+	}
 
 	return version;
 }
@@ -147,15 +145,13 @@ static int parse_opts(char *opts, struct p9_client *clnt)
 		return 0;
 
 	tmp_options = kstrdup(opts, GFP_KERNEL);
-	if (!tmp_options) {
-		p9_debug(P9_DEBUG_ERROR,
-			 "failed to allocate copy of option string\n");
+	if (!tmp_options)
 		return -ENOMEM;
-	}
 	options = tmp_options;
 
 	while ((p = strsep(&options, ",")) != NULL) {
 		int token, r;
+
 		if (!*p)
 			continue;
 		token = match_token(p, tokens, args);
@@ -187,7 +183,7 @@ static int parse_opts(char *opts, struct p9_client *clnt)
 
 			v9fs_put_trans(clnt->trans_mod);
 			clnt->trans_mod = v9fs_get_trans_by_name(s);
-			if (clnt->trans_mod == NULL) {
+			if (!clnt->trans_mod) {
 				pr_info("Could not find request transport: %s\n",
 					s);
 				ret = -EINVAL;
@@ -311,7 +307,7 @@ p9_tag_alloc(struct p9_client *c, int8_t type, unsigned int max_size)
 	 * callback), so p9_client_cb eats the second ref there
 	 * as the pointer is duplicated directly by virtqueue_add_sgs()
 	 */
-	refcount_set(&req->refcount.refcount, 2);
+	refcount_set(&req->refcount, 2);
 
 	return req;
 
@@ -347,7 +343,7 @@ again:
 		if (!p9_req_try_get(req))
 			goto again;
 		if (req->tc.tag != tag) {
-			p9_req_put(req);
+			p9_req_put(c, req);
 			goto again;
 		}
 	}
@@ -373,20 +369,18 @@ static int p9_tag_remove(struct p9_client *c, struct p9_req_t *r)
 	spin_lock_irqsave(&c->lock, flags);
 	idr_remove(&c->reqs, tag);
 	spin_unlock_irqrestore(&c->lock, flags);
-	return p9_req_put(r);
-}
-
-static void p9_req_free(struct kref *ref)
-{
-	struct p9_req_t *r = container_of(ref, struct p9_req_t, refcount);
-	p9_fcall_fini(&r->tc);
-	p9_fcall_fini(&r->rc);
-	kmem_cache_free(p9_req_cache, r);
+	return p9_req_put(c, r);
 }
 
-int p9_req_put(struct p9_req_t *r)
+int p9_req_put(struct p9_client *c, struct p9_req_t *r)
 {
-	return kref_put(&r->refcount, p9_req_free);
+	if (refcount_dec_and_test(&r->refcount)) {
+		p9_fcall_fini(&r->tc);
+		p9_fcall_fini(&r->rc);
+		kmem_cache_free(p9_req_cache, r);
+		return 1;
+	}
+	return 0;
 }
 EXPORT_SYMBOL(p9_req_put);
 
@@ -423,8 +417,7 @@ void p9_client_cb(struct p9_client *c, struct p9_req_t *req, int status)
 {
 	p9_debug(P9_DEBUG_MUX, " tag %d\n", req->tc.tag);
 
-	/*
-	 * This barrier is needed to make sure any change made to req before
+	/* This barrier is needed to make sure any change made to req before
 	 * the status change is visible to another thread
 	 */
 	smp_wmb();
@@ -432,7 +425,7 @@ void p9_client_cb(struct p9_client *c, struct p9_req_t *req, int status)
 
 	wake_up(&req->wq);
 	p9_debug(P9_DEBUG_MUX, "wakeup: %d\n", req->tc.tag);
-	p9_req_put(req);
+	p9_req_put(c, req);
 }
 EXPORT_SYMBOL(p9_client_cb);
 
@@ -446,12 +439,12 @@ EXPORT_SYMBOL(p9_client_cb);
  */
 
 int
-p9_parse_header(struct p9_fcall *pdu, int32_t *size, int8_t *type, int16_t *tag,
-								int rewind)
+p9_parse_header(struct p9_fcall *pdu, int32_t *size, int8_t *type,
+		int16_t *tag, int rewind)
 {
-	int8_t r_type;
-	int16_t r_tag;
-	int32_t r_size;
+	s8 r_type;
+	s16 r_tag;
+	s32 r_size;
 	int offset = pdu->offset;
 	int err;
 
@@ -499,7 +492,7 @@ EXPORT_SYMBOL(p9_parse_header);
 
 static int p9_check_errors(struct p9_client *c, struct p9_req_t *req)
 {
-	int8_t type;
+	s8 type;
 	int err;
 	int ecode;
 
@@ -510,8 +503,7 @@ static int p9_check_errors(struct p9_client *c, struct p9_req_t *req)
 			 req->rc.size);
 		return -EIO;
 	}
-	/*
-	 * dump the response from server
+	/* dump the response from server
 	 * This should be after check errors which poplulate pdu_fcall.
 	 */
 	trace_9p_protocol_dump(c, &req->rc);
@@ -524,6 +516,7 @@ static int p9_check_errors(struct p9_client *c, struct p9_req_t *req)
 
 	if (!p9_is_proto_dotl(c)) {
 		char *ename;
+
 		err = p9pdu_readf(&req->rc, c->proto_version, "s?d",
 				  &ename, &ecode);
 		if (err)
@@ -574,12 +567,11 @@ static int p9_check_zc_errors(struct p9_client *c, struct p9_req_t *req,
 {
 	int err;
 	int ecode;
-	int8_t type;
+	s8 type;
 	char *ename = NULL;
 
 	err = p9_parse_header(&req->rc, NULL, &type, NULL, 0);
-	/*
-	 * dump the response from server
+	/* dump the response from server
 	 * This should be after parse_header which poplulate pdu_fcall.
 	 */
 	trace_9p_protocol_dump(c, &req->rc);
@@ -607,7 +599,7 @@ static int p9_check_zc_errors(struct p9_client *c, struct p9_req_t *req,
 		if (len > inline_len) {
 			/* We have error in external buffer */
 			if (!copy_from_iter_full(ename + inline_len,
-					     len - inline_len, uidata)) {
+						 len - inline_len, uidata)) {
 				err = -EFAULT;
 				goto out_err;
 			}
@@ -659,7 +651,7 @@ p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...);
 static int p9_client_flush(struct p9_client *c, struct p9_req_t *oldreq)
 {
 	struct p9_req_t *req;
-	int16_t oldtag;
+	s16 oldtag;
 	int err;
 
 	err = p9_parse_header(&oldreq->tc, NULL, NULL, &oldtag, 1);
@@ -672,8 +664,7 @@ static int p9_client_flush(struct p9_client *c, struct p9_req_t *oldreq)
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
-	/*
-	 * if we haven't received a response for oldreq,
+	/* if we haven't received a response for oldreq,
 	 * remove it from the list
 	 */
 	if (oldreq->status == REQ_STATUS_SENT) {
@@ -699,7 +690,7 @@ static struct p9_req_t *p9_client_prepare_req(struct p9_client *c,
 		return ERR_PTR(-EIO);
 
 	/* if status is begin_disconnected we allow only clunk request */
-	if ((c->status == BeginDisconnect) && (type != P9_TCLUNK))
+	if (c->status == BeginDisconnect && type != P9_TCLUNK)
 		return ERR_PTR(-EIO);
 
 	req = p9_tag_alloc(c, type, req_size);
@@ -717,7 +708,7 @@ static struct p9_req_t *p9_client_prepare_req(struct p9_client *c,
 reterr:
 	p9_tag_remove(c, req);
 	/* We have to put also the 2nd reference as it won't be used */
-	p9_req_put(req);
+	p9_req_put(c, req);
 	return ERR_PTR(err);
 }
 
@@ -747,13 +738,14 @@ p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...)
 	if (signal_pending(current)) {
 		sigpending = 1;
 		clear_thread_flag(TIF_SIGPENDING);
-	} else
+	} else {
 		sigpending = 0;
+	}
 
 	err = c->trans_mod->request(c, req);
 	if (err < 0) {
 		/* write won't happen */
-		p9_req_put(req);
+		p9_req_put(c, req);
 		if (err != -ERESTARTSYS && err != -EFAULT)
 			c->status = Disconnected;
 		goto recalc_sigpending;
@@ -762,14 +754,13 @@ again:
 	/* Wait for the response */
 	err = wait_event_killable(req->wq, req->status >= REQ_STATUS_RCVD);
 
-	/*
-	 * Make sure our req is coherent with regard to updates in other
+	/* Make sure our req is coherent with regard to updates in other
 	 * threads - echoes to wmb() in the callback
 	 */
 	smp_rmb();
 
-	if ((err == -ERESTARTSYS) && (c->status == Connected)
-				  && (type == P9_TFLUSH)) {
+	if (err == -ERESTARTSYS && c->status == Connected &&
+	    type == P9_TFLUSH) {
 		sigpending = 1;
 		clear_thread_flag(TIF_SIGPENDING);
 		goto again;
@@ -779,7 +770,7 @@ again:
 		p9_debug(P9_DEBUG_ERROR, "req_status error %d\n", req->t_err);
 		err = req->t_err;
 	}
-	if ((err == -ERESTARTSYS) && (c->status == Connected)) {
+	if (err == -ERESTARTSYS && c->status == Connected) {
 		p9_debug(P9_DEBUG_MUX, "flushing\n");
 		sigpending = 1;
 		clear_thread_flag(TIF_SIGPENDING);
@@ -834,8 +825,7 @@ static struct p9_req_t *p9_client_zc_rpc(struct p9_client *c, int8_t type,
 	struct p9_req_t *req;
 
 	va_start(ap, fmt);
-	/*
-	 * We allocate a inline protocol data of only 4k bytes.
+	/* We allocate a inline protocol data of only 4k bytes.
 	 * The actual content is passed in zero-copy fashion.
 	 */
 	req = p9_client_prepare_req(c, type, P9_ZC_HDR_SZ, fmt, ap);
@@ -846,8 +836,9 @@ static struct p9_req_t *p9_client_zc_rpc(struct p9_client *c, int8_t type,
 	if (signal_pending(current)) {
 		sigpending = 1;
 		clear_thread_flag(TIF_SIGPENDING);
-	} else
+	} else {
 		sigpending = 0;
+	}
 
 	err = c->trans_mod->zc_request(c, req, uidata, uodata,
 				       inlen, olen, in_hdrlen);
@@ -861,7 +852,7 @@ static struct p9_req_t *p9_client_zc_rpc(struct p9_client *c, int8_t type,
 		p9_debug(P9_DEBUG_ERROR, "req_status error %d\n", req->t_err);
 		err = req->t_err;
 	}
-	if ((err == -ERESTARTSYS) && (c->status == Connected)) {
+	if (err == -ERESTARTSYS && c->status == Connected) {
 		p9_debug(P9_DEBUG_MUX, "flushing\n");
 		sigpending = 1;
 		clear_thread_flag(TIF_SIGPENDING);
@@ -897,16 +888,13 @@ static struct p9_fid *p9_fid_create(struct p9_client *clnt)
 	struct p9_fid *fid;
 
 	p9_debug(P9_DEBUG_FID, "clnt %p\n", clnt);
-	fid = kmalloc(sizeof(struct p9_fid), GFP_KERNEL);
+	fid = kzalloc(sizeof(*fid), GFP_KERNEL);
 	if (!fid)
 		return NULL;
 
-	memset(&fid->qid, 0, sizeof(struct p9_qid));
 	fid->mode = -1;
 	fid->uid = current_fsuid();
 	fid->clnt = clnt;
-	fid->rdir = NULL;
-	fid->fid = 0;
 	refcount_set(&fid->count, 1);
 
 	idr_preload(GFP_KERNEL);
@@ -949,15 +937,15 @@ static int p9_client_version(struct p9_client *c)
 	switch (c->proto_version) {
 	case p9_proto_2000L:
 		req = p9_client_rpc(c, P9_TVERSION, "ds",
-					c->msize, "9P2000.L");
+				    c->msize, "9P2000.L");
 		break;
 	case p9_proto_2000u:
 		req = p9_client_rpc(c, P9_TVERSION, "ds",
-					c->msize, "9P2000.u");
+				    c->msize, "9P2000.u");
 		break;
 	case p9_proto_legacy:
 		req = p9_client_rpc(c, P9_TVERSION, "ds",
-					c->msize, "9P2000");
+				    c->msize, "9P2000");
 		break;
 	default:
 		return -EINVAL;
@@ -974,13 +962,13 @@ static int p9_client_version(struct p9_client *c)
 	}
 
 	p9_debug(P9_DEBUG_9P, "<<< RVERSION msize %d %s\n", msize, version);
-	if (!strncmp(version, "9P2000.L", 8))
+	if (!strncmp(version, "9P2000.L", 8)) {
 		c->proto_version = p9_proto_2000L;
-	else if (!strncmp(version, "9P2000.u", 8))
+	} else if (!strncmp(version, "9P2000.u", 8)) {
 		c->proto_version = p9_proto_2000u;
-	else if (!strncmp(version, "9P2000", 6))
+	} else if (!strncmp(version, "9P2000", 6)) {
 		c->proto_version = p9_proto_legacy;
-	else {
+	} else {
 		p9_debug(P9_DEBUG_ERROR,
 			 "server returned an unknown version: %s\n", version);
 		err = -EREMOTEIO;
@@ -1010,7 +998,7 @@ struct p9_client *p9_client_create(const char *dev_name, char *options)
 	char *client_id;
 
 	err = 0;
-	clnt = kmalloc(sizeof(struct p9_client), GFP_KERNEL);
+	clnt = kmalloc(sizeof(*clnt), GFP_KERNEL);
 	if (!clnt)
 		return ERR_PTR(-ENOMEM);
 
@@ -1032,7 +1020,7 @@ struct p9_client *p9_client_create(const char *dev_name, char *options)
 	if (!clnt->trans_mod)
 		clnt->trans_mod = v9fs_get_default_trans();
 
-	if (clnt->trans_mod == NULL) {
+	if (!clnt->trans_mod) {
 		err = -EPROTONOSUPPORT;
 		p9_debug(P9_DEBUG_ERROR,
 			 "No transport defined or default transport\n");
@@ -1120,14 +1108,14 @@ void p9_client_begin_disconnect(struct p9_client *clnt)
 EXPORT_SYMBOL(p9_client_begin_disconnect);
 
 struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid,
-	const char *uname, kuid_t n_uname, const char *aname)
+				const char *uname, kuid_t n_uname,
+				const char *aname)
 {
 	int err = 0;
 	struct p9_req_t *req;
 	struct p9_fid *fid;
 	struct p9_qid qid;
 
-
 	p9_debug(P9_DEBUG_9P, ">>> TATTACH afid %d uname %s aname %s\n",
 		 afid ? afid->fid : -1, uname, aname);
 	fid = p9_fid_create(clnt);
@@ -1138,7 +1126,7 @@ struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid,
 	fid->uid = n_uname;
 
 	req = p9_client_rpc(clnt, P9_TATTACH, "ddss?u", fid->fid,
-			afid ? afid->fid : P9_NOFID, uname, aname, n_uname);
+			    afid ? afid->fid : P9_NOFID, uname, aname, n_uname);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
 		goto error;
@@ -1152,7 +1140,7 @@ struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid,
 	}
 
 	p9_debug(P9_DEBUG_9P, "<<< RATTACH qid %x.%llx.%x\n",
-		 qid.type, (unsigned long long)qid.path, qid.version);
+		 qid.type, qid.path, qid.version);
 
 	memmove(&fid->qid, &qid, sizeof(struct p9_qid));
 
@@ -1167,14 +1155,14 @@ error:
 EXPORT_SYMBOL(p9_client_attach);
 
 struct p9_fid *p9_client_walk(struct p9_fid *oldfid, uint16_t nwname,
-		const unsigned char * const *wnames, int clone)
+			      const unsigned char * const *wnames, int clone)
 {
 	int err;
 	struct p9_client *clnt;
 	struct p9_fid *fid;
 	struct p9_qid *wqids;
 	struct p9_req_t *req;
-	uint16_t nwqids, count;
+	u16 nwqids, count;
 
 	err = 0;
 	wqids = NULL;
@@ -1187,14 +1175,14 @@ struct p9_fid *p9_client_walk(struct p9_fid *oldfid, uint16_t nwname,
 		}
 
 		fid->uid = oldfid->uid;
-	} else
+	} else {
 		fid = oldfid;
-
+	}
 
 	p9_debug(P9_DEBUG_9P, ">>> TWALK fids %d,%d nwname %ud wname[0] %s\n",
 		 oldfid->fid, fid->fid, nwname, wnames ? wnames[0] : NULL);
 	req = p9_client_rpc(clnt, P9_TWALK, "ddT", oldfid->fid, fid->fid,
-								nwname, wnames);
+			    nwname, wnames);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
 		goto error;
@@ -1217,9 +1205,9 @@ struct p9_fid *p9_client_walk(struct p9_fid *oldfid, uint16_t nwname,
 
 	for (count = 0; count < nwqids; count++)
 		p9_debug(P9_DEBUG_9P, "<<<     [%d] %x.%llx.%x\n",
-			count, wqids[count].type,
-			(unsigned long long)wqids[count].path,
-			wqids[count].version);
+			 count, wqids[count].type,
+			 wqids[count].path,
+			 wqids[count].version);
 
 	if (nwname)
 		memmove(&fid->qid, &wqids[nwqids - 1], sizeof(struct p9_qid));
@@ -1235,7 +1223,7 @@ clunk_fid:
 	fid = NULL;
 
 error:
-	if (fid && (fid != oldfid))
+	if (fid && fid != oldfid)
 		p9_fid_destroy(fid);
 
 	return ERR_PTR(err);
@@ -1252,7 +1240,7 @@ int p9_client_open(struct p9_fid *fid, int mode)
 
 	clnt = fid->clnt;
 	p9_debug(P9_DEBUG_9P, ">>> %s fid %d mode %d\n",
-		p9_is_proto_dotl(clnt) ? "TLOPEN" : "TOPEN", fid->fid, mode);
+		 p9_is_proto_dotl(clnt) ? "TLOPEN" : "TOPEN", fid->fid, mode);
 	err = 0;
 
 	if (fid->mode != -1)
@@ -1274,8 +1262,8 @@ int p9_client_open(struct p9_fid *fid, int mode)
 	}
 
 	p9_debug(P9_DEBUG_9P, "<<< %s qid %x.%llx.%x iounit %x\n",
-		p9_is_proto_dotl(clnt) ? "RLOPEN" : "ROPEN",  qid.type,
-		(unsigned long long)qid.path, qid.version, iounit);
+		 p9_is_proto_dotl(clnt) ? "RLOPEN" : "ROPEN",  qid.type,
+		 qid.path, qid.version, iounit);
 
 	memmove(&fid->qid, &qid, sizeof(struct p9_qid));
 	fid->mode = mode;
@@ -1288,8 +1276,8 @@ error:
 }
 EXPORT_SYMBOL(p9_client_open);
 
-int p9_client_create_dotl(struct p9_fid *ofid, const char *name, u32 flags, u32 mode,
-		kgid_t gid, struct p9_qid *qid)
+int p9_client_create_dotl(struct p9_fid *ofid, const char *name, u32 flags,
+			  u32 mode, kgid_t gid, struct p9_qid *qid)
 {
 	int err = 0;
 	struct p9_client *clnt;
@@ -1297,16 +1285,16 @@ int p9_client_create_dotl(struct p9_fid *ofid, const char *name, u32 flags, u32
 	int iounit;
 
 	p9_debug(P9_DEBUG_9P,
-			">>> TLCREATE fid %d name %s flags %d mode %d gid %d\n",
-			ofid->fid, name, flags, mode,
-		 	from_kgid(&init_user_ns, gid));
+		 ">>> TLCREATE fid %d name %s flags %d mode %d gid %d\n",
+		 ofid->fid, name, flags, mode,
+		 from_kgid(&init_user_ns, gid));
 	clnt = ofid->clnt;
 
 	if (ofid->mode != -1)
 		return -EINVAL;
 
 	req = p9_client_rpc(clnt, P9_TLCREATE, "dsddg", ofid->fid, name, flags,
-			mode, gid);
+			    mode, gid);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
 		goto error;
@@ -1319,9 +1307,7 @@ int p9_client_create_dotl(struct p9_fid *ofid, const char *name, u32 flags, u32
 	}
 
 	p9_debug(P9_DEBUG_9P, "<<< RLCREATE qid %x.%llx.%x iounit %x\n",
-			qid->type,
-			(unsigned long long)qid->path,
-			qid->version, iounit);
+		 qid->type, qid->path, qid->version, iounit);
 
 	memmove(&ofid->qid, qid, sizeof(struct p9_qid));
 	ofid->mode = mode;
@@ -1344,7 +1330,7 @@ int p9_client_fcreate(struct p9_fid *fid, const char *name, u32 perm, int mode,
 	int iounit;
 
 	p9_debug(P9_DEBUG_9P, ">>> TCREATE fid %d name %s perm %d mode %d\n",
-						fid->fid, name, perm, mode);
+		 fid->fid, name, perm, mode);
 	err = 0;
 	clnt = fid->clnt;
 
@@ -1352,7 +1338,7 @@ int p9_client_fcreate(struct p9_fid *fid, const char *name, u32 perm, int mode,
 		return -EINVAL;
 
 	req = p9_client_rpc(clnt, P9_TCREATE, "dsdb?s", fid->fid, name, perm,
-				mode, extension);
+			    mode, extension);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
 		goto error;
@@ -1365,9 +1351,7 @@ int p9_client_fcreate(struct p9_fid *fid, const char *name, u32 perm, int mode,
 	}
 
 	p9_debug(P9_DEBUG_9P, "<<< RCREATE qid %x.%llx.%x iounit %x\n",
-				qid.type,
-				(unsigned long long)qid.path,
-				qid.version, iounit);
+		 qid.type, qid.path, qid.version, iounit);
 
 	memmove(&fid->qid, &qid, sizeof(struct p9_qid));
 	fid->mode = mode;
@@ -1381,18 +1365,18 @@ error:
 EXPORT_SYMBOL(p9_client_fcreate);
 
 int p9_client_symlink(struct p9_fid *dfid, const char *name,
-		const char *symtgt, kgid_t gid, struct p9_qid *qid)
+		      const char *symtgt, kgid_t gid, struct p9_qid *qid)
 {
 	int err = 0;
 	struct p9_client *clnt;
 	struct p9_req_t *req;
 
 	p9_debug(P9_DEBUG_9P, ">>> TSYMLINK dfid %d name %s  symtgt %s\n",
-			dfid->fid, name, symtgt);
+		 dfid->fid, name, symtgt);
 	clnt = dfid->clnt;
 
 	req = p9_client_rpc(clnt, P9_TSYMLINK, "dssg", dfid->fid, name, symtgt,
-			gid);
+			    gid);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
 		goto error;
@@ -1405,7 +1389,7 @@ int p9_client_symlink(struct p9_fid *dfid, const char *name,
 	}
 
 	p9_debug(P9_DEBUG_9P, "<<< RSYMLINK qid %x.%llx.%x\n",
-			qid->type, (unsigned long long)qid->path, qid->version);
+		 qid->type, qid->path, qid->version);
 
 free_and_error:
 	p9_tag_remove(clnt, req);
@@ -1420,10 +1404,10 @@ int p9_client_link(struct p9_fid *dfid, struct p9_fid *oldfid, const char *newna
 	struct p9_req_t *req;
 
 	p9_debug(P9_DEBUG_9P, ">>> TLINK dfid %d oldfid %d newname %s\n",
-			dfid->fid, oldfid->fid, newname);
+		 dfid->fid, oldfid->fid, newname);
 	clnt = dfid->clnt;
 	req = p9_client_rpc(clnt, P9_TLINK, "dds", dfid->fid, oldfid->fid,
-			newname);
+			    newname);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
@@ -1440,7 +1424,7 @@ int p9_client_fsync(struct p9_fid *fid, int datasync)
 	struct p9_req_t *req;
 
 	p9_debug(P9_DEBUG_9P, ">>> TFSYNC fid %d datasync:%d\n",
-			fid->fid, datasync);
+		 fid->fid, datasync);
 	err = 0;
 	clnt = fid->clnt;
 
@@ -1476,8 +1460,8 @@ int p9_client_clunk(struct p9_fid *fid)
 		return 0;
 
 again:
-	p9_debug(P9_DEBUG_9P, ">>> TCLUNK fid %d (try %d)\n", fid->fid,
-								retries);
+	p9_debug(P9_DEBUG_9P, ">>> TCLUNK fid %d (try %d)\n",
+		 fid->fid, retries);
 	err = 0;
 	clnt = fid->clnt;
 
@@ -1491,16 +1475,16 @@ again:
 
 	p9_tag_remove(clnt, req);
 error:
-	/*
-	 * Fid is not valid even after a failed clunk
+	/* Fid is not valid even after a failed clunk
 	 * If interrupted, retry once then give up and
 	 * leak fid until umount.
 	 */
 	if (err == -ERESTARTSYS) {
 		if (retries++ == 0)
 			goto again;
-	} else
+	} else {
 		p9_fid_destroy(fid);
+	}
 	return err;
 }
 EXPORT_SYMBOL(p9_client_clunk);
@@ -1540,7 +1524,7 @@ int p9_client_unlinkat(struct p9_fid *dfid, const char *name, int flags)
 	struct p9_client *clnt;
 
 	p9_debug(P9_DEBUG_9P, ">>> TUNLINKAT fid %d %s %d\n",
-		   dfid->fid, name, flags);
+		 dfid->fid, name, flags);
 
 	clnt = dfid->clnt;
 	req = p9_client_rpc(clnt, P9_TUNLINKAT, "dsd", dfid->fid, name, flags);
@@ -1586,8 +1570,8 @@ p9_client_read_once(struct p9_fid *fid, u64 offset, struct iov_iter *to,
 	char *dataptr;
 
 	*err = 0;
-	p9_debug(P9_DEBUG_9P, ">>> TREAD fid %d offset %llu %d\n",
-		   fid->fid, (unsigned long long) offset, (int)iov_iter_count(to));
+	p9_debug(P9_DEBUG_9P, ">>> TREAD fid %d offset %llu %zu\n",
+		 fid->fid, offset, iov_iter_count(to));
 
 	rsize = fid->iounit;
 	if (!rsize || rsize > clnt->msize - P9_IOHDRSZ)
@@ -1653,13 +1637,13 @@ p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err)
 	*err = 0;
 
 	p9_debug(P9_DEBUG_9P, ">>> TWRITE fid %d offset %llu count %zd\n",
-				fid->fid, (unsigned long long) offset,
-				iov_iter_count(from));
+		 fid->fid, offset, iov_iter_count(from));
 
 	while (iov_iter_count(from)) {
 		int count = iov_iter_count(from);
 		int rsize = fid->iounit;
-		if (!rsize || rsize > clnt->msize-P9_IOHDRSZ)
+
+		if (!rsize || rsize > clnt->msize - P9_IOHDRSZ)
 			rsize = clnt->msize - P9_IOHDRSZ;
 
 		if (count < rsize)
@@ -1672,7 +1656,7 @@ p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err)
 					       fid->fid, offset, rsize);
 		} else {
 			req = p9_client_rpc(clnt, P9_TWRITE, "dqV", fid->fid,
-						    offset, rsize, from);
+					    offset, rsize, from);
 		}
 		if (IS_ERR(req)) {
 			*err = PTR_ERR(req);
@@ -1705,12 +1689,13 @@ struct p9_wstat *p9_client_stat(struct p9_fid *fid)
 {
 	int err;
 	struct p9_client *clnt;
-	struct p9_wstat *ret = kmalloc(sizeof(struct p9_wstat), GFP_KERNEL);
+	struct p9_wstat *ret;
 	struct p9_req_t *req;
 	u16 ignored;
 
 	p9_debug(P9_DEBUG_9P, ">>> TSTAT fid %d\n", fid->fid);
 
+	ret = kmalloc(sizeof(*ret), GFP_KERNEL);
 	if (!ret)
 		return ERR_PTR(-ENOMEM);
 
@@ -1731,17 +1716,17 @@ struct p9_wstat *p9_client_stat(struct p9_fid *fid)
 	}
 
 	p9_debug(P9_DEBUG_9P,
-		"<<< RSTAT sz=%x type=%x dev=%x qid=%x.%llx.%x\n"
-		"<<<    mode=%8.8x atime=%8.8x mtime=%8.8x length=%llx\n"
-		"<<<    name=%s uid=%s gid=%s muid=%s extension=(%s)\n"
-		"<<<    uid=%d gid=%d n_muid=%d\n",
-		ret->size, ret->type, ret->dev, ret->qid.type,
-		(unsigned long long)ret->qid.path, ret->qid.version, ret->mode,
-		ret->atime, ret->mtime, (unsigned long long)ret->length,
-		ret->name, ret->uid, ret->gid, ret->muid, ret->extension,
-		from_kuid(&init_user_ns, ret->n_uid),
-		from_kgid(&init_user_ns, ret->n_gid),
-		from_kuid(&init_user_ns, ret->n_muid));
+		 "<<< RSTAT sz=%x type=%x dev=%x qid=%x.%llx.%x\n"
+		 "<<<    mode=%8.8x atime=%8.8x mtime=%8.8x length=%llx\n"
+		 "<<<    name=%s uid=%s gid=%s muid=%s extension=(%s)\n"
+		 "<<<    uid=%d gid=%d n_muid=%d\n",
+		 ret->size, ret->type, ret->dev, ret->qid.type, ret->qid.path,
+		 ret->qid.version, ret->mode,
+		 ret->atime, ret->mtime, ret->length,
+		 ret->name, ret->uid, ret->gid, ret->muid, ret->extension,
+		 from_kuid(&init_user_ns, ret->n_uid),
+		 from_kgid(&init_user_ns, ret->n_gid),
+		 from_kuid(&init_user_ns, ret->n_muid));
 
 	p9_tag_remove(clnt, req);
 	return ret;
@@ -1753,17 +1738,17 @@ error:
 EXPORT_SYMBOL(p9_client_stat);
 
 struct p9_stat_dotl *p9_client_getattr_dotl(struct p9_fid *fid,
-							u64 request_mask)
+					    u64 request_mask)
 {
 	int err;
 	struct p9_client *clnt;
-	struct p9_stat_dotl *ret = kmalloc(sizeof(struct p9_stat_dotl),
-								GFP_KERNEL);
+	struct p9_stat_dotl *ret;
 	struct p9_req_t *req;
 
 	p9_debug(P9_DEBUG_9P, ">>> TGETATTR fid %d, request_mask %lld\n",
-							fid->fid, request_mask);
+		 fid->fid, request_mask);
 
+	ret = kmalloc(sizeof(*ret), GFP_KERNEL);
 	if (!ret)
 		return ERR_PTR(-ENOMEM);
 
@@ -1783,26 +1768,27 @@ struct p9_stat_dotl *p9_client_getattr_dotl(struct p9_fid *fid,
 		goto error;
 	}
 
-	p9_debug(P9_DEBUG_9P,
-		"<<< RGETATTR st_result_mask=%lld\n"
-		"<<< qid=%x.%llx.%x\n"
-		"<<< st_mode=%8.8x st_nlink=%llu\n"
-		"<<< st_uid=%d st_gid=%d\n"
-		"<<< st_rdev=%llx st_size=%llx st_blksize=%llu st_blocks=%llu\n"
-		"<<< st_atime_sec=%lld st_atime_nsec=%lld\n"
-		"<<< st_mtime_sec=%lld st_mtime_nsec=%lld\n"
-		"<<< st_ctime_sec=%lld st_ctime_nsec=%lld\n"
-		"<<< st_btime_sec=%lld st_btime_nsec=%lld\n"
-		"<<< st_gen=%lld st_data_version=%lld\n",
-		ret->st_result_mask, ret->qid.type, ret->qid.path,
-		ret->qid.version, ret->st_mode, ret->st_nlink,
-		from_kuid(&init_user_ns, ret->st_uid),
-		from_kgid(&init_user_ns, ret->st_gid),
-		ret->st_rdev, ret->st_size, ret->st_blksize,
-		ret->st_blocks, ret->st_atime_sec, ret->st_atime_nsec,
-		ret->st_mtime_sec, ret->st_mtime_nsec, ret->st_ctime_sec,
-		ret->st_ctime_nsec, ret->st_btime_sec, ret->st_btime_nsec,
-		ret->st_gen, ret->st_data_version);
+	p9_debug(P9_DEBUG_9P, "<<< RGETATTR st_result_mask=%lld\n"
+		 "<<< qid=%x.%llx.%x\n"
+		 "<<< st_mode=%8.8x st_nlink=%llu\n"
+		 "<<< st_uid=%d st_gid=%d\n"
+		 "<<< st_rdev=%llx st_size=%llx st_blksize=%llu st_blocks=%llu\n"
+		 "<<< st_atime_sec=%lld st_atime_nsec=%lld\n"
+		 "<<< st_mtime_sec=%lld st_mtime_nsec=%lld\n"
+		 "<<< st_ctime_sec=%lld st_ctime_nsec=%lld\n"
+		 "<<< st_btime_sec=%lld st_btime_nsec=%lld\n"
+		 "<<< st_gen=%lld st_data_version=%lld\n",
+		 ret->st_result_mask,
+		 ret->qid.type, ret->qid.path, ret->qid.version,
+		 ret->st_mode, ret->st_nlink,
+		 from_kuid(&init_user_ns, ret->st_uid),
+		 from_kgid(&init_user_ns, ret->st_gid),
+		 ret->st_rdev, ret->st_size, ret->st_blksize, ret->st_blocks,
+		 ret->st_atime_sec, ret->st_atime_nsec,
+		 ret->st_mtime_sec, ret->st_mtime_nsec,
+		 ret->st_ctime_sec, ret->st_ctime_nsec,
+		 ret->st_btime_sec, ret->st_btime_nsec,
+		 ret->st_gen, ret->st_data_version);
 
 	p9_tag_remove(clnt, req);
 	return ret;
@@ -1821,7 +1807,7 @@ static int p9_client_statsize(struct p9_wstat *wst, int proto_version)
 	/* size[2] type[2] dev[4] qid[13] */
 	/* mode[4] atime[4] mtime[4] length[8]*/
 	/* name[s] uid[s] gid[s] muid[s] */
-	ret = 2+4+13+4+4+4+8+2+2+2+2;
+	ret = 2 + 4 + 13 + 4 + 4 + 4 + 8 + 2 + 2 + 2 + 2;
 
 	if (wst->name)
 		ret += strlen(wst->name);
@@ -1832,9 +1818,10 @@ static int p9_client_statsize(struct p9_wstat *wst, int proto_version)
 	if (wst->muid)
 		ret += strlen(wst->muid);
 
-	if ((proto_version == p9_proto_2000u) ||
-		(proto_version == p9_proto_2000L)) {
-		ret += 2+4+4+4;	/* extension[s] n_uid[4] n_gid[4] n_muid[4] */
+	if (proto_version == p9_proto_2000u ||
+	    proto_version == p9_proto_2000L) {
+		/* extension[s] n_uid[4] n_gid[4] n_muid[4] */
+		ret += 2 + 4 + 4 + 4;
 		if (wst->extension)
 			ret += strlen(wst->extension);
 	}
@@ -1851,21 +1838,23 @@ int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst)
 	err = 0;
 	clnt = fid->clnt;
 	wst->size = p9_client_statsize(wst, clnt->proto_version);
-	p9_debug(P9_DEBUG_9P, ">>> TWSTAT fid %d\n", fid->fid);
+	p9_debug(P9_DEBUG_9P, ">>> TWSTAT fid %d\n",
+		 fid->fid);
 	p9_debug(P9_DEBUG_9P,
-		"     sz=%x type=%x dev=%x qid=%x.%llx.%x\n"
-		"     mode=%8.8x atime=%8.8x mtime=%8.8x length=%llx\n"
-		"     name=%s uid=%s gid=%s muid=%s extension=(%s)\n"
-		"     uid=%d gid=%d n_muid=%d\n",
-		wst->size, wst->type, wst->dev, wst->qid.type,
-		(unsigned long long)wst->qid.path, wst->qid.version, wst->mode,
-		wst->atime, wst->mtime, (unsigned long long)wst->length,
-		wst->name, wst->uid, wst->gid, wst->muid, wst->extension,
-		from_kuid(&init_user_ns, wst->n_uid),
-		from_kgid(&init_user_ns, wst->n_gid),
-		from_kuid(&init_user_ns, wst->n_muid));
-
-	req = p9_client_rpc(clnt, P9_TWSTAT, "dwS", fid->fid, wst->size+2, wst);
+		 "     sz=%x type=%x dev=%x qid=%x.%llx.%x\n"
+		 "     mode=%8.8x atime=%8.8x mtime=%8.8x length=%llx\n"
+		 "     name=%s uid=%s gid=%s muid=%s extension=(%s)\n"
+		 "     uid=%d gid=%d n_muid=%d\n",
+		 wst->size, wst->type, wst->dev, wst->qid.type,
+		 wst->qid.path, wst->qid.version,
+		 wst->mode, wst->atime, wst->mtime, wst->length,
+		 wst->name, wst->uid, wst->gid, wst->muid, wst->extension,
+		 from_kuid(&init_user_ns, wst->n_uid),
+		 from_kgid(&init_user_ns, wst->n_gid),
+		 from_kuid(&init_user_ns, wst->n_muid));
+
+	req = p9_client_rpc(clnt, P9_TWSTAT, "dwS",
+			    fid->fid, wst->size + 2, wst);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
 		goto error;
@@ -1888,15 +1877,15 @@ int p9_client_setattr(struct p9_fid *fid, struct p9_iattr_dotl *p9attr)
 	err = 0;
 	clnt = fid->clnt;
 	p9_debug(P9_DEBUG_9P, ">>> TSETATTR fid %d\n", fid->fid);
-	p9_debug(P9_DEBUG_9P,
-		"    valid=%x mode=%x uid=%d gid=%d size=%lld\n"
-		"    atime_sec=%lld atime_nsec=%lld\n"
-		"    mtime_sec=%lld mtime_nsec=%lld\n",
-		p9attr->valid, p9attr->mode,
-		from_kuid(&init_user_ns, p9attr->uid),
-		from_kgid(&init_user_ns, p9attr->gid),
-		p9attr->size, p9attr->atime_sec, p9attr->atime_nsec,
-		p9attr->mtime_sec, p9attr->mtime_nsec);
+	p9_debug(P9_DEBUG_9P, "    valid=%x mode=%x uid=%d gid=%d size=%lld\n",
+		 p9attr->valid, p9attr->mode,
+		 from_kuid(&init_user_ns, p9attr->uid),
+		 from_kgid(&init_user_ns, p9attr->gid),
+		 p9attr->size);
+	p9_debug(P9_DEBUG_9P, "    atime_sec=%lld atime_nsec=%lld\n",
+		 p9attr->atime_sec, p9attr->atime_nsec);
+	p9_debug(P9_DEBUG_9P, "    mtime_sec=%lld mtime_nsec=%lld\n",
+		 p9attr->mtime_sec, p9attr->mtime_nsec);
 
 	req = p9_client_rpc(clnt, P9_TSETATTR, "dI", fid->fid, p9attr);
 
@@ -1937,12 +1926,10 @@ int p9_client_statfs(struct p9_fid *fid, struct p9_rstatfs *sb)
 		goto error;
 	}
 
-	p9_debug(P9_DEBUG_9P, "<<< RSTATFS fid %d type 0x%lx bsize %ld "
-		"blocks %llu bfree %llu bavail %llu files %llu ffree %llu "
-		"fsid %llu namelen %ld\n",
-		fid->fid, (long unsigned int)sb->type, (long int)sb->bsize,
-		sb->blocks, sb->bfree, sb->bavail, sb->files,  sb->ffree,
-		sb->fsid, (long int)sb->namelen);
+	p9_debug(P9_DEBUG_9P,
+		 "<<< RSTATFS fid %d type 0x%x bsize %u blocks %llu bfree %llu bavail %llu files %llu ffree %llu fsid %llu namelen %u\n",
+		 fid->fid, sb->type, sb->bsize, sb->blocks, sb->bfree,
+		 sb->bavail, sb->files, sb->ffree, sb->fsid, sb->namelen);
 
 	p9_tag_remove(clnt, req);
 error:
@@ -1961,10 +1948,10 @@ int p9_client_rename(struct p9_fid *fid,
 	clnt = fid->clnt;
 
 	p9_debug(P9_DEBUG_9P, ">>> TRENAME fid %d newdirfid %d name %s\n",
-			fid->fid, newdirfid->fid, name);
+		 fid->fid, newdirfid->fid, name);
 
 	req = p9_client_rpc(clnt, P9_TRENAME, "dds", fid->fid,
-			newdirfid->fid, name);
+			    newdirfid->fid, name);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
 		goto error;
@@ -1988,9 +1975,9 @@ int p9_client_renameat(struct p9_fid *olddirfid, const char *old_name,
 	err = 0;
 	clnt = olddirfid->clnt;
 
-	p9_debug(P9_DEBUG_9P, ">>> TRENAMEAT olddirfid %d old name %s"
-		   " newdirfid %d new name %s\n", olddirfid->fid, old_name,
-		   newdirfid->fid, new_name);
+	p9_debug(P9_DEBUG_9P,
+		 ">>> TRENAMEAT olddirfid %d old name %s newdirfid %d new name %s\n",
+		 olddirfid->fid, old_name, newdirfid->fid, new_name);
 
 	req = p9_client_rpc(clnt, P9_TRENAMEAT, "dsds", olddirfid->fid,
 			    old_name, newdirfid->fid, new_name);
@@ -2000,7 +1987,7 @@ int p9_client_renameat(struct p9_fid *olddirfid, const char *old_name,
 	}
 
 	p9_debug(P9_DEBUG_9P, "<<< RRENAMEAT newdirfid %d new name %s\n",
-		   newdirfid->fid, new_name);
+		 newdirfid->fid, new_name);
 
 	p9_tag_remove(clnt, req);
 error:
@@ -2008,11 +1995,10 @@ error:
 }
 EXPORT_SYMBOL(p9_client_renameat);
 
-/*
- * An xattrwalk without @attr_name gives the fid for the lisxattr namespace
+/* An xattrwalk without @attr_name gives the fid for the lisxattr namespace
  */
 struct p9_fid *p9_client_xattrwalk(struct p9_fid *file_fid,
-				const char *attr_name, u64 *attr_size)
+				   const char *attr_name, u64 *attr_size)
 {
 	int err;
 	struct p9_req_t *req;
@@ -2027,11 +2013,11 @@ struct p9_fid *p9_client_xattrwalk(struct p9_fid *file_fid,
 		goto error;
 	}
 	p9_debug(P9_DEBUG_9P,
-		">>> TXATTRWALK file_fid %d, attr_fid %d name %s\n",
-		file_fid->fid, attr_fid->fid, attr_name);
+		 ">>> TXATTRWALK file_fid %d, attr_fid %d name %s\n",
+		 file_fid->fid, attr_fid->fid, attr_name);
 
 	req = p9_client_rpc(clnt, P9_TXATTRWALK, "dds",
-			file_fid->fid, attr_fid->fid, attr_name);
+			    file_fid->fid, attr_fid->fid, attr_name);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
 		goto error;
@@ -2044,13 +2030,13 @@ struct p9_fid *p9_client_xattrwalk(struct p9_fid *file_fid,
 	}
 	p9_tag_remove(clnt, req);
 	p9_debug(P9_DEBUG_9P, "<<<  RXATTRWALK fid %d size %llu\n",
-		attr_fid->fid, *attr_size);
+		 attr_fid->fid, *attr_size);
 	return attr_fid;
 clunk_fid:
 	p9_client_clunk(attr_fid);
 	attr_fid = NULL;
 error:
-	if (attr_fid && (attr_fid != file_fid))
+	if (attr_fid && attr_fid != file_fid)
 		p9_fid_destroy(attr_fid);
 
 	return ERR_PTR(err);
@@ -2058,19 +2044,19 @@ error:
 EXPORT_SYMBOL_GPL(p9_client_xattrwalk);
 
 int p9_client_xattrcreate(struct p9_fid *fid, const char *name,
-			u64 attr_size, int flags)
+			  u64 attr_size, int flags)
 {
 	int err;
 	struct p9_req_t *req;
 	struct p9_client *clnt;
 
 	p9_debug(P9_DEBUG_9P,
-		">>> TXATTRCREATE fid %d name  %s size %lld flag %d\n",
-		fid->fid, name, (long long)attr_size, flags);
+		 ">>> TXATTRCREATE fid %d name  %s size %llu flag %d\n",
+		 fid->fid, name, attr_size, flags);
 	err = 0;
 	clnt = fid->clnt;
 	req = p9_client_rpc(clnt, P9_TXATTRCREATE, "dsqd",
-			fid->fid, name, attr_size, flags);
+			    fid->fid, name, attr_size, flags);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
 		goto error;
@@ -2094,13 +2080,13 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset)
 	iov_iter_kvec(&to, READ, &kv, 1, count);
 
 	p9_debug(P9_DEBUG_9P, ">>> TREADDIR fid %d offset %llu count %d\n",
-				fid->fid, (unsigned long long) offset, count);
+		 fid->fid, offset, count);
 
 	err = 0;
 	clnt = fid->clnt;
 
 	rsize = fid->iounit;
-	if (!rsize || rsize > clnt->msize-P9_READDIRHDRSZ)
+	if (!rsize || rsize > clnt->msize - P9_READDIRHDRSZ)
 		rsize = clnt->msize - P9_READDIRHDRSZ;
 
 	if (count < rsize)
@@ -2108,8 +2094,7 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset)
 
 	/* Don't bother zerocopy for small IO (< 1024) */
 	if (clnt->trans_mod->zc_request && rsize > 1024) {
-		/*
-		 * response header len is 11
+		/* response header len is 11
 		 * PDU Header(7) + IO Size (4)
 		 */
 		req = p9_client_zc_rpc(clnt, P9_TREADDIR, &to, NULL, rsize, 0,
@@ -2150,7 +2135,7 @@ error:
 EXPORT_SYMBOL(p9_client_readdir);
 
 int p9_client_mknod_dotl(struct p9_fid *fid, const char *name, int mode,
-			dev_t rdev, kgid_t gid, struct p9_qid *qid)
+			 dev_t rdev, kgid_t gid, struct p9_qid *qid)
 {
 	int err;
 	struct p9_client *clnt;
@@ -2158,10 +2143,11 @@ int p9_client_mknod_dotl(struct p9_fid *fid, const char *name, int mode,
 
 	err = 0;
 	clnt = fid->clnt;
-	p9_debug(P9_DEBUG_9P, ">>> TMKNOD fid %d name %s mode %d major %d "
-		"minor %d\n", fid->fid, name, mode, MAJOR(rdev), MINOR(rdev));
+	p9_debug(P9_DEBUG_9P,
+		 ">>> TMKNOD fid %d name %s mode %d major %d minor %d\n",
+		 fid->fid, name, mode, MAJOR(rdev), MINOR(rdev));
 	req = p9_client_rpc(clnt, P9_TMKNOD, "dsdddg", fid->fid, name, mode,
-		MAJOR(rdev), MINOR(rdev), gid);
+			    MAJOR(rdev), MINOR(rdev), gid);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
@@ -2170,18 +2156,17 @@ int p9_client_mknod_dotl(struct p9_fid *fid, const char *name, int mode,
 		trace_9p_protocol_dump(clnt, &req->rc);
 		goto error;
 	}
-	p9_debug(P9_DEBUG_9P, "<<< RMKNOD qid %x.%llx.%x\n", qid->type,
-				(unsigned long long)qid->path, qid->version);
+	p9_debug(P9_DEBUG_9P, "<<< RMKNOD qid %x.%llx.%x\n",
+		 qid->type, qid->path, qid->version);
 
 error:
 	p9_tag_remove(clnt, req);
 	return err;
-
 }
 EXPORT_SYMBOL(p9_client_mknod_dotl);
 
 int p9_client_mkdir_dotl(struct p9_fid *fid, const char *name, int mode,
-				kgid_t gid, struct p9_qid *qid)
+			 kgid_t gid, struct p9_qid *qid)
 {
 	int err;
 	struct p9_client *clnt;
@@ -2191,8 +2176,8 @@ int p9_client_mkdir_dotl(struct p9_fid *fid, const char *name, int mode,
 	clnt = fid->clnt;
 	p9_debug(P9_DEBUG_9P, ">>> TMKDIR fid %d name %s mode %d gid %d\n",
 		 fid->fid, name, mode, from_kgid(&init_user_ns, gid));
-	req = p9_client_rpc(clnt, P9_TMKDIR, "dsdg", fid->fid, name, mode,
-		gid);
+	req = p9_client_rpc(clnt, P9_TMKDIR, "dsdg",
+			    fid->fid, name, mode, gid);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
@@ -2202,12 +2187,11 @@ int p9_client_mkdir_dotl(struct p9_fid *fid, const char *name, int mode,
 		goto error;
 	}
 	p9_debug(P9_DEBUG_9P, "<<< RMKDIR qid %x.%llx.%x\n", qid->type,
-				(unsigned long long)qid->path, qid->version);
+		 qid->path, qid->version);
 
 error:
 	p9_tag_remove(clnt, req);
 	return err;
-
 }
 EXPORT_SYMBOL(p9_client_mkdir_dotl);
 
@@ -2219,14 +2203,14 @@ int p9_client_lock_dotl(struct p9_fid *fid, struct p9_flock *flock, u8 *status)
 
 	err = 0;
 	clnt = fid->clnt;
-	p9_debug(P9_DEBUG_9P, ">>> TLOCK fid %d type %i flags %d "
-			"start %lld length %lld proc_id %d client_id %s\n",
-			fid->fid, flock->type, flock->flags, flock->start,
-			flock->length, flock->proc_id, flock->client_id);
+	p9_debug(P9_DEBUG_9P,
+		 ">>> TLOCK fid %d type %i flags %d start %lld length %lld proc_id %d client_id %s\n",
+		 fid->fid, flock->type, flock->flags, flock->start,
+		 flock->length, flock->proc_id, flock->client_id);
 
 	req = p9_client_rpc(clnt, P9_TLOCK, "dbdqqds", fid->fid, flock->type,
-				flock->flags, flock->start, flock->length,
-					flock->proc_id, flock->client_id);
+			    flock->flags, flock->start, flock->length,
+			    flock->proc_id, flock->client_id);
 
 	if (IS_ERR(req))
 		return PTR_ERR(req);
@@ -2240,7 +2224,6 @@ int p9_client_lock_dotl(struct p9_fid *fid, struct p9_flock *flock, u8 *status)
 error:
 	p9_tag_remove(clnt, req);
 	return err;
-
 }
 EXPORT_SYMBOL(p9_client_lock_dotl);
 
@@ -2252,12 +2235,14 @@ int p9_client_getlock_dotl(struct p9_fid *fid, struct p9_getlock *glock)
 
 	err = 0;
 	clnt = fid->clnt;
-	p9_debug(P9_DEBUG_9P, ">>> TGETLOCK fid %d, type %i start %lld "
-		"length %lld proc_id %d client_id %s\n", fid->fid, glock->type,
-		glock->start, glock->length, glock->proc_id, glock->client_id);
+	p9_debug(P9_DEBUG_9P,
+		 ">>> TGETLOCK fid %d, type %i start %lld length %lld proc_id %d client_id %s\n",
+		 fid->fid, glock->type, glock->start, glock->length,
+		 glock->proc_id, glock->client_id);
 
-	req = p9_client_rpc(clnt, P9_TGETLOCK, "dbqqds", fid->fid,  glock->type,
-		glock->start, glock->length, glock->proc_id, glock->client_id);
+	req = p9_client_rpc(clnt, P9_TGETLOCK, "dbqqds", fid->fid,
+			    glock->type, glock->start, glock->length,
+			    glock->proc_id, glock->client_id);
 
 	if (IS_ERR(req))
 		return PTR_ERR(req);
@@ -2269,9 +2254,10 @@ int p9_client_getlock_dotl(struct p9_fid *fid, struct p9_getlock *glock)
 		trace_9p_protocol_dump(clnt, &req->rc);
 		goto error;
 	}
-	p9_debug(P9_DEBUG_9P, "<<< RGETLOCK type %i start %lld length %lld "
-		"proc_id %d client_id %s\n", glock->type, glock->start,
-		glock->length, glock->proc_id, glock->client_id);
+	p9_debug(P9_DEBUG_9P,
+		 "<<< RGETLOCK type %i start %lld length %lld proc_id %d client_id %s\n",
+		 glock->type, glock->start, glock->length,
+		 glock->proc_id, glock->client_id);
 error:
 	p9_tag_remove(clnt, req);
 	return err;
diff --git a/net/9p/error.c b/net/9p/error.c
index 61c18daf3050..ff935746754e 100644
--- a/net/9p/error.c
+++ b/net/9p/error.c
@@ -185,7 +185,7 @@ int p9_error_init(void)
 		INIT_HLIST_HEAD(&hash_errmap[bucket]);
 
 	/* load initial error map into hash table */
-	for (c = errmap; c->name != NULL; c++) {
+	for (c = errmap; c->name; c++) {
 		c->namelen = strlen(c->name);
 		bucket = jhash(c->name, c->namelen, 0) % ERRHASHSZ;
 		INIT_HLIST_NODE(&c->list);
diff --git a/net/9p/mod.c b/net/9p/mod.c
index 5126566850bd..535cf016633c 100644
--- a/net/9p/mod.c
+++ b/net/9p/mod.c
@@ -24,13 +24,13 @@
 #include <linux/spinlock.h>
 
 #ifdef CONFIG_NET_9P_DEBUG
-unsigned int p9_debug_level = 0;	/* feature-rific global debug level  */
+unsigned int p9_debug_level;	/* feature-rific global debug level  */
 EXPORT_SYMBOL(p9_debug_level);
 module_param_named(debug, p9_debug_level, uint, 0);
 MODULE_PARM_DESC(debug, "9P debugging level");
 
 void _p9_debug(enum p9_debug_flags level, const char *func,
-		const char *fmt, ...)
+	       const char *fmt, ...)
 {
 	struct va_format vaf;
 	va_list args;
@@ -53,10 +53,7 @@ void _p9_debug(enum p9_debug_flags level, const char *func,
 EXPORT_SYMBOL(_p9_debug);
 #endif
 
-/*
- * Dynamic Transport Registration Routines
- *
- */
+/* Dynamic Transport Registration Routines */
 
 static DEFINE_SPINLOCK(v9fs_trans_lock);
 static LIST_HEAD(v9fs_trans_list);
diff --git a/net/9p/protocol.c b/net/9p/protocol.c
index 03593eb240d8..59eb71f357fa 100644
--- a/net/9p/protocol.c
+++ b/net/9p/protocol.c
@@ -46,6 +46,7 @@ EXPORT_SYMBOL(p9stat_free);
 size_t pdu_read(struct p9_fcall *pdu, void *data, size_t size)
 {
 	size_t len = min(pdu->size - pdu->offset, size);
+
 	memcpy(data, &pdu->sdata[pdu->offset], len);
 	pdu->offset += len;
 	return size - len;
@@ -54,6 +55,7 @@ size_t pdu_read(struct p9_fcall *pdu, void *data, size_t size)
 static size_t pdu_write(struct p9_fcall *pdu, const void *data, size_t size)
 {
 	size_t len = min(pdu->capacity - pdu->size, size);
+
 	memcpy(&pdu->sdata[pdu->size], data, len);
 	pdu->size += len;
 	return size - len;
@@ -64,6 +66,7 @@ pdu_write_u(struct p9_fcall *pdu, struct iov_iter *from, size_t size)
 {
 	size_t len = min(pdu->capacity - pdu->size, size);
 	struct iov_iter i = *from;
+
 	if (!copy_from_iter_full(&pdu->sdata[pdu->size], len, &i))
 		len = 0;
 
@@ -71,26 +74,25 @@ pdu_write_u(struct p9_fcall *pdu, struct iov_iter *from, size_t size)
 	return size - len;
 }
 
-/*
-	b - int8_t
-	w - int16_t
-	d - int32_t
-	q - int64_t
-	s - string
-	u - numeric uid
-	g - numeric gid
-	S - stat
-	Q - qid
-	D - data blob (int32_t size followed by void *, results are not freed)
-	T - array of strings (int16_t count, followed by strings)
-	R - array of qids (int16_t count, followed by qids)
-	A - stat for 9p2000.L (p9_stat_dotl)
-	? - if optional = 1, continue parsing
-*/
+/*	b - int8_t
+ *	w - int16_t
+ *	d - int32_t
+ *	q - int64_t
+ *	s - string
+ *	u - numeric uid
+ *	g - numeric gid
+ *	S - stat
+ *	Q - qid
+ *	D - data blob (int32_t size followed by void *, results are not freed)
+ *	T - array of strings (int16_t count, followed by strings)
+ *	R - array of qids (int16_t count, followed by qids)
+ *	A - stat for 9p2000.L (p9_stat_dotl)
+ *	? - if optional = 1, continue parsing
+ */
 
 static int
 p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt,
-	va_list ap)
+	     va_list ap)
 {
 	const char *ptr;
 	int errcode = 0;
diff --git a/net/9p/protocol.h b/net/9p/protocol.h
index 6835f91cfda5..4a2f68651037 100644
--- a/net/9p/protocol.h
+++ b/net/9p/protocol.h
@@ -11,7 +11,7 @@
  */
 
 int p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt,
-								va_list ap);
+		  va_list ap);
 int p9pdu_readf(struct p9_fcall *pdu, int proto_version, const char *fmt, ...);
 int p9pdu_prepare(struct p9_fcall *pdu, int16_t tag, int8_t type);
 int p9pdu_finalize(struct p9_client *clnt, struct p9_fcall *pdu);
diff --git a/net/9p/trans_common.h b/net/9p/trans_common.h
index c43babb3f635..65c094c321a2 100644
--- a/net/9p/trans_common.h
+++ b/net/9p/trans_common.h
@@ -12,4 +12,4 @@
  *
  */
 
-void p9_release_pages(struct page **, int);
+void p9_release_pages(struct page **pages, int nr_pages);
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index 007bbcc68010..6fe3719c1fc6 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -345,6 +345,7 @@ static void p9_read_work(struct work_struct *work)
 			p9_debug(P9_DEBUG_ERROR,
 				 "No recv fcall for tag %d (req %p), disconnecting!\n",
 				 m->rc.tag, m->rreq);
+			p9_req_put(m->client, m->rreq);
 			m->rreq = NULL;
 			err = -EIO;
 			goto error;
@@ -380,7 +381,7 @@ static void p9_read_work(struct work_struct *work)
 		m->rc.sdata = NULL;
 		m->rc.offset = 0;
 		m->rc.capacity = 0;
-		p9_req_put(m->rreq);
+		p9_req_put(m->client, m->rreq);
 		m->rreq = NULL;
 	}
 
@@ -494,7 +495,7 @@ static void p9_write_work(struct work_struct *work)
 	m->wpos += err;
 	if (m->wpos == m->wsize) {
 		m->wpos = m->wsize = 0;
-		p9_req_put(m->wreq);
+		p9_req_put(m->client, m->wreq);
 		m->wreq = NULL;
 	}
 
@@ -697,7 +698,7 @@ static int p9_fd_cancel(struct p9_client *client, struct p9_req_t *req)
 	if (req->status == REQ_STATUS_UNSENT) {
 		list_del(&req->req_list);
 		req->status = REQ_STATUS_FLSHD;
-		p9_req_put(req);
+		p9_req_put(client, req);
 		ret = 0;
 	}
 	spin_unlock(&client->lock);
@@ -724,7 +725,7 @@ static int p9_fd_cancelled(struct p9_client *client, struct p9_req_t *req)
 	list_del(&req->req_list);
 	req->status = REQ_STATUS_FLSHD;
 	spin_unlock(&client->lock);
-	p9_req_put(req);
+	p9_req_put(client, req);
 
 	return 0;
 }
@@ -885,12 +886,12 @@ static void p9_conn_destroy(struct p9_conn *m)
 	p9_mux_poll_stop(m);
 	cancel_work_sync(&m->rq);
 	if (m->rreq) {
-		p9_req_put(m->rreq);
+		p9_req_put(m->client, m->rreq);
 		m->rreq = NULL;
 	}
 	cancel_work_sync(&m->wq);
 	if (m->wreq) {
-		p9_req_put(m->wreq);
+		p9_req_put(m->client, m->wreq);
 		m->wreq = NULL;
 	}
 
diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c
index af0a8a6cd3fd..f6d145873b49 100644
--- a/net/9p/trans_rdma.c
+++ b/net/9p/trans_rdma.c
@@ -352,7 +352,7 @@ send_done(struct ib_cq *cq, struct ib_wc *wc)
 			    c->busa, c->req->tc.size,
 			    DMA_TO_DEVICE);
 	up(&rdma->sq_sem);
-	p9_req_put(c->req);
+	p9_req_put(client, c->req);
 	kfree(c);
 }
 
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index 490a4c900339..d110df3cb4e1 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -199,7 +199,7 @@ static int p9_virtio_cancel(struct p9_client *client, struct p9_req_t *req)
 /* Reply won't come, so drop req ref */
 static int p9_virtio_cancelled(struct p9_client *client, struct p9_req_t *req)
 {
-	p9_req_put(req);
+	p9_req_put(client, req);
 	return 0;
 }
 
@@ -523,7 +523,7 @@ err_out:
 	kvfree(out_pages);
 	if (!kicked) {
 		/* reply won't come */
-		p9_req_put(req);
+		p9_req_put(client, req);
 	}
 	return err;
 }
diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c
index 432ac5a16f2e..427f6caefa29 100644
--- a/net/9p/trans_xen.c
+++ b/net/9p/trans_xen.c
@@ -186,7 +186,7 @@ again:
 	ring->intf->out_prod = prod;
 	spin_unlock_irqrestore(&ring->lock, flags);
 	notify_remote_via_irq(ring->irq);
-	p9_req_put(p9_req);
+	p9_req_put(client, p9_req);
 
 	return 0;
 }
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 5ac3aca6deeb..2337e9275863 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1559,7 +1559,9 @@ static void hci_cc_le_clear_accept_list(struct hci_dev *hdev,
 	if (status)
 		return;
 
+	hci_dev_lock(hdev);
 	hci_bdaddr_list_clear(&hdev->le_accept_list);
+	hci_dev_unlock(hdev);
 }
 
 static void hci_cc_le_add_to_accept_list(struct hci_dev *hdev,
@@ -1577,8 +1579,10 @@ static void hci_cc_le_add_to_accept_list(struct hci_dev *hdev,
 	if (!sent)
 		return;
 
+	hci_dev_lock(hdev);
 	hci_bdaddr_list_add(&hdev->le_accept_list, &sent->bdaddr,
 			    sent->bdaddr_type);
+	hci_dev_unlock(hdev);
 }
 
 static void hci_cc_le_del_from_accept_list(struct hci_dev *hdev,
@@ -1596,8 +1600,10 @@ static void hci_cc_le_del_from_accept_list(struct hci_dev *hdev,
 	if (!sent)
 		return;
 
+	hci_dev_lock(hdev);
 	hci_bdaddr_list_del(&hdev->le_accept_list, &sent->bdaddr,
 			    sent->bdaddr_type);
+	hci_dev_unlock(hdev);
 }
 
 static void hci_cc_le_read_supported_states(struct hci_dev *hdev,
@@ -1661,9 +1667,11 @@ static void hci_cc_le_add_to_resolv_list(struct hci_dev *hdev,
 	if (!sent)
 		return;
 
+	hci_dev_lock(hdev);
 	hci_bdaddr_list_add_with_irk(&hdev->le_resolv_list, &sent->bdaddr,
 				sent->bdaddr_type, sent->peer_irk,
 				sent->local_irk);
+	hci_dev_unlock(hdev);
 }
 
 static void hci_cc_le_del_from_resolv_list(struct hci_dev *hdev,
@@ -1681,8 +1689,10 @@ static void hci_cc_le_del_from_resolv_list(struct hci_dev *hdev,
 	if (!sent)
 		return;
 
+	hci_dev_lock(hdev);
 	hci_bdaddr_list_del_with_irk(&hdev->le_resolv_list, &sent->bdaddr,
 			    sent->bdaddr_type);
+	hci_dev_unlock(hdev);
 }
 
 static void hci_cc_le_clear_resolv_list(struct hci_dev *hdev,
@@ -1695,7 +1705,9 @@ static void hci_cc_le_clear_resolv_list(struct hci_dev *hdev,
 	if (status)
 		return;
 
+	hci_dev_lock(hdev);
 	hci_bdaddr_list_clear(&hdev->le_resolv_list);
+	hci_dev_unlock(hdev);
 }
 
 static void hci_cc_le_read_resolv_list_size(struct hci_dev *hdev,
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index c57a45df7a26..e8de1e7d6ff4 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -111,7 +111,8 @@ static struct l2cap_chan *__l2cap_get_chan_by_scid(struct l2cap_conn *conn,
 }
 
 /* Find channel with given SCID.
- * Returns locked channel. */
+ * Returns a reference locked channel.
+ */
 static struct l2cap_chan *l2cap_get_chan_by_scid(struct l2cap_conn *conn,
 						 u16 cid)
 {
@@ -119,15 +120,19 @@ static struct l2cap_chan *l2cap_get_chan_by_scid(struct l2cap_conn *conn,
 
 	mutex_lock(&conn->chan_lock);
 	c = __l2cap_get_chan_by_scid(conn, cid);
-	if (c)
-		l2cap_chan_lock(c);
+	if (c) {
+		/* Only lock if chan reference is not 0 */
+		c = l2cap_chan_hold_unless_zero(c);
+		if (c)
+			l2cap_chan_lock(c);
+	}
 	mutex_unlock(&conn->chan_lock);
 
 	return c;
 }
 
 /* Find channel with given DCID.
- * Returns locked channel.
+ * Returns a reference locked channel.
  */
 static struct l2cap_chan *l2cap_get_chan_by_dcid(struct l2cap_conn *conn,
 						 u16 cid)
@@ -136,8 +141,12 @@ static struct l2cap_chan *l2cap_get_chan_by_dcid(struct l2cap_conn *conn,
 
 	mutex_lock(&conn->chan_lock);
 	c = __l2cap_get_chan_by_dcid(conn, cid);
-	if (c)
-		l2cap_chan_lock(c);
+	if (c) {
+		/* Only lock if chan reference is not 0 */
+		c = l2cap_chan_hold_unless_zero(c);
+		if (c)
+			l2cap_chan_lock(c);
+	}
 	mutex_unlock(&conn->chan_lock);
 
 	return c;
@@ -162,8 +171,12 @@ static struct l2cap_chan *l2cap_get_chan_by_ident(struct l2cap_conn *conn,
 
 	mutex_lock(&conn->chan_lock);
 	c = __l2cap_get_chan_by_ident(conn, ident);
-	if (c)
-		l2cap_chan_lock(c);
+	if (c) {
+		/* Only lock if chan reference is not 0 */
+		c = l2cap_chan_hold_unless_zero(c);
+		if (c)
+			l2cap_chan_lock(c);
+	}
 	mutex_unlock(&conn->chan_lock);
 
 	return c;
@@ -497,6 +510,16 @@ void l2cap_chan_hold(struct l2cap_chan *c)
 	kref_get(&c->kref);
 }
 
+struct l2cap_chan *l2cap_chan_hold_unless_zero(struct l2cap_chan *c)
+{
+	BT_DBG("chan %p orig refcnt %u", c, kref_read(&c->kref));
+
+	if (!kref_get_unless_zero(&c->kref))
+		return NULL;
+
+	return c;
+}
+
 void l2cap_chan_put(struct l2cap_chan *c)
 {
 	BT_DBG("chan %p orig refcnt %u", c, kref_read(&c->kref));
@@ -1947,11 +1970,11 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm,
 						   bdaddr_t *dst,
 						   u8 link_type)
 {
-	struct l2cap_chan *c, *c1 = NULL;
+	struct l2cap_chan *c, *tmp, *c1 = NULL;
 
 	read_lock(&chan_list_lock);
 
-	list_for_each_entry(c, &chan_list, global_l) {
+	list_for_each_entry_safe(c, tmp, &chan_list, global_l) {
 		if (state && c->state != state)
 			continue;
 
@@ -1969,7 +1992,9 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm,
 			src_match = !bacmp(&c->src, src);
 			dst_match = !bacmp(&c->dst, dst);
 			if (src_match && dst_match) {
-				l2cap_chan_hold(c);
+				if (!l2cap_chan_hold_unless_zero(c))
+					continue;
+
 				read_unlock(&chan_list_lock);
 				return c;
 			}
@@ -1984,7 +2009,7 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm,
 	}
 
 	if (c1)
-		l2cap_chan_hold(c1);
+		c1 = l2cap_chan_hold_unless_zero(c1);
 
 	read_unlock(&chan_list_lock);
 
@@ -4464,6 +4489,7 @@ static inline int l2cap_config_req(struct l2cap_conn *conn,
 
 unlock:
 	l2cap_chan_unlock(chan);
+	l2cap_chan_put(chan);
 	return err;
 }
 
@@ -4578,6 +4604,7 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn,
 
 done:
 	l2cap_chan_unlock(chan);
+	l2cap_chan_put(chan);
 	return err;
 }
 
@@ -5305,6 +5332,7 @@ send_move_response:
 	l2cap_send_move_chan_rsp(chan, result);
 
 	l2cap_chan_unlock(chan);
+	l2cap_chan_put(chan);
 
 	return 0;
 }
@@ -5397,6 +5425,7 @@ static void l2cap_move_continue(struct l2cap_conn *conn, u16 icid, u16 result)
 	}
 
 	l2cap_chan_unlock(chan);
+	l2cap_chan_put(chan);
 }
 
 static void l2cap_move_fail(struct l2cap_conn *conn, u8 ident, u16 icid,
@@ -5426,6 +5455,7 @@ static void l2cap_move_fail(struct l2cap_conn *conn, u8 ident, u16 icid,
 	l2cap_send_move_chan_cfm(chan, L2CAP_MC_UNCONFIRMED);
 
 	l2cap_chan_unlock(chan);
+	l2cap_chan_put(chan);
 }
 
 static int l2cap_move_channel_rsp(struct l2cap_conn *conn,
@@ -5489,6 +5519,7 @@ static int l2cap_move_channel_confirm(struct l2cap_conn *conn,
 	l2cap_send_move_chan_cfm_rsp(conn, cmd->ident, icid);
 
 	l2cap_chan_unlock(chan);
+	l2cap_chan_put(chan);
 
 	return 0;
 }
@@ -5524,6 +5555,7 @@ static inline int l2cap_move_channel_confirm_rsp(struct l2cap_conn *conn,
 	}
 
 	l2cap_chan_unlock(chan);
+	l2cap_chan_put(chan);
 
 	return 0;
 }
@@ -5896,12 +5928,11 @@ static inline int l2cap_le_credits(struct l2cap_conn *conn,
 	if (credits > max_credits) {
 		BT_ERR("LE credits overflow");
 		l2cap_send_disconn_req(chan, ECONNRESET);
-		l2cap_chan_unlock(chan);
 
 		/* Return 0 so that we don't trigger an unnecessary
 		 * command reject packet.
 		 */
-		return 0;
+		goto unlock;
 	}
 
 	chan->tx_credits += credits;
@@ -5912,7 +5943,9 @@ static inline int l2cap_le_credits(struct l2cap_conn *conn,
 	if (chan->tx_credits)
 		chan->ops->resume(chan);
 
+unlock:
 	l2cap_chan_unlock(chan);
+	l2cap_chan_put(chan);
 
 	return 0;
 }
@@ -7598,6 +7631,7 @@ drop:
 
 done:
 	l2cap_chan_unlock(chan);
+	l2cap_chan_put(chan);
 }
 
 static void l2cap_conless_channel(struct l2cap_conn *conn, __le16 psm,
@@ -8086,7 +8120,7 @@ static struct l2cap_chan *l2cap_global_fixed_chan(struct l2cap_chan *c,
 		if (src_type != c->src_type)
 			continue;
 
-		l2cap_chan_hold(c);
+		c = l2cap_chan_hold_unless_zero(c);
 		read_unlock(&chan_list_lock);
 		return c;
 	}
diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c
index f2bacb464ccf..7324764384b6 100644
--- a/net/bluetooth/rfcomm/core.c
+++ b/net/bluetooth/rfcomm/core.c
@@ -549,22 +549,58 @@ struct rfcomm_dlc *rfcomm_dlc_exists(bdaddr_t *src, bdaddr_t *dst, u8 channel)
 	return dlc;
 }
 
+static int rfcomm_dlc_send_frag(struct rfcomm_dlc *d, struct sk_buff *frag)
+{
+	int len = frag->len;
+
+	BT_DBG("dlc %p mtu %d len %d", d, d->mtu, len);
+
+	if (len > d->mtu)
+		return -EINVAL;
+
+	rfcomm_make_uih(frag, d->addr);
+	__skb_queue_tail(&d->tx_queue, frag);
+
+	return len;
+}
+
 int rfcomm_dlc_send(struct rfcomm_dlc *d, struct sk_buff *skb)
 {
-	int len = skb->len;
+	unsigned long flags;
+	struct sk_buff *frag, *next;
+	int len;
 
 	if (d->state != BT_CONNECTED)
 		return -ENOTCONN;
 
-	BT_DBG("dlc %p mtu %d len %d", d, d->mtu, len);
+	frag = skb_shinfo(skb)->frag_list;
+	skb_shinfo(skb)->frag_list = NULL;
 
-	if (len > d->mtu)
-		return -EINVAL;
+	/* Queue all fragments atomically. */
+	spin_lock_irqsave(&d->tx_queue.lock, flags);
 
-	rfcomm_make_uih(skb, d->addr);
-	skb_queue_tail(&d->tx_queue, skb);
+	len = rfcomm_dlc_send_frag(d, skb);
+	if (len < 0 || !frag)
+		goto unlock;
+
+	for (; frag; frag = next) {
+		int ret;
+
+		next = frag->next;
+
+		ret = rfcomm_dlc_send_frag(d, frag);
+		if (ret < 0) {
+			kfree_skb(frag);
+			goto unlock;
+		}
+
+		len += ret;
+	}
+
+unlock:
+	spin_unlock_irqrestore(&d->tx_queue.lock, flags);
 
-	if (!test_bit(RFCOMM_TX_THROTTLED, &d->flags))
+	if (len > 0 && !test_bit(RFCOMM_TX_THROTTLED, &d->flags))
 		rfcomm_schedule();
 	return len;
 }
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index 2c95bb58f901..4bf4ea6cbb5e 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -575,46 +575,20 @@ static int rfcomm_sock_sendmsg(struct socket *sock, struct msghdr *msg,
 	lock_sock(sk);
 
 	sent = bt_sock_wait_ready(sk, msg->msg_flags);
-	if (sent)
-		goto done;
-
-	while (len) {
-		size_t size = min_t(size_t, len, d->mtu);
-		int err;
-
-		skb = sock_alloc_send_skb(sk, size + RFCOMM_SKB_RESERVE,
-				msg->msg_flags & MSG_DONTWAIT, &err);
-		if (!skb) {
-			if (sent == 0)
-				sent = err;
-			break;
-		}
-		skb_reserve(skb, RFCOMM_SKB_HEAD_RESERVE);
-
-		err = memcpy_from_msg(skb_put(skb, size), msg, size);
-		if (err) {
-			kfree_skb(skb);
-			if (sent == 0)
-				sent = err;
-			break;
-		}
 
-		skb->priority = sk->sk_priority;
+	release_sock(sk);
 
-		err = rfcomm_dlc_send(d, skb);
-		if (err < 0) {
-			kfree_skb(skb);
-			if (sent == 0)
-				sent = err;
-			break;
-		}
+	if (sent)
+		return sent;
 
-		sent += size;
-		len  -= size;
-	}
+	skb = bt_skb_sendmmsg(sk, msg, len, d->mtu, RFCOMM_SKB_HEAD_RESERVE,
+			      RFCOMM_SKB_TAIL_RESERVE);
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
 
-done:
-	release_sock(sk);
+	sent = rfcomm_dlc_send(d, skb);
+	if (sent < 0)
+		kfree_skb(skb);
 
 	return sent;
 }
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index c7b43c75677f..9a8814d4565a 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -280,12 +280,10 @@ static int sco_connect(struct hci_dev *hdev, struct sock *sk)
 	return err;
 }
 
-static int sco_send_frame(struct sock *sk, void *buf, int len,
-			  unsigned int msg_flags)
+static int sco_send_frame(struct sock *sk, struct sk_buff *skb)
 {
 	struct sco_conn *conn = sco_pi(sk)->conn;
-	struct sk_buff *skb;
-	int err;
+	int len = skb->len;
 
 	/* Check outgoing MTU */
 	if (len > conn->mtu)
@@ -293,11 +291,6 @@ static int sco_send_frame(struct sock *sk, void *buf, int len,
 
 	BT_DBG("sk %p len %d", sk, len);
 
-	skb = bt_skb_send_alloc(sk, len, msg_flags & MSG_DONTWAIT, &err);
-	if (!skb)
-		return err;
-
-	memcpy(skb_put(skb, len), buf, len);
 	hci_send_sco(conn->hcon, skb);
 
 	return len;
@@ -727,7 +720,7 @@ static int sco_sock_sendmsg(struct socket *sock, struct msghdr *msg,
 			    size_t len)
 {
 	struct sock *sk = sock->sk;
-	void *buf;
+	struct sk_buff *skb;
 	int err;
 
 	BT_DBG("sock %p, sk %p", sock, sk);
@@ -739,24 +732,21 @@ static int sco_sock_sendmsg(struct socket *sock, struct msghdr *msg,
 	if (msg->msg_flags & MSG_OOB)
 		return -EOPNOTSUPP;
 
-	buf = kmalloc(len, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	if (memcpy_from_msg(buf, msg, len)) {
-		kfree(buf);
-		return -EFAULT;
-	}
+	skb = bt_skb_sendmsg(sk, msg, len, len, 0, 0);
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
 
 	lock_sock(sk);
 
 	if (sk->sk_state == BT_CONNECTED)
-		err = sco_send_frame(sk, buf, len, msg->msg_flags);
+		err = sco_send_frame(sk, skb);
 	else
 		err = -ENOTCONN;
 
 	release_sock(sk);
-	kfree(buf);
+
+	if (err < 0)
+		kfree_skb(skb);
 	return err;
 }
 
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 655ee0e2de86..a9fb16b9c735 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -469,6 +469,9 @@ static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb)
 {
 	struct qdisc_skb_cb *cb = (struct qdisc_skb_cb *)skb->cb;
 
+	if (!skb->len)
+		return -EINVAL;
+
 	if (!__skb)
 		return 0;
 
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 68c0d0f92890..a718204c4bfd 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -384,6 +384,7 @@ static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_
 				/* - Bridged-and-DNAT'ed traffic doesn't
 				 *   require ip_forwarding. */
 				if (rt->dst.dev == dev) {
+					skb_dst_drop(skb);
 					skb_dst_set(skb, &rt->dst);
 					goto bridged_dnat;
 				}
@@ -413,6 +414,7 @@ bridged_dnat:
 			kfree_skb(skb);
 			return 0;
 		}
+		skb_dst_drop(skb);
 		skb_dst_set_noref(skb, &rt->dst);
 	}
 
@@ -1012,9 +1014,24 @@ int br_nf_hook_thresh(unsigned int hook, struct net *net,
 		return okfn(net, sk, skb);
 
 	ops = nf_hook_entries_get_hook_ops(e);
-	for (i = 0; i < e->num_hook_entries &&
-	      ops[i]->priority <= NF_BR_PRI_BRNF; i++)
-		;
+	for (i = 0; i < e->num_hook_entries; i++) {
+		/* These hooks have already been called */
+		if (ops[i]->priority < NF_BR_PRI_BRNF)
+			continue;
+
+		/* These hooks have not been called yet, run them. */
+		if (ops[i]->priority > NF_BR_PRI_BRNF)
+			break;
+
+		/* take a closer look at NF_BR_PRI_BRNF. */
+		if (ops[i]->hook == br_nf_pre_routing) {
+			/* This hook diverted the skb to this function,
+			 * hooks after this have not been run yet.
+			 */
+			i++;
+			break;
+		}
+	}
 
 	nf_hook_state_init(&state, hook, NFPROTO_BRIDGE, indev, outdev,
 			   sk, net, okfn);
diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c
index e4e0c836c3f5..6b07f30675bb 100644
--- a/net/bridge/br_netfilter_ipv6.c
+++ b/net/bridge/br_netfilter_ipv6.c
@@ -197,6 +197,7 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc
 			kfree_skb(skb);
 			return 0;
 		}
+		skb_dst_drop(skb);
 		skb_dst_set_noref(skb, &rt->dst);
 	}
 
diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c
index a7af4eaff17d..3d4ea774d7e8 100644
--- a/net/bridge/netfilter/ebtable_broute.c
+++ b/net/bridge/netfilter/ebtable_broute.c
@@ -36,18 +36,10 @@ static struct ebt_replace_kernel initial_table = {
 	.entries	= (char *)&initial_chain,
 };
 
-static int check(const struct ebt_table_info *info, unsigned int valid_hooks)
-{
-	if (valid_hooks & ~(1 << NF_BR_BROUTING))
-		return -EINVAL;
-	return 0;
-}
-
 static const struct ebt_table broute_table = {
 	.name		= "broute",
 	.table		= &initial_table,
 	.valid_hooks	= 1 << NF_BR_BROUTING,
-	.check		= check,
 	.me		= THIS_MODULE,
 };
 
diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c
index c0b121df4a9a..257d63b5dec1 100644
--- a/net/bridge/netfilter/ebtable_filter.c
+++ b/net/bridge/netfilter/ebtable_filter.c
@@ -43,18 +43,10 @@ static struct ebt_replace_kernel initial_table = {
 	.entries	= (char *)initial_chains,
 };
 
-static int check(const struct ebt_table_info *info, unsigned int valid_hooks)
-{
-	if (valid_hooks & ~FILTER_VALID_HOOKS)
-		return -EINVAL;
-	return 0;
-}
-
 static const struct ebt_table frame_filter = {
 	.name		= "filter",
 	.table		= &initial_table,
 	.valid_hooks	= FILTER_VALID_HOOKS,
-	.check		= check,
 	.me		= THIS_MODULE,
 };
 
diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c
index 4078151c224f..39179c2cf87d 100644
--- a/net/bridge/netfilter/ebtable_nat.c
+++ b/net/bridge/netfilter/ebtable_nat.c
@@ -43,18 +43,10 @@ static struct ebt_replace_kernel initial_table = {
 	.entries	= (char *)initial_chains,
 };
 
-static int check(const struct ebt_table_info *info, unsigned int valid_hooks)
-{
-	if (valid_hooks & ~NAT_VALID_HOOKS)
-		return -EINVAL;
-	return 0;
-}
-
 static const struct ebt_table frame_nat = {
 	.name		= "nat",
 	.table		= &initial_table,
 	.valid_hooks	= NAT_VALID_HOOKS,
-	.check		= check,
 	.me		= THIS_MODULE,
 };
 
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index ba045f35114d..8905fe2fe023 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1040,8 +1040,7 @@ static int do_replace_finish(struct net *net, struct ebt_replace *repl,
 		goto free_iterate;
 	}
 
-	/* the table doesn't like it */
-	if (t->check && (ret = t->check(newinfo, repl->valid_hooks)))
+	if (repl->valid_hooks != t->valid_hooks)
 		goto free_unlock;
 
 	if (repl->num_counters && repl->num_counters != t->private->nentries) {
@@ -1231,11 +1230,6 @@ int ebt_register_table(struct net *net, const struct ebt_table *input_table,
 	if (ret != 0)
 		goto free_chainstack;
 
-	if (table->check && table->check(newinfo, table->valid_hooks)) {
-		ret = -EINVAL;
-		goto free_chainstack;
-	}
-
 	table->private = newinfo;
 	rwlock_init(&table->lock);
 	mutex_lock(&ebt_mutex);
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 508f67de0b80..e5ffd2bd62ab 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -100,6 +100,7 @@ static inline u64 get_u64(const struct canfd_frame *cp, int offset)
 
 struct bcm_op {
 	struct list_head list;
+	struct rcu_head rcu;
 	int ifindex;
 	canid_t can_id;
 	u32 flags;
@@ -718,10 +719,9 @@ static struct bcm_op *bcm_find_op(struct list_head *ops,
 	return NULL;
 }
 
-static void bcm_remove_op(struct bcm_op *op)
+static void bcm_free_op_rcu(struct rcu_head *rcu_head)
 {
-	hrtimer_cancel(&op->timer);
-	hrtimer_cancel(&op->thrtimer);
+	struct bcm_op *op = container_of(rcu_head, struct bcm_op, rcu);
 
 	if ((op->frames) && (op->frames != &op->sframe))
 		kfree(op->frames);
@@ -732,6 +732,14 @@ static void bcm_remove_op(struct bcm_op *op)
 	kfree(op);
 }
 
+static void bcm_remove_op(struct bcm_op *op)
+{
+	hrtimer_cancel(&op->timer);
+	hrtimer_cancel(&op->thrtimer);
+
+	call_rcu(&op->rcu, bcm_free_op_rcu);
+}
+
 static void bcm_rx_unreg(struct net_device *dev, struct bcm_op *op)
 {
 	if (op->rx_reg_dev == dev) {
@@ -757,6 +765,9 @@ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh,
 		if ((op->can_id == mh->can_id) && (op->ifindex == ifindex) &&
 		    (op->flags & CAN_FD_FRAME) == (mh->flags & CAN_FD_FRAME)) {
 
+			/* disable automatic timer on frame reception */
+			op->flags |= RX_NO_AUTOTIMER;
+
 			/*
 			 * Don't care if we're bound or not (due to netdev
 			 * problems) can_rx_unregister() is always a save
@@ -785,7 +796,6 @@ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh,
 						  bcm_rx_handler, op);
 
 			list_del(&op->list);
-			synchronize_rcu();
 			bcm_remove_op(op);
 			return 1; /* done */
 		}
diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c
index 6dff4510687a..41016aff21c5 100644
--- a/net/can/j1939/socket.c
+++ b/net/can/j1939/socket.c
@@ -178,7 +178,10 @@ activate_next:
 	if (!first)
 		return;
 
-	if (WARN_ON_ONCE(j1939_session_activate(first))) {
+	if (j1939_session_activate(first)) {
+		netdev_warn_once(first->priv->ndev,
+				 "%s: 0x%p: Identical session is already activated.\n",
+				 __func__, first);
 		first->err = -EBUSY;
 		goto activate_next;
 	} else {
diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c
index 307ee1174a6e..d7d86c944d76 100644
--- a/net/can/j1939/transport.c
+++ b/net/can/j1939/transport.c
@@ -260,6 +260,8 @@ static void __j1939_session_drop(struct j1939_session *session)
 
 static void j1939_session_destroy(struct j1939_session *session)
 {
+	struct sk_buff *skb;
+
 	if (session->transmission) {
 		if (session->err)
 			j1939_sk_errqueue(session, J1939_ERRQUEUE_TX_ABORT);
@@ -274,7 +276,11 @@ static void j1939_session_destroy(struct j1939_session *session)
 	WARN_ON_ONCE(!list_empty(&session->sk_session_queue_entry));
 	WARN_ON_ONCE(!list_empty(&session->active_session_list_entry));
 
-	skb_queue_purge(&session->skb_queue);
+	while ((skb = skb_dequeue(&session->skb_queue)) != NULL) {
+		/* drop ref taken in j1939_session_skb_queue() */
+		skb_unref(skb);
+		kfree_skb(skb);
+	}
 	__j1939_session_drop(session);
 	j1939_priv_put(session->priv);
 	kfree(session);
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index ea61dfe19c86..910ca41cb9e6 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -305,11 +305,12 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk)
 static int bpf_sk_storage_charge(struct bpf_local_storage_map *smap,
 				 void *owner, u32 size)
 {
+	int optmem_max = READ_ONCE(sysctl_optmem_max);
 	struct sock *sk = (struct sock *)owner;
 
 	/* same check as in sock_kmalloc() */
-	if (size <= sysctl_optmem_max &&
-	    atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
+	if (size <= optmem_max &&
+	    atomic_read(&sk->sk_omem_alloc) + size < optmem_max) {
 		atomic_add(size, &sk->sk_omem_alloc);
 		return 0;
 	}
@@ -865,10 +866,18 @@ static int bpf_iter_init_sk_storage_map(void *priv_data,
 {
 	struct bpf_iter_seq_sk_storage_map_info *seq_info = priv_data;
 
+	bpf_map_inc_with_uref(aux->map);
 	seq_info->map = aux->map;
 	return 0;
 }
 
+static void bpf_iter_fini_sk_storage_map(void *priv_data)
+{
+	struct bpf_iter_seq_sk_storage_map_info *seq_info = priv_data;
+
+	bpf_map_put_with_uref(seq_info->map);
+}
+
 static int bpf_iter_attach_map(struct bpf_prog *prog,
 			       union bpf_iter_link_info *linfo,
 			       struct bpf_iter_aux_info *aux)
@@ -886,7 +895,7 @@ static int bpf_iter_attach_map(struct bpf_prog *prog,
 	if (map->map_type != BPF_MAP_TYPE_SK_STORAGE)
 		goto put_map;
 
-	if (prog->aux->max_rdonly_access > map->value_size) {
+	if (prog->aux->max_rdwr_access > map->value_size) {
 		err = -EACCES;
 		goto put_map;
 	}
@@ -914,7 +923,7 @@ static const struct seq_operations bpf_sk_storage_map_seq_ops = {
 static const struct bpf_iter_seq_info iter_seq_info = {
 	.seq_ops		= &bpf_sk_storage_map_seq_ops,
 	.init_seq_private	= bpf_iter_init_sk_storage_map,
-	.fini_seq_private	= NULL,
+	.fini_seq_private	= bpf_iter_fini_sk_storage_map,
 	.seq_priv_size		= sizeof(struct bpf_iter_seq_sk_storage_map_info),
 };
 
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 15ab9ffb27fe..28e5f921dcaf 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -677,7 +677,7 @@ int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb,
 				page_ref_sub(last_head, refs);
 				refs = 0;
 			}
-			skb_fill_page_desc(skb, frag++, head, start, size);
+			skb_fill_page_desc_noacc(skb, frag++, head, start, size);
 		}
 		if (refs)
 			page_ref_sub(last_head, refs);
diff --git a/net/core/dev.c b/net/core/dev.c
index 6111506a4105..be51644e95da 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4147,6 +4147,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 	bool again = false;
 
 	skb_reset_mac_header(skb);
+	skb_assert_len(skb);
 
 	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP))
 		__skb_tstamp_tx(skb, NULL, NULL, skb->sk, SCM_TSTAMP_SCHED);
@@ -4589,7 +4590,7 @@ static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen)
 	struct softnet_data *sd;
 	unsigned int old_flow, new_flow;
 
-	if (qlen < (netdev_max_backlog >> 1))
+	if (qlen < (READ_ONCE(netdev_max_backlog) >> 1))
 		return false;
 
 	sd = this_cpu_ptr(&softnet_data);
@@ -4637,7 +4638,7 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
 	if (!netif_running(skb->dev))
 		goto drop;
 	qlen = skb_queue_len(&sd->input_pkt_queue);
-	if (qlen <= netdev_max_backlog && !skb_flow_limit(skb, qlen)) {
+	if (qlen <= READ_ONCE(netdev_max_backlog) && !skb_flow_limit(skb, qlen)) {
 		if (qlen) {
 enqueue:
 			__skb_queue_tail(&sd->input_pkt_queue, skb);
@@ -4893,7 +4894,7 @@ static int netif_rx_internal(struct sk_buff *skb)
 {
 	int ret;
 
-	net_timestamp_check(netdev_tstamp_prequeue, skb);
+	net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb);
 
 	trace_netif_rx(skb);
 
@@ -5005,7 +5006,8 @@ static __latent_entropy void net_tx_action(struct softirq_action *h)
 			if (likely(get_kfree_skb_cb(skb)->reason == SKB_REASON_CONSUMED))
 				trace_consume_skb(skb);
 			else
-				trace_kfree_skb(skb, net_tx_action);
+				trace_kfree_skb(skb, net_tx_action,
+						SKB_DROP_REASON_NOT_SPECIFIED);
 
 			if (skb->fclone != SKB_FCLONE_UNAVAILABLE)
 				__kfree_skb(skb);
@@ -5252,7 +5254,7 @@ static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc,
 	int ret = NET_RX_DROP;
 	__be16 type;
 
-	net_timestamp_check(!netdev_tstamp_prequeue, skb);
+	net_timestamp_check(!READ_ONCE(netdev_tstamp_prequeue), skb);
 
 	trace_netif_receive_skb(skb);
 
@@ -5633,7 +5635,7 @@ static int netif_receive_skb_internal(struct sk_buff *skb)
 {
 	int ret;
 
-	net_timestamp_check(netdev_tstamp_prequeue, skb);
+	net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb);
 
 	if (skb_defer_rx_timestamp(skb))
 		return NET_RX_SUCCESS;
@@ -5663,7 +5665,7 @@ static void netif_receive_skb_list_internal(struct list_head *head)
 
 	INIT_LIST_HEAD(&sublist);
 	list_for_each_entry_safe(skb, next, head, list) {
-		net_timestamp_check(netdev_tstamp_prequeue, skb);
+		net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb);
 		skb_list_del_init(skb);
 		if (!skb_defer_rx_timestamp(skb))
 			list_add_tail(&skb->list, &sublist);
@@ -6436,7 +6438,7 @@ static int process_backlog(struct napi_struct *napi, int quota)
 		net_rps_action_and_irq_enable(sd);
 	}
 
-	napi->weight = dev_rx_weight;
+	napi->weight = READ_ONCE(dev_rx_weight);
 	while (again) {
 		struct sk_buff *skb;
 
@@ -7136,8 +7138,8 @@ static __latent_entropy void net_rx_action(struct softirq_action *h)
 {
 	struct softnet_data *sd = this_cpu_ptr(&softnet_data);
 	unsigned long time_limit = jiffies +
-		usecs_to_jiffies(netdev_budget_usecs);
-	int budget = netdev_budget;
+		usecs_to_jiffies(READ_ONCE(netdev_budget_usecs));
+	int budget = READ_ONCE(netdev_budget);
 	LIST_HEAD(list);
 	LIST_HEAD(repoll);
 
diff --git a/net/core/devlink.c b/net/core/devlink.c
index db76c55e1a6d..b4d7a7f749c1 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -4413,7 +4413,7 @@ static int devlink_param_get(struct devlink *devlink,
 			     const struct devlink_param *param,
 			     struct devlink_param_gset_ctx *ctx)
 {
-	if (!param->get)
+	if (!param->get || devlink->reload_failed)
 		return -EOPNOTSUPP;
 	return param->get(devlink, param->id, ctx);
 }
@@ -4422,7 +4422,7 @@ static int devlink_param_set(struct devlink *devlink,
 			     const struct devlink_param *param,
 			     struct devlink_param_gset_ctx *ctx)
 {
-	if (!param->set)
+	if (!param->set || devlink->reload_failed)
 		return -EOPNOTSUPP;
 	return param->set(devlink, param->id, ctx);
 }
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 1d99b731e5b2..78202141930f 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -110,7 +110,8 @@ static u32 net_dm_queue_len = 1000;
 
 struct net_dm_alert_ops {
 	void (*kfree_skb_probe)(void *ignore, struct sk_buff *skb,
-				void *location);
+				void *location,
+				enum skb_drop_reason reason);
 	void (*napi_poll_probe)(void *ignore, struct napi_struct *napi,
 				int work, int budget);
 	void (*work_item_func)(struct work_struct *work);
@@ -262,7 +263,9 @@ out:
 	spin_unlock_irqrestore(&data->lock, flags);
 }
 
-static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location)
+static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb,
+				void *location,
+				enum skb_drop_reason reason)
 {
 	trace_drop_common(skb, location);
 }
@@ -494,7 +497,8 @@ static const struct net_dm_alert_ops net_dm_alert_summary_ops = {
 
 static void net_dm_packet_trace_kfree_skb_hit(void *ignore,
 					      struct sk_buff *skb,
-					      void *location)
+					      void *location,
+					      enum skb_drop_reason reason)
 {
 	ktime_t tstamp = ktime_get_real();
 	struct per_cpu_dm_data *data;
diff --git a/net/core/filter.c b/net/core/filter.c
index d1e2ef77ce4c..fb5b9dbf3bc0 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1213,10 +1213,11 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
 static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp)
 {
 	u32 filter_size = bpf_prog_size(fp->prog->len);
+	int optmem_max = READ_ONCE(sysctl_optmem_max);
 
 	/* same check as in sock_kmalloc() */
-	if (filter_size <= sysctl_optmem_max &&
-	    atomic_read(&sk->sk_omem_alloc) + filter_size < sysctl_optmem_max) {
+	if (filter_size <= optmem_max &&
+	    atomic_read(&sk->sk_omem_alloc) + filter_size < optmem_max) {
 		atomic_add(filter_size, &sk->sk_omem_alloc);
 		return true;
 	}
@@ -1548,7 +1549,7 @@ int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
 
-	if (bpf_prog_size(prog->len) > sysctl_optmem_max)
+	if (bpf_prog_size(prog->len) > READ_ONCE(sysctl_optmem_max))
 		err = -ENOMEM;
 	else
 		err = reuseport_attach_prog(sk, prog);
@@ -1615,7 +1616,7 @@ int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk)
 		}
 	} else {
 		/* BPF_PROG_TYPE_SOCKET_FILTER */
-		if (bpf_prog_size(prog->len) > sysctl_optmem_max) {
+		if (bpf_prog_size(prog->len) > READ_ONCE(sysctl_optmem_max)) {
 			err = -ENOMEM;
 			goto err_prog_put;
 		}
@@ -4744,14 +4745,14 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 		/* Only some socketops are supported */
 		switch (optname) {
 		case SO_RCVBUF:
-			val = min_t(u32, val, sysctl_rmem_max);
+			val = min_t(u32, val, READ_ONCE(sysctl_rmem_max));
 			val = min_t(int, val, INT_MAX / 2);
 			sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
 			WRITE_ONCE(sk->sk_rcvbuf,
 				   max_t(int, val * 2, SOCK_MIN_RCVBUF));
 			break;
 		case SO_SNDBUF:
-			val = min_t(u32, val, sysctl_wmem_max);
+			val = min_t(u32, val, READ_ONCE(sysctl_wmem_max));
 			val = min_t(int, val, INT_MAX / 2);
 			sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
 			WRITE_ONCE(sk->sk_sndbuf,
@@ -5851,7 +5852,6 @@ static int bpf_push_seg6_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len
 	if (err)
 		return err;
 
-	ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
 	skb_set_transport_header(skb, sizeof(struct ipv6hdr));
 
 	return seg6_lookup_nexthop(skb, NULL, 0);
@@ -6735,7 +6735,7 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len
 	if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN)
 		return -EINVAL;
 
-	if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies)
+	if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies))
 		return -EINVAL;
 
 	if (!th->ack || th->rst || th->syn)
@@ -6810,7 +6810,7 @@ BPF_CALL_5(bpf_tcp_gen_syncookie, struct sock *, sk, void *, iph, u32, iph_len,
 	if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN)
 		return -EINVAL;
 
-	if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies)
+	if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies))
 		return -ENOENT;
 
 	if (!th->syn || th->ack || th->fin || th->rst)
diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c
index 6eb2e5ec2c50..2f66f3f29563 100644
--- a/net/core/gro_cells.c
+++ b/net/core/gro_cells.c
@@ -26,7 +26,7 @@ int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb)
 
 	cell = this_cpu_ptr(gcells->cells);
 
-	if (skb_queue_len(&cell->napi_skbs) > netdev_max_backlog) {
+	if (skb_queue_len(&cell->napi_skbs) > READ_ONCE(netdev_max_backlog)) {
 drop:
 		atomic_long_inc(&dev->rx_dropped);
 		kfree_skb(skb);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index ff049733ccee..b3556c5c1c08 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -279,11 +279,26 @@ static int neigh_del_timer(struct neighbour *n)
 	return 0;
 }
 
-static void pneigh_queue_purge(struct sk_buff_head *list)
+static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net)
 {
+	struct sk_buff_head tmp;
+	unsigned long flags;
 	struct sk_buff *skb;
 
-	while ((skb = skb_dequeue(list)) != NULL) {
+	skb_queue_head_init(&tmp);
+	spin_lock_irqsave(&list->lock, flags);
+	skb = skb_peek(list);
+	while (skb != NULL) {
+		struct sk_buff *skb_next = skb_peek_next(skb, list);
+		if (net == NULL || net_eq(dev_net(skb->dev), net)) {
+			__skb_unlink(skb, list);
+			__skb_queue_tail(&tmp, skb);
+		}
+		skb = skb_next;
+	}
+	spin_unlock_irqrestore(&list->lock, flags);
+
+	while ((skb = __skb_dequeue(&tmp))) {
 		dev_put(skb->dev);
 		kfree_skb(skb);
 	}
@@ -357,9 +372,9 @@ static int __neigh_ifdown(struct neigh_table *tbl, struct net_device *dev,
 	write_lock_bh(&tbl->lock);
 	neigh_flush_dev(tbl, dev, skip_perm);
 	pneigh_ifdown_and_unlock(tbl, dev);
-
-	del_timer_sync(&tbl->proxy_timer);
-	pneigh_queue_purge(&tbl->proxy_queue);
+	pneigh_queue_purge(&tbl->proxy_queue, dev_net(dev));
+	if (skb_queue_empty_lockless(&tbl->proxy_queue))
+		del_timer_sync(&tbl->proxy_timer);
 	return 0;
 }
 
@@ -1735,7 +1750,7 @@ int neigh_table_clear(int index, struct neigh_table *tbl)
 	/* It is not clean... Fix it to unload IPv6 module safely */
 	cancel_delayed_work_sync(&tbl->gc_work);
 	del_timer_sync(&tbl->proxy_timer);
-	pneigh_queue_purge(&tbl->proxy_queue);
+	pneigh_queue_purge(&tbl->proxy_queue, NULL);
 	neigh_ifdown(tbl, NULL);
 	if (atomic_read(&tbl->entries))
 		pr_crit("neighbour leakage\n");
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index 7131cd1fb2ad..189eea1372d5 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -64,7 +64,7 @@ u32 secure_tcpv6_ts_off(const struct net *net,
 		.daddr = *(struct in6_addr *)daddr,
 	};
 
-	if (net->ipv4.sysctl_tcp_timestamps != 1)
+	if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1)
 		return 0;
 
 	ts_secret_init();
@@ -120,7 +120,7 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral);
 #ifdef CONFIG_INET
 u32 secure_tcp_ts_off(const struct net *net, __be32 saddr, __be32 daddr)
 {
-	if (net->ipv4.sysctl_tcp_timestamps != 1)
+	if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1)
 		return 0;
 
 	ts_secret_init();
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 7b8fdfafa693..a04636b9bfe8 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -759,21 +759,23 @@ void __kfree_skb(struct sk_buff *skb)
 EXPORT_SYMBOL(__kfree_skb);
 
 /**
- *	kfree_skb - free an sk_buff
+ *	kfree_skb_reason - free an sk_buff with special reason
  *	@skb: buffer to free
+ *	@reason: reason why this skb is dropped
  *
  *	Drop a reference to the buffer and free it if the usage count has
- *	hit zero.
+ *	hit zero. Meanwhile, pass the drop reason to 'kfree_skb'
+ *	tracepoint.
  */
-void kfree_skb(struct sk_buff *skb)
+void kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason)
 {
 	if (!skb_unref(skb))
 		return;
 
-	trace_kfree_skb(skb, __builtin_return_address(0));
+	trace_kfree_skb(skb, __builtin_return_address(0), reason);
 	__kfree_skb(skb);
 }
-EXPORT_SYMBOL(kfree_skb);
+EXPORT_SYMBOL(kfree_skb_reason);
 
 void kfree_skb_list(struct sk_buff *segs)
 {
@@ -4212,9 +4214,8 @@ normal:
 				SKB_GSO_CB(nskb)->csum_start =
 					skb_headroom(nskb) + doffset;
 			} else {
-				skb_copy_bits(head_skb, offset,
-					      skb_put(nskb, len),
-					      len);
+				if (skb_copy_bits(head_skb, offset, skb_put(nskb, len), len))
+					goto err;
 			}
 			continue;
 		}
@@ -4916,7 +4917,7 @@ static bool skb_may_tx_timestamp(struct sock *sk, bool tsonly)
 {
 	bool ret;
 
-	if (likely(sysctl_tstamp_allow_data || tsonly))
+	if (likely(READ_ONCE(sysctl_tstamp_allow_data) || tsonly))
 		return true;
 
 	read_lock_bh(&sk->sk_callback_lock);
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index ede0af308f40..054073c7cbb9 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -462,7 +462,7 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
 
 			if (copied == len)
 				break;
-		} while (i != msg_rx->sg.end);
+		} while ((i != msg_rx->sg.end) && !sg_is_last(sge));
 
 		if (unlikely(peek)) {
 			msg_rx = sk_psock_next_msg(psock, msg_rx);
@@ -472,7 +472,7 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
 		}
 
 		msg_rx->sg.start = i;
-		if (!sge->length && msg_rx->sg.start == msg_rx->sg.end) {
+		if (!sge->length && (i == msg_rx->sg.end || sg_is_last(sge))) {
 			msg_rx = sk_psock_dequeue_msg(psock);
 			kfree_sk_msg(msg_rx);
 		}
@@ -731,7 +731,9 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node)
 	sk_psock_set_state(psock, SK_PSOCK_TX_ENABLED);
 	refcount_set(&psock->refcnt, 1);
 
-	rcu_assign_sk_user_data_nocopy(sk, psock);
+	__rcu_assign_sk_user_data_with_flags(sk, psock,
+					     SK_USER_DATA_NOCOPY |
+					     SK_USER_DATA_PSOCK);
 	sock_hold(sk);
 
 out:
diff --git a/net/core/sock.c b/net/core/sock.c
index deaed1b20682..9bcffe1d5332 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1014,7 +1014,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
 		 * play 'guess the biggest size' games. RCVBUF/SNDBUF
 		 * are treated in BSD as hints
 		 */
-		val = min_t(u32, val, sysctl_wmem_max);
+		val = min_t(u32, val, READ_ONCE(sysctl_wmem_max));
 set_sndbuf:
 		/* Ensure val * 2 fits into an int, to prevent max_t()
 		 * from treating it as a negative value.
@@ -1046,7 +1046,7 @@ set_sndbuf:
 		 * play 'guess the biggest size' games. RCVBUF/SNDBUF
 		 * are treated in BSD as hints
 		 */
-		__sock_set_rcvbuf(sk, min_t(u32, val, sysctl_rmem_max));
+		__sock_set_rcvbuf(sk, min_t(u32, val, READ_ONCE(sysctl_rmem_max)));
 		break;
 
 	case SO_RCVBUFFORCE:
@@ -2368,7 +2368,7 @@ struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size,
 
 	/* small safe race: SKB_TRUESIZE may differ from final skb->truesize */
 	if (atomic_read(&sk->sk_omem_alloc) + SKB_TRUESIZE(size) >
-	    sysctl_optmem_max)
+	    READ_ONCE(sysctl_optmem_max))
 		return NULL;
 
 	skb = alloc_skb(size, priority);
@@ -2386,8 +2386,10 @@ struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size,
  */
 void *sock_kmalloc(struct sock *sk, int size, gfp_t priority)
 {
-	if ((unsigned int)size <= sysctl_optmem_max &&
-	    atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
+	int optmem_max = READ_ONCE(sysctl_optmem_max);
+
+	if ((unsigned int)size <= optmem_max &&
+	    atomic_read(&sk->sk_omem_alloc) + size < optmem_max) {
 		void *mem;
 		/* First do the add, to avoid the race if kmalloc
 		 * might sleep.
@@ -3124,8 +3126,8 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 	timer_setup(&sk->sk_timer, NULL, 0);
 
 	sk->sk_allocation	=	GFP_KERNEL;
-	sk->sk_rcvbuf		=	sysctl_rmem_default;
-	sk->sk_sndbuf		=	sysctl_wmem_default;
+	sk->sk_rcvbuf		=	READ_ONCE(sysctl_rmem_default);
+	sk->sk_sndbuf		=	READ_ONCE(sysctl_wmem_default);
 	sk->sk_state		=	TCP_CLOSE;
 	sk_set_socket(sk, sock);
 
@@ -3180,7 +3182,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	sk->sk_napi_id		=	0;
-	sk->sk_ll_usec		=	sysctl_net_busy_read;
+	sk->sk_ll_usec		=	READ_ONCE(sysctl_net_busy_read);
 #endif
 
 	sk->sk_max_pacing_rate = ~0UL;
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 6351b6af7aca..795b3acfb9fd 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -789,13 +789,22 @@ static int sock_map_init_seq_private(void *priv_data,
 {
 	struct sock_map_seq_info *info = priv_data;
 
+	bpf_map_inc_with_uref(aux->map);
 	info->map = aux->map;
 	return 0;
 }
 
+static void sock_map_fini_seq_private(void *priv_data)
+{
+	struct sock_map_seq_info *info = priv_data;
+
+	bpf_map_put_with_uref(info->map);
+}
+
 static const struct bpf_iter_seq_info sock_map_iter_seq_info = {
 	.seq_ops		= &sock_map_seq_ops,
 	.init_seq_private	= sock_map_init_seq_private,
+	.fini_seq_private	= sock_map_fini_seq_private,
 	.seq_priv_size		= sizeof(struct sock_map_seq_info),
 };
 
@@ -1376,18 +1385,27 @@ static const struct seq_operations sock_hash_seq_ops = {
 };
 
 static int sock_hash_init_seq_private(void *priv_data,
-				     struct bpf_iter_aux_info *aux)
+				      struct bpf_iter_aux_info *aux)
 {
 	struct sock_hash_seq_info *info = priv_data;
 
+	bpf_map_inc_with_uref(aux->map);
 	info->map = aux->map;
 	info->htab = container_of(aux->map, struct bpf_shtab, map);
 	return 0;
 }
 
+static void sock_hash_fini_seq_private(void *priv_data)
+{
+	struct sock_hash_seq_info *info = priv_data;
+
+	bpf_map_put_with_uref(info->map);
+}
+
 static const struct bpf_iter_seq_info sock_hash_iter_seq_info = {
 	.seq_ops		= &sock_hash_seq_ops,
 	.init_seq_private	= sock_hash_init_seq_private,
+	.fini_seq_private	= sock_hash_fini_seq_private,
 	.seq_priv_size		= sizeof(struct sock_hash_seq_info),
 };
 
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index 3f00a28fe762..5daa1fa54249 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -387,7 +387,7 @@ void reuseport_stop_listen_sock(struct sock *sk)
 		prog = rcu_dereference_protected(reuse->prog,
 						 lockdep_is_held(&reuseport_lock));
 
-		if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req ||
+		if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_migrate_req) ||
 		    (prog && prog->expected_attach_type == BPF_SK_REUSEPORT_SELECT_OR_MIGRATE)) {
 			/* Migration capable, move sk from the listening section
 			 * to the closed section.
@@ -545,7 +545,7 @@ struct sock *reuseport_migrate_sock(struct sock *sk,
 	hash = migrating_sk->sk_hash;
 	prog = rcu_dereference(reuse->prog);
 	if (!prog || prog->expected_attach_type != BPF_SK_REUSEPORT_SELECT_OR_MIGRATE) {
-		if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req)
+		if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_migrate_req))
 			goto select_by_hash;
 		goto failure;
 	}
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 5f88526ad61c..ed20cbdd1931 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -236,14 +236,17 @@ static int set_default_qdisc(struct ctl_table *table, int write,
 static int proc_do_dev_weight(struct ctl_table *table, int write,
 			   void *buffer, size_t *lenp, loff_t *ppos)
 {
-	int ret;
+	static DEFINE_MUTEX(dev_weight_mutex);
+	int ret, weight;
 
+	mutex_lock(&dev_weight_mutex);
 	ret = proc_dointvec(table, write, buffer, lenp, ppos);
-	if (ret != 0)
-		return ret;
-
-	dev_rx_weight = weight_p * dev_weight_rx_bias;
-	dev_tx_weight = weight_p * dev_weight_tx_bias;
+	if (!ret && write) {
+		weight = READ_ONCE(weight_p);
+		WRITE_ONCE(dev_rx_weight, weight * dev_weight_rx_bias);
+		WRITE_ONCE(dev_tx_weight, weight * dev_weight_tx_bias);
+	}
+	mutex_unlock(&dev_weight_mutex);
 
 	return ret;
 }
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index fc44dadc778b..c4de716f4994 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -747,11 +747,6 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	lock_sock(sk);
 
-	if (dccp_qpolicy_full(sk)) {
-		rc = -EAGAIN;
-		goto out_release;
-	}
-
 	timeo = sock_sndtimeo(sk, noblock);
 
 	/*
@@ -770,6 +765,11 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	if (skb == NULL)
 		goto out_release;
 
+	if (dccp_qpolicy_full(sk)) {
+		rc = -EAGAIN;
+		goto out_discard;
+	}
+
 	if (sk->sk_state == DCCP_CLOSED) {
 		rc = -ENOTCONN;
 		goto out_discard;
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index dc92a67baea3..7d542eb46172 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -480,8 +480,8 @@ static struct sock *dn_alloc_sock(struct net *net, struct socket *sock, gfp_t gf
 	sk->sk_family      = PF_DECnet;
 	sk->sk_protocol    = 0;
 	sk->sk_allocation  = gfp;
-	sk->sk_sndbuf	   = sysctl_decnet_wmem[1];
-	sk->sk_rcvbuf	   = sysctl_decnet_rmem[1];
+	sk->sk_sndbuf	   = READ_ONCE(sysctl_decnet_wmem[1]);
+	sk->sk_rcvbuf	   = READ_ONCE(sysctl_decnet_rmem[1]);
 
 	/* Initialization of DECnet Session Control Port		*/
 	scp = DN_SK(sk);
diff --git a/net/dsa/port.c b/net/dsa/port.c
index 92b401263382..f36ad87b6838 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -111,11 +111,14 @@ int dsa_port_set_state(struct dsa_port *dp, u8 state, bool do_fast_age)
 static void dsa_port_set_state_now(struct dsa_port *dp, u8 state,
 				   bool do_fast_age)
 {
+	struct dsa_switch *ds = dp->ds;
 	int err;
 
 	err = dsa_port_set_state(dp, state, do_fast_age);
-	if (err)
-		pr_err("DSA: failed to set STP state %u (%d)\n", state, err);
+	if (err && err != -EOPNOTSUPP) {
+		dev_err(ds->dev, "port %d failed to set STP state %u: %pe\n",
+			dp->index, state, ERR_PTR(err));
+	}
 }
 
 int dsa_port_enable_rt(struct dsa_port *dp, struct phy_device *phy)
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 353d8fff3166..ae9119a06c74 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -355,7 +355,7 @@ static int dsa_slave_set_mac_address(struct net_device *dev, void *a)
 		dsa_port_standalone_host_fdb_del(dp, dev->dev_addr, 0);
 
 out_change_dev_addr:
-	ether_addr_copy(dev->dev_addr, addr->sa_data);
+	eth_hw_addr_set(dev, addr->sa_data);
 
 	return 0;
 
@@ -2334,7 +2334,7 @@ int dsa_slave_create(struct dsa_port *port)
 	slave_dev->dcbnl_ops = &dsa_slave_dcbnl_ops;
 #endif
 	if (!is_zero_ether_addr(port->mac))
-		ether_addr_copy(slave_dev->dev_addr, port->mac);
+		eth_hw_addr_set(slave_dev, port->mac);
 	else
 		eth_hw_addr_inherit(slave_dev, master);
 	slave_dev->priv_flags |= IFF_NO_QUEUE;
diff --git a/net/dsa/tag_hellcreek.c b/net/dsa/tag_hellcreek.c
index eb204ad36eee..846588c0070a 100644
--- a/net/dsa/tag_hellcreek.c
+++ b/net/dsa/tag_hellcreek.c
@@ -45,7 +45,7 @@ static struct sk_buff *hellcreek_rcv(struct sk_buff *skb,
 
 	skb->dev = dsa_master_find_slave(dev, 0, port);
 	if (!skb->dev) {
-		netdev_warn(dev, "Failed to get source port: %d\n", port);
+		netdev_warn_once(dev, "Failed to get source port: %d\n", port);
 		return NULL;
 	}
 
diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index ea7b96e296ef..a1045c3d71b4 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -493,7 +493,7 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2],
 	INIT_LIST_HEAD(&hsr->self_node_db);
 	spin_lock_init(&hsr->list_lock);
 
-	ether_addr_copy(hsr_dev->dev_addr, slave[0]->dev_addr);
+	eth_hw_addr_set(hsr_dev, slave[0]->dev_addr);
 
 	/* initialize protocol specific functions */
 	if (protocol_version == PRP_V1) {
diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c
index f7e284f23b1f..b099c3150150 100644
--- a/net/hsr/hsr_main.c
+++ b/net/hsr/hsr_main.c
@@ -75,7 +75,7 @@ static int hsr_netdev_notify(struct notifier_block *nb, unsigned long event,
 		master = hsr_port_get_hsr(hsr, HSR_PT_MASTER);
 
 		if (port->type == HSR_PT_SLAVE_A) {
-			ether_addr_copy(master->dev->dev_addr, dev->dev_addr);
+			eth_hw_addr_set(master->dev, dev->dev_addr);
 			call_netdevice_notifiers(NETDEV_CHANGEADDR,
 						 master->dev);
 		}
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 77534b44b8c7..e4b2ced66261 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -220,7 +220,7 @@ int inet_listen(struct socket *sock, int backlog)
 		 * because the socket was in TCP_LISTEN state previously but
 		 * was shutdown() rather than close().
 		 */
-		tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen;
+		tcp_fastopen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen);
 		if ((tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) &&
 		    (tcp_fastopen & TFO_SERVER_ENABLE) &&
 		    !inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) {
@@ -338,7 +338,7 @@ lookup_protocol:
 			inet->hdrincl = 1;
 	}
 
-	if (net->ipv4.sysctl_ip_no_pmtu_disc)
+	if (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc))
 		inet->pmtudisc = IP_PMTUDISC_DONT;
 	else
 		inet->pmtudisc = IP_PMTUDISC_WANT;
@@ -1251,7 +1251,7 @@ static int inet_sk_reselect_saddr(struct sock *sk)
 	if (new_saddr == old_saddr)
 		return 0;
 
-	if (sock_net(sk)->ipv4.sysctl_ip_dynaddr > 1) {
+	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_dynaddr) > 1) {
 		pr_info("%s(): shifting inet->saddr from %pI4 to %pI4\n",
 			__func__, &old_saddr, &new_saddr);
 	}
@@ -1306,7 +1306,7 @@ int inet_sk_rebuild_header(struct sock *sk)
 		 * Other protocols have to map its equivalent state to TCP_SYN_SENT.
 		 * DCCP maps its DCCP_REQUESTING state to TCP_SYN_SENT. -acme
 		 */
-		if (!sock_net(sk)->ipv4.sysctl_ip_dynaddr ||
+		if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_dynaddr) ||
 		    sk->sk_state != TCP_SYN_SENT ||
 		    (sk->sk_userlocks & SOCK_BINDADDR_LOCK) ||
 		    (err = inet_sk_reselect_saddr(sk)) != 0)
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 099259fc826a..75ac14525344 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -239,7 +239,7 @@ static int cipso_v4_cache_check(const unsigned char *key,
 	struct cipso_v4_map_cache_entry *prev_entry = NULL;
 	u32 hash;
 
-	if (!cipso_v4_cache_enabled)
+	if (!READ_ONCE(cipso_v4_cache_enabled))
 		return -ENOENT;
 
 	hash = cipso_v4_map_cache_hash(key, key_len);
@@ -296,13 +296,14 @@ static int cipso_v4_cache_check(const unsigned char *key,
 int cipso_v4_cache_add(const unsigned char *cipso_ptr,
 		       const struct netlbl_lsm_secattr *secattr)
 {
+	int bkt_size = READ_ONCE(cipso_v4_cache_bucketsize);
 	int ret_val = -EPERM;
 	u32 bkt;
 	struct cipso_v4_map_cache_entry *entry = NULL;
 	struct cipso_v4_map_cache_entry *old_entry = NULL;
 	u32 cipso_ptr_len;
 
-	if (!cipso_v4_cache_enabled || cipso_v4_cache_bucketsize <= 0)
+	if (!READ_ONCE(cipso_v4_cache_enabled) || bkt_size <= 0)
 		return 0;
 
 	cipso_ptr_len = cipso_ptr[1];
@@ -322,7 +323,7 @@ int cipso_v4_cache_add(const unsigned char *cipso_ptr,
 
 	bkt = entry->hash & (CIPSO_V4_CACHE_BUCKETS - 1);
 	spin_lock_bh(&cipso_v4_cache[bkt].lock);
-	if (cipso_v4_cache[bkt].size < cipso_v4_cache_bucketsize) {
+	if (cipso_v4_cache[bkt].size < bkt_size) {
 		list_add(&entry->list, &cipso_v4_cache[bkt].list);
 		cipso_v4_cache[bkt].size += 1;
 	} else {
@@ -1199,7 +1200,8 @@ static int cipso_v4_gentag_rbm(const struct cipso_v4_doi *doi_def,
 		/* This will send packets using the "optimized" format when
 		 * possible as specified in  section 3.4.2.6 of the
 		 * CIPSO draft. */
-		if (cipso_v4_rbm_optfmt && ret_val > 0 && ret_val <= 10)
+		if (READ_ONCE(cipso_v4_rbm_optfmt) && ret_val > 0 &&
+		    ret_val <= 10)
 			tag_len = 14;
 		else
 			tag_len = 4 + ret_val;
@@ -1603,7 +1605,7 @@ int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option)
 			 * all the CIPSO validations here but it doesn't
 			 * really specify _exactly_ what we need to validate
 			 * ... so, just make it a sysctl tunable. */
-			if (cipso_v4_rbm_strictvalid) {
+			if (READ_ONCE(cipso_v4_rbm_strictvalid)) {
 				if (cipso_v4_map_lvl_valid(doi_def,
 							   tag[3]) < 0) {
 					err_offset = opt_iter + 3;
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 4744c7839de5..9ac41ffdc634 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -2673,23 +2673,27 @@ static __net_init int devinet_init_net(struct net *net)
 #endif
 
 	if (!net_eq(net, &init_net)) {
-		if (IS_ENABLED(CONFIG_SYSCTL) &&
-		    sysctl_devconf_inherit_init_net == 3) {
+		switch (net_inherit_devconf()) {
+		case 3:
 			/* copy from the current netns */
 			memcpy(all, current->nsproxy->net_ns->ipv4.devconf_all,
 			       sizeof(ipv4_devconf));
 			memcpy(dflt,
 			       current->nsproxy->net_ns->ipv4.devconf_dflt,
 			       sizeof(ipv4_devconf_dflt));
-		} else if (!IS_ENABLED(CONFIG_SYSCTL) ||
-			   sysctl_devconf_inherit_init_net != 2) {
-			/* inherit == 0 or 1: copy from init_net */
+			break;
+		case 0:
+		case 1:
+			/* copy from init_net */
 			memcpy(all, init_net.ipv4.devconf_all,
 			       sizeof(ipv4_devconf));
 			memcpy(dflt, init_net.ipv4.devconf_dflt,
 			       sizeof(ipv4_devconf_dflt));
+			break;
+		case 2:
+			/* use compiled values */
+			break;
 		}
-		/* else inherit == 2: use compiled values */
 	}
 
 #ifdef CONFIG_SYSCTL
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 1eb7795edb9d..1452bb72b7d9 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -389,7 +389,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 	dev_match = dev_match || (res.type == RTN_LOCAL &&
 				  dev == net->loopback_dev);
 	if (dev_match) {
-		ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST;
+		ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_LINK;
 		return ret;
 	}
 	if (no_addr)
@@ -401,7 +401,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 	ret = 0;
 	if (fib_lookup(net, &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE) == 0) {
 		if (res.type == RTN_UNICAST)
-			ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST;
+			ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_LINK;
 	}
 	return ret;
 
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index b5563f5ff176..55de6fa83dea 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1228,7 +1228,7 @@ static int fib_check_nh_nongw(struct net *net, struct fib_nh *nh,
 
 	nh->fib_nh_dev = in_dev->dev;
 	dev_hold(nh->fib_nh_dev);
-	nh->fib_nh_scope = RT_SCOPE_HOST;
+	nh->fib_nh_scope = RT_SCOPE_LINK;
 	if (!netif_carrier_ok(nh->fib_nh_dev))
 		nh->fib_nh_flags |= RTNH_F_LINKDOWN;
 	err = 0;
@@ -1829,7 +1829,7 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 			goto nla_put_failure;
 		if (nexthop_is_blackhole(fi->nh))
 			rtm->rtm_type = RTN_BLACKHOLE;
-		if (!fi->fib_net->ipv4.sysctl_nexthop_compat_mode)
+		if (!READ_ONCE(fi->fib_net->ipv4.sysctl_nexthop_compat_mode))
 			goto offload;
 	}
 
@@ -2233,7 +2233,7 @@ void fib_select_multipath(struct fib_result *res, int hash)
 	}
 
 	change_nexthops(fi) {
-		if (net->ipv4.sysctl_fib_multipath_use_neigh) {
+		if (READ_ONCE(net->ipv4.sysctl_fib_multipath_use_neigh)) {
 			if (!fib_good_nh(nexthop_nh))
 				continue;
 			if (!first) {
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index f7f74d5c14da..19c6e7b93d3d 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -497,7 +497,7 @@ static void tnode_free(struct key_vector *tn)
 		tn = container_of(head, struct tnode, rcu)->kv;
 	}
 
-	if (tnode_free_size >= sysctl_fib_sync_mem) {
+	if (tnode_free_size >= READ_ONCE(sysctl_fib_sync_mem)) {
 		tnode_free_size = 0;
 		synchronize_rcu();
 	}
@@ -1037,6 +1037,7 @@ fib_find_matching_alias(struct net *net, const struct fib_rt_info *fri)
 
 void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri)
 {
+	u8 fib_notify_on_flag_change;
 	struct fib_alias *fa_match;
 	struct sk_buff *skb;
 	int err;
@@ -1058,14 +1059,16 @@ void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri)
 	WRITE_ONCE(fa_match->offload, fri->offload);
 	WRITE_ONCE(fa_match->trap, fri->trap);
 
+	fib_notify_on_flag_change = READ_ONCE(net->ipv4.sysctl_fib_notify_on_flag_change);
+
 	/* 2 means send notifications only if offload_failed was changed. */
-	if (net->ipv4.sysctl_fib_notify_on_flag_change == 2 &&
+	if (fib_notify_on_flag_change == 2 &&
 	    READ_ONCE(fa_match->offload_failed) == fri->offload_failed)
 		goto out;
 
 	WRITE_ONCE(fa_match->offload_failed, fri->offload_failed);
 
-	if (!net->ipv4.sysctl_fib_notify_on_flag_change)
+	if (!fib_notify_on_flag_change)
 		goto out;
 
 	skb = nlmsg_new(fib_nlmsg_size(fa_match->fa_info), GFP_ATOMIC);
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index b7e277d8a84d..609c4ff7edc6 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -261,11 +261,12 @@ bool icmp_global_allow(void)
 	spin_lock(&icmp_global.lock);
 	delta = min_t(u32, now - icmp_global.stamp, HZ);
 	if (delta >= HZ / 50) {
-		incr = sysctl_icmp_msgs_per_sec * delta / HZ ;
+		incr = READ_ONCE(sysctl_icmp_msgs_per_sec) * delta / HZ;
 		if (incr)
 			WRITE_ONCE(icmp_global.stamp, now);
 	}
-	credit = min_t(u32, icmp_global.credit + incr, sysctl_icmp_msgs_burst);
+	credit = min_t(u32, icmp_global.credit + incr,
+		       READ_ONCE(sysctl_icmp_msgs_burst));
 	if (credit) {
 		/* We want to use a credit of one in average, but need to randomize
 		 * it for security reasons.
@@ -289,7 +290,7 @@ static bool icmpv4_mask_allow(struct net *net, int type, int code)
 		return true;
 
 	/* Limit if icmp type is enabled in ratemask. */
-	if (!((1 << type) & net->ipv4.sysctl_icmp_ratemask))
+	if (!((1 << type) & READ_ONCE(net->ipv4.sysctl_icmp_ratemask)))
 		return true;
 
 	return false;
@@ -327,7 +328,8 @@ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt,
 
 	vif = l3mdev_master_ifindex(dst->dev);
 	peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, vif, 1);
-	rc = inet_peer_xrlim_allow(peer, net->ipv4.sysctl_icmp_ratelimit);
+	rc = inet_peer_xrlim_allow(peer,
+				   READ_ONCE(net->ipv4.sysctl_icmp_ratelimit));
 	if (peer)
 		inet_putpeer(peer);
 out:
@@ -701,7 +703,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
 
 		rcu_read_lock();
 		if (rt_is_input_route(rt) &&
-		    net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr)
+		    READ_ONCE(net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr))
 			dev = dev_get_by_index_rcu(net, inet_iif(skb_in));
 
 		if (dev)
@@ -885,7 +887,7 @@ static bool icmp_unreach(struct sk_buff *skb)
 			 * values please see
 			 * Documentation/networking/ip-sysctl.rst
 			 */
-			switch (net->ipv4.sysctl_ip_no_pmtu_disc) {
+			switch (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc)) {
 			default:
 				net_dbg_ratelimited("%pI4: fragmentation needed and DF set\n",
 						    &iph->daddr);
@@ -938,7 +940,7 @@ static bool icmp_unreach(struct sk_buff *skb)
 	 *	get the other vendor to fix their kit.
 	 */
 
-	if (!net->ipv4.sysctl_icmp_ignore_bogus_error_responses &&
+	if (!READ_ONCE(net->ipv4.sysctl_icmp_ignore_bogus_error_responses) &&
 	    inet_addr_type_dev_table(net, skb->dev, iph->daddr) == RTN_BROADCAST) {
 		net_warn_ratelimited("%pI4 sent an invalid ICMP type %u, code %u error to a broadcast: %pI4 on %s\n",
 				     &ip_hdr(skb)->saddr,
@@ -1033,7 +1035,7 @@ bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr)
 	u16 ident_len;
 	u8 status;
 
-	if (!net->ipv4.sysctl_icmp_echo_enable_probe)
+	if (!READ_ONCE(net->ipv4.sysctl_icmp_echo_enable_probe))
 		return false;
 
 	/* We currently only support probing interfaces on the proxy node
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 930f6c41f519..e07d10b2c486 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -467,7 +467,8 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
 
 	if (pmc->multiaddr == IGMP_ALL_HOSTS)
 		return skb;
-	if (ipv4_is_local_multicast(pmc->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports)
+	if (ipv4_is_local_multicast(pmc->multiaddr) &&
+	    !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
 		return skb;
 
 	mtu = READ_ONCE(dev->mtu);
@@ -593,7 +594,7 @@ static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc)
 			if (pmc->multiaddr == IGMP_ALL_HOSTS)
 				continue;
 			if (ipv4_is_local_multicast(pmc->multiaddr) &&
-			     !net->ipv4.sysctl_igmp_llm_reports)
+			    !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
 				continue;
 			spin_lock_bh(&pmc->lock);
 			if (pmc->sfcount[MCAST_EXCLUDE])
@@ -736,7 +737,8 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc,
 	if (type == IGMPV3_HOST_MEMBERSHIP_REPORT)
 		return igmpv3_send_report(in_dev, pmc);
 
-	if (ipv4_is_local_multicast(group) && !net->ipv4.sysctl_igmp_llm_reports)
+	if (ipv4_is_local_multicast(group) &&
+	    !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
 		return 0;
 
 	if (type == IGMP_HOST_LEAVE_MESSAGE)
@@ -825,7 +827,7 @@ static void igmp_ifc_event(struct in_device *in_dev)
 	struct net *net = dev_net(in_dev->dev);
 	if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev))
 		return;
-	WRITE_ONCE(in_dev->mr_ifc_count, in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv);
+	WRITE_ONCE(in_dev->mr_ifc_count, in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv));
 	igmp_ifc_start_timer(in_dev, 1);
 }
 
@@ -920,7 +922,8 @@ static bool igmp_heard_report(struct in_device *in_dev, __be32 group)
 
 	if (group == IGMP_ALL_HOSTS)
 		return false;
-	if (ipv4_is_local_multicast(group) && !net->ipv4.sysctl_igmp_llm_reports)
+	if (ipv4_is_local_multicast(group) &&
+	    !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
 		return false;
 
 	rcu_read_lock();
@@ -1006,7 +1009,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb,
 		 * received value was zero, use the default or statically
 		 * configured value.
 		 */
-		in_dev->mr_qrv = ih3->qrv ?: net->ipv4.sysctl_igmp_qrv;
+		in_dev->mr_qrv = ih3->qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv);
 		in_dev->mr_qi = IGMPV3_QQIC(ih3->qqic)*HZ ?: IGMP_QUERY_INTERVAL;
 
 		/* RFC3376, 8.3. Query Response Interval:
@@ -1045,7 +1048,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb,
 		if (im->multiaddr == IGMP_ALL_HOSTS)
 			continue;
 		if (ipv4_is_local_multicast(im->multiaddr) &&
-		    !net->ipv4.sysctl_igmp_llm_reports)
+		    !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
 			continue;
 		spin_lock_bh(&im->lock);
 		if (im->tm_running)
@@ -1186,7 +1189,7 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im,
 	pmc->interface = im->interface;
 	in_dev_hold(in_dev);
 	pmc->multiaddr = im->multiaddr;
-	pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+	pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv);
 	pmc->sfmode = im->sfmode;
 	if (pmc->sfmode == MCAST_INCLUDE) {
 		struct ip_sf_list *psf;
@@ -1237,9 +1240,11 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im)
 			swap(im->tomb, pmc->tomb);
 			swap(im->sources, pmc->sources);
 			for (psf = im->sources; psf; psf = psf->sf_next)
-				psf->sf_crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+				psf->sf_crcount = in_dev->mr_qrv ?:
+					READ_ONCE(net->ipv4.sysctl_igmp_qrv);
 		} else {
-			im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+			im->crcount = in_dev->mr_qrv ?:
+				READ_ONCE(net->ipv4.sysctl_igmp_qrv);
 		}
 		in_dev_put(pmc->interface);
 		kfree_pmc(pmc);
@@ -1296,7 +1301,8 @@ static void __igmp_group_dropped(struct ip_mc_list *im, gfp_t gfp)
 #ifdef CONFIG_IP_MULTICAST
 	if (im->multiaddr == IGMP_ALL_HOSTS)
 		return;
-	if (ipv4_is_local_multicast(im->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports)
+	if (ipv4_is_local_multicast(im->multiaddr) &&
+	    !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
 		return;
 
 	reporter = im->reporter;
@@ -1338,13 +1344,14 @@ static void igmp_group_added(struct ip_mc_list *im)
 #ifdef CONFIG_IP_MULTICAST
 	if (im->multiaddr == IGMP_ALL_HOSTS)
 		return;
-	if (ipv4_is_local_multicast(im->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports)
+	if (ipv4_is_local_multicast(im->multiaddr) &&
+	    !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
 		return;
 
 	if (in_dev->dead)
 		return;
 
-	im->unsolicit_count = net->ipv4.sysctl_igmp_qrv;
+	im->unsolicit_count = READ_ONCE(net->ipv4.sysctl_igmp_qrv);
 	if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) {
 		spin_lock_bh(&im->lock);
 		igmp_start_timer(im, IGMP_INITIAL_REPORT_DELAY);
@@ -1358,7 +1365,7 @@ static void igmp_group_added(struct ip_mc_list *im)
 	 * IN() to IN(A).
 	 */
 	if (im->sfmode == MCAST_EXCLUDE)
-		im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+		im->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv);
 
 	igmp_ifc_event(in_dev);
 #endif
@@ -1642,7 +1649,7 @@ static void ip_mc_rejoin_groups(struct in_device *in_dev)
 		if (im->multiaddr == IGMP_ALL_HOSTS)
 			continue;
 		if (ipv4_is_local_multicast(im->multiaddr) &&
-		    !net->ipv4.sysctl_igmp_llm_reports)
+		    !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
 			continue;
 
 		/* a failover is happening and switches
@@ -1749,7 +1756,7 @@ static void ip_mc_reset(struct in_device *in_dev)
 
 	in_dev->mr_qi = IGMP_QUERY_INTERVAL;
 	in_dev->mr_qri = IGMP_QUERY_RESPONSE_INTERVAL;
-	in_dev->mr_qrv = net->ipv4.sysctl_igmp_qrv;
+	in_dev->mr_qrv = READ_ONCE(net->ipv4.sysctl_igmp_qrv);
 }
 #else
 static void ip_mc_reset(struct in_device *in_dev)
@@ -1883,7 +1890,7 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode,
 #ifdef CONFIG_IP_MULTICAST
 		if (psf->sf_oldin &&
 		    !IGMP_V1_SEEN(in_dev) && !IGMP_V2_SEEN(in_dev)) {
-			psf->sf_crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+			psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv);
 			psf->sf_next = pmc->tomb;
 			pmc->tomb = psf;
 			rv = 1;
@@ -1947,7 +1954,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
 		/* filter mode change */
 		pmc->sfmode = MCAST_INCLUDE;
 #ifdef CONFIG_IP_MULTICAST
-		pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+		pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv);
 		WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount);
 		for (psf = pmc->sources; psf; psf = psf->sf_next)
 			psf->sf_crcount = 0;
@@ -2126,7 +2133,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
 #ifdef CONFIG_IP_MULTICAST
 		/* else no filters; keep old mode for reports */
 
-		pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+		pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv);
 		WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount);
 		for (psf = pmc->sources; psf; psf = psf->sf_next)
 			psf->sf_crcount = 0;
@@ -2192,7 +2199,7 @@ static int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr,
 		count++;
 	}
 	err = -ENOBUFS;
-	if (count >= net->ipv4.sysctl_igmp_max_memberships)
+	if (count >= READ_ONCE(net->ipv4.sysctl_igmp_max_memberships))
 		goto done;
 	iml = sock_kmalloc(sk, sizeof(*iml), GFP_KERNEL);
 	if (!iml)
@@ -2379,7 +2386,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct
 	}
 	/* else, add a new source to the filter */
 
-	if (psl && psl->sl_count >= net->ipv4.sysctl_igmp_max_msf) {
+	if (psl && psl->sl_count >= READ_ONCE(net->ipv4.sysctl_igmp_max_msf)) {
 		err = -ENOBUFS;
 		goto done;
 	}
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 62a67fdc344c..a53f9bf7886f 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -259,7 +259,7 @@ next_port:
 		goto other_half_scan;
 	}
 
-	if (net->ipv4.sysctl_ip_autobind_reuse && !relax) {
+	if (READ_ONCE(net->ipv4.sysctl_ip_autobind_reuse) && !relax) {
 		/* We still have a chance to connect to different destinations */
 		relax = true;
 		goto ports_exhausted;
@@ -829,7 +829,8 @@ static void reqsk_timer_handler(struct timer_list *t)
 
 	icsk = inet_csk(sk_listener);
 	net = sock_net(sk_listener);
-	max_syn_ack_retries = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_synack_retries;
+	max_syn_ack_retries = icsk->icsk_syn_retries ? :
+		READ_ONCE(net->ipv4.sysctl_tcp_synack_retries);
 	/* Normally all the openreqs are young and become mature
 	 * (i.e. converted to established socket) for first timeout.
 	 * If synack was not acknowledged for 1 second, it means
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 342f3df77835..26c4dd4ec459 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -410,13 +410,11 @@ begin:
 	sk_nulls_for_each_rcu(sk, node, &head->chain) {
 		if (sk->sk_hash != hash)
 			continue;
-		if (likely(INET_MATCH(sk, net, acookie,
-				      saddr, daddr, ports, dif, sdif))) {
+		if (likely(INET_MATCH(net, sk, acookie, ports, dif, sdif))) {
 			if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
 				goto out;
-			if (unlikely(!INET_MATCH(sk, net, acookie,
-						 saddr, daddr, ports,
-						 dif, sdif))) {
+			if (unlikely(!INET_MATCH(net, sk, acookie,
+						 ports, dif, sdif))) {
 				sock_gen_put(sk);
 				goto begin;
 			}
@@ -465,8 +463,7 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row,
 		if (sk2->sk_hash != hash)
 			continue;
 
-		if (likely(INET_MATCH(sk2, net, acookie,
-					 saddr, daddr, ports, dif, sdif))) {
+		if (likely(INET_MATCH(net, sk2, acookie, ports, dif, sdif))) {
 			if (sk2->sk_state == TCP_TIME_WAIT) {
 				tw = inet_twsk(sk2);
 				if (twsk_unique(sk, sk2, twp))
@@ -532,16 +529,14 @@ static bool inet_ehash_lookup_by_sk(struct sock *sk,
 		if (esk->sk_hash != sk->sk_hash)
 			continue;
 		if (sk->sk_family == AF_INET) {
-			if (unlikely(INET_MATCH(esk, net, acookie,
-						sk->sk_daddr,
-						sk->sk_rcv_saddr,
+			if (unlikely(INET_MATCH(net, esk, acookie,
 						ports, dif, sdif))) {
 				return true;
 			}
 		}
 #if IS_ENABLED(CONFIG_IPV6)
 		else if (sk->sk_family == AF_INET6) {
-			if (unlikely(INET6_MATCH(esk, net,
+			if (unlikely(inet6_match(net, esk,
 						 &sk->sk_v6_daddr,
 						 &sk->sk_v6_rcv_saddr,
 						 ports, dif, sdif))) {
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index da21dfce24d7..e9fed83e9b3c 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -141,16 +141,20 @@ static void inet_peer_gc(struct inet_peer_base *base,
 			 struct inet_peer *gc_stack[],
 			 unsigned int gc_cnt)
 {
+	int peer_threshold, peer_maxttl, peer_minttl;
 	struct inet_peer *p;
 	__u32 delta, ttl;
 	int i;
 
-	if (base->total >= inet_peer_threshold)
+	peer_threshold = READ_ONCE(inet_peer_threshold);
+	peer_maxttl = READ_ONCE(inet_peer_maxttl);
+	peer_minttl = READ_ONCE(inet_peer_minttl);
+
+	if (base->total >= peer_threshold)
 		ttl = 0; /* be aggressive */
 	else
-		ttl = inet_peer_maxttl
-				- (inet_peer_maxttl - inet_peer_minttl) / HZ *
-					base->total / inet_peer_threshold * HZ;
+		ttl = peer_maxttl - (peer_maxttl - peer_minttl) / HZ *
+			base->total / peer_threshold * HZ;
 	for (i = 0; i < gc_cnt; i++) {
 		p = gc_stack[i];
 
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 00ec819f949b..29730edda220 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -151,7 +151,7 @@ int ip_forward(struct sk_buff *skb)
 	    !skb_sec_path(skb))
 		ip_rt_send_redirect(skb);
 
-	if (net->ipv4.sysctl_ip_fwd_update_priority)
+	if (READ_ONCE(net->ipv4.sysctl_ip_fwd_update_priority))
 		skb->priority = rt_tos2priority(iph->tos);
 
 	return NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD,
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 3a025c011971..d5222c0fa87c 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -318,8 +318,10 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk,
 {
 	const struct iphdr *iph = ip_hdr(skb);
 	int (*edemux)(struct sk_buff *skb);
+	int err, drop_reason;
 	struct rtable *rt;
-	int err;
+
+	drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
 
 	if (ip_can_use_hint(skb, iph, hint)) {
 		err = ip_route_use_hint(skb, iph->daddr, iph->saddr, iph->tos,
@@ -396,19 +398,23 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk,
 		 * so-called "hole-196" attack) so do it for both.
 		 */
 		if (in_dev &&
-		    IN_DEV_ORCONF(in_dev, DROP_UNICAST_IN_L2_MULTICAST))
+		    IN_DEV_ORCONF(in_dev, DROP_UNICAST_IN_L2_MULTICAST)) {
+			drop_reason = SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST;
 			goto drop;
+		}
 	}
 
 	return NET_RX_SUCCESS;
 
 drop:
-	kfree_skb(skb);
+	kfree_skb_reason(skb, drop_reason);
 	return NET_RX_DROP;
 
 drop_error:
-	if (err == -EXDEV)
+	if (err == -EXDEV) {
+		drop_reason = SKB_DROP_REASON_IP_RPFILTER;
 		__NET_INC_STATS(net, LINUX_MIB_IPRPFILTER);
+	}
 	goto drop;
 }
 
@@ -436,13 +442,16 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net)
 {
 	const struct iphdr *iph;
+	int drop_reason;
 	u32 len;
 
 	/* When the interface is in promisc. mode, drop all the crap
 	 * that it receives, do not try to analyse it.
 	 */
-	if (skb->pkt_type == PACKET_OTHERHOST)
+	if (skb->pkt_type == PACKET_OTHERHOST) {
+		drop_reason = SKB_DROP_REASON_OTHERHOST;
 		goto drop;
+	}
 
 	__IP_UPD_PO_STATS(net, IPSTATS_MIB_IN, skb->len);
 
@@ -452,6 +461,7 @@ static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net)
 		goto out;
 	}
 
+	drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
 	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
 		goto inhdr_error;
 
@@ -488,6 +498,7 @@ static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net)
 
 	len = ntohs(iph->tot_len);
 	if (skb->len < len) {
+		drop_reason = SKB_DROP_REASON_PKT_TOO_SMALL;
 		__IP_INC_STATS(net, IPSTATS_MIB_INTRUNCATEDPKTS);
 		goto drop;
 	} else if (len < (iph->ihl*4))
@@ -516,11 +527,14 @@ static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net)
 	return skb;
 
 csum_error:
+	drop_reason = SKB_DROP_REASON_IP_CSUM;
 	__IP_INC_STATS(net, IPSTATS_MIB_CSUMERRORS);
 inhdr_error:
+	if (drop_reason == SKB_DROP_REASON_NOT_SPECIFIED)
+		drop_reason = SKB_DROP_REASON_IP_INHDR;
 	__IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS);
 drop:
-	kfree_skb(skb);
+	kfree_skb_reason(skb, drop_reason);
 out:
 	return NULL;
 }
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 131066d0319a..ef786c6232df 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1704,7 +1704,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 			   tcp_hdr(skb)->source, tcp_hdr(skb)->dest,
 			   arg->uid);
 	security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4));
-	rt = ip_route_output_key(net, &fl4);
+	rt = ip_route_output_flow(net, &fl4, sk);
 	if (IS_ERR(rt))
 		return;
 
@@ -1712,7 +1712,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 
 	sk->sk_protocol = ip_hdr(skb)->protocol;
 	sk->sk_bound_dev_if = arg->bound_dev_if;
-	sk->sk_sndbuf = sysctl_wmem_default;
+	sk->sk_sndbuf = READ_ONCE(sysctl_wmem_default);
 	ipc.sockc.mark = fl4.flowi4_mark;
 	err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base,
 			     len, 0, &ipc, &rt, MSG_DONTWAIT);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index b297bb28556e..1e2af5f8822d 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -772,7 +772,7 @@ static int ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen)
 
 	if (optlen < GROUP_FILTER_SIZE(0))
 		return -EINVAL;
-	if (optlen > sysctl_optmem_max)
+	if (optlen > READ_ONCE(sysctl_optmem_max))
 		return -ENOBUFS;
 
 	gsf = memdup_sockptr(optval, optlen);
@@ -782,7 +782,7 @@ static int ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen)
 	/* numsrc >= (4G-140)/128 overflow in 32 bits */
 	err = -ENOBUFS;
 	if (gsf->gf_numsrc >= 0x1ffffff ||
-	    gsf->gf_numsrc > sock_net(sk)->ipv4.sysctl_igmp_max_msf)
+	    gsf->gf_numsrc > READ_ONCE(sock_net(sk)->ipv4.sysctl_igmp_max_msf))
 		goto out_free_gsf;
 
 	err = -EINVAL;
@@ -808,7 +808,7 @@ static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval,
 
 	if (optlen < size0)
 		return -EINVAL;
-	if (optlen > sysctl_optmem_max - 4)
+	if (optlen > READ_ONCE(sysctl_optmem_max) - 4)
 		return -ENOBUFS;
 
 	p = kmalloc(optlen + 4, GFP_KERNEL);
@@ -832,7 +832,7 @@ static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval,
 
 	/* numsrc >= (4G-140)/128 overflow in 32 bits */
 	err = -ENOBUFS;
-	if (n > sock_net(sk)->ipv4.sysctl_igmp_max_msf)
+	if (n > READ_ONCE(sock_net(sk)->ipv4.sysctl_igmp_max_msf))
 		goto out_free_gsf;
 	err = set_mcast_msfilter(sk, gf32->gf_interface, n, gf32->gf_fmode,
 				 &gf32->gf_group, gf32->gf_slist_flex);
@@ -1231,7 +1231,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, int optname,
 
 		if (optlen < IP_MSFILTER_SIZE(0))
 			goto e_inval;
-		if (optlen > sysctl_optmem_max) {
+		if (optlen > READ_ONCE(sysctl_optmem_max)) {
 			err = -ENOBUFS;
 			break;
 		}
@@ -1242,7 +1242,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, int optname,
 		}
 		/* numsrc >= (1G-4) overflow in 32 bits */
 		if (msf->imsf_numsrc >= 0x3ffffffcU ||
-		    msf->imsf_numsrc > net->ipv4.sysctl_igmp_max_msf) {
+		    msf->imsf_numsrc > READ_ONCE(net->ipv4.sysctl_igmp_max_msf)) {
 			kfree(msf);
 			err = -ENOBUFS;
 			break;
@@ -1597,7 +1597,7 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
 	{
 		struct net *net = sock_net(sk);
 		val = (inet->uc_ttl == -1 ?
-		       net->ipv4.sysctl_ip_default_ttl :
+		       READ_ONCE(net->ipv4.sysctl_ip_default_ttl) :
 		       inet->uc_ttl);
 		break;
 	}
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 6b2dc7b2b612..cc1caab4a654 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -410,7 +410,7 @@ int skb_tunnel_check_pmtu(struct sk_buff *skb, struct dst_entry *encap_dst,
 	u32 mtu = dst_mtu(encap_dst) - headroom;
 
 	if ((skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) ||
-	    (!skb_is_gso(skb) && (skb->len - skb_mac_header_len(skb)) <= mtu))
+	    (!skb_is_gso(skb) && (skb->len - skb_network_offset(skb)) <= mtu))
 		return 0;
 
 	skb_dst_update_pmtu_no_confirm(skb, mtu);
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
index 4eed5afca392..f2edb40c0db0 100644
--- a/net/ipv4/netfilter/nf_reject_ipv4.c
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -62,7 +62,7 @@ struct sk_buff *nf_reject_skb_v4_tcp_reset(struct net *net,
 
 	skb_reserve(nskb, LL_MAX_HEADER);
 	niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP,
-				   net->ipv4.sysctl_ip_default_ttl);
+				   READ_ONCE(net->ipv4.sysctl_ip_default_ttl));
 	nf_reject_ip_tcphdr_put(nskb, oldskb, oth);
 	niph->tot_len = htons(nskb->len);
 	ip_send_check(niph);
@@ -115,7 +115,7 @@ struct sk_buff *nf_reject_skb_v4_unreach(struct net *net,
 
 	skb_reserve(nskb, LL_MAX_HEADER);
 	niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_ICMP,
-				   net->ipv4.sysctl_ip_default_ttl);
+				   READ_ONCE(net->ipv4.sysctl_ip_default_ttl));
 
 	skb_reset_transport_header(nskb);
 	icmph = skb_put_zero(nskb, sizeof(struct icmphdr));
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 5dbd4b5505eb..cc8f120149f6 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -1857,7 +1857,7 @@ static void __remove_nexthop_fib(struct net *net, struct nexthop *nh)
 		/* __ip6_del_rt does a release, so do a hold here */
 		fib6_info_hold(f6i);
 		ipv6_stub->ip6_del_rt(net, f6i,
-				      !net->ipv4.sysctl_nexthop_compat_mode);
+				      !READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode));
 	}
 }
 
@@ -2362,7 +2362,8 @@ out:
 	if (!rc) {
 		nh_base_seq_inc(net);
 		nexthop_notify(RTM_NEWNEXTHOP, new_nh, &cfg->nlinfo);
-		if (replace_notify && net->ipv4.sysctl_nexthop_compat_mode)
+		if (replace_notify &&
+		    READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode))
 			nexthop_replace_notify(net, new_nh, &cfg->nlinfo);
 	}
 
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index f30273afb539..4b9280a3b673 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -387,7 +387,7 @@ static int snmp_seq_show_ipstats(struct seq_file *seq, void *v)
 
 	seq_printf(seq, "\nIp: %d %d",
 		   IPV4_DEVCONF_ALL(net, FORWARDING) ? 1 : 2,
-		   net->ipv4.sysctl_ip_default_ttl);
+		   READ_ONCE(net->ipv4.sysctl_ip_default_ttl));
 
 	BUILD_BUG_ON(offsetof(struct ipstats_mib, mibs) != 0);
 	snmp_get_cpu_field64_batch(buff64, snmp4_ipstats_list,
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 1db2fda22830..ca59b61fd3a3 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1404,7 +1404,7 @@ u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr)
 	struct fib_info *fi = res->fi;
 	u32 mtu = 0;
 
-	if (dev_net(dev)->ipv4.sysctl_ip_fwd_use_pmtu ||
+	if (READ_ONCE(dev_net(dev)->ipv4.sysctl_ip_fwd_use_pmtu) ||
 	    fi->fib_metrics->metrics[RTAX_LOCK - 1] & (1 << RTAX_MTU))
 		mtu = fi->fib_mtu;
 
@@ -1929,7 +1929,7 @@ static u32 fib_multipath_custom_hash_outer(const struct net *net,
 					   const struct sk_buff *skb,
 					   bool *p_has_inner)
 {
-	u32 hash_fields = net->ipv4.sysctl_fib_multipath_hash_fields;
+	u32 hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields);
 	struct flow_keys keys, hash_keys;
 
 	if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK))
@@ -1958,7 +1958,7 @@ static u32 fib_multipath_custom_hash_inner(const struct net *net,
 					   const struct sk_buff *skb,
 					   bool has_inner)
 {
-	u32 hash_fields = net->ipv4.sysctl_fib_multipath_hash_fields;
+	u32 hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields);
 	struct flow_keys keys, hash_keys;
 
 	/* We assume the packet carries an encapsulation, but if none was
@@ -2018,7 +2018,7 @@ static u32 fib_multipath_custom_hash_skb(const struct net *net,
 static u32 fib_multipath_custom_hash_fl4(const struct net *net,
 					 const struct flowi4 *fl4)
 {
-	u32 hash_fields = net->ipv4.sysctl_fib_multipath_hash_fields;
+	u32 hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields);
 	struct flow_keys hash_keys;
 
 	if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK))
@@ -2048,7 +2048,7 @@ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4,
 	struct flow_keys hash_keys;
 	u32 mhash = 0;
 
-	switch (net->ipv4.sysctl_fib_multipath_hash_policy) {
+	switch (READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_policy)) {
 	case 0:
 		memset(&hash_keys, 0, sizeof(hash_keys));
 		hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 10b469aee492..940839264025 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -249,12 +249,12 @@ bool cookie_timestamp_decode(const struct net *net,
 		return true;
 	}
 
-	if (!net->ipv4.sysctl_tcp_timestamps)
+	if (!READ_ONCE(net->ipv4.sysctl_tcp_timestamps))
 		return false;
 
 	tcp_opt->sack_ok = (options & TS_OPT_SACK) ? TCP_SACK_SEEN : 0;
 
-	if (tcp_opt->sack_ok && !net->ipv4.sysctl_tcp_sack)
+	if (tcp_opt->sack_ok && !READ_ONCE(net->ipv4.sysctl_tcp_sack))
 		return false;
 
 	if ((options & TS_OPT_WSCALE_MASK) == TS_OPT_WSCALE_MASK)
@@ -263,7 +263,7 @@ bool cookie_timestamp_decode(const struct net *net,
 	tcp_opt->wscale_ok = 1;
 	tcp_opt->snd_wscale = options & TS_OPT_WSCALE_MASK;
 
-	return net->ipv4.sysctl_tcp_window_scaling != 0;
+	return READ_ONCE(net->ipv4.sysctl_tcp_window_scaling) != 0;
 }
 EXPORT_SYMBOL(cookie_timestamp_decode);
 
@@ -275,7 +275,7 @@ bool cookie_ecn_ok(const struct tcp_options_received *tcp_opt,
 	if (!ecn_ok)
 		return false;
 
-	if (net->ipv4.sysctl_tcp_ecn)
+	if (READ_ONCE(net->ipv4.sysctl_tcp_ecn))
 		return true;
 
 	return dst_feature(dst, RTAX_FEATURE_ECN);
@@ -342,7 +342,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	struct flowi4 fl4;
 	u32 tsoff = 0;
 
-	if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies || !th->ack || th->rst)
+	if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies) ||
+	    !th->ack || th->rst)
 		goto out;
 
 	if (tcp_synq_no_recent_overflow(sk))
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 6f1e64d49232..a36728277e32 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -97,7 +97,7 @@ static int ipv4_local_port_range(struct ctl_table *table, int write,
 		 * port limit.
 		 */
 		if ((range[1] < range[0]) ||
-		    (range[0] < net->ipv4.sysctl_ip_prot_sock))
+		    (range[0] < READ_ONCE(net->ipv4.sysctl_ip_prot_sock)))
 			ret = -EINVAL;
 		else
 			set_local_port_range(net, range);
@@ -123,7 +123,7 @@ static int ipv4_privileged_ports(struct ctl_table *table, int write,
 		.extra2 = &ip_privileged_port_max,
 	};
 
-	pports = net->ipv4.sysctl_ip_prot_sock;
+	pports = READ_ONCE(net->ipv4.sysctl_ip_prot_sock);
 
 	ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
 
@@ -135,7 +135,7 @@ static int ipv4_privileged_ports(struct ctl_table *table, int write,
 		if (range[0] < pports)
 			ret = -EINVAL;
 		else
-			net->ipv4.sysctl_ip_prot_sock = pports;
+			WRITE_ONCE(net->ipv4.sysctl_ip_prot_sock, pports);
 	}
 
 	return ret;
@@ -639,6 +639,8 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(u8),
 		.mode		= 0644,
 		.proc_handler	= proc_dou8vec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE
 	},
 	{
 		.procname	= "icmp_errors_use_inbound_ifaddr",
@@ -646,6 +648,8 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(u8),
 		.mode		= 0644,
 		.proc_handler	= proc_dou8vec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE
 	},
 	{
 		.procname	= "icmp_ratelimit",
@@ -685,6 +689,8 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(u8),
 		.mode		= 0644,
 		.proc_handler	= proc_dou8vec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_TWO,
 	},
 	{
 		.procname	= "tcp_ecn_fallback",
@@ -692,6 +698,8 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(u8),
 		.mode		= 0644,
 		.proc_handler	= proc_dou8vec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
 	},
 	{
 		.procname	= "ip_dynaddr",
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f79b5a98888c..4f6b897ccf23 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -447,7 +447,7 @@ void tcp_init_sock(struct sock *sk)
 	tp->snd_cwnd_clamp = ~0;
 	tp->mss_cache = TCP_MSS_DEFAULT;
 
-	tp->reordering = sock_net(sk)->ipv4.sysctl_tcp_reordering;
+	tp->reordering = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reordering);
 	tcp_assign_congestion_control(sk);
 
 	tp->tsoffset = 0;
@@ -458,8 +458,8 @@ void tcp_init_sock(struct sock *sk)
 
 	icsk->icsk_sync_mss = tcp_sync_mss;
 
-	WRITE_ONCE(sk->sk_sndbuf, sock_net(sk)->ipv4.sysctl_tcp_wmem[1]);
-	WRITE_ONCE(sk->sk_rcvbuf, sock_net(sk)->ipv4.sysctl_tcp_rmem[1]);
+	WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1]));
+	WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1]));
 
 	sk_sockets_allocated_inc(sk);
 	sk->sk_route_forced_caps = NETIF_F_GSO;
@@ -644,7 +644,7 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 }
 EXPORT_SYMBOL(tcp_ioctl);
 
-static inline void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb)
+void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb)
 {
 	TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH;
 	tp->pushed_seq = tp->write_seq;
@@ -655,7 +655,7 @@ static inline bool forced_push(const struct tcp_sock *tp)
 	return after(tp->write_seq, tp->pushed_seq + (tp->max_window >> 1));
 }
 
-static void skb_entail(struct sock *sk, struct sk_buff *skb)
+void tcp_skb_entail(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
@@ -694,7 +694,7 @@ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb,
 				int size_goal)
 {
 	return skb->len < size_goal &&
-	       sock_net(sk)->ipv4.sysctl_tcp_autocorking &&
+	       READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_autocorking) &&
 	       !tcp_rtx_queue_empty(sk) &&
 	       refcount_read(&sk->sk_wmem_alloc) > skb->truesize;
 }
@@ -982,7 +982,7 @@ new_segment:
 #ifdef CONFIG_TLS_DEVICE
 		skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED);
 #endif
-		skb_entail(sk, skb);
+		tcp_skb_entail(sk, skb);
 		copy = size_goal;
 	}
 
@@ -991,7 +991,7 @@ new_segment:
 
 	i = skb_shinfo(skb)->nr_frags;
 	can_coalesce = skb_can_coalesce(skb, i, page, offset);
-	if (!can_coalesce && i >= sysctl_max_skb_frags) {
+	if (!can_coalesce && i >= READ_ONCE(sysctl_max_skb_frags)) {
 		tcp_mark_push(tp, skb);
 		goto new_segment;
 	}
@@ -1002,7 +1002,7 @@ new_segment:
 		skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
 	} else {
 		get_page(page);
-		skb_fill_page_desc(skb, i, page, offset, copy);
+		skb_fill_page_desc_noacc(skb, i, page, offset, copy);
 	}
 
 	if (!(flags & MSG_NO_SHARED_FRAGS))
@@ -1159,7 +1159,8 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 	struct sockaddr *uaddr = msg->msg_name;
 	int err, flags;
 
-	if (!(sock_net(sk)->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) ||
+	if (!(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen) &
+	      TFO_CLIENT_ENABLE) ||
 	    (uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) &&
 	     uaddr->sa_family == AF_UNSPEC))
 		return -EOPNOTSUPP;
@@ -1311,7 +1312,7 @@ new_segment:
 			process_backlog++;
 			skb->ip_summed = CHECKSUM_PARTIAL;
 
-			skb_entail(sk, skb);
+			tcp_skb_entail(sk, skb);
 			copy = size_goal;
 
 			/* All packets are restored as if they have
@@ -1343,7 +1344,7 @@ new_segment:
 
 			if (!skb_can_coalesce(skb, i, pfrag->page,
 					      pfrag->offset)) {
-				if (i >= sysctl_max_skb_frags) {
+				if (i >= READ_ONCE(sysctl_max_skb_frags)) {
 					tcp_mark_push(tp, skb);
 					goto new_segment;
 				}
@@ -1721,7 +1722,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val)
 	if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
 		cap = sk->sk_rcvbuf >> 1;
 	else
-		cap = sock_net(sk)->ipv4.sysctl_tcp_rmem[2] >> 1;
+		cap = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1;
 	val = min(val, cap);
 	WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
 
@@ -2714,7 +2715,8 @@ static void tcp_orphan_update(struct timer_list *unused)
 
 static bool tcp_too_many_orphans(int shift)
 {
-	return READ_ONCE(tcp_orphan_cache) << shift > sysctl_tcp_max_orphans;
+	return READ_ONCE(tcp_orphan_cache) << shift >
+		READ_ONCE(sysctl_tcp_max_orphans);
 }
 
 bool tcp_check_oom(struct sock *sk, int shift)
@@ -3625,7 +3627,8 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 	case TCP_FASTOPEN_CONNECT:
 		if (val > 1 || val < 0) {
 			err = -EINVAL;
-		} else if (net->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) {
+		} else if (READ_ONCE(net->ipv4.sysctl_tcp_fastopen) &
+			   TFO_CLIENT_ENABLE) {
 			if (sk->sk_state == TCP_CLOSE)
 				tp->fastopen_connect = val;
 			else
@@ -3973,12 +3976,13 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 		val = keepalive_probes(tp);
 		break;
 	case TCP_SYNCNT:
-		val = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries;
+		val = icsk->icsk_syn_retries ? :
+			READ_ONCE(net->ipv4.sysctl_tcp_syn_retries);
 		break;
 	case TCP_LINGER2:
 		val = tp->linger2;
 		if (val >= 0)
-			val = (val ? : net->ipv4.sysctl_tcp_fin_timeout) / HZ;
+			val = (val ? : READ_ONCE(net->ipv4.sysctl_tcp_fin_timeout)) / HZ;
 		break;
 	case TCP_DEFER_ACCEPT:
 		val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept,
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 59412d6354a0..6e0a8ef5e816 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -338,7 +338,7 @@ static bool tcp_fastopen_no_cookie(const struct sock *sk,
 				   const struct dst_entry *dst,
 				   int flag)
 {
-	return (sock_net(sk)->ipv4.sysctl_tcp_fastopen & flag) ||
+	return (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen) & flag) ||
 	       tcp_sk(sk)->fastopen_no_cookie ||
 	       (dst && dst_metric(dst, RTAX_FASTOPEN_NO_COOKIE));
 }
@@ -353,7 +353,7 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
 			      const struct dst_entry *dst)
 {
 	bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1;
-	int tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen;
+	int tcp_fastopen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen);
 	struct tcp_fastopen_cookie valid_foc = { .len = -1 };
 	struct sock *child;
 	int ret = 0;
@@ -495,7 +495,7 @@ void tcp_fastopen_active_disable(struct sock *sk)
 {
 	struct net *net = sock_net(sk);
 
-	if (!sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout)
+	if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout))
 		return;
 
 	/* Paired with READ_ONCE() in tcp_fastopen_active_should_disable() */
@@ -516,7 +516,8 @@ void tcp_fastopen_active_disable(struct sock *sk)
  */
 bool tcp_fastopen_active_should_disable(struct sock *sk)
 {
-	unsigned int tfo_bh_timeout = sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout;
+	unsigned int tfo_bh_timeout =
+		READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout);
 	unsigned long timeout;
 	int tfo_da_times;
 	int multiplier;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 0ff2f620f8e4..686e210d89c2 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -426,7 +426,7 @@ static void tcp_sndbuf_expand(struct sock *sk)
 
 	if (sk->sk_sndbuf < sndmem)
 		WRITE_ONCE(sk->sk_sndbuf,
-			   min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2]));
+			   min(sndmem, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[2])));
 }
 
 /* 2. Tuning advertised window (window_clamp, rcv_ssthresh)
@@ -461,7 +461,7 @@ static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb,
 	struct tcp_sock *tp = tcp_sk(sk);
 	/* Optimize this! */
 	int truesize = tcp_win_from_space(sk, skbtruesize) >> 1;
-	int window = tcp_win_from_space(sk, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1;
+	int window = tcp_win_from_space(sk, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])) >> 1;
 
 	while (tp->rcv_ssthresh <= window) {
 		if (truesize <= skb->len)
@@ -526,7 +526,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb,
  */
 static void tcp_init_buffer_space(struct sock *sk)
 {
-	int tcp_app_win = sock_net(sk)->ipv4.sysctl_tcp_app_win;
+	int tcp_app_win = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_app_win);
 	struct tcp_sock *tp = tcp_sk(sk);
 	int maxwin;
 
@@ -566,16 +566,17 @@ static void tcp_clamp_window(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct net *net = sock_net(sk);
+	int rmem2;
 
 	icsk->icsk_ack.quick = 0;
+	rmem2 = READ_ONCE(net->ipv4.sysctl_tcp_rmem[2]);
 
-	if (sk->sk_rcvbuf < net->ipv4.sysctl_tcp_rmem[2] &&
+	if (sk->sk_rcvbuf < rmem2 &&
 	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) &&
 	    !tcp_under_memory_pressure(sk) &&
 	    sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) {
 		WRITE_ONCE(sk->sk_rcvbuf,
-			   min(atomic_read(&sk->sk_rmem_alloc),
-			       net->ipv4.sysctl_tcp_rmem[2]));
+			   min(atomic_read(&sk->sk_rmem_alloc), rmem2));
 	}
 	if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
 		tp->rcv_ssthresh = min(tp->window_clamp, 2U * tp->advmss);
@@ -716,7 +717,7 @@ void tcp_rcv_space_adjust(struct sock *sk)
 	 * <prev RTT . ><current RTT .. ><next RTT .... >
 	 */
 
-	if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf &&
+	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) &&
 	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
 		int rcvmem, rcvbuf;
 		u64 rcvwin, grow;
@@ -737,7 +738,7 @@ void tcp_rcv_space_adjust(struct sock *sk)
 
 		do_div(rcvwin, tp->advmss);
 		rcvbuf = min_t(u64, rcvwin * rcvmem,
-			       sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
+			       READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
 		if (rcvbuf > sk->sk_rcvbuf) {
 			WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
 
@@ -902,9 +903,9 @@ static void tcp_update_pacing_rate(struct sock *sk)
 	 *	 end of slow start and should slow down.
 	 */
 	if (tcp_snd_cwnd(tp) < tp->snd_ssthresh / 2)
-		rate *= sock_net(sk)->ipv4.sysctl_tcp_pacing_ss_ratio;
+		rate *= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_pacing_ss_ratio);
 	else
-		rate *= sock_net(sk)->ipv4.sysctl_tcp_pacing_ca_ratio;
+		rate *= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_pacing_ca_ratio);
 
 	rate *= max(tcp_snd_cwnd(tp), tp->packets_out);
 
@@ -1043,7 +1044,7 @@ static void tcp_check_sack_reordering(struct sock *sk, const u32 low_seq,
 			 tp->undo_marker ? tp->undo_retrans : 0);
 #endif
 		tp->reordering = min_t(u32, (metric + mss - 1) / mss,
-				       sock_net(sk)->ipv4.sysctl_tcp_max_reordering);
+				       READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_max_reordering));
 	}
 
 	/* This exciting event is worth to be remembered. 8) */
@@ -2022,7 +2023,7 @@ static void tcp_check_reno_reordering(struct sock *sk, const int addend)
 		return;
 
 	tp->reordering = min_t(u32, tp->packets_out + addend,
-			       sock_net(sk)->ipv4.sysctl_tcp_max_reordering);
+			       READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_max_reordering));
 	tp->reord_seen++;
 	NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRENOREORDER);
 }
@@ -2087,7 +2088,8 @@ static inline void tcp_init_undo(struct tcp_sock *tp)
 
 static bool tcp_is_rack(const struct sock *sk)
 {
-	return sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_LOSS_DETECTION;
+	return READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) &
+		TCP_RACK_LOSS_DETECTION;
 }
 
 /* If we detect SACK reneging, forget all SACK information
@@ -2131,6 +2133,7 @@ void tcp_enter_loss(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct net *net = sock_net(sk);
 	bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery;
+	u8 reordering;
 
 	tcp_timeout_mark_lost(sk);
 
@@ -2151,10 +2154,12 @@ void tcp_enter_loss(struct sock *sk)
 	/* Timeout in disordered state after receiving substantial DUPACKs
 	 * suggests that the degree of reordering is over-estimated.
 	 */
+	reordering = READ_ONCE(net->ipv4.sysctl_tcp_reordering);
 	if (icsk->icsk_ca_state <= TCP_CA_Disorder &&
-	    tp->sacked_out >= net->ipv4.sysctl_tcp_reordering)
+	    tp->sacked_out >= reordering)
 		tp->reordering = min_t(unsigned int, tp->reordering,
-				       net->ipv4.sysctl_tcp_reordering);
+				       reordering);
+
 	tcp_set_ca_state(sk, TCP_CA_Loss);
 	tp->high_seq = tp->snd_nxt;
 	tcp_ecn_queue_cwr(tp);
@@ -2163,7 +2168,7 @@ void tcp_enter_loss(struct sock *sk)
 	 * loss recovery is underway except recurring timeout(s) on
 	 * the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing
 	 */
-	tp->frto = net->ipv4.sysctl_tcp_frto &&
+	tp->frto = READ_ONCE(net->ipv4.sysctl_tcp_frto) &&
 		   (new_recovery || icsk->icsk_retransmits) &&
 		   !inet_csk(sk)->icsk_mtup.probe_size;
 }
@@ -2501,6 +2506,21 @@ static inline bool tcp_may_undo(const struct tcp_sock *tp)
 	return tp->undo_marker && (!tp->undo_retrans || tcp_packet_delayed(tp));
 }
 
+static bool tcp_is_non_sack_preventing_reopen(struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) {
+		/* Hold old state until something *above* high_seq
+		 * is ACKed. For Reno it is MUST to prevent false
+		 * fast retransmits (RFC2582). SACK TCP is safe. */
+		if (!tcp_any_retrans_done(sk))
+			tp->retrans_stamp = 0;
+		return true;
+	}
+	return false;
+}
+
 /* People celebrate: "We love our President!" */
 static bool tcp_try_undo_recovery(struct sock *sk)
 {
@@ -2523,14 +2543,8 @@ static bool tcp_try_undo_recovery(struct sock *sk)
 	} else if (tp->rack.reo_wnd_persist) {
 		tp->rack.reo_wnd_persist--;
 	}
-	if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) {
-		/* Hold old state until something *above* high_seq
-		 * is ACKed. For Reno it is MUST to prevent false
-		 * fast retransmits (RFC2582). SACK TCP is safe. */
-		if (!tcp_any_retrans_done(sk))
-			tp->retrans_stamp = 0;
+	if (tcp_is_non_sack_preventing_reopen(sk))
 		return true;
-	}
 	tcp_set_ca_state(sk, TCP_CA_Open);
 	tp->is_sack_reneg = 0;
 	return false;
@@ -2566,6 +2580,8 @@ static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo)
 			NET_INC_STATS(sock_net(sk),
 					LINUX_MIB_TCPSPURIOUSRTOS);
 		inet_csk(sk)->icsk_retransmits = 0;
+		if (tcp_is_non_sack_preventing_reopen(sk))
+			return true;
 		if (frto_undo || tcp_is_sack(tp)) {
 			tcp_set_ca_state(sk, TCP_CA_Open);
 			tp->is_sack_reneg = 0;
@@ -3046,7 +3062,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
 
 static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us, const int flag)
 {
-	u32 wlen = sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen * HZ;
+	u32 wlen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen) * HZ;
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	if ((flag & FLAG_ACK_MAYBE_DELAYED) && rtt_us > tcp_min_rtt(tp)) {
@@ -3457,7 +3473,8 @@ static inline bool tcp_may_raise_cwnd(const struct sock *sk, const int flag)
 	 * new SACK or ECE mark may first advance cwnd here and later reduce
 	 * cwnd in tcp_fastretrans_alert() based on more states.
 	 */
-	if (tcp_sk(sk)->reordering > sock_net(sk)->ipv4.sysctl_tcp_reordering)
+	if (tcp_sk(sk)->reordering >
+	    READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reordering))
 		return flag & FLAG_FORWARD_PROGRESS;
 
 	return flag & FLAG_DATA_ACKED;
@@ -3569,7 +3586,8 @@ static bool __tcp_oow_rate_limited(struct net *net, int mib_idx,
 	if (*last_oow_ack_time) {
 		s32 elapsed = (s32)(tcp_jiffies32 - *last_oow_ack_time);
 
-		if (0 <= elapsed && elapsed < net->ipv4.sysctl_tcp_invalid_ratelimit) {
+		if (0 <= elapsed &&
+		    elapsed < READ_ONCE(net->ipv4.sysctl_tcp_invalid_ratelimit)) {
 			NET_INC_STATS(net, mib_idx);
 			return true;	/* rate-limited: don't send yet! */
 		}
@@ -3616,11 +3634,11 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb)
 
 	/* Then check host-wide RFC 5961 rate limit. */
 	now = jiffies / HZ;
-	if (now != challenge_timestamp) {
-		u32 ack_limit = net->ipv4.sysctl_tcp_challenge_ack_limit;
+	if (now != READ_ONCE(challenge_timestamp)) {
+		u32 ack_limit = READ_ONCE(net->ipv4.sysctl_tcp_challenge_ack_limit);
 		u32 half = (ack_limit + 1) >> 1;
 
-		challenge_timestamp = now;
+		WRITE_ONCE(challenge_timestamp, now);
 		WRITE_ONCE(challenge_count, half + prandom_u32_max(ack_limit));
 	}
 	count = READ_ONCE(challenge_count);
@@ -4049,7 +4067,7 @@ void tcp_parse_options(const struct net *net,
 				break;
 			case TCPOPT_WINDOW:
 				if (opsize == TCPOLEN_WINDOW && th->syn &&
-				    !estab && net->ipv4.sysctl_tcp_window_scaling) {
+				    !estab && READ_ONCE(net->ipv4.sysctl_tcp_window_scaling)) {
 					__u8 snd_wscale = *(__u8 *)ptr;
 					opt_rx->wscale_ok = 1;
 					if (snd_wscale > TCP_MAX_WSCALE) {
@@ -4065,7 +4083,7 @@ void tcp_parse_options(const struct net *net,
 			case TCPOPT_TIMESTAMP:
 				if ((opsize == TCPOLEN_TIMESTAMP) &&
 				    ((estab && opt_rx->tstamp_ok) ||
-				     (!estab && net->ipv4.sysctl_tcp_timestamps))) {
+				     (!estab && READ_ONCE(net->ipv4.sysctl_tcp_timestamps)))) {
 					opt_rx->saw_tstamp = 1;
 					opt_rx->rcv_tsval = get_unaligned_be32(ptr);
 					opt_rx->rcv_tsecr = get_unaligned_be32(ptr + 4);
@@ -4073,7 +4091,7 @@ void tcp_parse_options(const struct net *net,
 				break;
 			case TCPOPT_SACK_PERM:
 				if (opsize == TCPOLEN_SACK_PERM && th->syn &&
-				    !estab && net->ipv4.sysctl_tcp_sack) {
+				    !estab && READ_ONCE(net->ipv4.sysctl_tcp_sack)) {
 					opt_rx->sack_ok = TCP_SACK_SEEN;
 					tcp_sack_reset(opt_rx);
 				}
@@ -4414,7 +4432,7 @@ static void tcp_dsack_set(struct sock *sk, u32 seq, u32 end_seq)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) {
+	if (tcp_is_sack(tp) && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_dsack)) {
 		int mib_idx;
 
 		if (before(seq, tp->rcv_nxt))
@@ -4461,7 +4479,7 @@ static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb)
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST);
 		tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS);
 
-		if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) {
+		if (tcp_is_sack(tp) && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_dsack)) {
 			u32 end_seq = TCP_SKB_CB(skb)->end_seq;
 
 			tcp_rcv_spurious_retrans(sk, skb);
@@ -5484,7 +5502,7 @@ send_now:
 	}
 
 	if (!tcp_is_sack(tp) ||
-	    tp->compressed_ack >= sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr)
+	    tp->compressed_ack >= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr))
 		goto send_now;
 
 	if (tp->compressed_ack_rcv_nxt != tp->rcv_nxt) {
@@ -5505,11 +5523,12 @@ send_now:
 	if (tp->srtt_us && tp->srtt_us < rtt)
 		rtt = tp->srtt_us;
 
-	delay = min_t(unsigned long, sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns,
+	delay = min_t(unsigned long,
+		      READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns),
 		      rtt * (NSEC_PER_USEC >> 3)/20);
 	sock_hold(sk);
 	hrtimer_start_range_ns(&tp->compressed_ack_timer, ns_to_ktime(delay),
-			       sock_net(sk)->ipv4.sysctl_tcp_comp_sack_slack_ns,
+			       READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_slack_ns),
 			       HRTIMER_MODE_REL_PINNED_SOFT);
 }
 
@@ -5537,7 +5556,7 @@ static void tcp_check_urg(struct sock *sk, const struct tcphdr *th)
 	struct tcp_sock *tp = tcp_sk(sk);
 	u32 ptr = ntohs(th->urg_ptr);
 
-	if (ptr && !sock_net(sk)->ipv4.sysctl_tcp_stdurg)
+	if (ptr && !READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_stdurg))
 		ptr--;
 	ptr += ntohl(th->seq);
 
@@ -6669,7 +6688,7 @@ static void tcp_ecn_create_request(struct request_sock *req,
 
 	ect = !INET_ECN_is_not_ect(TCP_SKB_CB(skb)->ip_dsfield);
 	ecn_ok_dst = dst_feature(dst, DST_FEATURE_ECN_MASK);
-	ecn_ok = net->ipv4.sysctl_tcp_ecn || ecn_ok_dst;
+	ecn_ok = READ_ONCE(net->ipv4.sysctl_tcp_ecn) || ecn_ok_dst;
 
 	if (((!ect || th->res1) && ecn_ok) || tcp_ca_needs_ecn(listen_sk) ||
 	    (ecn_ok_dst & DST_FEATURE_ECN_CA) ||
@@ -6735,11 +6754,14 @@ static bool tcp_syn_flood_action(const struct sock *sk, const char *proto)
 {
 	struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
 	const char *msg = "Dropping request";
-	bool want_cookie = false;
 	struct net *net = sock_net(sk);
+	bool want_cookie = false;
+	u8 syncookies;
+
+	syncookies = READ_ONCE(net->ipv4.sysctl_tcp_syncookies);
 
 #ifdef CONFIG_SYN_COOKIES
-	if (net->ipv4.sysctl_tcp_syncookies) {
+	if (syncookies) {
 		msg = "Sending cookies";
 		want_cookie = true;
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPREQQFULLDOCOOKIES);
@@ -6747,8 +6769,7 @@ static bool tcp_syn_flood_action(const struct sock *sk, const char *proto)
 #endif
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP);
 
-	if (!queue->synflood_warned &&
-	    net->ipv4.sysctl_tcp_syncookies != 2 &&
+	if (!queue->synflood_warned && syncookies != 2 &&
 	    xchg(&queue->synflood_warned, 1) == 0)
 		net_info_ratelimited("%s: Possible SYN flooding on port %d. %s.  Check SNMP counters.\n",
 				     proto, sk->sk_num, msg);
@@ -6797,7 +6818,7 @@ u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops,
 	struct tcp_sock *tp = tcp_sk(sk);
 	u16 mss;
 
-	if (sock_net(sk)->ipv4.sysctl_tcp_syncookies != 2 &&
+	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies) != 2 &&
 	    !inet_csk_reqsk_queue_is_full(sk))
 		return 0;
 
@@ -6831,13 +6852,15 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	bool want_cookie = false;
 	struct dst_entry *dst;
 	struct flowi fl;
+	u8 syncookies;
+
+	syncookies = READ_ONCE(net->ipv4.sysctl_tcp_syncookies);
 
 	/* TW buckets are converted to open requests without
 	 * limitations, they conserve resources and peer is
 	 * evidently real one.
 	 */
-	if ((net->ipv4.sysctl_tcp_syncookies == 2 ||
-	     inet_csk_reqsk_queue_is_full(sk)) && !isn) {
+	if ((syncookies == 2 || inet_csk_reqsk_queue_is_full(sk)) && !isn) {
 		want_cookie = tcp_syn_flood_action(sk, rsk_ops->slab_name);
 		if (!want_cookie)
 			goto drop;
@@ -6886,10 +6909,12 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 		tcp_rsk(req)->ts_off = af_ops->init_ts_off(net, skb);
 
 	if (!want_cookie && !isn) {
+		int max_syn_backlog = READ_ONCE(net->ipv4.sysctl_max_syn_backlog);
+
 		/* Kill the following clause, if you dislike this way. */
-		if (!net->ipv4.sysctl_tcp_syncookies &&
-		    (net->ipv4.sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
-		     (net->ipv4.sysctl_max_syn_backlog >> 2)) &&
+		if (!syncookies &&
+		    (max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
+		     (max_syn_backlog >> 2)) &&
 		    !tcp_peer_is_proven(req, dst)) {
 			/* Without syncookies last quarter of
 			 * backlog is filled with destinations,
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a189625098ba..88a45d5650da 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -91,6 +91,8 @@ static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
 struct inet_hashinfo tcp_hashinfo;
 EXPORT_SYMBOL(tcp_hashinfo);
 
+static DEFINE_PER_CPU(struct sock *, ipv4_tcp_sk);
+
 static u32 tcp_v4_init_seq(const struct sk_buff *skb)
 {
 	return secure_tcp_seq(ip_hdr(skb)->daddr,
@@ -106,10 +108,10 @@ static u32 tcp_v4_init_ts_off(const struct net *net, const struct sk_buff *skb)
 
 int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 {
+	int reuse = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tw_reuse);
 	const struct inet_timewait_sock *tw = inet_twsk(sktw);
 	const struct tcp_timewait_sock *tcptw = tcp_twsk(sktw);
 	struct tcp_sock *tp = tcp_sk(sk);
-	int reuse = sock_net(sk)->ipv4.sysctl_tcp_tw_reuse;
 
 	if (reuse == 2) {
 		/* Still does not detect *everything* that goes through
@@ -807,13 +809,15 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 	arg.tos = ip_hdr(skb)->tos;
 	arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL);
 	local_bh_disable();
-	ctl_sk = this_cpu_read(*net->ipv4.tcp_sk);
+	ctl_sk = this_cpu_read(ipv4_tcp_sk);
+	sock_net_set(ctl_sk, net);
 	if (sk) {
 		ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
 				   inet_twsk(sk)->tw_mark : sk->sk_mark;
 		ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ?
 				   inet_twsk(sk)->tw_priority : sk->sk_priority;
 		transmit_time = tcp_transmit_time(sk);
+		xfrm_sk_clone_policy(ctl_sk, sk);
 	}
 	ip_send_unicast_reply(ctl_sk,
 			      skb, &TCP_SKB_CB(skb)->header.h4.opt,
@@ -822,6 +826,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 			      transmit_time);
 
 	ctl_sk->sk_mark = 0;
+	xfrm_sk_free_policy(ctl_sk);
+	sock_net_set(ctl_sk, &init_net);
 	__TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
 	__TCP_INC_STATS(net, TCP_MIB_OUTRSTS);
 	local_bh_enable();
@@ -905,7 +911,8 @@ static void tcp_v4_send_ack(const struct sock *sk,
 	arg.tos = tos;
 	arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL);
 	local_bh_disable();
-	ctl_sk = this_cpu_read(*net->ipv4.tcp_sk);
+	ctl_sk = this_cpu_read(ipv4_tcp_sk);
+	sock_net_set(ctl_sk, net);
 	ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
 			   inet_twsk(sk)->tw_mark : sk->sk_mark;
 	ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ?
@@ -918,6 +925,7 @@ static void tcp_v4_send_ack(const struct sock *sk,
 			      transmit_time);
 
 	ctl_sk->sk_mark = 0;
+	sock_net_set(ctl_sk, &init_net);
 	__TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
 	local_bh_enable();
 }
@@ -998,7 +1006,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
 	if (skb) {
 		__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);
 
-		tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
+		tos = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) ?
 				(tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |
 				(inet_sk(sk)->tos & INET_ECN_MASK) :
 				inet_sk(sk)->tos;
@@ -1584,7 +1592,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	/* Set ToS of the new socket based upon the value of incoming SYN.
 	 * ECT bits are set later in tcp_init_transfer().
 	 */
-	if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)
+	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos))
 		newinet->tos = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK;
 
 	if (!dst) {
@@ -1970,8 +1978,10 @@ int tcp_v4_rcv(struct sk_buff *skb)
 	const struct tcphdr *th;
 	bool refcounted;
 	struct sock *sk;
+	int drop_reason;
 	int ret;
 
+	drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
 	if (skb->pkt_type != PACKET_HOST)
 		goto discard_it;
 
@@ -1983,8 +1993,10 @@ int tcp_v4_rcv(struct sk_buff *skb)
 
 	th = (const struct tcphdr *)skb->data;
 
-	if (unlikely(th->doff < sizeof(struct tcphdr) / 4))
+	if (unlikely(th->doff < sizeof(struct tcphdr) / 4)) {
+		drop_reason = SKB_DROP_REASON_PKT_TOO_SMALL;
 		goto bad_packet;
+	}
 	if (!pskb_may_pull(skb, th->doff * 4))
 		goto discard_it;
 
@@ -2014,7 +2026,8 @@ process:
 		struct sock *nsk;
 
 		sk = req->rsk_listener;
-		if (unlikely(tcp_v4_inbound_md5_hash(sk, skb, dif, sdif))) {
+		if (unlikely(!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb) ||
+			     tcp_v4_inbound_md5_hash(sk, skb, dif, sdif))) {
 			sk_drops_add(sk, skb);
 			reqsk_put(req);
 			goto discard_it;
@@ -2061,6 +2074,7 @@ process:
 			}
 			goto discard_and_relse;
 		}
+		nf_reset_ct(skb);
 		if (nsk == sk) {
 			reqsk_put(req);
 			tcp_v4_restore_cb(skb);
@@ -2085,8 +2099,10 @@ process:
 
 	nf_reset_ct(skb);
 
-	if (tcp_filter(sk, skb))
+	if (tcp_filter(sk, skb)) {
+		drop_reason = SKB_DROP_REASON_SOCKET_FILTER;
 		goto discard_and_relse;
+	}
 	th = (const struct tcphdr *)skb->data;
 	iph = ip_hdr(skb);
 	tcp_v4_fill_cb(skb, iph, th);
@@ -2123,6 +2139,7 @@ put_and_return:
 	return ret;
 
 no_tcp_socket:
+	drop_reason = SKB_DROP_REASON_NO_SOCKET;
 	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
 		goto discard_it;
 
@@ -2130,6 +2147,7 @@ no_tcp_socket:
 
 	if (tcp_checksum_complete(skb)) {
 csum_error:
+		drop_reason = SKB_DROP_REASON_TCP_CSUM;
 		trace_tcp_bad_csum(skb);
 		__TCP_INC_STATS(net, TCP_MIB_CSUMERRORS);
 bad_packet:
@@ -2140,7 +2158,7 @@ bad_packet:
 
 discard_it:
 	/* Discard frame. */
-	kfree_skb(skb);
+	kfree_skb_reason(skb, drop_reason);
 	return 0;
 
 discard_and_relse:
@@ -3101,41 +3119,14 @@ EXPORT_SYMBOL(tcp_prot);
 
 static void __net_exit tcp_sk_exit(struct net *net)
 {
-	int cpu;
-
 	if (net->ipv4.tcp_congestion_control)
 		bpf_module_put(net->ipv4.tcp_congestion_control,
 			       net->ipv4.tcp_congestion_control->owner);
-
-	for_each_possible_cpu(cpu)
-		inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu));
-	free_percpu(net->ipv4.tcp_sk);
 }
 
 static int __net_init tcp_sk_init(struct net *net)
 {
-	int res, cpu, cnt;
-
-	net->ipv4.tcp_sk = alloc_percpu(struct sock *);
-	if (!net->ipv4.tcp_sk)
-		return -ENOMEM;
-
-	for_each_possible_cpu(cpu) {
-		struct sock *sk;
-
-		res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW,
-					   IPPROTO_TCP, net);
-		if (res)
-			goto fail;
-		sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);
-
-		/* Please enforce IP_DF and IPID==0 for RST and
-		 * ACK sent in SYN-RECV and TIME-WAIT state.
-		 */
-		inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO;
-
-		*per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk;
-	}
+	int cnt;
 
 	net->ipv4.sysctl_tcp_ecn = 2;
 	net->ipv4.sysctl_tcp_ecn_fallback = 1;
@@ -3219,10 +3210,6 @@ static int __net_init tcp_sk_init(struct net *net)
 		net->ipv4.tcp_congestion_control = &tcp_reno;
 
 	return 0;
-fail:
-	tcp_sk_exit(net);
-
-	return res;
 }
 
 static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
@@ -3316,6 +3303,24 @@ static void __init bpf_iter_register(void)
 
 void __init tcp_v4_init(void)
 {
+	int cpu, res;
+
+	for_each_possible_cpu(cpu) {
+		struct sock *sk;
+
+		res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW,
+					   IPPROTO_TCP, &init_net);
+		if (res)
+			panic("Failed to create the TCP control socket.\n");
+		sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);
+
+		/* Please enforce IP_DF and IPID==0 for RST and
+		 * ACK sent in SYN-RECV and TIME-WAIT state.
+		 */
+		inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO;
+
+		per_cpu(ipv4_tcp_sk, cpu) = sk;
+	}
 	if (register_pernet_subsys(&tcp_sk_ops))
 		panic("Failed to create the TCP control socket.\n");
 
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 7029b0e98edb..d58e672be31c 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -329,7 +329,7 @@ void tcp_update_metrics(struct sock *sk)
 	int m;
 
 	sk_dst_confirm(sk);
-	if (net->ipv4.sysctl_tcp_nometrics_save || !dst)
+	if (READ_ONCE(net->ipv4.sysctl_tcp_nometrics_save) || !dst)
 		return;
 
 	rcu_read_lock();
@@ -385,7 +385,7 @@ void tcp_update_metrics(struct sock *sk)
 
 	if (tcp_in_initial_slowstart(tp)) {
 		/* Slow start still did not finish. */
-		if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save &&
+		if (!READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) &&
 		    !tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) {
 			val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH);
 			if (val && (tcp_snd_cwnd(tp) >> 1) > val)
@@ -401,7 +401,7 @@ void tcp_update_metrics(struct sock *sk)
 	} else if (!tcp_in_slow_start(tp) &&
 		   icsk->icsk_ca_state == TCP_CA_Open) {
 		/* Cong. avoidance phase, cwnd is reliable. */
-		if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save &&
+		if (!READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) &&
 		    !tcp_metric_locked(tm, TCP_METRIC_SSTHRESH))
 			tcp_metric_set(tm, TCP_METRIC_SSTHRESH,
 				       max(tcp_snd_cwnd(tp) >> 1, tp->snd_ssthresh));
@@ -418,7 +418,7 @@ void tcp_update_metrics(struct sock *sk)
 			tcp_metric_set(tm, TCP_METRIC_CWND,
 				       (val + tp->snd_ssthresh) >> 1);
 		}
-		if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save &&
+		if (!READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) &&
 		    !tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) {
 			val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH);
 			if (val && tp->snd_ssthresh > val)
@@ -428,7 +428,8 @@ void tcp_update_metrics(struct sock *sk)
 		if (!tcp_metric_locked(tm, TCP_METRIC_REORDERING)) {
 			val = tcp_metric_get(tm, TCP_METRIC_REORDERING);
 			if (val < tp->reordering &&
-			    tp->reordering != net->ipv4.sysctl_tcp_reordering)
+			    tp->reordering !=
+			    READ_ONCE(net->ipv4.sysctl_tcp_reordering))
 				tcp_metric_set(tm, TCP_METRIC_REORDERING,
 					       tp->reordering);
 		}
@@ -462,7 +463,7 @@ void tcp_init_metrics(struct sock *sk)
 	if (tcp_metric_locked(tm, TCP_METRIC_CWND))
 		tp->snd_cwnd_clamp = tcp_metric_get(tm, TCP_METRIC_CWND);
 
-	val = net->ipv4.sysctl_tcp_no_ssthresh_metrics_save ?
+	val = READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) ?
 	      0 : tcp_metric_get(tm, TCP_METRIC_SSTHRESH);
 	if (val) {
 		tp->snd_ssthresh = val;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 13783fc58e03..41368e77fbb8 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -180,7 +180,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 			 * Oh well... nobody has a sufficient solution to this
 			 * protocol bug yet.
 			 */
-			if (twsk_net(tw)->ipv4.sysctl_tcp_rfc1337 == 0) {
+			if (!READ_ONCE(twsk_net(tw)->ipv4.sysctl_tcp_rfc1337)) {
 kill:
 				inet_twsk_deschedule_put(tw);
 				return TCP_TW_SUCCESS;
@@ -789,7 +789,7 @@ listen_overflow:
 	if (sk != req->rsk_listener)
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQFAILURE);
 
-	if (!sock_net(sk)->ipv4.sysctl_tcp_abort_on_overflow) {
+	if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_abort_on_overflow)) {
 		inet_rsk(req)->acked = 1;
 		return NULL;
 	}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index dc3b4668fcde..ed2e1836c0c0 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -167,16 +167,13 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
 	if (tcp_packets_in_flight(tp) == 0)
 		tcp_ca_event(sk, CA_EVENT_TX_START);
 
-	/* If this is the first data packet sent in response to the
-	 * previous received data,
-	 * and it is a reply for ato after last received packet,
-	 * increase pingpong count.
-	 */
-	if (before(tp->lsndtime, icsk->icsk_ack.lrcvtime) &&
-	    (u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato)
-		inet_csk_inc_pingpong_cnt(sk);
-
 	tp->lsndtime = now;
+
+	/* If it is a reply for ato after last received
+	 * packet, enter pingpong mode.
+	 */
+	if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato)
+		inet_csk_enter_pingpong_mode(sk);
 }
 
 /* Account for an ACK we sent. */
@@ -241,8 +238,8 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
 	*rcv_wscale = 0;
 	if (wscale_ok) {
 		/* Set window scaling on max possible window */
-		space = max_t(u32, space, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
-		space = max_t(u32, space, sysctl_rmem_max);
+		space = max_t(u32, space, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
+		space = max_t(u32, space, READ_ONCE(sysctl_rmem_max));
 		space = min_t(u32, space, *window_clamp);
 		*rcv_wscale = clamp_t(int, ilog2(space) - 15,
 				      0, TCP_MAX_WSCALE);
@@ -324,7 +321,7 @@ static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	bool bpf_needs_ecn = tcp_bpf_ca_needs_ecn(sk);
-	bool use_ecn = sock_net(sk)->ipv4.sysctl_tcp_ecn == 1 ||
+	bool use_ecn = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn) == 1 ||
 		tcp_ca_needs_ecn(sk) || bpf_needs_ecn;
 
 	if (!use_ecn) {
@@ -346,7 +343,7 @@ static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb)
 
 static void tcp_ecn_clear_syn(struct sock *sk, struct sk_buff *skb)
 {
-	if (sock_net(sk)->ipv4.sysctl_tcp_ecn_fallback)
+	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn_fallback))
 		/* tp->ecn_flags are cleared at a later point in time when
 		 * SYN ACK is ultimatively being received.
 		 */
@@ -790,18 +787,18 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 	opts->mss = tcp_advertise_mss(sk);
 	remaining -= TCPOLEN_MSS_ALIGNED;
 
-	if (likely(sock_net(sk)->ipv4.sysctl_tcp_timestamps && !*md5)) {
+	if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps) && !*md5)) {
 		opts->options |= OPTION_TS;
 		opts->tsval = tcp_skb_timestamp(skb) + tp->tsoffset;
 		opts->tsecr = tp->rx_opt.ts_recent;
 		remaining -= TCPOLEN_TSTAMP_ALIGNED;
 	}
-	if (likely(sock_net(sk)->ipv4.sysctl_tcp_window_scaling)) {
+	if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_window_scaling))) {
 		opts->ws = tp->rx_opt.rcv_wscale;
 		opts->options |= OPTION_WSCALE;
 		remaining -= TCPOLEN_WSCALE_ALIGNED;
 	}
-	if (likely(sock_net(sk)->ipv4.sysctl_tcp_sack)) {
+	if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_sack))) {
 		opts->options |= OPTION_SACK_ADVERTISE;
 		if (unlikely(!(OPTION_TS & opts->options)))
 			remaining -= TCPOLEN_SACKPERM_ALIGNED;
@@ -1722,7 +1719,8 @@ static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu)
 	mss_now -= icsk->icsk_ext_hdr_len;
 
 	/* Then reserve room for full set of TCP options and 8 bytes of data */
-	mss_now = max(mss_now, sock_net(sk)->ipv4.sysctl_tcp_min_snd_mss);
+	mss_now = max(mss_now,
+		      READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_snd_mss));
 	return mss_now;
 }
 
@@ -1765,10 +1763,10 @@ void tcp_mtup_init(struct sock *sk)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct net *net = sock_net(sk);
 
-	icsk->icsk_mtup.enabled = net->ipv4.sysctl_tcp_mtu_probing > 1;
+	icsk->icsk_mtup.enabled = READ_ONCE(net->ipv4.sysctl_tcp_mtu_probing) > 1;
 	icsk->icsk_mtup.search_high = tp->rx_opt.mss_clamp + sizeof(struct tcphdr) +
 			       icsk->icsk_af_ops->net_header_len;
-	icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, net->ipv4.sysctl_tcp_base_mss);
+	icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, READ_ONCE(net->ipv4.sysctl_tcp_base_mss));
 	icsk->icsk_mtup.probe_size = 0;
 	if (icsk->icsk_mtup.enabled)
 		icsk->icsk_mtup.probe_timestamp = tcp_jiffies32;
@@ -1900,7 +1898,7 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited)
 		if (tp->packets_out > tp->snd_cwnd_used)
 			tp->snd_cwnd_used = tp->packets_out;
 
-		if (sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle &&
+		if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle) &&
 		    (s32)(tcp_jiffies32 - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto &&
 		    !ca_ops->cong_control)
 			tcp_cwnd_application_limited(sk);
@@ -1988,7 +1986,7 @@ static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now)
 
 	min_tso = ca_ops->min_tso_segs ?
 			ca_ops->min_tso_segs(sk) :
-			sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs;
+			READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs);
 
 	tso_segs = tcp_tso_autosize(sk, mss_now, min_tso);
 	return min_t(u32, tso_segs, sk->sk_gso_max_segs);
@@ -2280,7 +2278,7 @@ static inline void tcp_mtu_check_reprobe(struct sock *sk)
 	u32 interval;
 	s32 delta;
 
-	interval = net->ipv4.sysctl_tcp_probe_interval;
+	interval = READ_ONCE(net->ipv4.sysctl_tcp_probe_interval);
 	delta = tcp_jiffies32 - icsk->icsk_mtup.probe_timestamp;
 	if (unlikely(delta >= interval * HZ)) {
 		int mss = tcp_current_mss(sk);
@@ -2362,7 +2360,7 @@ static int tcp_mtu_probe(struct sock *sk)
 	 * probing process by not resetting search range to its orignal.
 	 */
 	if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high) ||
-		interval < net->ipv4.sysctl_tcp_probe_threshold) {
+	    interval < READ_ONCE(net->ipv4.sysctl_tcp_probe_threshold)) {
 		/* Check whether enough time has elaplased for
 		 * another round of probing.
 		 */
@@ -2505,7 +2503,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
 		      sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift));
 	if (sk->sk_pacing_status == SK_PACING_NONE)
 		limit = min_t(unsigned long, limit,
-			      sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes);
+			      READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes));
 	limit <<= factor;
 
 	if (static_branch_unlikely(&tcp_tx_delay_enabled) &&
@@ -2738,7 +2736,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto)
 	if (rcu_access_pointer(tp->fastopen_rsk))
 		return false;
 
-	early_retrans = sock_net(sk)->ipv4.sysctl_tcp_early_retrans;
+	early_retrans = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_early_retrans);
 	/* Schedule a loss probe in 2*RTT for SACK capable connections
 	 * not in loss recovery, that are either limited by cwnd or application.
 	 */
@@ -3107,7 +3105,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to,
 	struct sk_buff *skb = to, *tmp;
 	bool first = true;
 
-	if (!sock_net(sk)->ipv4.sysctl_tcp_retrans_collapse)
+	if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retrans_collapse))
 		return;
 	if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
 		return;
@@ -3147,7 +3145,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 	struct tcp_sock *tp = tcp_sk(sk);
 	unsigned int cur_mss;
 	int diff, len, err;
-
+	int avail_wnd;
 
 	/* Inconclusive MTU probe */
 	if (icsk->icsk_mtup.probe_size)
@@ -3169,17 +3167,25 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 		return -EHOSTUNREACH; /* Routing failure or similar. */
 
 	cur_mss = tcp_current_mss(sk);
+	avail_wnd = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq;
 
 	/* If receiver has shrunk his window, and skb is out of
 	 * new window, do not retransmit it. The exception is the
 	 * case, when window is shrunk to zero. In this case
-	 * our retransmit serves as a zero window probe.
+	 * our retransmit of one segment serves as a zero window probe.
 	 */
-	if (!before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp)) &&
-	    TCP_SKB_CB(skb)->seq != tp->snd_una)
-		return -EAGAIN;
+	if (avail_wnd <= 0) {
+		if (TCP_SKB_CB(skb)->seq != tp->snd_una)
+			return -EAGAIN;
+		avail_wnd = cur_mss;
+	}
 
 	len = cur_mss * segs;
+	if (len > avail_wnd) {
+		len = rounddown(avail_wnd, cur_mss);
+		if (!len)
+			len = avail_wnd;
+	}
 	if (skb->len > len) {
 		if (tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, len,
 				 cur_mss, GFP_ATOMIC))
@@ -3193,8 +3199,9 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 		diff -= tcp_skb_pcount(skb);
 		if (diff)
 			tcp_adjust_pcount(sk, skb, diff);
-		if (skb->len < cur_mss)
-			tcp_retrans_try_collapse(sk, skb, cur_mss);
+		avail_wnd = min_t(int, avail_wnd, cur_mss);
+		if (skb->len < avail_wnd)
+			tcp_retrans_try_collapse(sk, skb, avail_wnd);
 	}
 
 	/* RFC3168, section 6.1.1.1. ECN fallback */
@@ -3365,11 +3372,12 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
  */
 void sk_forced_mem_schedule(struct sock *sk, int size)
 {
-	int amt;
+	int delta, amt;
 
-	if (size <= sk->sk_forward_alloc)
+	delta = size - sk->sk_forward_alloc;
+	if (delta <= 0)
 		return;
-	amt = sk_mem_pages(size);
+	amt = sk_mem_pages(delta);
 	sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
 	sk_memory_allocated_add(sk, amt);
 
@@ -3648,7 +3656,7 @@ static void tcp_connect_init(struct sock *sk)
 	 * See tcp_input.c:tcp_rcv_state_process case TCP_SYN_SENT.
 	 */
 	tp->tcp_header_len = sizeof(struct tcphdr);
-	if (sock_net(sk)->ipv4.sysctl_tcp_timestamps)
+	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps))
 		tp->tcp_header_len += TCPOLEN_TSTAMP_ALIGNED;
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -3684,7 +3692,7 @@ static void tcp_connect_init(struct sock *sk)
 				  tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0),
 				  &tp->rcv_wnd,
 				  &tp->window_clamp,
-				  sock_net(sk)->ipv4.sysctl_tcp_window_scaling,
+				  READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_window_scaling),
 				  &rcv_wscale,
 				  rcv_wnd);
 
@@ -4092,7 +4100,7 @@ void tcp_send_probe0(struct sock *sk)
 
 	icsk->icsk_probes_out++;
 	if (err <= 0) {
-		if (icsk->icsk_backoff < net->ipv4.sysctl_tcp_retries2)
+		if (icsk->icsk_backoff < READ_ONCE(net->ipv4.sysctl_tcp_retries2))
 			icsk->icsk_backoff++;
 		timeout = tcp_probe0_when(sk, TCP_RTO_MAX);
 	} else {
diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
index fd113f6226ef..ac14216f6204 100644
--- a/net/ipv4/tcp_recovery.c
+++ b/net/ipv4/tcp_recovery.c
@@ -19,7 +19,8 @@ static u32 tcp_rack_reo_wnd(const struct sock *sk)
 			return 0;
 
 		if (tp->sacked_out >= tp->reordering &&
-		    !(sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_NO_DUPTHRESH))
+		    !(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) &
+		      TCP_RACK_NO_DUPTHRESH))
 			return 0;
 	}
 
@@ -192,7 +193,8 @@ void tcp_rack_update_reo_wnd(struct sock *sk, struct rate_sample *rs)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_STATIC_REO_WND ||
+	if ((READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) &
+	     TCP_RACK_STATIC_REO_WND) ||
 	    !rs->prior_delivered)
 		return;
 
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 20cf4a98c69d..50bba370486e 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -143,7 +143,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset)
  */
 static int tcp_orphan_retries(struct sock *sk, bool alive)
 {
-	int retries = sock_net(sk)->ipv4.sysctl_tcp_orphan_retries; /* May be zero. */
+	int retries = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_orphan_retries); /* May be zero. */
 
 	/* We know from an ICMP that something is wrong. */
 	if (sk->sk_err_soft && !alive)
@@ -163,7 +163,7 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk)
 	int mss;
 
 	/* Black hole detection */
-	if (!net->ipv4.sysctl_tcp_mtu_probing)
+	if (!READ_ONCE(net->ipv4.sysctl_tcp_mtu_probing))
 		return;
 
 	if (!icsk->icsk_mtup.enabled) {
@@ -171,9 +171,9 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk)
 		icsk->icsk_mtup.probe_timestamp = tcp_jiffies32;
 	} else {
 		mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1;
-		mss = min(net->ipv4.sysctl_tcp_base_mss, mss);
-		mss = max(mss, net->ipv4.sysctl_tcp_mtu_probe_floor);
-		mss = max(mss, net->ipv4.sysctl_tcp_min_snd_mss);
+		mss = min(READ_ONCE(net->ipv4.sysctl_tcp_base_mss), mss);
+		mss = max(mss, READ_ONCE(net->ipv4.sysctl_tcp_mtu_probe_floor));
+		mss = max(mss, READ_ONCE(net->ipv4.sysctl_tcp_min_snd_mss));
 		icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss);
 	}
 	tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
@@ -239,17 +239,18 @@ static int tcp_write_timeout(struct sock *sk)
 	if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
 		if (icsk->icsk_retransmits)
 			__dst_negative_advice(sk);
-		retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries;
+		retry_until = icsk->icsk_syn_retries ? :
+			READ_ONCE(net->ipv4.sysctl_tcp_syn_retries);
 		expired = icsk->icsk_retransmits >= retry_until;
 	} else {
-		if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1, 0)) {
+		if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1), 0)) {
 			/* Black hole detection */
 			tcp_mtu_probing(icsk, sk);
 
 			__dst_negative_advice(sk);
 		}
 
-		retry_until = net->ipv4.sysctl_tcp_retries2;
+		retry_until = READ_ONCE(net->ipv4.sysctl_tcp_retries2);
 		if (sock_flag(sk, SOCK_DEAD)) {
 			const bool alive = icsk->icsk_rto < TCP_RTO_MAX;
 
@@ -380,7 +381,7 @@ static void tcp_probe_timer(struct sock *sk)
 		 msecs_to_jiffies(icsk->icsk_user_timeout))
 		goto abort;
 
-	max_probes = sock_net(sk)->ipv4.sysctl_tcp_retries2;
+	max_probes = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retries2);
 	if (sock_flag(sk, SOCK_DEAD)) {
 		const bool alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX;
 
@@ -406,12 +407,15 @@ abort:		tcp_write_err(sk);
 static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
-	int max_retries = icsk->icsk_syn_retries ? :
-	    sock_net(sk)->ipv4.sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */
 	struct tcp_sock *tp = tcp_sk(sk);
+	int max_retries;
 
 	req->rsk_ops->syn_ack_timeout(req);
 
+	/* add one more retry for fastopen */
+	max_retries = icsk->icsk_syn_retries ? :
+		READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_synack_retries) + 1;
+
 	if (req->num_timeout >= max_retries) {
 		tcp_write_err(sk);
 		return;
@@ -574,7 +578,7 @@ out_reset_timer:
 	 * linear-timeout retransmissions into a black hole
 	 */
 	if (sk->sk_state == TCP_ESTABLISHED &&
-	    (tp->thin_lto || net->ipv4.sysctl_tcp_thin_linear_timeouts) &&
+	    (tp->thin_lto || READ_ONCE(net->ipv4.sysctl_tcp_thin_linear_timeouts)) &&
 	    tcp_stream_is_thin(tp) &&
 	    icsk->icsk_retransmits <= TCP_THIN_LINEAR_RETRIES) {
 		icsk->icsk_backoff = 0;
@@ -585,7 +589,7 @@ out_reset_timer:
 	}
 	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
 				  tcp_clamp_rto_to_user_timeout(sk), TCP_RTO_MAX);
-	if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1 + 1, 0))
+	if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1) + 1, 0))
 		__sk_dst_reset(sk);
 
 out:;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 835b9d6e4e68..75d1977ecc07 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -781,6 +781,8 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
 	 */
 	if (tunnel) {
 		/* ...not for tunnels though: we don't have a sending socket */
+		if (udp_sk(sk)->encap_err_rcv)
+			udp_sk(sk)->encap_err_rcv(sk, skb, iph->ihl << 2);
 		goto out;
 	}
 	if (!inet->recverr) {
@@ -2411,6 +2413,9 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	__be32 saddr, daddr;
 	struct net *net = dev_net(skb->dev);
 	bool refcounted;
+	int drop_reason;
+
+	drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
 
 	/*
 	 *  Validate the packet.
@@ -2466,6 +2471,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	if (udp_lib_checksum_complete(skb))
 		goto csum_error;
 
+	drop_reason = SKB_DROP_REASON_NO_SOCKET;
 	__UDP_INC_STATS(net, UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE);
 	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
 
@@ -2473,10 +2479,11 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	 * Hmm.  We got an UDP packet to a port to which we
 	 * don't wanna listen.  Ignore it.
 	 */
-	kfree_skb(skb);
+	kfree_skb_reason(skb, drop_reason);
 	return 0;
 
 short_packet:
+	drop_reason = SKB_DROP_REASON_PKT_TOO_SMALL;
 	net_dbg_ratelimited("UDP%s: short packet: From %pI4:%u %d/%d to %pI4:%u\n",
 			    proto == IPPROTO_UDPLITE ? "Lite" : "",
 			    &saddr, ntohs(uh->source),
@@ -2489,6 +2496,7 @@ csum_error:
 	 * RFC1122: OK.  Discards the bad packet silently (as far as
 	 * the network is concerned, anyway) as per 4.1.3.4 (MUST).
 	 */
+	drop_reason = SKB_DROP_REASON_UDP_CSUM;
 	net_dbg_ratelimited("UDP%s: bad checksum. From %pI4:%u to %pI4:%u ulen %d\n",
 			    proto == IPPROTO_UDPLITE ? "Lite" : "",
 			    &saddr, ntohs(uh->source), &daddr, ntohs(uh->dest),
@@ -2496,7 +2504,7 @@ csum_error:
 	__UDP_INC_STATS(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE);
 drop:
 	__UDP_INC_STATS(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE);
-	kfree_skb(skb);
+	kfree_skb_reason(skb, drop_reason);
 	return 0;
 }
 
@@ -2548,8 +2556,7 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net,
 	struct sock *sk;
 
 	udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
-		if (INET_MATCH(sk, net, acookie, rmt_addr,
-			       loc_addr, ports, dif, sdif))
+		if (INET_MATCH(net, sk, acookie, ports, dif, sdif))
 			return sk;
 		/* Only check first socket in chain */
 		break;
diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c
index b97e3635acf5..46101fd67a47 100644
--- a/net/ipv4/udp_tunnel_core.c
+++ b/net/ipv4/udp_tunnel_core.c
@@ -75,6 +75,7 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
 
 	udp_sk(sk)->encap_type = cfg->encap_type;
 	udp_sk(sk)->encap_rcv = cfg->encap_rcv;
+	udp_sk(sk)->encap_err_rcv = cfg->encap_err_rcv;
 	udp_sk(sk)->encap_err_lookup = cfg->encap_err_lookup;
 	udp_sk(sk)->encap_destroy = cfg->encap_destroy;
 	udp_sk(sk)->gro_receive = cfg->gro_receive;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 07b868c002a3..8800987fdb40 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1111,10 +1111,6 @@ ipv6_add_addr(struct inet6_dev *idev, struct ifa6_config *cfg,
 		goto out;
 	}
 
-	if (net->ipv6.devconf_all->disable_policy ||
-	    idev->cnf.disable_policy)
-		f6i->dst_nopolicy = true;
-
 	neigh_parms_data_state_setall(idev->nd_parms);
 
 	ifa->addr = *cfg->pfx;
@@ -5170,9 +5166,9 @@ next:
 		fillargs->event = RTM_GETMULTICAST;
 
 		/* multicast address */
-		for (ifmca = rcu_dereference(idev->mc_list);
+		for (ifmca = rtnl_dereference(idev->mc_list);
 		     ifmca;
-		     ifmca = rcu_dereference(ifmca->next), ip_idx++) {
+		     ifmca = rtnl_dereference(ifmca->next), ip_idx++) {
 			if (ip_idx < s_ip_idx)
 				continue;
 			err = inet6_fill_ifmcaddr(skb, ifmca, fillargs);
@@ -7132,9 +7128,8 @@ static int __net_init addrconf_init_net(struct net *net)
 	if (!dflt)
 		goto err_alloc_dflt;
 
-	if (IS_ENABLED(CONFIG_SYSCTL) &&
-	    !net_eq(net, &init_net)) {
-		switch (sysctl_devconf_inherit_init_net) {
+	if (!net_eq(net, &init_net)) {
+		switch (net_inherit_devconf()) {
 		case 1:  /* copy from init_net */
 			memcpy(all, init_net.ipv6.devconf_all,
 			       sizeof(ipv6_devconf));
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index dab4a047590b..3a91d0d40aec 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -226,7 +226,7 @@ lookup_protocol:
 	RCU_INIT_POINTER(inet->mc_list, NULL);
 	inet->rcv_tos	= 0;
 
-	if (net->ipv4.sysctl_ip_no_pmtu_disc)
+	if (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc))
 		inet->pmtudisc = IP_PMTUDISC_DONT;
 	else
 		inet->pmtudisc = IP_PMTUDISC_WANT;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 96c5cc0f30ce..716e7717fe8f 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -927,7 +927,7 @@ static int icmpv6_rcv(struct sk_buff *skb)
 		break;
 	case ICMPV6_EXT_ECHO_REQUEST:
 		if (!net->ipv6.sysctl.icmpv6_echo_ignore_all &&
-		    net->ipv4.sysctl_icmp_echo_enable_probe)
+		    READ_ONCE(net->ipv4.sysctl_icmp_echo_enable_probe))
 			icmpv6_echo_reply(skb);
 		break;
 
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 40203255ed88..b4a5e01e1201 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -71,12 +71,12 @@ begin:
 	sk_nulls_for_each_rcu(sk, node, &head->chain) {
 		if (sk->sk_hash != hash)
 			continue;
-		if (!INET6_MATCH(sk, net, saddr, daddr, ports, dif, sdif))
+		if (!inet6_match(net, sk, saddr, daddr, ports, dif, sdif))
 			continue;
 		if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
 			goto out;
 
-		if (unlikely(!INET6_MATCH(sk, net, saddr, daddr, ports, dif, sdif))) {
+		if (unlikely(!inet6_match(net, sk, saddr, daddr, ports, dif, sdif))) {
 			sock_gen_put(sk);
 			goto begin;
 		}
@@ -269,7 +269,7 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row,
 		if (sk2->sk_hash != hash)
 			continue;
 
-		if (likely(INET6_MATCH(sk2, net, saddr, daddr, ports,
+		if (likely(inet6_match(net, sk2, saddr, daddr, ports,
 				       dif, sdif))) {
 			if (sk2->sk_state == TCP_TIME_WAIT) {
 				tw = inet_twsk(sk2);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 04c3cb4c5fec..7951ade74d14 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1289,8 +1289,7 @@ struct dst_entry *ip6_dst_lookup_tunnel(struct sk_buff *skb,
 	fl6.daddr = info->key.u.ipv6.dst;
 	fl6.saddr = info->key.u.ipv6.src;
 	prio = info->key.tos;
-	fl6.flowlabel = ip6_make_flowinfo(RT_TOS(prio),
-					  info->key.label);
+	fl6.flowlabel = ip6_make_flowinfo(prio, info->key.label);
 
 	dst = ipv6_stub->ipv6_dst_lookup_flow(net, sock->sk, &fl6,
 					      NULL);
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index e4bdb09c5586..8a1c78f38508 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -208,7 +208,7 @@ static int ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval,
 
 	if (optlen < GROUP_FILTER_SIZE(0))
 		return -EINVAL;
-	if (optlen > sysctl_optmem_max)
+	if (optlen > READ_ONCE(sysctl_optmem_max))
 		return -ENOBUFS;
 
 	gsf = memdup_sockptr(optval, optlen);
@@ -242,7 +242,7 @@ static int compat_ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval,
 
 	if (optlen < size0)
 		return -EINVAL;
-	if (optlen > sysctl_optmem_max - 4)
+	if (optlen > READ_ONCE(sysctl_optmem_max) - 4)
 		return -ENOBUFS;
 
 	p = kmalloc(optlen + 4, GFP_KERNEL);
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 7f695c39d9a8..87c699d57b36 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1522,7 +1522,6 @@ static void mld_query_work(struct work_struct *work)
 
 		if (++cnt >= MLD_MAX_QUEUE) {
 			rework = true;
-			schedule_delayed_work(&idev->mc_query_work, 0);
 			break;
 		}
 	}
@@ -1533,8 +1532,10 @@ static void mld_query_work(struct work_struct *work)
 		__mld_query_work(skb);
 	mutex_unlock(&idev->mc_lock);
 
-	if (!rework)
-		in6_dev_put(idev);
+	if (rework && queue_delayed_work(mld_wq, &idev->mc_query_work, 0))
+		return;
+
+	in6_dev_put(idev);
 }
 
 /* called with rcu_read_lock() */
@@ -1624,7 +1625,6 @@ static void mld_report_work(struct work_struct *work)
 
 		if (++cnt >= MLD_MAX_QUEUE) {
 			rework = true;
-			schedule_delayed_work(&idev->mc_report_work, 0);
 			break;
 		}
 	}
@@ -1635,8 +1635,10 @@ static void mld_report_work(struct work_struct *work)
 		__mld_report_work(skb);
 	mutex_unlock(&idev->mc_lock);
 
-	if (!rework)
-		in6_dev_put(idev);
+	if (rework && queue_delayed_work(mld_wq, &idev->mc_report_work, 0))
+		return;
+
+	in6_dev_put(idev);
 }
 
 static bool is_in(struct ifmcaddr6 *pmc, struct ip6_sf_list *psf, int type,
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 4b098521a44c..8108e9a941d0 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1317,6 +1317,9 @@ static void ndisc_router_discovery(struct sk_buff *skb)
 	if (!rt && lifetime) {
 		ND_PRINTK(3, info, "RA: adding default router\n");
 
+		if (neigh)
+			neigh_release(neigh);
+
 		rt = rt6_add_dflt_router(net, &ipv6_hdr(skb)->saddr,
 					 skb->dev, pref, defrtr_usr_metric);
 		if (!rt) {
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 6ac88fe24a8e..135e3a060caa 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -22,6 +22,11 @@
 #include <linux/proc_fs.h>
 #include <net/ping.h>
 
+static void ping_v6_destroy(struct sock *sk)
+{
+	inet6_destroy_sock(sk);
+}
+
 /* Compatibility glue so we can support IPv6 when it's compiled as a module */
 static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len,
 				 int *addr_len)
@@ -166,6 +171,7 @@ struct proto pingv6_prot = {
 	.owner =	THIS_MODULE,
 	.init =		ping_init_sock,
 	.close =	ping_close,
+	.destroy =	ping_v6_destroy,
 	.connect =	ip6_datagram_connect_v6_only,
 	.disconnect =	__udp_disconnect,
 	.setsockopt =	ipv6_setsockopt,
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 0ca7c780d97a..27274fc3619a 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -4590,8 +4590,15 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net,
 	}
 
 	f6i = ip6_route_info_create(&cfg, gfp_flags, NULL);
-	if (!IS_ERR(f6i))
+	if (!IS_ERR(f6i)) {
 		f6i->dst_nocount = true;
+
+		if (!anycast &&
+		    (net->ipv6.devconf_all->disable_policy ||
+		     idev->cnf.disable_policy))
+			f6i->dst_nopolicy = true;
+	}
+
 	return f6i;
 }
 
@@ -5749,7 +5756,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 		if (nexthop_is_blackhole(rt->nh))
 			rtm->rtm_type = RTN_BLACKHOLE;
 
-		if (net->ipv4.sysctl_nexthop_compat_mode &&
+		if (READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode) &&
 		    rt6_fill_node_nexthop(skb, rt->nh, &nh_flags) < 0)
 			goto nla_put_failure;
 
diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c
index fa6b64c95d3a..0c7c6fc16c3c 100644
--- a/net/ipv6/seg6.c
+++ b/net/ipv6/seg6.c
@@ -191,6 +191,11 @@ static int seg6_genl_sethmac(struct sk_buff *skb, struct genl_info *info)
 		goto out_unlock;
 	}
 
+	if (slen > nla_len(info->attrs[SEG6_ATTR_SECRET])) {
+		err = -EINVAL;
+		goto out_unlock;
+	}
+
 	if (hinfo) {
 		err = seg6_hmac_info_del(net, hmackeyid);
 		if (err)
diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c
index 5b2c9ce53395..b7d6b64cc532 100644
--- a/net/ipv6/seg6_hmac.c
+++ b/net/ipv6/seg6_hmac.c
@@ -408,7 +408,6 @@ int __net_init seg6_hmac_net_init(struct net *net)
 
 	return 0;
 }
-EXPORT_SYMBOL(seg6_hmac_net_init);
 
 void seg6_hmac_exit(void)
 {
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index d64855010948..e756ba705fd9 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -189,6 +189,8 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
 	}
 #endif
 
+	hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
+
 	skb_postpush_rcsum(skb, hdr, tot_len);
 
 	return 0;
@@ -241,6 +243,8 @@ int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
 	}
 #endif
 
+	hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
+
 	skb_postpush_rcsum(skb, hdr, sizeof(struct ipv6hdr) + hdrlen);
 
 	return 0;
@@ -302,7 +306,6 @@ static int seg6_do_srh(struct sk_buff *skb)
 		break;
 	}
 
-	ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
 	skb_set_transport_header(skb, sizeof(struct ipv6hdr));
 	nf_reset_ct(skb);
 
diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index ef88489c71f5..59454285d5c5 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c
@@ -824,7 +824,6 @@ static int input_action_end_b6(struct sk_buff *skb, struct seg6_local_lwt *slwt)
 	if (err)
 		goto drop;
 
-	ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
 	skb_set_transport_header(skb, sizeof(struct ipv6hdr));
 
 	seg6_lookup_nexthop(skb, NULL, 0);
@@ -856,7 +855,6 @@ static int input_action_end_b6_encap(struct sk_buff *skb,
 	if (err)
 		goto drop;
 
-	ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
 	skb_set_transport_header(skb, sizeof(struct ipv6hdr));
 
 	seg6_lookup_nexthop(skb, NULL, 0);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 626cb53aa57a..637cd99bd7a6 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -323,8 +323,6 @@ static int ipip6_tunnel_get_prl(struct net_device *dev, struct ip_tunnel_prl __u
 		kcalloc(cmax, sizeof(*kp), GFP_KERNEL_ACCOUNT | __GFP_NOWARN) :
 		NULL;
 
-	rcu_read_lock();
-
 	ca = min(t->prl_count, cmax);
 
 	if (!kp) {
@@ -341,7 +339,7 @@ static int ipip6_tunnel_get_prl(struct net_device *dev, struct ip_tunnel_prl __u
 		}
 	}
 
-	c = 0;
+	rcu_read_lock();
 	for_each_prl_rcu(t->prl) {
 		if (c >= cmax)
 			break;
@@ -353,7 +351,7 @@ static int ipip6_tunnel_get_prl(struct net_device *dev, struct ip_tunnel_prl __u
 		if (kprl.addr != htonl(INADDR_ANY))
 			break;
 	}
-out:
+
 	rcu_read_unlock();
 
 	len = sizeof(*kp) * c;
@@ -362,7 +360,7 @@ out:
 		ret = -EFAULT;
 
 	kfree(kp);
-
+out:
 	return ret;
 }
 
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index ca92dd6981de..12ae817aaf2e 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -141,7 +141,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	__u8 rcv_wscale;
 	u32 tsoff = 0;
 
-	if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies || !th->ack || th->rst)
+	if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies) ||
+	    !th->ack || th->rst)
 		goto out;
 
 	if (tcp_synq_no_recent_overflow(sk))
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index beaa0c2ada23..66d00368db82 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -542,7 +542,7 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
 		if (np->repflow && ireq->pktopts)
 			fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
 
-		tclass = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
+		tclass = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) ?
 				(tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |
 				(np->tclass & INET_ECN_MASK) :
 				np->tclass;
@@ -1001,7 +1001,10 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
 	 * Underlying function will use this to retrieve the network
 	 * namespace
 	 */
-	dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL);
+	if (sk && sk->sk_state != TCP_TIME_WAIT)
+		dst = ip6_dst_lookup_flow(net, sk, &fl6, NULL); /*sk's xfrm_policy can be referred*/
+	else
+		dst = ip6_dst_lookup_flow(net, ctl_sk, &fl6, NULL);
 	if (!IS_ERR(dst)) {
 		skb_dst_set(buff, dst);
 		ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL,
@@ -1364,7 +1367,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 	/* Set ToS of the new socket based upon the value of incoming SYN.
 	 * ECT bits are set later in tcp_init_transfer().
 	 */
-	if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)
+	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos))
 		newnp->tclass = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK;
 
 	/* Clone native IPv6 options from listening socket (if any)
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 932c6f2a5494..07726a51a3f0 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -614,8 +614,11 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	}
 
 	/* Tunnels don't have an application socket: don't pass errors back */
-	if (tunnel)
+	if (tunnel) {
+		if (udp_sk(sk)->encap_err_rcv)
+			udp_sk(sk)->encap_err_rcv(sk, skb, offset);
 		goto out;
+	}
 
 	if (!np->recverr) {
 		if (!harderr || sk->sk_state != TCP_ESTABLISHED)
@@ -1035,7 +1038,7 @@ static struct sock *__udp6_lib_demux_lookup(struct net *net,
 
 	udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
 		if (sk->sk_state == TCP_ESTABLISHED &&
-		    INET6_MATCH(sk, net, rmt_addr, loc_addr, ports, dif, sdif))
+		    inet6_match(net, sk, rmt_addr, loc_addr, ports, dif, sdif))
 			return sk;
 		/* Only check first socket in chain */
 		break;
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 11a715d76a4f..f780fbe82e7d 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -1411,12 +1411,6 @@ static int kcm_attach(struct socket *sock, struct socket *csock,
 	psock->sk = csk;
 	psock->bpf_prog = prog;
 
-	err = strp_init(&psock->strp, csk, &cb);
-	if (err) {
-		kmem_cache_free(kcm_psockp, psock);
-		goto out;
-	}
-
 	write_lock_bh(&csk->sk_callback_lock);
 
 	/* Check if sk_user_data is already by KCM or someone else.
@@ -1424,13 +1418,18 @@ static int kcm_attach(struct socket *sock, struct socket *csock,
 	 */
 	if (csk->sk_user_data) {
 		write_unlock_bh(&csk->sk_callback_lock);
-		strp_stop(&psock->strp);
-		strp_done(&psock->strp);
 		kmem_cache_free(kcm_psockp, psock);
 		err = -EALREADY;
 		goto out;
 	}
 
+	err = strp_init(&psock->strp, csk, &cb);
+	if (err) {
+		write_unlock_bh(&csk->sk_callback_lock);
+		kmem_cache_free(kcm_psockp, psock);
+		goto out;
+	}
+
 	psock->save_data_ready = csk->sk_data_ready;
 	psock->save_write_space = csk->sk_write_space;
 	psock->save_state_change = csk->sk_state_change;
diff --git a/net/key/af_key.c b/net/key/af_key.c
index d93bde657359..53cca9019158 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -1697,9 +1697,12 @@ static int pfkey_register(struct sock *sk, struct sk_buff *skb, const struct sad
 		pfk->registered |= (1<<hdr->sadb_msg_satype);
 	}
 
+	mutex_lock(&pfkey_mutex);
 	xfrm_probe_algs();
 
 	supp_skb = compose_sadb_supported(hdr, GFP_KERNEL | __GFP_ZERO);
+	mutex_unlock(&pfkey_mutex);
+
 	if (!supp_skb) {
 		if (hdr->sadb_msg_satype != SADB_SATYPE_UNSPEC)
 			pfk->registered &= ~(1<<hdr->sadb_msg_satype);
diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c
index ef729b1e39ea..e43176794149 100644
--- a/net/mac80211/agg-rx.c
+++ b/net/mac80211/agg-rx.c
@@ -310,7 +310,7 @@ void ___ieee80211_start_rx_ba_session(struct sta_info *sta,
 	}
 
 	if (sta->sta.he_cap.has_he)
-		max_buf_size = IEEE80211_MAX_AMPDU_BUF;
+		max_buf_size = IEEE80211_MAX_AMPDU_BUF_HE;
 	else
 		max_buf_size = IEEE80211_MAX_AMPDU_BUF_HT;
 
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index 5d6ca4c3e698..1e133ca58e78 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -534,6 +534,10 @@ int ieee80211_ibss_finish_csa(struct ieee80211_sub_if_data *sdata)
 
 	sdata_assert_lock(sdata);
 
+	/* When not connected/joined, sending CSA doesn't make sense. */
+	if (ifibss->state != IEEE80211_IBSS_MLME_JOINED)
+		return -ENOLINK;
+
 	/* update cfg80211 bss information with the new channel */
 	if (!is_zero_ether_addr(ifibss->bssid)) {
 		cbss = cfg80211_get_bss(sdata->local->hw.wiphy,
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 887f945bb12d..d6afaacaf7ef 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -461,16 +461,19 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted)
 	scan_req = rcu_dereference_protected(local->scan_req,
 					     lockdep_is_held(&local->mtx));
 
-	if (scan_req != local->int_scan_req) {
-		local->scan_info.aborted = aborted;
-		cfg80211_scan_done(scan_req, &local->scan_info);
-	}
 	RCU_INIT_POINTER(local->scan_req, NULL);
 	RCU_INIT_POINTER(local->scan_sdata, NULL);
 
 	local->scanning = 0;
 	local->scan_chandef.chan = NULL;
 
+	synchronize_rcu();
+
+	if (scan_req != local->int_scan_req) {
+		local->scan_info.aborted = aborted;
+		cfg80211_scan_done(scan_req, &local->scan_info);
+	}
+
 	/* Set power back to normal operating levels. */
 	ieee80211_hw_config(local, 0);
 
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 2b5acb37587f..f1e263b2c295 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -641,13 +641,13 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU)
 	/* check if STA exists already */
 	if (sta_info_get_bss(sdata, sta->sta.addr)) {
 		err = -EEXIST;
-		goto out_err;
+		goto out_cleanup;
 	}
 
 	sinfo = kzalloc(sizeof(struct station_info), GFP_KERNEL);
 	if (!sinfo) {
 		err = -ENOMEM;
-		goto out_err;
+		goto out_cleanup;
 	}
 
 	local->num_sta++;
@@ -703,8 +703,8 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU)
  out_drop_sta:
 	local->num_sta--;
 	synchronize_net();
+ out_cleanup:
 	cleanup_single_sta(sta);
- out_err:
 	mutex_unlock(&local->sta_mtx);
 	kfree(sinfo);
 	rcu_read_lock();
@@ -2206,9 +2206,9 @@ static inline u64 sta_get_tidstats_msdu(struct ieee80211_sta_rx_stats *rxstats,
 	u64 value;
 
 	do {
-		start = u64_stats_fetch_begin(&rxstats->syncp);
+		start = u64_stats_fetch_begin_irq(&rxstats->syncp);
 		value = rxstats->msdu[tid];
-	} while (u64_stats_fetch_retry(&rxstats->syncp, start));
+	} while (u64_stats_fetch_retry_irq(&rxstats->syncp, start));
 
 	return value;
 }
@@ -2272,9 +2272,9 @@ static inline u64 sta_get_stats_bytes(struct ieee80211_sta_rx_stats *rxstats)
 	u64 value;
 
 	do {
-		start = u64_stats_fetch_begin(&rxstats->syncp);
+		start = u64_stats_fetch_begin_irq(&rxstats->syncp);
 		value = rxstats->bytes;
-	} while (u64_stats_fetch_retry(&rxstats->syncp, start));
+	} while (u64_stats_fetch_retry_irq(&rxstats->syncp, start));
 
 	return value;
 }
diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c
index 62c6733e0792..d50480b31750 100644
--- a/net/mac80211/wme.c
+++ b/net/mac80211/wme.c
@@ -147,8 +147,8 @@ u16 __ieee80211_select_queue(struct ieee80211_sub_if_data *sdata,
 	bool qos;
 
 	/* all mesh/ocb stations are required to support WME */
-	if (sdata->vif.type == NL80211_IFTYPE_MESH_POINT ||
-	    sdata->vif.type == NL80211_IFTYPE_OCB)
+	if (sta && (sdata->vif.type == NL80211_IFTYPE_MESH_POINT ||
+		    sdata->vif.type == NL80211_IFTYPE_OCB))
 		qos = true;
 	else if (sta)
 		qos = sta->sta.wme;
diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c
index b8ce84618a55..c439125ef2b9 100644
--- a/net/mac802154/rx.c
+++ b/net/mac802154/rx.c
@@ -44,7 +44,7 @@ ieee802154_subif_frame(struct ieee802154_sub_if_data *sdata,
 
 	switch (mac_cb(skb)->dest.mode) {
 	case IEEE802154_ADDR_NONE:
-		if (mac_cb(skb)->dest.mode != IEEE802154_ADDR_NONE)
+		if (hdr->source.mode != IEEE802154_ADDR_NONE)
 			/* FIXME: check if we are PAN coordinator */
 			skb->pkt_type = PACKET_OTHERHOST;
 		else
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 6e587feb705c..58a7075084d1 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -1079,9 +1079,9 @@ static void mpls_get_stats(struct mpls_dev *mdev,
 
 		p = per_cpu_ptr(mdev->stats, i);
 		do {
-			start = u64_stats_fetch_begin(&p->syncp);
+			start = u64_stats_fetch_begin_irq(&p->syncp);
 			local = p->stats;
-		} while (u64_stats_fetch_retry(&p->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&p->syncp, start));
 
 		stats->rx_packets	+= local.rx_packets;
 		stats->rx_bytes		+= local.rx_bytes;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index d6def23b8cba..47f359dac247 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1224,6 +1224,7 @@ static struct sk_buff *__mptcp_do_alloc_tx_skb(struct sock *sk, gfp_t gfp)
 		if (likely(__mptcp_add_ext(skb, gfp))) {
 			skb_reserve(skb, MAX_TCP_HEADER);
 			skb->reserved_tailroom = skb->end - skb->tail;
+			INIT_LIST_HEAD(&skb->tcp_tsorted_anchor);
 			return skb;
 		}
 		__kfree_skb(skb);
@@ -1233,31 +1234,24 @@ static struct sk_buff *__mptcp_do_alloc_tx_skb(struct sock *sk, gfp_t gfp)
 	return NULL;
 }
 
-static bool __mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, gfp_t gfp)
+static struct sk_buff *__mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, gfp_t gfp)
 {
 	struct sk_buff *skb;
 
-	if (ssk->sk_tx_skb_cache) {
-		skb = ssk->sk_tx_skb_cache;
-		if (unlikely(!skb_ext_find(skb, SKB_EXT_MPTCP) &&
-			     !__mptcp_add_ext(skb, gfp)))
-			return false;
-		return true;
-	}
-
 	skb = __mptcp_do_alloc_tx_skb(sk, gfp);
 	if (!skb)
-		return false;
+		return NULL;
 
 	if (likely(sk_wmem_schedule(ssk, skb->truesize))) {
-		ssk->sk_tx_skb_cache = skb;
-		return true;
+		tcp_skb_entail(ssk, skb);
+		return skb;
 	}
+	tcp_skb_tsorted_anchor_cleanup(skb);
 	kfree_skb(skb);
-	return false;
+	return NULL;
 }
 
-static bool mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, bool data_lock_held)
+static struct sk_buff *mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, bool data_lock_held)
 {
 	gfp_t gfp = data_lock_held ? GFP_ATOMIC : sk->sk_allocation;
 
@@ -1287,23 +1281,29 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 			      struct mptcp_sendmsg_info *info)
 {
 	u64 data_seq = dfrag->data_seq + info->sent;
+	int offset = dfrag->offset + info->sent;
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	bool zero_window_probe = false;
 	struct mptcp_ext *mpext = NULL;
-	struct sk_buff *skb, *tail;
-	bool must_collapse = false;
-	int size_bias = 0;
-	int avail_size;
-	size_t ret = 0;
+	bool can_coalesce = false;
+	bool reuse_skb = true;
+	struct sk_buff *skb;
+	size_t copy;
+	int i;
 
 	pr_debug("msk=%p ssk=%p sending dfrag at seq=%llu len=%u already sent=%u",
 		 msk, ssk, dfrag->data_seq, dfrag->data_len, info->sent);
 
+	if (WARN_ON_ONCE(info->sent > info->limit ||
+			 info->limit > dfrag->data_len))
+		return 0;
+
 	/* compute send limit */
 	info->mss_now = tcp_send_mss(ssk, &info->size_goal, info->flags);
-	avail_size = info->size_goal;
+	copy = info->size_goal;
+
 	skb = tcp_write_queue_tail(ssk);
-	if (skb) {
+	if (skb && copy > skb->len) {
 		/* Limit the write to the size available in the
 		 * current skb, if any, so that we create at most a new skb.
 		 * Explicitly tells TCP internals to avoid collapsing on later
@@ -1316,62 +1316,80 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 			goto alloc_skb;
 		}
 
-		must_collapse = (info->size_goal > skb->len) &&
-				(skb_shinfo(skb)->nr_frags < sysctl_max_skb_frags);
-		if (must_collapse) {
-			size_bias = skb->len;
-			avail_size = info->size_goal - skb->len;
+		i = skb_shinfo(skb)->nr_frags;
+		can_coalesce = skb_can_coalesce(skb, i, dfrag->page, offset);
+		if (!can_coalesce && i >= READ_ONCE(sysctl_max_skb_frags)) {
+			tcp_mark_push(tcp_sk(ssk), skb);
+			goto alloc_skb;
 		}
-	}
 
+		copy -= skb->len;
+	} else {
 alloc_skb:
-	if (!must_collapse &&
-	    !mptcp_alloc_tx_skb(sk, ssk, info->data_lock_held))
-		return 0;
+		skb = mptcp_alloc_tx_skb(sk, ssk, info->data_lock_held);
+		if (!skb)
+			return -ENOMEM;
+
+		i = skb_shinfo(skb)->nr_frags;
+		reuse_skb = false;
+		mpext = skb_ext_find(skb, SKB_EXT_MPTCP);
+	}
 
 	/* Zero window and all data acked? Probe. */
-	avail_size = mptcp_check_allowed_size(msk, data_seq, avail_size);
-	if (avail_size == 0) {
+	copy = mptcp_check_allowed_size(msk, data_seq, copy);
+	if (copy == 0) {
 		u64 snd_una = READ_ONCE(msk->snd_una);
 
-		if (skb || snd_una != msk->snd_nxt)
+		if (snd_una != msk->snd_nxt) {
+			tcp_remove_empty_skb(ssk, tcp_write_queue_tail(ssk));
 			return 0;
+		}
+
 		zero_window_probe = true;
 		data_seq = snd_una - 1;
-		avail_size = 1;
-	}
+		copy = 1;
 
-	if (WARN_ON_ONCE(info->sent > info->limit ||
-			 info->limit > dfrag->data_len))
-		return 0;
+		/* all mptcp-level data is acked, no skbs should be present into the
+		 * ssk write queue
+		 */
+		WARN_ON_ONCE(reuse_skb);
+	}
 
-	ret = info->limit - info->sent;
-	tail = tcp_build_frag(ssk, avail_size + size_bias, info->flags,
-			      dfrag->page, dfrag->offset + info->sent, &ret);
-	if (!tail) {
-		tcp_remove_empty_skb(sk, tcp_write_queue_tail(ssk));
+	copy = min_t(size_t, copy, info->limit - info->sent);
+	if (!sk_wmem_schedule(ssk, copy)) {
+		tcp_remove_empty_skb(ssk, tcp_write_queue_tail(ssk));
 		return -ENOMEM;
 	}
 
-	/* if the tail skb is still the cached one, collapsing really happened.
-	 */
-	if (skb == tail) {
-		TCP_SKB_CB(tail)->tcp_flags &= ~TCPHDR_PSH;
-		mpext->data_len += ret;
+	if (can_coalesce) {
+		skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
+	} else {
+		get_page(dfrag->page);
+		skb_fill_page_desc(skb, i, dfrag->page, offset, copy);
+	}
+
+	skb->len += copy;
+	skb->data_len += copy;
+	skb->truesize += copy;
+	sk_wmem_queued_add(ssk, copy);
+	sk_mem_charge(ssk, copy);
+	skb->ip_summed = CHECKSUM_PARTIAL;
+	WRITE_ONCE(tcp_sk(ssk)->write_seq, tcp_sk(ssk)->write_seq + copy);
+	TCP_SKB_CB(skb)->end_seq += copy;
+	tcp_skb_pcount_set(skb, 0);
+
+	/* on skb reuse we just need to update the DSS len */
+	if (reuse_skb) {
+		TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
+		mpext->data_len += copy;
 		WARN_ON_ONCE(zero_window_probe);
 		goto out;
 	}
 
-	mpext = skb_ext_find(tail, SKB_EXT_MPTCP);
-	if (WARN_ON_ONCE(!mpext)) {
-		/* should never reach here, stream corrupted */
-		return -EINVAL;
-	}
-
 	memset(mpext, 0, sizeof(*mpext));
 	mpext->data_seq = data_seq;
 	mpext->subflow_seq = mptcp_subflow_ctx(ssk)->rel_write_seq;
-	mpext->data_len = ret;
+	mpext->data_len = copy;
 	mpext->use_map = 1;
 	mpext->dsn64 = 1;
 
@@ -1380,18 +1398,18 @@ alloc_skb:
 		 mpext->dsn64);
 
 	if (zero_window_probe) {
-		mptcp_subflow_ctx(ssk)->rel_write_seq += ret;
+		mptcp_subflow_ctx(ssk)->rel_write_seq += copy;
 		mpext->frozen = 1;
 		if (READ_ONCE(msk->csum_enabled))
-			mptcp_update_data_checksum(tail, ret);
+			mptcp_update_data_checksum(skb, copy);
 		tcp_push_pending_frames(ssk);
 		return 0;
 	}
 out:
 	if (READ_ONCE(msk->csum_enabled))
-		mptcp_update_data_checksum(tail, ret);
-	mptcp_subflow_ctx(ssk)->rel_write_seq += ret;
-	return ret;
+		mptcp_update_data_checksum(skb, copy);
+	mptcp_subflow_ctx(ssk)->rel_write_seq += copy;
+	return copy;
 }
 
 #define MPTCP_SEND_BURST_SIZE		((1 << 16) - \
@@ -1881,7 +1899,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
 	if (msk->rcvq_space.copied <= msk->rcvq_space.space)
 		goto new_measure;
 
-	if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf &&
+	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) &&
 	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
 		int rcvmem, rcvbuf;
 		u64 rcvwin, grow;
@@ -1899,7 +1917,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
 
 		do_div(rcvwin, advmss);
 		rcvbuf = min_t(u64, rcvwin * rcvmem,
-			       sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
+			       READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
 
 		if (rcvbuf > sk->sk_rcvbuf) {
 			u32 window_clamp;
@@ -2532,8 +2550,8 @@ static int mptcp_init_sock(struct sock *sk)
 	icsk->icsk_ca_ops = NULL;
 
 	sk_sockets_allocated_inc(sk);
-	sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1];
-	sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1];
+	sk->sk_rcvbuf = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1]);
+	sk->sk_sndbuf = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1]);
 
 	return 0;
 }
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 92a747896f80..4f645d51c257 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -133,7 +133,6 @@ config NF_CONNTRACK_ZONES
 
 config NF_CONNTRACK_PROCFS
 	bool "Supply CT list in procfs (OBSOLETE)"
-	default y
 	depends on PROC_FS
 	help
 	This option enables for the list of known conntrack entries
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 60332fdb6dd4..cca0762a9010 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -592,7 +592,8 @@ int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state,
 		case NF_ACCEPT:
 			break;
 		case NF_DROP:
-			kfree_skb(skb);
+			kfree_skb_reason(skb,
+					 SKB_DROP_REASON_NETFILTER_DROP);
 			ret = NF_DROP_GETERR(verdict);
 			if (ret == 0)
 				ret = -EPERM;
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 9d43277b8b4f..a56fd0b5a430 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1280,12 +1280,12 @@ static void set_sock_size(struct sock *sk, int mode, int val)
 	lock_sock(sk);
 	if (mode) {
 		val = clamp_t(int, val, (SOCK_MIN_SNDBUF + 1) / 2,
-			      sysctl_wmem_max);
+			      READ_ONCE(sysctl_wmem_max));
 		sk->sk_sndbuf = val * 2;
 		sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
 	} else {
 		val = clamp_t(int, val, (SOCK_MIN_RCVBUF + 1) / 2,
-			      sysctl_rmem_max);
+			      READ_ONCE(sysctl_rmem_max));
 		sk->sk_rcvbuf = val * 2;
 		sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
 	}
diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c
index 08ee4e760a3d..18b90e334b5b 100644
--- a/net/netfilter/nf_conntrack_irc.c
+++ b/net/netfilter/nf_conntrack_irc.c
@@ -188,8 +188,9 @@ static int help(struct sk_buff *skb, unsigned int protoff,
 
 			/* dcc_ip can be the internal OR external (NAT'ed) IP */
 			tuple = &ct->tuplehash[dir].tuple;
-			if (tuple->src.u3.ip != dcc_ip &&
-			    tuple->dst.u3.ip != dcc_ip) {
+			if ((tuple->src.u3.ip != dcc_ip &&
+			     ct->tuplehash[!dir].tuple.dst.u3.ip != dcc_ip) ||
+			    dcc_port == 0) {
 				net_warn_ratelimited("Forged DCC command from %pI4: %pI4:%u\n",
 						     &tuple->src.u3.ip,
 						     &dcc_ip, dcc_port);
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index 3cee5d8ee702..1ecfdc4f23be 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -671,6 +671,37 @@ static bool tcp_in_window(struct nf_conn *ct,
 		    tn->tcp_be_liberal)
 			res = true;
 		if (!res) {
+			bool seq_ok = before(seq, sender->td_maxend + 1);
+
+			if (!seq_ok) {
+				u32 overshot = end - sender->td_maxend + 1;
+				bool ack_ok;
+
+				ack_ok = after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1);
+
+				if (in_recv_win &&
+				    ack_ok &&
+				    overshot <= receiver->td_maxwin &&
+				    before(sack, receiver->td_end + 1)) {
+					/* Work around TCPs that send more bytes than allowed by
+					 * the receive window.
+					 *
+					 * If the (marked as invalid) packet is allowed to pass by
+					 * the ruleset and the peer acks this data, then its possible
+					 * all future packets will trigger 'ACK is over upper bound' check.
+					 *
+					 * Thus if only the sequence check fails then do update td_end so
+					 * possible ACK for this data can update internal state.
+					 */
+					sender->td_end = end;
+					sender->flags |= IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED;
+
+					nf_ct_l4proto_log_invalid(skb, ct, hook_state,
+								  "%u bytes more than expected", overshot);
+					return res;
+				}
+			}
+
 			nf_ct_l4proto_log_invalid(skb, ct, hook_state,
 			"%s",
 			before(seq, sender->td_maxend + 1) ?
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 9fb407084c50..4f61eb128283 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -436,12 +436,17 @@ static void nf_flow_offload_gc_step(struct nf_flowtable *flow_table,
 	}
 }
 
+void nf_flow_table_gc_run(struct nf_flowtable *flow_table)
+{
+	nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, NULL);
+}
+
 static void nf_flow_offload_work_gc(struct work_struct *work)
 {
 	struct nf_flowtable *flow_table;
 
 	flow_table = container_of(work, struct nf_flowtable, gc_work.work);
-	nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, NULL);
+	nf_flow_table_gc_run(flow_table);
 	queue_delayed_work(system_power_efficient_wq, &flow_table->gc_work, HZ);
 }
 
@@ -599,11 +604,11 @@ void nf_flow_table_free(struct nf_flowtable *flow_table)
 	mutex_unlock(&flowtable_lock);
 
 	cancel_delayed_work_sync(&flow_table->gc_work);
-	nf_flow_table_iterate(flow_table, nf_flow_table_do_cleanup, NULL);
-	nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, NULL);
 	nf_flow_table_offload_flush(flow_table);
-	if (nf_flowtable_hw_offload(flow_table))
-		nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, NULL);
+	/* ... no more pending work after this stage ... */
+	nf_flow_table_iterate(flow_table, nf_flow_table_do_cleanup, NULL);
+	nf_flow_table_gc_run(flow_table);
+	nf_flow_table_offload_flush_cleanup(flow_table);
 	rhashtable_destroy(&flow_table->rhashtable);
 }
 EXPORT_SYMBOL_GPL(nf_flow_table_free);
diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
index b561e0a44a45..c4559fae8acd 100644
--- a/net/netfilter/nf_flow_table_offload.c
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -1050,6 +1050,14 @@ void nf_flow_offload_stats(struct nf_flowtable *flowtable,
 	flow_offload_queue_work(offload);
 }
 
+void nf_flow_table_offload_flush_cleanup(struct nf_flowtable *flowtable)
+{
+	if (nf_flowtable_hw_offload(flowtable)) {
+		flush_workqueue(nf_flow_offload_del_wq);
+		nf_flow_table_gc_run(flowtable);
+	}
+}
+
 void nf_flow_table_offload_flush(struct nf_flowtable *flowtable)
 {
 	if (nf_flowtable_hw_offload(flowtable)) {
diff --git a/net/netfilter/nf_log_syslog.c b/net/netfilter/nf_log_syslog.c
index 13234641cdb3..7000e069bc07 100644
--- a/net/netfilter/nf_log_syslog.c
+++ b/net/netfilter/nf_log_syslog.c
@@ -61,7 +61,7 @@ dump_arp_packet(struct nf_log_buf *m,
 	unsigned int logflags;
 	struct arphdr _arph;
 
-	ah = skb_header_pointer(skb, 0, sizeof(_arph), &_arph);
+	ah = skb_header_pointer(skb, nhoff, sizeof(_arph), &_arph);
 	if (!ah) {
 		nf_log_buf_add(m, "TRUNCATED");
 		return;
@@ -90,7 +90,7 @@ dump_arp_packet(struct nf_log_buf *m,
 	    ah->ar_pln != sizeof(__be32))
 		return;
 
-	ap = skb_header_pointer(skb, sizeof(_arph), sizeof(_arpp), &_arpp);
+	ap = skb_header_pointer(skb, nhoff + sizeof(_arph), sizeof(_arpp), &_arpp);
 	if (!ap) {
 		nf_log_buf_add(m, " INCOMPLETE [%zu bytes]",
 			       skb->len - sizeof(_arph));
@@ -144,7 +144,7 @@ static void nf_log_arp_packet(struct net *net, u_int8_t pf,
 
 	nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, loginfo,
 				  prefix);
-	dump_arp_packet(m, loginfo, skb, 0);
+	dump_arp_packet(m, loginfo, skb, skb_network_offset(skb));
 
 	nf_log_buf_close(m);
 }
@@ -829,7 +829,7 @@ static void nf_log_ip_packet(struct net *net, u_int8_t pf,
 	if (in)
 		dump_ipv4_mac_header(m, loginfo, skb);
 
-	dump_ipv4_packet(net, m, loginfo, skb, 0);
+	dump_ipv4_packet(net, m, loginfo, skb, skb_network_offset(skb));
 
 	nf_log_buf_close(m);
 }
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index 2dfc5dae0656..049a88f03801 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -427,7 +427,7 @@ synproxy_build_ip(struct net *net, struct sk_buff *skb, __be32 saddr,
 	iph->tos	= 0;
 	iph->id		= 0;
 	iph->frag_off	= htons(IP_DF);
-	iph->ttl	= net->ipv4.sysctl_ip_default_ttl;
+	iph->ttl	= READ_ONCE(net->ipv4.sysctl_ip_default_ttl);
 	iph->protocol	= IPPROTO_TCP;
 	iph->check	= 0;
 	iph->saddr	= saddr;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 1b4bc588f8d6..d35d09df83fe 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -32,7 +32,6 @@ static LIST_HEAD(nf_tables_objects);
 static LIST_HEAD(nf_tables_flowtables);
 static LIST_HEAD(nf_tables_destroy_list);
 static DEFINE_SPINLOCK(nf_tables_destroy_list_lock);
-static u64 table_handle;
 
 enum {
 	NFT_VALIDATE_SKIP	= 0,
@@ -153,6 +152,7 @@ static struct nft_trans *nft_trans_alloc_gfp(const struct nft_ctx *ctx,
 	if (trans == NULL)
 		return NULL;
 
+	INIT_LIST_HEAD(&trans->list);
 	trans->msg_type = msg_type;
 	trans->ctx	= *ctx;
 
@@ -836,7 +836,7 @@ static int nf_tables_dump_tables(struct sk_buff *skb,
 
 	rcu_read_lock();
 	nft_net = nft_pernet(net);
-	cb->seq = nft_net->base_seq;
+	cb->seq = READ_ONCE(nft_net->base_seq);
 
 	list_for_each_entry_rcu(table, &nft_net->tables, list) {
 		if (family != NFPROTO_UNSPEC && family != table->family)
@@ -1155,7 +1155,7 @@ static int nf_tables_newtable(struct sk_buff *skb, const struct nfnl_info *info,
 	INIT_LIST_HEAD(&table->flowtables);
 	table->family = family;
 	table->flags = flags;
-	table->handle = ++table_handle;
+	table->handle = ++nft_net->table_handle;
 	if (table->flags & NFT_TABLE_F_OWNER)
 		table->nlpid = NETLINK_CB(skb).portid;
 
@@ -1625,7 +1625,7 @@ static int nf_tables_dump_chains(struct sk_buff *skb,
 
 	rcu_read_lock();
 	nft_net = nft_pernet(net);
-	cb->seq = nft_net->base_seq;
+	cb->seq = READ_ONCE(nft_net->base_seq);
 
 	list_for_each_entry_rcu(table, &nft_net->tables, list) {
 		if (family != NFPROTO_UNSPEC && family != table->family)
@@ -2072,8 +2072,10 @@ static int nft_basechain_init(struct nft_base_chain *basechain, u8 family,
 	chain->flags |= NFT_CHAIN_BASE | flags;
 	basechain->policy = NF_ACCEPT;
 	if (chain->flags & NFT_CHAIN_HW_OFFLOAD &&
-	    !nft_chain_offload_support(basechain))
+	    !nft_chain_offload_support(basechain)) {
+		list_splice_init(&basechain->hook_list, &hook->list);
 		return -EOPNOTSUPP;
+	}
 
 	flow_block_init(&basechain->flow_block);
 
@@ -2101,9 +2103,9 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 			      struct netlink_ext_ack *extack)
 {
 	const struct nlattr * const *nla = ctx->nla;
+	struct nft_stats __percpu *stats = NULL;
 	struct nft_table *table = ctx->table;
 	struct nft_base_chain *basechain;
-	struct nft_stats __percpu *stats;
 	struct net *net = ctx->net;
 	char name[NFT_NAME_MAXLEN];
 	struct nft_trans *trans;
@@ -2140,7 +2142,6 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 				return PTR_ERR(stats);
 			}
 			rcu_assign_pointer(basechain->stats, stats);
-			static_branch_inc(&nft_counters_enabled);
 		}
 
 		err = nft_basechain_init(basechain, family, &hook, flags);
@@ -2223,6 +2224,9 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 		goto err_unregister_hook;
 	}
 
+	if (stats)
+		static_branch_inc(&nft_counters_enabled);
+
 	table->use++;
 
 	return 0;
@@ -2377,6 +2381,7 @@ err:
 }
 
 static struct nft_chain *nft_chain_lookup_byid(const struct net *net,
+					       const struct nft_table *table,
 					       const struct nlattr *nla)
 {
 	struct nftables_pernet *nft_net = nft_pernet(net);
@@ -2387,6 +2392,7 @@ static struct nft_chain *nft_chain_lookup_byid(const struct net *net,
 		struct nft_chain *chain = trans->ctx.chain;
 
 		if (trans->msg_type == NFT_MSG_NEWCHAIN &&
+		    chain->table == table &&
 		    id == nft_trans_chain_id(trans))
 			return chain;
 	}
@@ -2476,6 +2482,9 @@ static int nf_tables_newchain(struct sk_buff *skb, const struct nfnl_info *info,
 	nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla);
 
 	if (chain != NULL) {
+		if (chain->flags & NFT_CHAIN_BINDING)
+			return -EINVAL;
+
 		if (info->nlh->nlmsg_flags & NLM_F_EXCL) {
 			NL_SET_BAD_ATTR(extack, attr);
 			return -EEXIST;
@@ -3051,7 +3060,7 @@ static int nf_tables_dump_rules(struct sk_buff *skb,
 
 	rcu_read_lock();
 	nft_net = nft_pernet(net);
-	cb->seq = nft_net->base_seq;
+	cb->seq = READ_ONCE(nft_net->base_seq);
 
 	list_for_each_entry_rcu(table, &nft_net->tables, list) {
 		if (family != NFPROTO_UNSPEC && family != table->family)
@@ -3274,6 +3283,7 @@ static int nft_table_validate(struct net *net, const struct nft_table *table)
 }
 
 static struct nft_rule *nft_rule_lookup_byid(const struct net *net,
+					     const struct nft_chain *chain,
 					     const struct nlattr *nla);
 
 #define NFT_RULE_MAXEXPRS	128
@@ -3320,7 +3330,7 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info,
 			return -EOPNOTSUPP;
 
 	} else if (nla[NFTA_RULE_CHAIN_ID]) {
-		chain = nft_chain_lookup_byid(net, nla[NFTA_RULE_CHAIN_ID]);
+		chain = nft_chain_lookup_byid(net, table, nla[NFTA_RULE_CHAIN_ID]);
 		if (IS_ERR(chain)) {
 			NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN_ID]);
 			return PTR_ERR(chain);
@@ -3362,7 +3372,7 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info,
 				return PTR_ERR(old_rule);
 			}
 		} else if (nla[NFTA_RULE_POSITION_ID]) {
-			old_rule = nft_rule_lookup_byid(net, nla[NFTA_RULE_POSITION_ID]);
+			old_rule = nft_rule_lookup_byid(net, chain, nla[NFTA_RULE_POSITION_ID]);
 			if (IS_ERR(old_rule)) {
 				NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_POSITION_ID]);
 				return PTR_ERR(old_rule);
@@ -3507,6 +3517,7 @@ err_release_expr:
 }
 
 static struct nft_rule *nft_rule_lookup_byid(const struct net *net,
+					     const struct nft_chain *chain,
 					     const struct nlattr *nla)
 {
 	struct nftables_pernet *nft_net = nft_pernet(net);
@@ -3517,6 +3528,7 @@ static struct nft_rule *nft_rule_lookup_byid(const struct net *net,
 		struct nft_rule *rule = nft_trans_rule(trans);
 
 		if (trans->msg_type == NFT_MSG_NEWRULE &&
+		    trans->ctx.chain == chain &&
 		    id == nft_trans_rule_id(trans))
 			return rule;
 	}
@@ -3566,7 +3578,7 @@ static int nf_tables_delrule(struct sk_buff *skb, const struct nfnl_info *info,
 
 			err = nft_delrule(&ctx, rule);
 		} else if (nla[NFTA_RULE_ID]) {
-			rule = nft_rule_lookup_byid(net, nla[NFTA_RULE_ID]);
+			rule = nft_rule_lookup_byid(net, chain, nla[NFTA_RULE_ID]);
 			if (IS_ERR(rule)) {
 				NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_ID]);
 				return PTR_ERR(rule);
@@ -3745,6 +3757,7 @@ static struct nft_set *nft_set_lookup_byhandle(const struct nft_table *table,
 }
 
 static struct nft_set *nft_set_lookup_byid(const struct net *net,
+					   const struct nft_table *table,
 					   const struct nlattr *nla, u8 genmask)
 {
 	struct nftables_pernet *nft_net = nft_pernet(net);
@@ -3756,6 +3769,7 @@ static struct nft_set *nft_set_lookup_byid(const struct net *net,
 			struct nft_set *set = nft_trans_set(trans);
 
 			if (id == nft_trans_set_id(trans) &&
+			    set->table == table &&
 			    nft_active_genmask(set, genmask))
 				return set;
 		}
@@ -3776,7 +3790,7 @@ struct nft_set *nft_set_lookup_global(const struct net *net,
 		if (!nla_set_id)
 			return set;
 
-		set = nft_set_lookup_byid(net, nla_set_id, genmask);
+		set = nft_set_lookup_byid(net, table, nla_set_id, genmask);
 	}
 	return set;
 }
@@ -3802,7 +3816,7 @@ cont:
 		list_for_each_entry(i, &ctx->table->sets, list) {
 			int tmp;
 
-			if (!nft_is_active_next(ctx->net, set))
+			if (!nft_is_active_next(ctx->net, i))
 				continue;
 			if (!sscanf(i->name, name, &tmp))
 				continue;
@@ -4028,7 +4042,7 @@ static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb)
 
 	rcu_read_lock();
 	nft_net = nft_pernet(net);
-	cb->seq = nft_net->base_seq;
+	cb->seq = READ_ONCE(nft_net->base_seq);
 
 	list_for_each_entry_rcu(table, &nft_net->tables, list) {
 		if (ctx->family != NFPROTO_UNSPEC &&
@@ -4346,6 +4360,11 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
 		err = nf_tables_set_desc_parse(&desc, nla[NFTA_SET_DESC]);
 		if (err < 0)
 			return err;
+
+		if (desc.field_count > 1 && !(flags & NFT_SET_CONCAT))
+			return -EINVAL;
+	} else if (flags & NFT_SET_CONCAT) {
+		return -EINVAL;
 	}
 
 	if (nla[NFTA_SET_EXPR] || nla[NFTA_SET_EXPRESSIONS])
@@ -4956,6 +4975,8 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
 
 	rcu_read_lock();
 	nft_net = nft_pernet(net);
+	cb->seq = READ_ONCE(nft_net->base_seq);
+
 	list_for_each_entry_rcu(table, &nft_net->tables, list) {
 		if (dump_ctx->ctx.family != NFPROTO_UNSPEC &&
 		    dump_ctx->ctx.family != table->family)
@@ -5091,6 +5112,9 @@ static int nft_setelem_parse_flags(const struct nft_set *set,
 	if (!(set->flags & NFT_SET_INTERVAL) &&
 	    *flags & NFT_SET_ELEM_INTERVAL_END)
 		return -EINVAL;
+	if ((*flags & (NFT_SET_ELEM_INTERVAL_END | NFT_SET_ELEM_CATCHALL)) ==
+	    (NFT_SET_ELEM_INTERVAL_END | NFT_SET_ELEM_CATCHALL))
+		return -EINVAL;
 
 	return 0;
 }
@@ -5098,19 +5122,13 @@ static int nft_setelem_parse_flags(const struct nft_set *set,
 static int nft_setelem_parse_key(struct nft_ctx *ctx, struct nft_set *set,
 				 struct nft_data *key, struct nlattr *attr)
 {
-	struct nft_data_desc desc;
-	int err;
-
-	err = nft_data_init(ctx, key, NFT_DATA_VALUE_MAXLEN, &desc, attr);
-	if (err < 0)
-		return err;
-
-	if (desc.type != NFT_DATA_VALUE || desc.len != set->klen) {
-		nft_data_release(key, desc.type);
-		return -EINVAL;
-	}
+	struct nft_data_desc desc = {
+		.type	= NFT_DATA_VALUE,
+		.size	= NFT_DATA_VALUE_MAXLEN,
+		.len	= set->klen,
+	};
 
-	return 0;
+	return nft_data_init(ctx, key, &desc, attr);
 }
 
 static int nft_setelem_parse_data(struct nft_ctx *ctx, struct nft_set *set,
@@ -5118,18 +5136,19 @@ static int nft_setelem_parse_data(struct nft_ctx *ctx, struct nft_set *set,
 				  struct nft_data *data,
 				  struct nlattr *attr)
 {
-	int err;
+	u32 dtype;
 
-	err = nft_data_init(ctx, data, NFT_DATA_VALUE_MAXLEN, desc, attr);
-	if (err < 0)
-		return err;
+	if (set->dtype == NFT_DATA_VERDICT)
+		dtype = NFT_DATA_VERDICT;
+	else
+		dtype = NFT_DATA_VALUE;
 
-	if (desc->type != NFT_DATA_VERDICT && desc->len != set->dlen) {
-		nft_data_release(data, desc->type);
-		return -EINVAL;
-	}
+	desc->type = dtype;
+	desc->size = NFT_DATA_VALUE_MAXLEN;
+	desc->len = set->dlen;
+	desc->flags = NFT_DATA_DESC_SETELEM;
 
-	return 0;
+	return nft_data_init(ctx, data, desc, attr);
 }
 
 static void *nft_setelem_catchall_get(const struct net *net,
@@ -5462,7 +5481,7 @@ int nft_set_elem_expr_clone(const struct nft_ctx *ctx, struct nft_set *set,
 
 		err = nft_expr_clone(expr, set->exprs[i]);
 		if (err < 0) {
-			nft_expr_destroy(ctx, expr);
+			kfree(expr);
 			goto err_expr;
 		}
 		expr_array[i] = expr;
@@ -5694,6 +5713,24 @@ static void nft_setelem_remove(const struct net *net,
 		set->ops->remove(net, set, elem);
 }
 
+static bool nft_setelem_valid_key_end(const struct nft_set *set,
+				      struct nlattr **nla, u32 flags)
+{
+	if ((set->flags & (NFT_SET_CONCAT | NFT_SET_INTERVAL)) ==
+			  (NFT_SET_CONCAT | NFT_SET_INTERVAL)) {
+		if (flags & NFT_SET_ELEM_INTERVAL_END)
+			return false;
+		if (!nla[NFTA_SET_ELEM_KEY_END] &&
+		    !(flags & NFT_SET_ELEM_CATCHALL))
+			return false;
+	} else {
+		if (nla[NFTA_SET_ELEM_KEY_END])
+			return false;
+	}
+
+	return true;
+}
+
 static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 			    const struct nlattr *attr, u32 nlmsg_flags)
 {
@@ -5729,8 +5766,11 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	if (!nla[NFTA_SET_ELEM_KEY] && !(flags & NFT_SET_ELEM_CATCHALL))
 		return -EINVAL;
 
-	if (flags != 0)
-		nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS);
+	if (flags != 0) {
+		err = nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS);
+		if (err < 0)
+			return err;
+	}
 
 	if (set->flags & NFT_SET_MAP) {
 		if (nla[NFTA_SET_ELEM_DATA] == NULL &&
@@ -5741,6 +5781,18 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 			return -EINVAL;
 	}
 
+	if (set->flags & NFT_SET_OBJECT) {
+		if (!nla[NFTA_SET_ELEM_OBJREF] &&
+		    !(flags & NFT_SET_ELEM_INTERVAL_END))
+			return -EINVAL;
+	} else {
+		if (nla[NFTA_SET_ELEM_OBJREF])
+			return -EINVAL;
+	}
+
+	if (!nft_setelem_valid_key_end(set, nla, flags))
+		return -EINVAL;
+
 	if ((flags & NFT_SET_ELEM_INTERVAL_END) &&
 	     (nla[NFTA_SET_ELEM_DATA] ||
 	      nla[NFTA_SET_ELEM_OBJREF] ||
@@ -5748,6 +5800,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	      nla[NFTA_SET_ELEM_EXPIRATION] ||
 	      nla[NFTA_SET_ELEM_USERDATA] ||
 	      nla[NFTA_SET_ELEM_EXPR] ||
+	      nla[NFTA_SET_ELEM_KEY_END] ||
 	      nla[NFTA_SET_ELEM_EXPRESSIONS]))
 		return -EINVAL;
 
@@ -5839,7 +5892,9 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 		if (err < 0)
 			goto err_set_elem_expr;
 
-		nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen);
+		err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen);
+		if (err < 0)
+			goto err_parse_key;
 	}
 
 	if (nla[NFTA_SET_ELEM_KEY_END]) {
@@ -5848,29 +5903,34 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 		if (err < 0)
 			goto err_parse_key;
 
-		nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen);
+		err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen);
+		if (err < 0)
+			goto err_parse_key_end;
 	}
 
 	if (timeout > 0) {
-		nft_set_ext_add(&tmpl, NFT_SET_EXT_EXPIRATION);
-		if (timeout != set->timeout)
-			nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT);
+		err = nft_set_ext_add(&tmpl, NFT_SET_EXT_EXPIRATION);
+		if (err < 0)
+			goto err_parse_key_end;
+
+		if (timeout != set->timeout) {
+			err = nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT);
+			if (err < 0)
+				goto err_parse_key_end;
+		}
 	}
 
 	if (num_exprs) {
 		for (i = 0; i < num_exprs; i++)
 			size += expr_array[i]->ops->size;
 
-		nft_set_ext_add_length(&tmpl, NFT_SET_EXT_EXPRESSIONS,
-				       sizeof(struct nft_set_elem_expr) +
-				       size);
+		err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_EXPRESSIONS,
+					     sizeof(struct nft_set_elem_expr) + size);
+		if (err < 0)
+			goto err_parse_key_end;
 	}
 
 	if (nla[NFTA_SET_ELEM_OBJREF] != NULL) {
-		if (!(set->flags & NFT_SET_OBJECT)) {
-			err = -EINVAL;
-			goto err_parse_key_end;
-		}
 		obj = nft_obj_lookup(ctx->net, ctx->table,
 				     nla[NFTA_SET_ELEM_OBJREF],
 				     set->objtype, genmask);
@@ -5878,7 +5938,9 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 			err = PTR_ERR(obj);
 			goto err_parse_key_end;
 		}
-		nft_set_ext_add(&tmpl, NFT_SET_EXT_OBJREF);
+		err = nft_set_ext_add(&tmpl, NFT_SET_EXT_OBJREF);
+		if (err < 0)
+			goto err_parse_key_end;
 	}
 
 	if (nla[NFTA_SET_ELEM_DATA] != NULL) {
@@ -5912,7 +5974,9 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 							  NFT_VALIDATE_NEED);
 		}
 
-		nft_set_ext_add_length(&tmpl, NFT_SET_EXT_DATA, desc.len);
+		err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_DATA, desc.len);
+		if (err < 0)
+			goto err_parse_data;
 	}
 
 	/* The full maximum length of userdata can exceed the maximum
@@ -5922,9 +5986,12 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	ulen = 0;
 	if (nla[NFTA_SET_ELEM_USERDATA] != NULL) {
 		ulen = nla_len(nla[NFTA_SET_ELEM_USERDATA]);
-		if (ulen > 0)
-			nft_set_ext_add_length(&tmpl, NFT_SET_EXT_USERDATA,
-					       ulen);
+		if (ulen > 0) {
+			err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_USERDATA,
+						     ulen);
+			if (err < 0)
+				goto err_parse_data;
+		}
 	}
 
 	err = -ENOMEM;
@@ -6148,10 +6215,16 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
 	if (!nla[NFTA_SET_ELEM_KEY] && !(flags & NFT_SET_ELEM_CATCHALL))
 		return -EINVAL;
 
+	if (!nft_setelem_valid_key_end(set, nla, flags))
+		return -EINVAL;
+
 	nft_set_ext_prepare(&tmpl);
 
-	if (flags != 0)
-		nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS);
+	if (flags != 0) {
+		err = nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS);
+		if (err < 0)
+			return err;
+	}
 
 	if (nla[NFTA_SET_ELEM_KEY]) {
 		err = nft_setelem_parse_key(ctx, set, &elem.key.val,
@@ -6159,16 +6232,20 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
 		if (err < 0)
 			return err;
 
-		nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen);
+		err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen);
+		if (err < 0)
+			goto fail_elem;
 	}
 
 	if (nla[NFTA_SET_ELEM_KEY_END]) {
 		err = nft_setelem_parse_key(ctx, set, &elem.key_end.val,
 					    nla[NFTA_SET_ELEM_KEY_END]);
 		if (err < 0)
-			return err;
+			goto fail_elem;
 
-		nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen);
+		err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen);
+		if (err < 0)
+			goto fail_elem_key_end;
 	}
 
 	err = -ENOMEM;
@@ -6176,7 +6253,7 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
 				      elem.key_end.val.data, NULL, 0, 0,
 				      GFP_KERNEL);
 	if (elem.priv == NULL)
-		goto fail_elem;
+		goto fail_elem_key_end;
 
 	ext = nft_set_elem_ext(set, elem.priv);
 	if (flags)
@@ -6200,6 +6277,8 @@ fail_ops:
 	kfree(trans);
 fail_trans:
 	kfree(elem.priv);
+fail_elem_key_end:
+	nft_data_release(&elem.key_end.val, NFT_DATA_VALUE);
 fail_elem:
 	nft_data_release(&elem.key.val, NFT_DATA_VALUE);
 	return err;
@@ -6751,7 +6830,7 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb)
 
 	rcu_read_lock();
 	nft_net = nft_pernet(net);
-	cb->seq = nft_net->base_seq;
+	cb->seq = READ_ONCE(nft_net->base_seq);
 
 	list_for_each_entry_rcu(table, &nft_net->tables, list) {
 		if (family != NFPROTO_UNSPEC && family != table->family)
@@ -7683,7 +7762,7 @@ static int nf_tables_dump_flowtable(struct sk_buff *skb,
 
 	rcu_read_lock();
 	nft_net = nft_pernet(net);
-	cb->seq = nft_net->base_seq;
+	cb->seq = READ_ONCE(nft_net->base_seq);
 
 	list_for_each_entry_rcu(table, &nft_net->tables, list) {
 		if (family != NFPROTO_UNSPEC && family != table->family)
@@ -8567,6 +8646,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 	struct nft_trans_elem *te;
 	struct nft_chain *chain;
 	struct nft_table *table;
+	unsigned int base_seq;
 	LIST_HEAD(adl);
 	int err;
 
@@ -8616,9 +8696,12 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 	 * Bump generation counter, invalidate any dump in progress.
 	 * Cannot fail after this point.
 	 */
-	while (++nft_net->base_seq == 0)
+	base_seq = READ_ONCE(nft_net->base_seq);
+	while (++base_seq == 0)
 		;
 
+	WRITE_ONCE(nft_net->base_seq, base_seq);
+
 	/* step 3. Start new generation, rules_gen_X now in use. */
 	net->nft.gencursor = nft_gencursor_next(net);
 
@@ -9412,7 +9495,7 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
 						 tb[NFTA_VERDICT_CHAIN],
 						 genmask);
 		} else if (tb[NFTA_VERDICT_CHAIN_ID]) {
-			chain = nft_chain_lookup_byid(ctx->net,
+			chain = nft_chain_lookup_byid(ctx->net, ctx->table,
 						      tb[NFTA_VERDICT_CHAIN_ID]);
 			if (IS_ERR(chain))
 				return PTR_ERR(chain);
@@ -9424,6 +9507,11 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
 			return PTR_ERR(chain);
 		if (nft_is_base_chain(chain))
 			return -EOPNOTSUPP;
+		if (nft_chain_is_bound(chain))
+			return -EINVAL;
+		if (desc->flags & NFT_DATA_DESC_SETELEM &&
+		    chain->flags & NFT_CHAIN_BINDING)
+			return -EINVAL;
 
 		chain->use++;
 		data->verdict.chain = chain;
@@ -9431,7 +9519,7 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
 	}
 
 	desc->len = sizeof(data->verdict);
-	desc->type = NFT_DATA_VERDICT;
+
 	return 0;
 }
 
@@ -9484,20 +9572,25 @@ nla_put_failure:
 }
 
 static int nft_value_init(const struct nft_ctx *ctx,
-			  struct nft_data *data, unsigned int size,
-			  struct nft_data_desc *desc, const struct nlattr *nla)
+			  struct nft_data *data, struct nft_data_desc *desc,
+			  const struct nlattr *nla)
 {
 	unsigned int len;
 
 	len = nla_len(nla);
 	if (len == 0)
 		return -EINVAL;
-	if (len > size)
+	if (len > desc->size)
 		return -EOVERFLOW;
+	if (desc->len) {
+		if (len != desc->len)
+			return -EINVAL;
+	} else {
+		desc->len = len;
+	}
 
 	nla_memcpy(data->data, nla, len);
-	desc->type = NFT_DATA_VALUE;
-	desc->len  = len;
+
 	return 0;
 }
 
@@ -9517,7 +9610,6 @@ static const struct nla_policy nft_data_policy[NFTA_DATA_MAX + 1] = {
  *
  *	@ctx: context of the expression using the data
  *	@data: destination struct nft_data
- *	@size: maximum data length
  *	@desc: data description
  *	@nla: netlink attribute containing data
  *
@@ -9527,24 +9619,35 @@ static const struct nla_policy nft_data_policy[NFTA_DATA_MAX + 1] = {
  *	The caller can indicate that it only wants to accept data of type
  *	NFT_DATA_VALUE by passing NULL for the ctx argument.
  */
-int nft_data_init(const struct nft_ctx *ctx,
-		  struct nft_data *data, unsigned int size,
+int nft_data_init(const struct nft_ctx *ctx, struct nft_data *data,
 		  struct nft_data_desc *desc, const struct nlattr *nla)
 {
 	struct nlattr *tb[NFTA_DATA_MAX + 1];
 	int err;
 
+	if (WARN_ON_ONCE(!desc->size))
+		return -EINVAL;
+
 	err = nla_parse_nested_deprecated(tb, NFTA_DATA_MAX, nla,
 					  nft_data_policy, NULL);
 	if (err < 0)
 		return err;
 
-	if (tb[NFTA_DATA_VALUE])
-		return nft_value_init(ctx, data, size, desc,
-				      tb[NFTA_DATA_VALUE]);
-	if (tb[NFTA_DATA_VERDICT] && ctx != NULL)
-		return nft_verdict_init(ctx, data, desc, tb[NFTA_DATA_VERDICT]);
-	return -EINVAL;
+	if (tb[NFTA_DATA_VALUE]) {
+		if (desc->type != NFT_DATA_VALUE)
+			return -EINVAL;
+
+		err = nft_value_init(ctx, data, desc, tb[NFTA_DATA_VALUE]);
+	} else if (tb[NFTA_DATA_VERDICT] && ctx != NULL) {
+		if (desc->type != NFT_DATA_VERDICT)
+			return -EINVAL;
+
+		err = nft_verdict_init(ctx, data, desc, tb[NFTA_DATA_VERDICT]);
+	} else {
+		err = -EINVAL;
+	}
+
+	return err;
 }
 EXPORT_SYMBOL_GPL(nft_data_init);
 
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index 907e848dbc17..2ab4216d2a90 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -67,6 +67,50 @@ static void nft_cmp_fast_eval(const struct nft_expr *expr,
 	regs->verdict.code = NFT_BREAK;
 }
 
+static void nft_cmp16_fast_eval(const struct nft_expr *expr,
+				struct nft_regs *regs)
+{
+	const struct nft_cmp16_fast_expr *priv = nft_expr_priv(expr);
+	const u64 *reg_data = (const u64 *)&regs->data[priv->sreg];
+	const u64 *mask = (const u64 *)&priv->mask;
+	const u64 *data = (const u64 *)&priv->data;
+
+	if (((reg_data[0] & mask[0]) == data[0] &&
+	    ((reg_data[1] & mask[1]) == data[1])) ^ priv->inv)
+		return;
+	regs->verdict.code = NFT_BREAK;
+}
+
+static noinline void __nft_trace_verdict(struct nft_traceinfo *info,
+					 const struct nft_chain *chain,
+					 const struct nft_regs *regs)
+{
+	enum nft_trace_types type;
+
+	switch (regs->verdict.code) {
+	case NFT_CONTINUE:
+	case NFT_RETURN:
+		type = NFT_TRACETYPE_RETURN;
+		break;
+	default:
+		type = NFT_TRACETYPE_RULE;
+		break;
+	}
+
+	__nft_trace_packet(info, chain, type);
+}
+
+static inline void nft_trace_verdict(struct nft_traceinfo *info,
+				     const struct nft_chain *chain,
+				     const struct nft_rule *rule,
+				     const struct nft_regs *regs)
+{
+	if (static_branch_unlikely(&nft_trace_enabled)) {
+		info->rule = rule;
+		__nft_trace_verdict(info, chain, regs);
+	}
+}
+
 static bool nft_payload_fast_eval(const struct nft_expr *expr,
 				  struct nft_regs *regs,
 				  const struct nft_pktinfo *pkt)
@@ -79,7 +123,7 @@ static bool nft_payload_fast_eval(const struct nft_expr *expr,
 	if (priv->base == NFT_PAYLOAD_NETWORK_HEADER)
 		ptr = skb_network_header(skb);
 	else {
-		if (!pkt->tprot_set)
+		if (!(pkt->flags & NFT_PKTINFO_L4PROTO))
 			return false;
 		ptr = skb_network_header(skb) + nft_thoff(pkt);
 	}
@@ -185,6 +229,8 @@ next_rule:
 		nft_rule_for_each_expr(expr, last, rule) {
 			if (expr->ops == &nft_cmp_fast_ops)
 				nft_cmp_fast_eval(expr, &regs);
+			else if (expr->ops == &nft_cmp16_fast_ops)
+				nft_cmp16_fast_eval(expr, &regs);
 			else if (expr->ops == &nft_bitwise_fast_ops)
 				nft_bitwise_fast_eval(expr, &regs);
 			else if (expr->ops != &nft_payload_fast_ops ||
@@ -207,13 +253,13 @@ next_rule:
 		break;
 	}
 
+	nft_trace_verdict(&info, chain, rule, &regs);
+
 	switch (regs.verdict.code & NF_VERDICT_MASK) {
 	case NF_ACCEPT:
 	case NF_DROP:
 	case NF_QUEUE:
 	case NF_STOLEN:
-		nft_trace_packet(&info, chain, rule,
-				 NFT_TRACETYPE_RULE);
 		return regs.verdict.code;
 	}
 
@@ -226,15 +272,10 @@ next_rule:
 		stackptr++;
 		fallthrough;
 	case NFT_GOTO:
-		nft_trace_packet(&info, chain, rule,
-				 NFT_TRACETYPE_RULE);
-
 		chain = regs.verdict.chain;
 		goto do_chain;
 	case NFT_CONTINUE:
 	case NFT_RETURN:
-		nft_trace_packet(&info, chain, rule,
-				 NFT_TRACETYPE_RETURN);
 		break;
 	default:
 		WARN_ON(1);
diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c
index e4fe2f0780eb..84a7dea46efa 100644
--- a/net/netfilter/nf_tables_trace.c
+++ b/net/netfilter/nf_tables_trace.c
@@ -113,13 +113,13 @@ static int nf_trace_fill_pkt_info(struct sk_buff *nlskb,
 	int off = skb_network_offset(skb);
 	unsigned int len, nh_end;
 
-	nh_end = pkt->tprot_set ? nft_thoff(pkt) : skb->len;
+	nh_end = pkt->flags & NFT_PKTINFO_L4PROTO ? nft_thoff(pkt) : skb->len;
 	len = min_t(unsigned int, nh_end - skb_network_offset(skb),
 		    NFT_TRACETYPE_NETWORK_HSIZE);
 	if (trace_fill_header(nlskb, NFTA_TRACE_NETWORK_HEADER, skb, off, len))
 		return -1;
 
-	if (pkt->tprot_set) {
+	if (pkt->flags & NFT_PKTINFO_L4PROTO) {
 		len = min_t(unsigned int, skb->len - nft_thoff(pkt),
 			    NFT_TRACETYPE_TRANSPORT_HSIZE);
 		if (trace_fill_header(nlskb, NFTA_TRACE_TRANSPORT_HEADER, skb,
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 8787d0613ad8..5329ebf19a18 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -836,11 +836,16 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum)
 }
 
 static int
-nfqnl_mangle(void *data, int data_len, struct nf_queue_entry *e, int diff)
+nfqnl_mangle(void *data, unsigned int data_len, struct nf_queue_entry *e, int diff)
 {
 	struct sk_buff *nskb;
 
 	if (diff < 0) {
+		unsigned int min_len = skb_transport_offset(e->skb);
+
+		if (data_len < min_len)
+			return -EINVAL;
+
 		if (pskb_trim(e->skb, data_len))
 			return -ENOMEM;
 	} else if (diff > 0) {
diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c
index 47b0dba95054..d6ab7aa14adc 100644
--- a/net/netfilter/nft_bitwise.c
+++ b/net/netfilter/nft_bitwise.c
@@ -93,7 +93,16 @@ static const struct nla_policy nft_bitwise_policy[NFTA_BITWISE_MAX + 1] = {
 static int nft_bitwise_init_bool(struct nft_bitwise *priv,
 				 const struct nlattr *const tb[])
 {
-	struct nft_data_desc mask, xor;
+	struct nft_data_desc mask = {
+		.type	= NFT_DATA_VALUE,
+		.size	= sizeof(priv->mask),
+		.len	= priv->len,
+	};
+	struct nft_data_desc xor = {
+		.type	= NFT_DATA_VALUE,
+		.size	= sizeof(priv->xor),
+		.len	= priv->len,
+	};
 	int err;
 
 	if (tb[NFTA_BITWISE_DATA])
@@ -103,36 +112,30 @@ static int nft_bitwise_init_bool(struct nft_bitwise *priv,
 	    !tb[NFTA_BITWISE_XOR])
 		return -EINVAL;
 
-	err = nft_data_init(NULL, &priv->mask, sizeof(priv->mask), &mask,
-			    tb[NFTA_BITWISE_MASK]);
+	err = nft_data_init(NULL, &priv->mask, &mask, tb[NFTA_BITWISE_MASK]);
 	if (err < 0)
 		return err;
-	if (mask.type != NFT_DATA_VALUE || mask.len != priv->len) {
-		err = -EINVAL;
-		goto err1;
-	}
 
-	err = nft_data_init(NULL, &priv->xor, sizeof(priv->xor), &xor,
-			    tb[NFTA_BITWISE_XOR]);
+	err = nft_data_init(NULL, &priv->xor, &xor, tb[NFTA_BITWISE_XOR]);
 	if (err < 0)
-		goto err1;
-	if (xor.type != NFT_DATA_VALUE || xor.len != priv->len) {
-		err = -EINVAL;
-		goto err2;
-	}
+		goto err_xor_err;
 
 	return 0;
-err2:
-	nft_data_release(&priv->xor, xor.type);
-err1:
+
+err_xor_err:
 	nft_data_release(&priv->mask, mask.type);
+
 	return err;
 }
 
 static int nft_bitwise_init_shift(struct nft_bitwise *priv,
 				  const struct nlattr *const tb[])
 {
-	struct nft_data_desc d;
+	struct nft_data_desc desc = {
+		.type	= NFT_DATA_VALUE,
+		.size	= sizeof(priv->data),
+		.len	= sizeof(u32),
+	};
 	int err;
 
 	if (tb[NFTA_BITWISE_MASK] ||
@@ -142,13 +145,12 @@ static int nft_bitwise_init_shift(struct nft_bitwise *priv,
 	if (!tb[NFTA_BITWISE_DATA])
 		return -EINVAL;
 
-	err = nft_data_init(NULL, &priv->data, sizeof(priv->data), &d,
-			    tb[NFTA_BITWISE_DATA]);
+	err = nft_data_init(NULL, &priv->data, &desc, tb[NFTA_BITWISE_DATA]);
 	if (err < 0)
 		return err;
-	if (d.type != NFT_DATA_VALUE || d.len != sizeof(u32) ||
-	    priv->data.data[0] >= BITS_PER_TYPE(u32)) {
-		nft_data_release(&priv->data, d.type);
+
+	if (priv->data.data[0] >= BITS_PER_TYPE(u32)) {
+		nft_data_release(&priv->data, desc.type);
 		return -EINVAL;
 	}
 
@@ -290,22 +292,21 @@ static const struct nft_expr_ops nft_bitwise_ops = {
 static int
 nft_bitwise_extract_u32_data(const struct nlattr * const tb, u32 *out)
 {
-	struct nft_data_desc desc;
 	struct nft_data data;
-	int err = 0;
+	struct nft_data_desc desc = {
+		.type	= NFT_DATA_VALUE,
+		.size	= sizeof(data),
+		.len	= sizeof(u32),
+	};
+	int err;
 
-	err = nft_data_init(NULL, &data, sizeof(data), &desc, tb);
+	err = nft_data_init(NULL, &data, &desc, tb);
 	if (err < 0)
 		return err;
 
-	if (desc.type != NFT_DATA_VALUE || desc.len != sizeof(u32)) {
-		err = -EINVAL;
-		goto err;
-	}
 	*out = data.data[0];
-err:
-	nft_data_release(&data, desc.type);
-	return err;
+
+	return 0;
 }
 
 static int nft_bitwise_fast_init(const struct nft_ctx *ctx,
diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c
index 47b6d05f1ae6..461763a571f2 100644
--- a/net/netfilter/nft_cmp.c
+++ b/net/netfilter/nft_cmp.c
@@ -73,20 +73,16 @@ static int nft_cmp_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 			const struct nlattr * const tb[])
 {
 	struct nft_cmp_expr *priv = nft_expr_priv(expr);
-	struct nft_data_desc desc;
+	struct nft_data_desc desc = {
+		.type	= NFT_DATA_VALUE,
+		.size	= sizeof(priv->data),
+	};
 	int err;
 
-	err = nft_data_init(NULL, &priv->data, sizeof(priv->data), &desc,
-			    tb[NFTA_CMP_DATA]);
+	err = nft_data_init(NULL, &priv->data, &desc, tb[NFTA_CMP_DATA]);
 	if (err < 0)
 		return err;
 
-	if (desc.type != NFT_DATA_VALUE) {
-		err = -EINVAL;
-		nft_data_release(&priv->data, desc.type);
-		return err;
-	}
-
 	err = nft_parse_register_load(tb[NFTA_CMP_SREG], &priv->sreg, desc.len);
 	if (err < 0)
 		return err;
@@ -201,12 +197,14 @@ static int nft_cmp_fast_init(const struct nft_ctx *ctx,
 			     const struct nlattr * const tb[])
 {
 	struct nft_cmp_fast_expr *priv = nft_expr_priv(expr);
-	struct nft_data_desc desc;
 	struct nft_data data;
+	struct nft_data_desc desc = {
+		.type	= NFT_DATA_VALUE,
+		.size	= sizeof(data),
+	};
 	int err;
 
-	err = nft_data_init(NULL, &data, sizeof(data), &desc,
-			    tb[NFTA_CMP_DATA]);
+	err = nft_data_init(NULL, &data, &desc, tb[NFTA_CMP_DATA]);
 	if (err < 0)
 		return err;
 
@@ -272,12 +270,108 @@ const struct nft_expr_ops nft_cmp_fast_ops = {
 	.offload	= nft_cmp_fast_offload,
 };
 
+static u32 nft_cmp_mask(u32 bitlen)
+{
+	return (__force u32)cpu_to_le32(~0U >> (sizeof(u32) * BITS_PER_BYTE - bitlen));
+}
+
+static void nft_cmp16_fast_mask(struct nft_data *data, unsigned int bitlen)
+{
+	int len = bitlen / BITS_PER_BYTE;
+	int i, words = len / sizeof(u32);
+
+	for (i = 0; i < words; i++) {
+		data->data[i] = 0xffffffff;
+		bitlen -= sizeof(u32) * BITS_PER_BYTE;
+	}
+
+	if (len % sizeof(u32))
+		data->data[i++] = nft_cmp_mask(bitlen);
+
+	for (; i < 4; i++)
+		data->data[i] = 0;
+}
+
+static int nft_cmp16_fast_init(const struct nft_ctx *ctx,
+			       const struct nft_expr *expr,
+			       const struct nlattr * const tb[])
+{
+	struct nft_cmp16_fast_expr *priv = nft_expr_priv(expr);
+	struct nft_data_desc desc = {
+		.type	= NFT_DATA_VALUE,
+		.size	= sizeof(priv->data),
+	};
+	int err;
+
+	err = nft_data_init(NULL, &priv->data, &desc, tb[NFTA_CMP_DATA]);
+	if (err < 0)
+		return err;
+
+	err = nft_parse_register_load(tb[NFTA_CMP_SREG], &priv->sreg, desc.len);
+	if (err < 0)
+		return err;
+
+	nft_cmp16_fast_mask(&priv->mask, desc.len * BITS_PER_BYTE);
+	priv->inv = ntohl(nla_get_be32(tb[NFTA_CMP_OP])) != NFT_CMP_EQ;
+	priv->len = desc.len;
+
+	return 0;
+}
+
+static int nft_cmp16_fast_offload(struct nft_offload_ctx *ctx,
+				  struct nft_flow_rule *flow,
+				  const struct nft_expr *expr)
+{
+	const struct nft_cmp16_fast_expr *priv = nft_expr_priv(expr);
+	struct nft_cmp_expr cmp = {
+		.data	= priv->data,
+		.sreg	= priv->sreg,
+		.len	= priv->len,
+		.op	= priv->inv ? NFT_CMP_NEQ : NFT_CMP_EQ,
+	};
+
+	return __nft_cmp_offload(ctx, flow, &cmp);
+}
+
+static int nft_cmp16_fast_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_cmp16_fast_expr *priv = nft_expr_priv(expr);
+	enum nft_cmp_ops op = priv->inv ? NFT_CMP_NEQ : NFT_CMP_EQ;
+
+	if (nft_dump_register(skb, NFTA_CMP_SREG, priv->sreg))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_CMP_OP, htonl(op)))
+		goto nla_put_failure;
+
+	if (nft_data_dump(skb, NFTA_CMP_DATA, &priv->data,
+			  NFT_DATA_VALUE, priv->len) < 0)
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+
+const struct nft_expr_ops nft_cmp16_fast_ops = {
+	.type		= &nft_cmp_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_cmp16_fast_expr)),
+	.eval		= NULL,	/* inlined */
+	.init		= nft_cmp16_fast_init,
+	.dump		= nft_cmp16_fast_dump,
+	.offload	= nft_cmp16_fast_offload,
+};
+
 static const struct nft_expr_ops *
 nft_cmp_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[])
 {
-	struct nft_data_desc desc;
 	struct nft_data data;
+	struct nft_data_desc desc = {
+		.type	= NFT_DATA_VALUE,
+		.size	= sizeof(data),
+	};
 	enum nft_cmp_ops op;
+	u8 sreg;
 	int err;
 
 	if (tb[NFTA_CMP_SREG] == NULL ||
@@ -298,21 +392,21 @@ nft_cmp_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[])
 		return ERR_PTR(-EINVAL);
 	}
 
-	err = nft_data_init(NULL, &data, sizeof(data), &desc,
-			    tb[NFTA_CMP_DATA]);
+	err = nft_data_init(NULL, &data, &desc, tb[NFTA_CMP_DATA]);
 	if (err < 0)
 		return ERR_PTR(err);
 
-	if (desc.type != NFT_DATA_VALUE)
-		goto err1;
-
-	if (desc.len <= sizeof(u32) && (op == NFT_CMP_EQ || op == NFT_CMP_NEQ))
-		return &nft_cmp_fast_ops;
+	sreg = ntohl(nla_get_be32(tb[NFTA_CMP_SREG]));
 
+	if (op == NFT_CMP_EQ || op == NFT_CMP_NEQ) {
+		if (desc.len <= sizeof(u32))
+			return &nft_cmp_fast_ops;
+		else if (desc.len <= sizeof(data) &&
+			 ((sreg >= NFT_REG_1 && sreg <= NFT_REG_4) ||
+			  (sreg >= NFT_REG32_00 && sreg <= NFT_REG32_12 && sreg % 2 == 0)))
+			return &nft_cmp16_fast_ops;
+	}
 	return &nft_cmp_ops;
-err1:
-	nft_data_release(&data, desc.type);
-	return ERR_PTR(-EINVAL);
 }
 
 struct nft_expr_type nft_cmp_type __read_mostly = {
diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c
index dbe1f2e7dd9e..9e927ab4df15 100644
--- a/net/netfilter/nft_exthdr.c
+++ b/net/netfilter/nft_exthdr.c
@@ -167,7 +167,7 @@ nft_tcp_header_pointer(const struct nft_pktinfo *pkt,
 {
 	struct tcphdr *tcph;
 
-	if (pkt->tprot != IPPROTO_TCP)
+	if (pkt->tprot != IPPROTO_TCP || pkt->fragoff)
 		return NULL;
 
 	tcph = skb_header_pointer(pkt->skb, nft_thoff(pkt), sizeof(*tcph), buffer);
diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c
index d0f67d325bdf..fcdbc5ed3f36 100644
--- a/net/netfilter/nft_immediate.c
+++ b/net/netfilter/nft_immediate.c
@@ -29,20 +29,36 @@ static const struct nla_policy nft_immediate_policy[NFTA_IMMEDIATE_MAX + 1] = {
 	[NFTA_IMMEDIATE_DATA]	= { .type = NLA_NESTED },
 };
 
+static enum nft_data_types nft_reg_to_type(const struct nlattr *nla)
+{
+	enum nft_data_types type;
+	u8 reg;
+
+	reg = ntohl(nla_get_be32(nla));
+	if (reg == NFT_REG_VERDICT)
+		type = NFT_DATA_VERDICT;
+	else
+		type = NFT_DATA_VALUE;
+
+	return type;
+}
+
 static int nft_immediate_init(const struct nft_ctx *ctx,
 			      const struct nft_expr *expr,
 			      const struct nlattr * const tb[])
 {
 	struct nft_immediate_expr *priv = nft_expr_priv(expr);
-	struct nft_data_desc desc;
+	struct nft_data_desc desc = {
+		.size	= sizeof(priv->data),
+	};
 	int err;
 
 	if (tb[NFTA_IMMEDIATE_DREG] == NULL ||
 	    tb[NFTA_IMMEDIATE_DATA] == NULL)
 		return -EINVAL;
 
-	err = nft_data_init(ctx, &priv->data, sizeof(priv->data), &desc,
-			    tb[NFTA_IMMEDIATE_DATA]);
+	desc.type = nft_reg_to_type(tb[NFTA_IMMEDIATE_DREG]);
+	err = nft_data_init(ctx, &priv->data, &desc, tb[NFTA_IMMEDIATE_DATA]);
 	if (err < 0)
 		return err;
 
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 44d9b38e5f90..14412f69a34e 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -321,7 +321,7 @@ void nft_meta_get_eval(const struct nft_expr *expr,
 		nft_reg_store8(dest, nft_pf(pkt));
 		break;
 	case NFT_META_L4PROTO:
-		if (!pkt->tprot_set)
+		if (!(pkt->flags & NFT_PKTINFO_L4PROTO))
 			goto err;
 		nft_reg_store8(dest, pkt->tprot);
 		break;
diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c
index d82677e83400..720dc9fba6d4 100644
--- a/net/netfilter/nft_osf.c
+++ b/net/netfilter/nft_osf.c
@@ -115,9 +115,21 @@ static int nft_osf_validate(const struct nft_ctx *ctx,
 			    const struct nft_expr *expr,
 			    const struct nft_data **data)
 {
-	return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_LOCAL_IN) |
-						    (1 << NF_INET_PRE_ROUTING) |
-						    (1 << NF_INET_FORWARD));
+	unsigned int hooks;
+
+	switch (ctx->family) {
+	case NFPROTO_IPV4:
+	case NFPROTO_IPV6:
+	case NFPROTO_INET:
+		hooks = (1 << NF_INET_LOCAL_IN) |
+			(1 << NF_INET_PRE_ROUTING) |
+			(1 << NF_INET_FORWARD);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return nft_chain_validate_hooks(ctx->chain, hooks);
 }
 
 static struct nft_expr_type nft_osf_type;
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index 132875cd7fff..da652c21368e 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -22,6 +22,7 @@
 #include <linux/icmpv6.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
+#include <linux/ip.h>
 #include <net/sctp/checksum.h>
 
 static bool nft_payload_rebuild_vlan_hdr(const struct sk_buff *skb, int mac_off,
@@ -79,6 +80,45 @@ nft_payload_copy_vlan(u32 *d, const struct sk_buff *skb, u8 offset, u8 len)
 	return skb_copy_bits(skb, offset + mac_off, dst_u8, len) == 0;
 }
 
+static int __nft_payload_inner_offset(struct nft_pktinfo *pkt)
+{
+	unsigned int thoff = nft_thoff(pkt);
+
+	if (!(pkt->flags & NFT_PKTINFO_L4PROTO) || pkt->fragoff)
+		return -1;
+
+	switch (pkt->tprot) {
+	case IPPROTO_UDP:
+		pkt->inneroff = thoff + sizeof(struct udphdr);
+		break;
+	case IPPROTO_TCP: {
+		struct tcphdr *th, _tcph;
+
+		th = skb_header_pointer(pkt->skb, thoff, sizeof(_tcph), &_tcph);
+		if (!th)
+			return -1;
+
+		pkt->inneroff = thoff + __tcp_hdrlen(th);
+		}
+		break;
+	default:
+		return -1;
+	}
+
+	pkt->flags |= NFT_PKTINFO_INNER;
+
+	return 0;
+}
+
+static int nft_payload_inner_offset(const struct nft_pktinfo *pkt)
+{
+	if (!(pkt->flags & NFT_PKTINFO_INNER) &&
+	    __nft_payload_inner_offset((struct nft_pktinfo *)pkt) < 0)
+		return -1;
+
+	return pkt->inneroff;
+}
+
 void nft_payload_eval(const struct nft_expr *expr,
 		      struct nft_regs *regs,
 		      const struct nft_pktinfo *pkt)
@@ -108,10 +148,15 @@ void nft_payload_eval(const struct nft_expr *expr,
 		offset = skb_network_offset(skb);
 		break;
 	case NFT_PAYLOAD_TRANSPORT_HEADER:
-		if (!pkt->tprot_set)
+		if (!(pkt->flags & NFT_PKTINFO_L4PROTO) || pkt->fragoff)
 			goto err;
 		offset = nft_thoff(pkt);
 		break;
+	case NFT_PAYLOAD_INNER_HEADER:
+		offset = nft_payload_inner_offset(pkt);
+		if (offset < 0)
+			goto err;
+		break;
 	default:
 		BUG();
 	}
@@ -613,10 +658,15 @@ static void nft_payload_set_eval(const struct nft_expr *expr,
 		offset = skb_network_offset(skb);
 		break;
 	case NFT_PAYLOAD_TRANSPORT_HEADER:
-		if (!pkt->tprot_set)
+		if (!(pkt->flags & NFT_PKTINFO_L4PROTO) || pkt->fragoff)
 			goto err;
 		offset = nft_thoff(pkt);
 		break;
+	case NFT_PAYLOAD_INNER_HEADER:
+		offset = nft_payload_inner_offset(pkt);
+		if (offset < 0)
+			goto err;
+		break;
 	default:
 		BUG();
 	}
@@ -625,7 +675,8 @@ static void nft_payload_set_eval(const struct nft_expr *expr,
 	offset += priv->offset;
 
 	if ((priv->csum_type == NFT_PAYLOAD_CSUM_INET || priv->csum_flags) &&
-	    (priv->base != NFT_PAYLOAD_TRANSPORT_HEADER ||
+	    ((priv->base != NFT_PAYLOAD_TRANSPORT_HEADER &&
+	      priv->base != NFT_PAYLOAD_INNER_HEADER) ||
 	     skb->ip_summed != CHECKSUM_PARTIAL)) {
 		fsum = skb_checksum(skb, offset, priv->len, 0);
 		tsum = csum_partial(src, priv->len, 0);
@@ -646,7 +697,8 @@ static void nft_payload_set_eval(const struct nft_expr *expr,
 	if (priv->csum_type == NFT_PAYLOAD_CSUM_SCTP &&
 	    pkt->tprot == IPPROTO_SCTP &&
 	    skb->ip_summed != CHECKSUM_PARTIAL) {
-		if (nft_payload_csum_sctp(skb, nft_thoff(pkt)))
+		if (pkt->fragoff == 0 &&
+		    nft_payload_csum_sctp(skb, nft_thoff(pkt)))
 			goto err;
 	}
 
@@ -660,17 +712,23 @@ static int nft_payload_set_init(const struct nft_ctx *ctx,
 				const struct nlattr * const tb[])
 {
 	struct nft_payload_set *priv = nft_expr_priv(expr);
+	u32 csum_offset, csum_type = NFT_PAYLOAD_CSUM_NONE;
+	int err;
 
 	priv->base        = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE]));
 	priv->offset      = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET]));
 	priv->len         = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN]));
 
 	if (tb[NFTA_PAYLOAD_CSUM_TYPE])
-		priv->csum_type =
-			ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_TYPE]));
-	if (tb[NFTA_PAYLOAD_CSUM_OFFSET])
-		priv->csum_offset =
-			ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_OFFSET]));
+		csum_type = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_TYPE]));
+	if (tb[NFTA_PAYLOAD_CSUM_OFFSET]) {
+		err = nft_parse_u32_check(tb[NFTA_PAYLOAD_CSUM_OFFSET], U8_MAX,
+					  &csum_offset);
+		if (err < 0)
+			return err;
+
+		priv->csum_offset = csum_offset;
+	}
 	if (tb[NFTA_PAYLOAD_CSUM_FLAGS]) {
 		u32 flags;
 
@@ -681,7 +739,7 @@ static int nft_payload_set_init(const struct nft_ctx *ctx,
 		priv->csum_flags = flags;
 	}
 
-	switch (priv->csum_type) {
+	switch (csum_type) {
 	case NFT_PAYLOAD_CSUM_NONE:
 	case NFT_PAYLOAD_CSUM_INET:
 		break;
@@ -695,6 +753,7 @@ static int nft_payload_set_init(const struct nft_ctx *ctx,
 	default:
 		return -EOPNOTSUPP;
 	}
+	priv->csum_type = csum_type;
 
 	return nft_parse_register_load(tb[NFTA_PAYLOAD_SREG], &priv->sreg,
 				       priv->len);
@@ -733,6 +792,7 @@ nft_payload_select_ops(const struct nft_ctx *ctx,
 {
 	enum nft_payload_bases base;
 	unsigned int offset, len;
+	int err;
 
 	if (tb[NFTA_PAYLOAD_BASE] == NULL ||
 	    tb[NFTA_PAYLOAD_OFFSET] == NULL ||
@@ -744,6 +804,7 @@ nft_payload_select_ops(const struct nft_ctx *ctx,
 	case NFT_PAYLOAD_LL_HEADER:
 	case NFT_PAYLOAD_NETWORK_HEADER:
 	case NFT_PAYLOAD_TRANSPORT_HEADER:
+	case NFT_PAYLOAD_INNER_HEADER:
 		break;
 	default:
 		return ERR_PTR(-EOPNOTSUPP);
@@ -758,11 +819,16 @@ nft_payload_select_ops(const struct nft_ctx *ctx,
 	if (tb[NFTA_PAYLOAD_DREG] == NULL)
 		return ERR_PTR(-EINVAL);
 
-	offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET]));
-	len    = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN]));
+	err = nft_parse_u32_check(tb[NFTA_PAYLOAD_OFFSET], U8_MAX, &offset);
+	if (err < 0)
+		return ERR_PTR(err);
+
+	err = nft_parse_u32_check(tb[NFTA_PAYLOAD_LEN], U8_MAX, &len);
+	if (err < 0)
+		return ERR_PTR(err);
 
 	if (len <= 4 && is_power_of_2(len) && IS_ALIGNED(offset, len) &&
-	    base != NFT_PAYLOAD_LL_HEADER)
+	    base != NFT_PAYLOAD_LL_HEADER && base != NFT_PAYLOAD_INNER_HEADER)
 		return &nft_payload_fast_ops;
 	else
 		return &nft_payload_ops;
diff --git a/net/netfilter/nft_range.c b/net/netfilter/nft_range.c
index e4a1c44d7f51..e6bbe32c323d 100644
--- a/net/netfilter/nft_range.c
+++ b/net/netfilter/nft_range.c
@@ -51,7 +51,14 @@ static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr
 			const struct nlattr * const tb[])
 {
 	struct nft_range_expr *priv = nft_expr_priv(expr);
-	struct nft_data_desc desc_from, desc_to;
+	struct nft_data_desc desc_from = {
+		.type	= NFT_DATA_VALUE,
+		.size	= sizeof(priv->data_from),
+	};
+	struct nft_data_desc desc_to = {
+		.type	= NFT_DATA_VALUE,
+		.size	= sizeof(priv->data_to),
+	};
 	int err;
 	u32 op;
 
@@ -61,26 +68,16 @@ static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr
 	    !tb[NFTA_RANGE_TO_DATA])
 		return -EINVAL;
 
-	err = nft_data_init(NULL, &priv->data_from, sizeof(priv->data_from),
-			    &desc_from, tb[NFTA_RANGE_FROM_DATA]);
+	err = nft_data_init(NULL, &priv->data_from, &desc_from,
+			    tb[NFTA_RANGE_FROM_DATA]);
 	if (err < 0)
 		return err;
 
-	if (desc_from.type != NFT_DATA_VALUE) {
-		err = -EINVAL;
-		goto err1;
-	}
-
-	err = nft_data_init(NULL, &priv->data_to, sizeof(priv->data_to),
-			    &desc_to, tb[NFTA_RANGE_TO_DATA]);
+	err = nft_data_init(NULL, &priv->data_to, &desc_to,
+			    tb[NFTA_RANGE_TO_DATA]);
 	if (err < 0)
 		goto err1;
 
-	if (desc_to.type != NFT_DATA_VALUE) {
-		err = -EINVAL;
-		goto err2;
-	}
-
 	if (desc_from.len != desc_to.len) {
 		err = -EINVAL;
 		goto err2;
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index df40314de21f..76de6c8d9865 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -143,6 +143,7 @@ static bool nft_rhash_update(struct nft_set *set, const u32 *key,
 	/* Another cpu may race to insert the element with the same key */
 	if (prev) {
 		nft_set_elem_destroy(set, he, true);
+		atomic_dec(&set->nelems);
 		he = prev;
 	}
 
@@ -152,6 +153,7 @@ out:
 
 err2:
 	nft_set_elem_destroy(set, he, true);
+	atomic_dec(&set->nelems);
 err1:
 	return false;
 }
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index 2c8051d8cca6..4f9299b9dcdd 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -2125,6 +2125,32 @@ out_scratch:
 }
 
 /**
+ * nft_set_pipapo_match_destroy() - Destroy elements from key mapping array
+ * @set:	nftables API set representation
+ * @m:		matching data pointing to key mapping array
+ */
+static void nft_set_pipapo_match_destroy(const struct nft_set *set,
+					 struct nft_pipapo_match *m)
+{
+	struct nft_pipapo_field *f;
+	int i, r;
+
+	for (i = 0, f = m->f; i < m->field_count - 1; i++, f++)
+		;
+
+	for (r = 0; r < f->rules; r++) {
+		struct nft_pipapo_elem *e;
+
+		if (r < f->rules - 1 && f->mt[r + 1].e == f->mt[r].e)
+			continue;
+
+		e = f->mt[r].e;
+
+		nft_set_elem_destroy(set, e, true);
+	}
+}
+
+/**
  * nft_pipapo_destroy() - Free private data for set and all committed elements
  * @set:	nftables API set representation
  */
@@ -2132,26 +2158,13 @@ static void nft_pipapo_destroy(const struct nft_set *set)
 {
 	struct nft_pipapo *priv = nft_set_priv(set);
 	struct nft_pipapo_match *m;
-	struct nft_pipapo_field *f;
-	int i, r, cpu;
+	int cpu;
 
 	m = rcu_dereference_protected(priv->match, true);
 	if (m) {
 		rcu_barrier();
 
-		for (i = 0, f = m->f; i < m->field_count - 1; i++, f++)
-			;
-
-		for (r = 0; r < f->rules; r++) {
-			struct nft_pipapo_elem *e;
-
-			if (r < f->rules - 1 && f->mt[r + 1].e == f->mt[r].e)
-				continue;
-
-			e = f->mt[r].e;
-
-			nft_set_elem_destroy(set, e, true);
-		}
+		nft_set_pipapo_match_destroy(set, m);
 
 #ifdef NFT_PIPAPO_ALIGN
 		free_percpu(m->scratch_aligned);
@@ -2165,6 +2178,11 @@ static void nft_pipapo_destroy(const struct nft_set *set)
 	}
 
 	if (priv->clone) {
+		m = priv->clone;
+
+		if (priv->dirty)
+			nft_set_pipapo_match_destroy(set, m);
+
 #ifdef NFT_PIPAPO_ALIGN
 		free_percpu(priv->clone->scratch_aligned);
 #endif
diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c
index 3b27926d5382..2ee50996da8c 100644
--- a/net/netfilter/nft_tunnel.c
+++ b/net/netfilter/nft_tunnel.c
@@ -133,6 +133,7 @@ static const struct nft_expr_ops nft_tunnel_get_ops = {
 
 static struct nft_expr_type nft_tunnel_type __read_mostly = {
 	.name		= "tunnel",
+	.family		= NFPROTO_NETDEV,
 	.ops		= &nft_tunnel_get_ops,
 	.policy		= nft_tunnel_policy,
 	.maxattr	= NFTA_TUNNEL_MAX,
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 1afca2a6c2ac..57010927e20a 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -1174,13 +1174,17 @@ static int ctrl_dumppolicy_start(struct netlink_callback *cb)
 							     op.policy,
 							     op.maxattr);
 			if (err)
-				return err;
+				goto err_free_state;
 		}
 	}
 
 	if (!ctx->state)
 		return -ENODATA;
 	return 0;
+
+err_free_state:
+	netlink_policy_dump_free(ctx->state);
+	return err;
 }
 
 static void *ctrl_dumppolicy_prep(struct sk_buff *skb,
diff --git a/net/netlink/policy.c b/net/netlink/policy.c
index 8d7c900e27f4..87e3de0fde89 100644
--- a/net/netlink/policy.c
+++ b/net/netlink/policy.c
@@ -144,7 +144,7 @@ int netlink_policy_dump_add_policy(struct netlink_policy_dump_state **pstate,
 
 	err = add_policy(&state, policy, maxtype);
 	if (err)
-		return err;
+		goto err_try_undo;
 
 	for (policy_idx = 0;
 	     policy_idx < state->n_alloc && state->policies[policy_idx].policy;
@@ -164,7 +164,7 @@ int netlink_policy_dump_add_policy(struct netlink_policy_dump_state **pstate,
 						 policy[type].nested_policy,
 						 policy[type].len);
 				if (err)
-					return err;
+					goto err_try_undo;
 				break;
 			default:
 				break;
@@ -174,6 +174,16 @@ int netlink_policy_dump_add_policy(struct netlink_policy_dump_state **pstate,
 
 	*pstate = state;
 	return 0;
+
+err_try_undo:
+	/* Try to preserve reasonable unwind semantics - if we're starting from
+	 * scratch clean up fully, otherwise record what we got and caller will.
+	 */
+	if (!*pstate)
+		netlink_policy_dump_free(state);
+	else
+		*pstate = state;
+	return err;
 }
 
 static bool
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 67ad08320886..5e2c83cb7b12 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -1801,7 +1801,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 				ovs_dp_reset_user_features(skb, info);
 		}
 
-		goto err_unlock_and_destroy_meters;
+		goto err_destroy_portids;
 	}
 
 	err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
@@ -1816,6 +1816,8 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	ovs_notify(&dp_datapath_genl_family, reply, info);
 	return 0;
 
+err_destroy_portids:
+	kfree(rcu_dereference_raw(dp->upcall_portids));
 err_unlock_and_destroy_meters:
 	ovs_unlock();
 	ovs_meters_exit(dp);
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 88c3b5cf8d94..968dac3fcf58 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2989,8 +2989,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	if (err)
 		goto out_free;
 
-	if (sock->type == SOCK_RAW &&
-	    !dev_validate_header(dev, skb->data, len)) {
+	if ((sock->type == SOCK_RAW &&
+	     !dev_validate_header(dev, skb->data, len)) || !skb->len) {
 		err = -EINVAL;
 		goto out_free;
 	}
diff --git a/net/qrtr/mhi.c b/net/qrtr/mhi.c
index fa611678af05..49e7cab43d24 100644
--- a/net/qrtr/mhi.c
+++ b/net/qrtr/mhi.c
@@ -78,11 +78,6 @@ static int qcom_mhi_qrtr_probe(struct mhi_device *mhi_dev,
 	struct qrtr_mhi_dev *qdev;
 	int rc;
 
-	/* start channels */
-	rc = mhi_prepare_for_transfer(mhi_dev);
-	if (rc)
-		return rc;
-
 	qdev = devm_kzalloc(&mhi_dev->dev, sizeof(*qdev), GFP_KERNEL);
 	if (!qdev)
 		return -ENOMEM;
@@ -96,6 +91,13 @@ static int qcom_mhi_qrtr_probe(struct mhi_device *mhi_dev,
 	if (rc)
 		return rc;
 
+	/* start channels */
+	rc = mhi_prepare_for_transfer(mhi_dev);
+	if (rc) {
+		qrtr_endpoint_unregister(&qdev->ep);
+		return rc;
+	}
+
 	dev_dbg(qdev->dev, "Qualcomm MHI QRTR driver probed\n");
 
 	return 0;
diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c
index 6fdedd9dbbc2..cfbf0e129cba 100644
--- a/net/rds/ib_recv.c
+++ b/net/rds/ib_recv.c
@@ -363,6 +363,7 @@ static int acquire_refill(struct rds_connection *conn)
 static void release_refill(struct rds_connection *conn)
 {
 	clear_bit(RDS_RECV_REFILL, &conn->c_flags);
+	smp_mb__after_atomic();
 
 	/* We don't use wait_on_bit()/wake_up_bit() because our waking is in a
 	 * hot path and finding waiters is very rare.  We don't want to walk
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index cf7d974e0f61..29a208ed8fb8 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -191,6 +191,7 @@ static void rose_kill_by_device(struct net_device *dev)
 			rose_disconnect(s, ENETUNREACH, ROSE_OUT_OF_ORDER, 0);
 			if (rose->neighbour)
 				rose->neighbour->use--;
+			dev_put(rose->device);
 			rose->device = NULL;
 		}
 	}
@@ -591,6 +592,8 @@ static struct sock *rose_make_new(struct sock *osk)
 	rose->idle	= orose->idle;
 	rose->defer	= orose->defer;
 	rose->device	= orose->device;
+	if (rose->device)
+		dev_hold(rose->device);
 	rose->qbitincl	= orose->qbitincl;
 
 	return sk;
@@ -644,6 +647,7 @@ static int rose_release(struct socket *sock)
 		break;
 	}
 
+	dev_put(rose->device);
 	sock->sk = NULL;
 	release_sock(sk);
 	sock_put(sk);
@@ -720,7 +724,6 @@ static int rose_connect(struct socket *sock, struct sockaddr *uaddr, int addr_le
 	struct rose_sock *rose = rose_sk(sk);
 	struct sockaddr_rose *addr = (struct sockaddr_rose *)uaddr;
 	unsigned char cause, diagnostic;
-	struct net_device *dev;
 	ax25_uid_assoc *user;
 	int n, err = 0;
 
@@ -777,9 +780,12 @@ static int rose_connect(struct socket *sock, struct sockaddr *uaddr, int addr_le
 	}
 
 	if (sock_flag(sk, SOCK_ZAPPED)) {	/* Must bind first - autobinding in this may or may not work */
+		struct net_device *dev;
+
 		sock_reset_flag(sk, SOCK_ZAPPED);
 
-		if ((dev = rose_dev_first()) == NULL) {
+		dev = rose_dev_first();
+		if (!dev) {
 			err = -ENETUNREACH;
 			goto out_release;
 		}
@@ -787,6 +793,7 @@ static int rose_connect(struct socket *sock, struct sockaddr *uaddr, int addr_le
 		user = ax25_findbyuid(current_euid());
 		if (!user) {
 			err = -EINVAL;
+			dev_put(dev);
 			goto out_release;
 		}
 
diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c
index 11c45c8c6c16..036d92c0ad79 100644
--- a/net/rose/rose_loopback.c
+++ b/net/rose/rose_loopback.c
@@ -96,7 +96,8 @@ static void rose_loopback_timer(struct timer_list *unused)
 		}
 
 		if (frametype == ROSE_CALL_REQUEST) {
-			if (!rose_loopback_neigh->dev) {
+			if (!rose_loopback_neigh->dev &&
+			    !rose_loopback_neigh->loopback) {
 				kfree_skb(skb);
 				continue;
 			}
diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c
index c0e04c261a15..66aa05db5390 100644
--- a/net/rose/rose_route.c
+++ b/net/rose/rose_route.c
@@ -227,8 +227,8 @@ static void rose_remove_neigh(struct rose_neigh *rose_neigh)
 {
 	struct rose_neigh *s;
 
-	rose_stop_ftimer(rose_neigh);
-	rose_stop_t0timer(rose_neigh);
+	del_timer_sync(&rose_neigh->ftimer);
+	del_timer_sync(&rose_neigh->t0timer);
 
 	skb_queue_purge(&rose_neigh->queue);
 
@@ -615,6 +615,8 @@ struct net_device *rose_dev_first(void)
 			if (first == NULL || strncmp(dev->name, first->name, 3) < 0)
 				first = dev;
 	}
+	if (first)
+		dev_hold(first);
 	rcu_read_unlock();
 
 	return first;
diff --git a/net/rose/rose_timer.c b/net/rose/rose_timer.c
index b3138fc2e552..f06ddbed3fed 100644
--- a/net/rose/rose_timer.c
+++ b/net/rose/rose_timer.c
@@ -31,89 +31,89 @@ static void rose_idletimer_expiry(struct timer_list *);
 
 void rose_start_heartbeat(struct sock *sk)
 {
-	del_timer(&sk->sk_timer);
+	sk_stop_timer(sk, &sk->sk_timer);
 
 	sk->sk_timer.function = rose_heartbeat_expiry;
 	sk->sk_timer.expires  = jiffies + 5 * HZ;
 
-	add_timer(&sk->sk_timer);
+	sk_reset_timer(sk, &sk->sk_timer, sk->sk_timer.expires);
 }
 
 void rose_start_t1timer(struct sock *sk)
 {
 	struct rose_sock *rose = rose_sk(sk);
 
-	del_timer(&rose->timer);
+	sk_stop_timer(sk, &rose->timer);
 
 	rose->timer.function = rose_timer_expiry;
 	rose->timer.expires  = jiffies + rose->t1;
 
-	add_timer(&rose->timer);
+	sk_reset_timer(sk, &rose->timer, rose->timer.expires);
 }
 
 void rose_start_t2timer(struct sock *sk)
 {
 	struct rose_sock *rose = rose_sk(sk);
 
-	del_timer(&rose->timer);
+	sk_stop_timer(sk, &rose->timer);
 
 	rose->timer.function = rose_timer_expiry;
 	rose->timer.expires  = jiffies + rose->t2;
 
-	add_timer(&rose->timer);
+	sk_reset_timer(sk, &rose->timer, rose->timer.expires);
 }
 
 void rose_start_t3timer(struct sock *sk)
 {
 	struct rose_sock *rose = rose_sk(sk);
 
-	del_timer(&rose->timer);
+	sk_stop_timer(sk, &rose->timer);
 
 	rose->timer.function = rose_timer_expiry;
 	rose->timer.expires  = jiffies + rose->t3;
 
-	add_timer(&rose->timer);
+	sk_reset_timer(sk, &rose->timer, rose->timer.expires);
 }
 
 void rose_start_hbtimer(struct sock *sk)
 {
 	struct rose_sock *rose = rose_sk(sk);
 
-	del_timer(&rose->timer);
+	sk_stop_timer(sk, &rose->timer);
 
 	rose->timer.function = rose_timer_expiry;
 	rose->timer.expires  = jiffies + rose->hb;
 
-	add_timer(&rose->timer);
+	sk_reset_timer(sk, &rose->timer, rose->timer.expires);
 }
 
 void rose_start_idletimer(struct sock *sk)
 {
 	struct rose_sock *rose = rose_sk(sk);
 
-	del_timer(&rose->idletimer);
+	sk_stop_timer(sk, &rose->idletimer);
 
 	if (rose->idle > 0) {
 		rose->idletimer.function = rose_idletimer_expiry;
 		rose->idletimer.expires  = jiffies + rose->idle;
 
-		add_timer(&rose->idletimer);
+		sk_reset_timer(sk, &rose->idletimer, rose->idletimer.expires);
 	}
 }
 
 void rose_stop_heartbeat(struct sock *sk)
 {
-	del_timer(&sk->sk_timer);
+	sk_stop_timer(sk, &sk->sk_timer);
 }
 
 void rose_stop_timer(struct sock *sk)
 {
-	del_timer(&rose_sk(sk)->timer);
+	sk_stop_timer(sk, &rose_sk(sk)->timer);
 }
 
 void rose_stop_idletimer(struct sock *sk)
 {
-	del_timer(&rose_sk(sk)->idletimer);
+	sk_stop_timer(sk, &rose_sk(sk)->idletimer);
 }
 
 static void rose_heartbeat_expiry(struct timer_list *t)
@@ -130,6 +130,7 @@ static void rose_heartbeat_expiry(struct timer_list *t)
 		    (sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD))) {
 			bh_unlock_sock(sk);
 			rose_destroy_socket(sk);
+			sock_put(sk);
 			return;
 		}
 		break;
@@ -152,6 +153,7 @@ static void rose_heartbeat_expiry(struct timer_list *t)
 
 	rose_start_heartbeat(sk);
 	bh_unlock_sock(sk);
+	sock_put(sk);
 }
 
 static void rose_timer_expiry(struct timer_list *t)
@@ -181,6 +183,7 @@ static void rose_timer_expiry(struct timer_list *t)
 		break;
 	}
 	bh_unlock_sock(sk);
+	sock_put(sk);
 }
 
 static void rose_idletimer_expiry(struct timer_list *t)
@@ -205,4 +208,5 @@ static void rose_idletimer_expiry(struct timer_list *t)
 		sock_set_flag(sk, SOCK_DEAD);
 	}
 	bh_unlock_sock(sk);
+	sock_put(sk);
 }
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index dce056adb78c..f2e3fb77a02d 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -68,7 +68,7 @@ struct rxrpc_net {
 	struct proc_dir_entry	*proc_net;	/* Subdir in /proc/net */
 	u32			epoch;		/* Local epoch for detecting local-end reset */
 	struct list_head	calls;		/* List of calls active in this namespace */
-	rwlock_t		call_lock;	/* Lock for ->calls */
+	spinlock_t		call_lock;	/* Lock for ->calls */
 	atomic_t		nr_calls;	/* Count of allocated calls */
 
 	atomic_t		nr_conns;
@@ -990,6 +990,7 @@ void rxrpc_send_keepalive(struct rxrpc_peer *);
 /*
  * peer_event.c
  */
+void rxrpc_encap_err_rcv(struct sock *sk, struct sk_buff *skb, unsigned int udp_offset);
 void rxrpc_error_report(struct sock *);
 void rxrpc_peer_keepalive_worker(struct work_struct *);
 
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index 1ae90fb97936..8b24ffbc72ef 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -140,9 +140,9 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx,
 	write_unlock(&rx->call_lock);
 
 	rxnet = call->rxnet;
-	write_lock(&rxnet->call_lock);
-	list_add_tail(&call->link, &rxnet->calls);
-	write_unlock(&rxnet->call_lock);
+	spin_lock_bh(&rxnet->call_lock);
+	list_add_tail_rcu(&call->link, &rxnet->calls);
+	spin_unlock_bh(&rxnet->call_lock);
 
 	b->call_backlog[call_head] = call;
 	smp_store_release(&b->call_backlog_head, (call_head + 1) & (size - 1));
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index f8ecad2b730e..2a93e7b5fbd0 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -166,7 +166,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j)
 	_enter("{%d,%d}", call->tx_hard_ack, call->tx_top);
 
 	now = ktime_get_real();
-	max_age = ktime_sub(now, jiffies_to_usecs(call->peer->rto_j));
+	max_age = ktime_sub_us(now, jiffies_to_usecs(call->peer->rto_j));
 
 	spin_lock_bh(&call->lock);
 
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 043508fd8d8a..d674d90e7031 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -285,8 +285,10 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 	_enter("%p,%lx", rx, p->user_call_ID);
 
 	limiter = rxrpc_get_call_slot(p, gfp);
-	if (!limiter)
+	if (!limiter) {
+		release_sock(&rx->sk);
 		return ERR_PTR(-ERESTARTSYS);
+	}
 
 	call = rxrpc_alloc_client_call(rx, srx, gfp, debug_id);
 	if (IS_ERR(call)) {
@@ -337,9 +339,9 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 	write_unlock(&rx->call_lock);
 
 	rxnet = call->rxnet;
-	write_lock(&rxnet->call_lock);
-	list_add_tail(&call->link, &rxnet->calls);
-	write_unlock(&rxnet->call_lock);
+	spin_lock_bh(&rxnet->call_lock);
+	list_add_tail_rcu(&call->link, &rxnet->calls);
+	spin_unlock_bh(&rxnet->call_lock);
 
 	/* From this point on, the call is protected by its own lock. */
 	release_sock(&rx->sk);
@@ -631,9 +633,9 @@ void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace op)
 		ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE);
 
 		if (!list_empty(&call->link)) {
-			write_lock(&rxnet->call_lock);
+			spin_lock_bh(&rxnet->call_lock);
 			list_del_init(&call->link);
-			write_unlock(&rxnet->call_lock);
+			spin_unlock_bh(&rxnet->call_lock);
 		}
 
 		rxrpc_cleanup_call(call);
@@ -705,7 +707,7 @@ void rxrpc_destroy_all_calls(struct rxrpc_net *rxnet)
 	_enter("");
 
 	if (!list_empty(&rxnet->calls)) {
-		write_lock(&rxnet->call_lock);
+		spin_lock_bh(&rxnet->call_lock);
 
 		while (!list_empty(&rxnet->calls)) {
 			call = list_entry(rxnet->calls.next,
@@ -720,12 +722,12 @@ void rxrpc_destroy_all_calls(struct rxrpc_net *rxnet)
 			       rxrpc_call_states[call->state],
 			       call->flags, call->events);
 
-			write_unlock(&rxnet->call_lock);
+			spin_unlock_bh(&rxnet->call_lock);
 			cond_resched();
-			write_lock(&rxnet->call_lock);
+			spin_lock_bh(&rxnet->call_lock);
 		}
 
-		write_unlock(&rxnet->call_lock);
+		spin_unlock_bh(&rxnet->call_lock);
 	}
 
 	atomic_dec(&rxnet->nr_calls);
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 6a1611b0e303..1d15940f61d7 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -137,6 +137,7 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
 
 	tuncfg.encap_type = UDP_ENCAP_RXRPC;
 	tuncfg.encap_rcv = rxrpc_input_packet;
+	tuncfg.encap_err_rcv = rxrpc_encap_err_rcv;
 	tuncfg.sk_user_data = local;
 	setup_udp_tunnel_sock(net, local->socket, &tuncfg);
 
@@ -405,6 +406,9 @@ static void rxrpc_local_processor(struct work_struct *work)
 		container_of(work, struct rxrpc_local, processor);
 	bool again;
 
+	if (local->dead)
+		return;
+
 	trace_rxrpc_local(local->debug_id, rxrpc_local_processing,
 			  atomic_read(&local->usage), NULL);
 
diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c
index cc7e30733feb..e4d6d432515b 100644
--- a/net/rxrpc/net_ns.c
+++ b/net/rxrpc/net_ns.c
@@ -50,7 +50,7 @@ static __net_init int rxrpc_init_net(struct net *net)
 	rxnet->epoch |= RXRPC_RANDOM_EPOCH;
 
 	INIT_LIST_HEAD(&rxnet->calls);
-	rwlock_init(&rxnet->call_lock);
+	spin_lock_init(&rxnet->call_lock);
 	atomic_set(&rxnet->nr_calls, 1);
 
 	atomic_set(&rxnet->nr_conns, 1);
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index be032850ae8c..32561e9567fe 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -16,22 +16,105 @@
 #include <net/sock.h>
 #include <net/af_rxrpc.h>
 #include <net/ip.h>
+#include <net/icmp.h>
 #include "ar-internal.h"
 
+static void rxrpc_adjust_mtu(struct rxrpc_peer *, unsigned int);
 static void rxrpc_store_error(struct rxrpc_peer *, struct sock_exterr_skb *);
 static void rxrpc_distribute_error(struct rxrpc_peer *, int,
 				   enum rxrpc_call_completion);
 
 /*
- * Find the peer associated with an ICMP packet.
+ * Find the peer associated with an ICMPv4 packet.
  */
 static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
-						     const struct sk_buff *skb,
+						     struct sk_buff *skb,
+						     unsigned int udp_offset,
+						     unsigned int *info,
 						     struct sockaddr_rxrpc *srx)
 {
-	struct sock_exterr_skb *serr = SKB_EXT_ERR(skb);
+	struct iphdr *ip, *ip0 = ip_hdr(skb);
+	struct icmphdr *icmp = icmp_hdr(skb);
+	struct udphdr *udp = (struct udphdr *)(skb->data + udp_offset);
 
-	_enter("");
+	_enter("%u,%u,%u", ip0->protocol, icmp->type, icmp->code);
+
+	switch (icmp->type) {
+	case ICMP_DEST_UNREACH:
+		*info = ntohs(icmp->un.frag.mtu);
+		fallthrough;
+	case ICMP_TIME_EXCEEDED:
+	case ICMP_PARAMETERPROB:
+		ip = (struct iphdr *)((void *)icmp + 8);
+		break;
+	default:
+		return NULL;
+	}
+
+	memset(srx, 0, sizeof(*srx));
+	srx->transport_type = local->srx.transport_type;
+	srx->transport_len = local->srx.transport_len;
+	srx->transport.family = local->srx.transport.family;
+
+	/* Can we see an ICMP4 packet on an ICMP6 listening socket?  and vice
+	 * versa?
+	 */
+	switch (srx->transport.family) {
+	case AF_INET:
+		srx->transport_len = sizeof(srx->transport.sin);
+		srx->transport.family = AF_INET;
+		srx->transport.sin.sin_port = udp->dest;
+		memcpy(&srx->transport.sin.sin_addr, &ip->daddr,
+		       sizeof(struct in_addr));
+		break;
+
+#ifdef CONFIG_AF_RXRPC_IPV6
+	case AF_INET6:
+		srx->transport_len = sizeof(srx->transport.sin);
+		srx->transport.family = AF_INET;
+		srx->transport.sin.sin_port = udp->dest;
+		memcpy(&srx->transport.sin.sin_addr, &ip->daddr,
+		       sizeof(struct in_addr));
+		break;
+#endif
+
+	default:
+		WARN_ON_ONCE(1);
+		return NULL;
+	}
+
+	_net("ICMP {%pISp}", &srx->transport);
+	return rxrpc_lookup_peer_rcu(local, srx);
+}
+
+#ifdef CONFIG_AF_RXRPC_IPV6
+/*
+ * Find the peer associated with an ICMPv6 packet.
+ */
+static struct rxrpc_peer *rxrpc_lookup_peer_icmp6_rcu(struct rxrpc_local *local,
+						      struct sk_buff *skb,
+						      unsigned int udp_offset,
+						      unsigned int *info,
+						      struct sockaddr_rxrpc *srx)
+{
+	struct icmp6hdr *icmp = icmp6_hdr(skb);
+	struct ipv6hdr *ip, *ip0 = ipv6_hdr(skb);
+	struct udphdr *udp = (struct udphdr *)(skb->data + udp_offset);
+
+	_enter("%u,%u,%u", ip0->nexthdr, icmp->icmp6_type, icmp->icmp6_code);
+
+	switch (icmp->icmp6_type) {
+	case ICMPV6_DEST_UNREACH:
+		*info = ntohl(icmp->icmp6_mtu);
+		fallthrough;
+	case ICMPV6_PKT_TOOBIG:
+	case ICMPV6_TIME_EXCEED:
+	case ICMPV6_PARAMPROB:
+		ip = (struct ipv6hdr *)((void *)icmp + 8);
+		break;
+	default:
+		return NULL;
+	}
 
 	memset(srx, 0, sizeof(*srx));
 	srx->transport_type = local->srx.transport_type;
@@ -43,6 +126,165 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
 	 */
 	switch (srx->transport.family) {
 	case AF_INET:
+		_net("Rx ICMP6 on v4 sock");
+		srx->transport_len = sizeof(srx->transport.sin);
+		srx->transport.family = AF_INET;
+		srx->transport.sin.sin_port = udp->dest;
+		memcpy(&srx->transport.sin.sin_addr,
+		       &ip->daddr.s6_addr32[3], sizeof(struct in_addr));
+		break;
+	case AF_INET6:
+		_net("Rx ICMP6");
+		srx->transport.sin.sin_port = udp->dest;
+		memcpy(&srx->transport.sin6.sin6_addr, &ip->daddr,
+		       sizeof(struct in6_addr));
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return NULL;
+	}
+
+	_net("ICMP {%pISp}", &srx->transport);
+	return rxrpc_lookup_peer_rcu(local, srx);
+}
+#endif /* CONFIG_AF_RXRPC_IPV6 */
+
+/*
+ * Handle an error received on the local endpoint as a tunnel.
+ */
+void rxrpc_encap_err_rcv(struct sock *sk, struct sk_buff *skb,
+			 unsigned int udp_offset)
+{
+	struct sock_extended_err ee;
+	struct sockaddr_rxrpc srx;
+	struct rxrpc_local *local;
+	struct rxrpc_peer *peer;
+	unsigned int info = 0;
+	int err;
+	u8 version = ip_hdr(skb)->version;
+	u8 type = icmp_hdr(skb)->type;
+	u8 code = icmp_hdr(skb)->code;
+
+	rcu_read_lock();
+	local = rcu_dereference_sk_user_data(sk);
+	if (unlikely(!local)) {
+		rcu_read_unlock();
+		return;
+	}
+
+	rxrpc_new_skb(skb, rxrpc_skb_received);
+
+	switch (ip_hdr(skb)->version) {
+	case IPVERSION:
+		peer = rxrpc_lookup_peer_icmp_rcu(local, skb, udp_offset,
+						  &info, &srx);
+		break;
+#ifdef CONFIG_AF_RXRPC_IPV6
+	case 6:
+		peer = rxrpc_lookup_peer_icmp6_rcu(local, skb, udp_offset,
+						   &info, &srx);
+		break;
+#endif
+	default:
+		rcu_read_unlock();
+		return;
+	}
+
+	if (peer && !rxrpc_get_peer_maybe(peer))
+		peer = NULL;
+	if (!peer) {
+		rcu_read_unlock();
+		return;
+	}
+
+	memset(&ee, 0, sizeof(ee));
+
+	switch (version) {
+	case IPVERSION:
+		switch (type) {
+		case ICMP_DEST_UNREACH:
+			switch (code) {
+			case ICMP_FRAG_NEEDED:
+				rxrpc_adjust_mtu(peer, info);
+				rcu_read_unlock();
+				rxrpc_put_peer(peer);
+				return;
+			default:
+				break;
+			}
+
+			err = EHOSTUNREACH;
+			if (code <= NR_ICMP_UNREACH) {
+				/* Might want to do something different with
+				 * non-fatal errors
+				 */
+				//harderr = icmp_err_convert[code].fatal;
+				err = icmp_err_convert[code].errno;
+			}
+			break;
+
+		case ICMP_TIME_EXCEEDED:
+			err = EHOSTUNREACH;
+			break;
+		default:
+			err = EPROTO;
+			break;
+		}
+
+		ee.ee_origin = SO_EE_ORIGIN_ICMP;
+		ee.ee_type = type;
+		ee.ee_code = code;
+		ee.ee_errno = err;
+		break;
+
+#ifdef CONFIG_AF_RXRPC_IPV6
+	case 6:
+		switch (type) {
+		case ICMPV6_PKT_TOOBIG:
+			rxrpc_adjust_mtu(peer, info);
+			rcu_read_unlock();
+			rxrpc_put_peer(peer);
+			return;
+		}
+
+		icmpv6_err_convert(type, code, &err);
+
+		if (err == EACCES)
+			err = EHOSTUNREACH;
+
+		ee.ee_origin = SO_EE_ORIGIN_ICMP6;
+		ee.ee_type = type;
+		ee.ee_code = code;
+		ee.ee_errno = err;
+		break;
+#endif
+	}
+
+	trace_rxrpc_rx_icmp(peer, &ee, &srx);
+
+	rxrpc_distribute_error(peer, err, RXRPC_CALL_NETWORK_ERROR);
+	rcu_read_unlock();
+	rxrpc_put_peer(peer);
+}
+
+/*
+ * Find the peer associated with a local error.
+ */
+static struct rxrpc_peer *rxrpc_lookup_peer_local_rcu(struct rxrpc_local *local,
+						      const struct sk_buff *skb,
+						      struct sockaddr_rxrpc *srx)
+{
+	struct sock_exterr_skb *serr = SKB_EXT_ERR(skb);
+
+	_enter("");
+
+	memset(srx, 0, sizeof(*srx));
+	srx->transport_type = local->srx.transport_type;
+	srx->transport_len = local->srx.transport_len;
+	srx->transport.family = local->srx.transport.family;
+
+	switch (srx->transport.family) {
+	case AF_INET:
 		srx->transport_len = sizeof(srx->transport.sin);
 		srx->transport.family = AF_INET;
 		srx->transport.sin.sin_port = serr->port;
@@ -104,10 +346,8 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
 /*
  * Handle an MTU/fragmentation problem.
  */
-static void rxrpc_adjust_mtu(struct rxrpc_peer *peer, struct sock_exterr_skb *serr)
+static void rxrpc_adjust_mtu(struct rxrpc_peer *peer, unsigned int mtu)
 {
-	u32 mtu = serr->ee.ee_info;
-
 	_net("Rx ICMP Fragmentation Needed (%d)", mtu);
 
 	/* wind down the local interface MTU */
@@ -148,7 +388,7 @@ void rxrpc_error_report(struct sock *sk)
 	struct sock_exterr_skb *serr;
 	struct sockaddr_rxrpc srx;
 	struct rxrpc_local *local;
-	struct rxrpc_peer *peer;
+	struct rxrpc_peer *peer = NULL;
 	struct sk_buff *skb;
 
 	rcu_read_lock();
@@ -172,41 +412,20 @@ void rxrpc_error_report(struct sock *sk)
 	}
 	rxrpc_new_skb(skb, rxrpc_skb_received);
 	serr = SKB_EXT_ERR(skb);
-	if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) {
-		_leave("UDP empty message");
-		rcu_read_unlock();
-		rxrpc_free_skb(skb, rxrpc_skb_freed);
-		return;
-	}
 
-	peer = rxrpc_lookup_peer_icmp_rcu(local, skb, &srx);
-	if (peer && !rxrpc_get_peer_maybe(peer))
-		peer = NULL;
-	if (!peer) {
-		rcu_read_unlock();
-		rxrpc_free_skb(skb, rxrpc_skb_freed);
-		_leave(" [no peer]");
-		return;
-	}
-
-	trace_rxrpc_rx_icmp(peer, &serr->ee, &srx);
-
-	if ((serr->ee.ee_origin == SO_EE_ORIGIN_ICMP &&
-	     serr->ee.ee_type == ICMP_DEST_UNREACH &&
-	     serr->ee.ee_code == ICMP_FRAG_NEEDED)) {
-		rxrpc_adjust_mtu(peer, serr);
-		rcu_read_unlock();
-		rxrpc_free_skb(skb, rxrpc_skb_freed);
-		rxrpc_put_peer(peer);
-		_leave(" [MTU update]");
-		return;
+	if (serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL) {
+		peer = rxrpc_lookup_peer_local_rcu(local, skb, &srx);
+		if (peer && !rxrpc_get_peer_maybe(peer))
+			peer = NULL;
+		if (peer) {
+			trace_rxrpc_rx_icmp(peer, &serr->ee, &srx);
+			rxrpc_store_error(peer, serr);
+		}
 	}
 
-	rxrpc_store_error(peer, serr);
 	rcu_read_unlock();
 	rxrpc_free_skb(skb, rxrpc_skb_freed);
 	rxrpc_put_peer(peer);
-
 	_leave("");
 }
 
diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c
index e2f990754f88..5a67955cc00f 100644
--- a/net/rxrpc/proc.c
+++ b/net/rxrpc/proc.c
@@ -26,29 +26,23 @@ static const char *const rxrpc_conn_states[RXRPC_CONN__NR_STATES] = {
  */
 static void *rxrpc_call_seq_start(struct seq_file *seq, loff_t *_pos)
 	__acquires(rcu)
-	__acquires(rxnet->call_lock)
 {
 	struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
 
 	rcu_read_lock();
-	read_lock(&rxnet->call_lock);
-	return seq_list_start_head(&rxnet->calls, *_pos);
+	return seq_list_start_head_rcu(&rxnet->calls, *_pos);
 }
 
 static void *rxrpc_call_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
 
-	return seq_list_next(v, &rxnet->calls, pos);
+	return seq_list_next_rcu(v, &rxnet->calls, pos);
 }
 
 static void rxrpc_call_seq_stop(struct seq_file *seq, void *v)
-	__releases(rxnet->call_lock)
 	__releases(rcu)
 {
-	struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
-
-	read_unlock(&rxnet->call_lock);
 	rcu_read_unlock();
 }
 
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index 08aab5c01437..db47844f4ac9 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -540,7 +540,7 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb,
 	 * directly into the target buffer.
 	 */
 	sg = _sg;
-	nsg = skb_shinfo(skb)->nr_frags;
+	nsg = skb_shinfo(skb)->nr_frags + 1;
 	if (nsg <= 4) {
 		nsg = 4;
 	} else {
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 1d38e279e2ef..3c3a626459de 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -51,10 +51,7 @@ static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx,
 			return sock_intr_errno(*timeo);
 
 		trace_rxrpc_transmit(call, rxrpc_transmit_wait);
-		mutex_unlock(&call->user_mutex);
 		*timeo = schedule_timeout(*timeo);
-		if (mutex_lock_interruptible(&call->user_mutex) < 0)
-			return sock_intr_errno(*timeo);
 	}
 }
 
@@ -290,37 +287,48 @@ out:
 static int rxrpc_send_data(struct rxrpc_sock *rx,
 			   struct rxrpc_call *call,
 			   struct msghdr *msg, size_t len,
-			   rxrpc_notify_end_tx_t notify_end_tx)
+			   rxrpc_notify_end_tx_t notify_end_tx,
+			   bool *_dropped_lock)
 {
 	struct rxrpc_skb_priv *sp;
 	struct sk_buff *skb;
 	struct sock *sk = &rx->sk;
+	enum rxrpc_call_state state;
 	long timeo;
-	bool more;
-	int ret, copied;
+	bool more = msg->msg_flags & MSG_MORE;
+	int ret, copied = 0;
 
 	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
 
 	/* this should be in poll */
 	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
+reload:
+	ret = -EPIPE;
 	if (sk->sk_shutdown & SEND_SHUTDOWN)
-		return -EPIPE;
-
-	more = msg->msg_flags & MSG_MORE;
-
+		goto maybe_error;
+	state = READ_ONCE(call->state);
+	ret = -ESHUTDOWN;
+	if (state >= RXRPC_CALL_COMPLETE)
+		goto maybe_error;
+	ret = -EPROTO;
+	if (state != RXRPC_CALL_CLIENT_SEND_REQUEST &&
+	    state != RXRPC_CALL_SERVER_ACK_REQUEST &&
+	    state != RXRPC_CALL_SERVER_SEND_REPLY)
+		goto maybe_error;
+
+	ret = -EMSGSIZE;
 	if (call->tx_total_len != -1) {
-		if (len > call->tx_total_len)
-			return -EMSGSIZE;
-		if (!more && len != call->tx_total_len)
-			return -EMSGSIZE;
+		if (len - copied > call->tx_total_len)
+			goto maybe_error;
+		if (!more && len - copied != call->tx_total_len)
+			goto maybe_error;
 	}
 
 	skb = call->tx_pending;
 	call->tx_pending = NULL;
 	rxrpc_see_skb(skb, rxrpc_skb_seen);
 
-	copied = 0;
 	do {
 		/* Check to see if there's a ping ACK to reply to. */
 		if (call->ackr_reason == RXRPC_ACK_PING_RESPONSE)
@@ -331,16 +339,8 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 
 			_debug("alloc");
 
-			if (!rxrpc_check_tx_space(call, NULL)) {
-				ret = -EAGAIN;
-				if (msg->msg_flags & MSG_DONTWAIT)
-					goto maybe_error;
-				ret = rxrpc_wait_for_tx_window(rx, call,
-							       &timeo,
-							       msg->msg_flags & MSG_WAITALL);
-				if (ret < 0)
-					goto maybe_error;
-			}
+			if (!rxrpc_check_tx_space(call, NULL))
+				goto wait_for_space;
 
 			/* Work out the maximum size of a packet.  Assume that
 			 * the security header is going to be in the padded
@@ -468,6 +468,27 @@ maybe_error:
 efault:
 	ret = -EFAULT;
 	goto out;
+
+wait_for_space:
+	ret = -EAGAIN;
+	if (msg->msg_flags & MSG_DONTWAIT)
+		goto maybe_error;
+	mutex_unlock(&call->user_mutex);
+	*_dropped_lock = true;
+	ret = rxrpc_wait_for_tx_window(rx, call, &timeo,
+				       msg->msg_flags & MSG_WAITALL);
+	if (ret < 0)
+		goto maybe_error;
+	if (call->interruptibility == RXRPC_INTERRUPTIBLE) {
+		if (mutex_lock_interruptible(&call->user_mutex) < 0) {
+			ret = sock_intr_errno(timeo);
+			goto maybe_error;
+		}
+	} else {
+		mutex_lock(&call->user_mutex);
+	}
+	*_dropped_lock = false;
+	goto reload;
 }
 
 /*
@@ -629,6 +650,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 	enum rxrpc_call_state state;
 	struct rxrpc_call *call;
 	unsigned long now, j;
+	bool dropped_lock = false;
 	int ret;
 
 	struct rxrpc_send_params p = {
@@ -737,21 +759,13 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 			ret = rxrpc_send_abort_packet(call);
 	} else if (p.command != RXRPC_CMD_SEND_DATA) {
 		ret = -EINVAL;
-	} else if (rxrpc_is_client_call(call) &&
-		   state != RXRPC_CALL_CLIENT_SEND_REQUEST) {
-		/* request phase complete for this client call */
-		ret = -EPROTO;
-	} else if (rxrpc_is_service_call(call) &&
-		   state != RXRPC_CALL_SERVER_ACK_REQUEST &&
-		   state != RXRPC_CALL_SERVER_SEND_REPLY) {
-		/* Reply phase not begun or not complete for service call. */
-		ret = -EPROTO;
 	} else {
-		ret = rxrpc_send_data(rx, call, msg, len, NULL);
+		ret = rxrpc_send_data(rx, call, msg, len, NULL, &dropped_lock);
 	}
 
 out_put_unlock:
-	mutex_unlock(&call->user_mutex);
+	if (!dropped_lock)
+		mutex_unlock(&call->user_mutex);
 error_put:
 	rxrpc_put_call(call, rxrpc_call_put);
 	_leave(" = %d", ret);
@@ -779,6 +793,7 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call,
 			   struct msghdr *msg, size_t len,
 			   rxrpc_notify_end_tx_t notify_end_tx)
 {
+	bool dropped_lock = false;
 	int ret;
 
 	_enter("{%d,%s},", call->debug_id, rxrpc_call_states[call->state]);
@@ -796,7 +811,7 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call,
 	case RXRPC_CALL_SERVER_ACK_REQUEST:
 	case RXRPC_CALL_SERVER_SEND_REPLY:
 		ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len,
-				      notify_end_tx);
+				      notify_end_tx, &dropped_lock);
 		break;
 	case RXRPC_CALL_COMPLETE:
 		read_lock_bh(&call->state_lock);
@@ -810,7 +825,8 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call,
 		break;
 	}
 
-	mutex_unlock(&call->user_mutex);
+	if (!dropped_lock)
+		mutex_unlock(&call->user_mutex);
 	_leave(" = %d", ret);
 	return ret;
 }
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index e9cc2f3f023b..10198cfc218e 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -436,7 +436,8 @@ static int tcf_idr_release_unsafe(struct tc_action *p)
 }
 
 static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb,
-			  const struct tc_action_ops *ops)
+			  const struct tc_action_ops *ops,
+			  struct netlink_ext_ack *extack)
 {
 	struct nlattr *nest;
 	int n_i = 0;
@@ -452,20 +453,25 @@ static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb,
 	if (nla_put_string(skb, TCA_KIND, ops->kind))
 		goto nla_put_failure;
 
+	ret = 0;
 	mutex_lock(&idrinfo->lock);
 	idr_for_each_entry_ul(idr, p, tmp, id) {
 		if (IS_ERR(p))
 			continue;
 		ret = tcf_idr_release_unsafe(p);
-		if (ret == ACT_P_DELETED) {
+		if (ret == ACT_P_DELETED)
 			module_put(ops->owner);
-			n_i++;
-		} else if (ret < 0) {
-			mutex_unlock(&idrinfo->lock);
-			goto nla_put_failure;
-		}
+		else if (ret < 0)
+			break;
+		n_i++;
 	}
 	mutex_unlock(&idrinfo->lock);
+	if (ret < 0) {
+		if (n_i)
+			NL_SET_ERR_MSG(extack, "Unable to flush all TC actions");
+		else
+			goto nla_put_failure;
+	}
 
 	ret = nla_put_u32(skb, TCA_FCNT, n_i);
 	if (ret)
@@ -486,7 +492,7 @@ int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb,
 	struct tcf_idrinfo *idrinfo = tn->idrinfo;
 
 	if (type == RTM_DELACTION) {
-		return tcf_del_walker(idrinfo, skb, ops);
+		return tcf_del_walker(idrinfo, skb, ops, extack);
 	} else if (type == RTM_GETACTION) {
 		return tcf_dump_walker(idrinfo, skb, cb);
 	} else {
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index a35ab8c27866..48712bc51bda 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -424,6 +424,11 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp,
 			return -EINVAL;
 	}
 
+	if (!nhandle) {
+		NL_SET_ERR_MSG(extack, "Replacing with handle of 0 is invalid");
+		return -EINVAL;
+	}
+
 	h1 = to_hash(nhandle);
 	b = rtnl_dereference(head->table[h1]);
 	if (!b) {
@@ -477,6 +482,11 @@ static int route4_change(struct net *net, struct sk_buff *in_skb,
 	int err;
 	bool new = true;
 
+	if (!handle) {
+		NL_SET_ERR_MSG(extack, "Creating with handle of 0 is invalid");
+		return -EINVAL;
+	}
+
 	if (opt == NULL)
 		return handle ? -EINVAL : 0;
 
@@ -526,7 +536,7 @@ static int route4_change(struct net *net, struct sk_buff *in_skb,
 	rcu_assign_pointer(f->next, f1);
 	rcu_assign_pointer(*fp, f);
 
-	if (fold && fold->handle && f->handle != fold->handle) {
+	if (fold) {
 		th = to_hash(fold->handle);
 		h = from_hash(fold->handle >> 16);
 		b = rtnl_dereference(head->table[th]);
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 30c29a9a2efd..02299785209c 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -409,7 +409,7 @@ static inline bool qdisc_restart(struct Qdisc *q, int *packets)
 
 void __qdisc_run(struct Qdisc *q)
 {
-	int quota = dev_tx_weight;
+	int quota = READ_ONCE(dev_tx_weight);
 	int packets;
 
 	while (qdisc_restart(q, &packets)) {
@@ -1083,6 +1083,21 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
 }
 EXPORT_SYMBOL(dev_graft_qdisc);
 
+static void shutdown_scheduler_queue(struct net_device *dev,
+				     struct netdev_queue *dev_queue,
+				     void *_qdisc_default)
+{
+	struct Qdisc *qdisc = dev_queue->qdisc_sleeping;
+	struct Qdisc *qdisc_default = _qdisc_default;
+
+	if (qdisc) {
+		rcu_assign_pointer(dev_queue->qdisc, qdisc_default);
+		dev_queue->qdisc_sleeping = qdisc_default;
+
+		qdisc_put(qdisc);
+	}
+}
+
 static void attach_one_default_qdisc(struct net_device *dev,
 				     struct netdev_queue *dev_queue,
 				     void *_unused)
@@ -1130,6 +1145,7 @@ static void attach_default_qdiscs(struct net_device *dev)
 	if (qdisc == &noop_qdisc) {
 		netdev_warn(dev, "default qdisc (%s) fail, fallback to %s\n",
 			    default_qdisc_ops->id, noqueue_qdisc_ops.id);
+		netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc);
 		dev->priv_flags |= IFF_NO_QUEUE;
 		netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL);
 		qdisc = txq->qdisc_sleeping;
@@ -1384,21 +1400,6 @@ void dev_init_scheduler(struct net_device *dev)
 	timer_setup(&dev->watchdog_timer, dev_watchdog, 0);
 }
 
-static void shutdown_scheduler_queue(struct net_device *dev,
-				     struct netdev_queue *dev_queue,
-				     void *_qdisc_default)
-{
-	struct Qdisc *qdisc = dev_queue->qdisc_sleeping;
-	struct Qdisc *qdisc_default = _qdisc_default;
-
-	if (qdisc) {
-		rcu_assign_pointer(dev_queue->qdisc, qdisc_default);
-		dev_queue->qdisc_sleeping = qdisc_default;
-
-		qdisc_put(qdisc);
-	}
-}
-
 void dev_shutdown(struct net_device *dev)
 {
 	netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc);
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index 3d061a13d7ed..2829455211f8 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -135,15 +135,15 @@ static void increment_one_qlen(u32 sfbhash, u32 slot, struct sfb_sched_data *q)
 	}
 }
 
-static void increment_qlen(const struct sk_buff *skb, struct sfb_sched_data *q)
+static void increment_qlen(const struct sfb_skb_cb *cb, struct sfb_sched_data *q)
 {
 	u32 sfbhash;
 
-	sfbhash = sfb_hash(skb, 0);
+	sfbhash = cb->hashes[0];
 	if (sfbhash)
 		increment_one_qlen(sfbhash, 0, q);
 
-	sfbhash = sfb_hash(skb, 1);
+	sfbhash = cb->hashes[1];
 	if (sfbhash)
 		increment_one_qlen(sfbhash, 1, q);
 }
@@ -281,8 +281,10 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 {
 
 	struct sfb_sched_data *q = qdisc_priv(sch);
+	unsigned int len = qdisc_pkt_len(skb);
 	struct Qdisc *child = q->qdisc;
 	struct tcf_proto *fl;
+	struct sfb_skb_cb cb;
 	int i;
 	u32 p_min = ~0;
 	u32 minqlen = ~0;
@@ -399,11 +401,12 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	}
 
 enqueue:
+	memcpy(&cb, sfb_skb_cb(skb), sizeof(cb));
 	ret = qdisc_enqueue(skb, child, to_free);
 	if (likely(ret == NET_XMIT_SUCCESS)) {
-		qdisc_qstats_backlog_inc(sch, skb);
+		sch->qstats.backlog += len;
 		sch->q.qlen++;
-		increment_qlen(skb, q);
+		increment_qlen(&cb, q);
 	} else if (net_xmit_drop_count(ret)) {
 		q->stats.childdrop++;
 		qdisc_qstats_drop(sch);
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 78e79029dc63..6eb17004a9e4 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -342,6 +342,7 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt,
 	struct nlattr *tb[TCA_TBF_MAX + 1];
 	struct tc_tbf_qopt *qopt;
 	struct Qdisc *child = NULL;
+	struct Qdisc *old = NULL;
 	struct psched_ratecfg rate;
 	struct psched_ratecfg peak;
 	u64 max_size;
@@ -433,7 +434,7 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt,
 	sch_tree_lock(sch);
 	if (child) {
 		qdisc_tree_flush_backlog(q->qdisc);
-		qdisc_put(q->qdisc);
+		old = q->qdisc;
 		q->qdisc = child;
 	}
 	q->limit = qopt->limit;
@@ -453,6 +454,7 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt,
 	memcpy(&q->peak, &peak, sizeof(struct psched_ratecfg));
 
 	sch_tree_unlock(sch);
+	qdisc_put(old);
 	err = 0;
 
 	tbf_offload_change(sch);
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index be29da09cc7a..3460abceba44 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -229,9 +229,8 @@ static struct sctp_association *sctp_association_init(
 	if (!sctp_ulpq_init(&asoc->ulpq, asoc))
 		goto fail_init;
 
-	if (sctp_stream_init(&asoc->stream, asoc->c.sinit_num_ostreams,
-			     0, gfp))
-		goto fail_init;
+	if (sctp_stream_init(&asoc->stream, asoc->c.sinit_num_ostreams, 0, gfp))
+		goto stream_free;
 
 	/* Initialize default path MTU. */
 	asoc->pathmtu = sp->pathmtu;
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index ec0f52567c16..9987decdead2 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -359,7 +359,7 @@ static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp)
 	if (addr->v4.sin_addr.s_addr != htonl(INADDR_ANY) &&
 	   ret != RTN_LOCAL &&
 	   !sp->inet.freebind &&
-	   !net->ipv4.sysctl_ip_nonlocal_bind)
+	    !READ_ONCE(net->ipv4.sysctl_ip_nonlocal_bind))
 		return 0;
 
 	if (ipv6_only_sock(sctp_opt2sk(sp)))
diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 6dc95dcc0ff4..ef9fceadef8d 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -137,7 +137,7 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
 
 	ret = sctp_stream_alloc_out(stream, outcnt, gfp);
 	if (ret)
-		goto out_err;
+		return ret;
 
 	for (i = 0; i < stream->outcnt; i++)
 		SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN;
@@ -145,22 +145,9 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
 handle_in:
 	sctp_stream_interleave_init(stream);
 	if (!incnt)
-		goto out;
-
-	ret = sctp_stream_alloc_in(stream, incnt, gfp);
-	if (ret)
-		goto in_err;
-
-	goto out;
+		return 0;
 
-in_err:
-	sched->free(stream);
-	genradix_free(&stream->in);
-out_err:
-	genradix_free(&stream->out);
-	stream->outcnt = 0;
-out:
-	return ret;
+	return sctp_stream_alloc_in(stream, incnt, gfp);
 }
 
 int sctp_stream_init_ext(struct sctp_stream *stream, __u16 sid)
diff --git a/net/sctp/stream_sched.c b/net/sctp/stream_sched.c
index 99e5f69fbb74..a2e1d34f52c5 100644
--- a/net/sctp/stream_sched.c
+++ b/net/sctp/stream_sched.c
@@ -163,7 +163,7 @@ int sctp_sched_set_sched(struct sctp_association *asoc,
 		if (!SCTP_SO(&asoc->stream, i)->ext)
 			continue;
 
-		ret = n->init_sid(&asoc->stream, i, GFP_KERNEL);
+		ret = n->init_sid(&asoc->stream, i, GFP_ATOMIC);
 		if (ret)
 			goto err;
 	}
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 2ddd7b34b4ce..26f81e2e1dfb 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1490,7 +1490,6 @@ static void smc_listen_out_connected(struct smc_sock *new_smc)
 {
 	struct sock *newsmcsk = &new_smc->sk;
 
-	sk_refcnt_debug_inc(newsmcsk);
 	if (newsmcsk->sk_state == SMC_INIT)
 		newsmcsk->sk_state = SMC_ACTIVE;
 
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index ee1f0fdba085..0ef15f8fba90 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -1787,7 +1787,7 @@ void smc_llc_lgr_init(struct smc_link_group *lgr, struct smc_sock *smc)
 	init_waitqueue_head(&lgr->llc_flow_waiter);
 	init_waitqueue_head(&lgr->llc_msg_waiter);
 	mutex_init(&lgr->llc_conf_mutex);
-	lgr->llc_testlink_time = net->ipv4.sysctl_tcp_keepalive_time;
+	lgr->llc_testlink_time = READ_ONCE(net->ipv4.sysctl_tcp_keepalive_time);
 }
 
 /* called after lgr was removed from lgr_list */
diff --git a/net/socket.c b/net/socket.c
index 5053eb0100e4..73666b878f2c 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1721,7 +1721,7 @@ int __sys_listen(int fd, int backlog)
 
 	sock = sockfd_lookup_light(fd, &err, &fput_needed);
 	if (sock) {
-		somaxconn = sock_net(sock->sk)->core.sysctl_somaxconn;
+		somaxconn = READ_ONCE(sock_net(sock->sk)->core.sysctl_somaxconn);
 		if ((unsigned int)backlog > somaxconn)
 			backlog = somaxconn;
 
diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c
index a9f0d17fdb0d..1bae32c48284 100644
--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -445,7 +445,7 @@ rpcauth_prune_expired(struct list_head *free, int nr_to_scan)
 		 * Enforce a 60 second garbage collection moratorium
 		 * Note that the cred_unused list must be time-ordered.
 		 */
-		if (!time_in_range(cred->cr_expire, expired, jiffies))
+		if (time_in_range(cred->cr_expire, expired, jiffies))
 			continue;
 		if (!rpcauth_unhash_cred(cred))
 			continue;
diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c
index 22a2c235abf1..77e347a45344 100644
--- a/net/sunrpc/backchannel_rqst.c
+++ b/net/sunrpc/backchannel_rqst.c
@@ -64,6 +64,17 @@ static void xprt_free_allocation(struct rpc_rqst *req)
 	kfree(req);
 }
 
+static void xprt_bc_reinit_xdr_buf(struct xdr_buf *buf)
+{
+	buf->head[0].iov_len = PAGE_SIZE;
+	buf->tail[0].iov_len = 0;
+	buf->pages = NULL;
+	buf->page_len = 0;
+	buf->flags = 0;
+	buf->len = 0;
+	buf->buflen = PAGE_SIZE;
+}
+
 static int xprt_alloc_xdr_buf(struct xdr_buf *buf, gfp_t gfp_flags)
 {
 	struct page *page;
@@ -292,6 +303,9 @@ void xprt_free_bc_rqst(struct rpc_rqst *req)
 	 */
 	spin_lock_bh(&xprt->bc_pa_lock);
 	if (xprt_need_to_requeue(xprt)) {
+		xprt_bc_reinit_xdr_buf(&req->rq_snd_buf);
+		xprt_bc_reinit_xdr_buf(&req->rq_rcv_buf);
+		req->rq_rcv_buf.len = PAGE_SIZE;
 		list_add_tail(&req->rq_bc_pa_list, &xprt->bc_pa_list);
 		xprt->bc_alloc_count++;
 		atomic_inc(&xprt->bc_slot_count);
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 6a035e9339d2..ca2a494d727b 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1881,7 +1881,7 @@ call_encode(struct rpc_task *task)
 			break;
 		case -EKEYEXPIRED:
 			if (!task->tk_cred_retry) {
-				rpc_exit(task, task->tk_status);
+				rpc_call_rpcerror(task, task->tk_status);
 			} else {
 				task->tk_action = call_refresh;
 				task->tk_cred_retry--;
diff --git a/net/sunrpc/sysfs.c b/net/sunrpc/sysfs.c
index 326a31422a3c..a7020b1f3ec7 100644
--- a/net/sunrpc/sysfs.c
+++ b/net/sunrpc/sysfs.c
@@ -282,8 +282,10 @@ static ssize_t rpc_sysfs_xprt_state_change(struct kobject *kobj,
 	int offline = 0, online = 0, remove = 0;
 	struct rpc_xprt_switch *xps = rpc_sysfs_xprt_kobj_get_xprt_switch(kobj);
 
-	if (!xprt)
-		return 0;
+	if (!xprt || !xps) {
+		count = 0;
+		goto out_put;
+	}
 
 	if (!strncmp(buf, "offline", 7))
 		offline = 1;
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 85473264cccf..f0a0a4ad6d52 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -979,7 +979,7 @@ static __be32 *xdr_get_next_encode_buffer(struct xdr_stream *xdr,
 	 */
 	xdr->p = (void *)p + frag2bytes;
 	space_left = xdr->buf->buflen - xdr->buf->len;
-	if (space_left - nbytes >= PAGE_SIZE)
+	if (space_left - frag1bytes >= PAGE_SIZE)
 		xdr->end = (void *)p + PAGE_SIZE;
 	else
 		xdr->end = (void *)p + space_left - frag1bytes;
diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c
index 2f4d23238a7e..9618e4429f0f 100644
--- a/net/tipc/monitor.c
+++ b/net/tipc/monitor.c
@@ -160,7 +160,7 @@ static void map_set(u64 *up_map, int i, unsigned int v)
 
 static int map_get(u64 up_map, int i)
 {
-	return (up_map & (1 << i)) >> i;
+	return (up_map & (1ULL << i)) >> i;
 }
 
 static struct tipc_peer *peer_prev(struct tipc_peer *peer)
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 6ef95ce565bd..b48d97cbbe29 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -472,8 +472,8 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr, u8 *peer_id,
 				   bool preliminary)
 {
 	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	struct tipc_link *l, *snd_l = tipc_bc_sndlink(net);
 	struct tipc_node *n, *temp_node;
-	struct tipc_link *l;
 	unsigned long intv;
 	int bearer_id;
 	int i;
@@ -488,6 +488,16 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr, u8 *peer_id,
 			goto exit;
 		/* A preliminary node becomes "real" now, refresh its data */
 		tipc_node_write_lock(n);
+		if (!tipc_link_bc_create(net, tipc_own_addr(net), addr, peer_id, U16_MAX,
+					 tipc_link_min_win(snd_l), tipc_link_max_win(snd_l),
+					 n->capabilities, &n->bc_entry.inputq1,
+					 &n->bc_entry.namedq, snd_l, &n->bc_entry.link)) {
+			pr_warn("Broadcast rcv link refresh failed, no memory\n");
+			tipc_node_write_unlock_fast(n);
+			tipc_node_put(n);
+			n = NULL;
+			goto exit;
+		}
 		n->preliminary = false;
 		n->addr = addr;
 		hlist_del_rcu(&n->hash);
@@ -567,7 +577,16 @@ update:
 	n->signature = INVALID_NODE_SIG;
 	n->active_links[0] = INVALID_BEARER_ID;
 	n->active_links[1] = INVALID_BEARER_ID;
-	n->bc_entry.link = NULL;
+	if (!preliminary &&
+	    !tipc_link_bc_create(net, tipc_own_addr(net), addr, peer_id, U16_MAX,
+				 tipc_link_min_win(snd_l), tipc_link_max_win(snd_l),
+				 n->capabilities, &n->bc_entry.inputq1,
+				 &n->bc_entry.namedq, snd_l, &n->bc_entry.link)) {
+		pr_warn("Broadcast rcv link creation failed, no memory\n");
+		kfree(n);
+		n = NULL;
+		goto exit;
+	}
 	tipc_node_get(n);
 	timer_setup(&n->timer, tipc_node_timeout, 0);
 	/* Start a slow timer anyway, crypto needs it */
@@ -1155,7 +1174,7 @@ void tipc_node_check_dest(struct net *net, u32 addr,
 			  bool *respond, bool *dupl_addr)
 {
 	struct tipc_node *n;
-	struct tipc_link *l, *snd_l;
+	struct tipc_link *l;
 	struct tipc_link_entry *le;
 	bool addr_match = false;
 	bool sign_match = false;
@@ -1175,22 +1194,6 @@ void tipc_node_check_dest(struct net *net, u32 addr,
 		return;
 
 	tipc_node_write_lock(n);
-	if (unlikely(!n->bc_entry.link)) {
-		snd_l = tipc_bc_sndlink(net);
-		if (!tipc_link_bc_create(net, tipc_own_addr(net),
-					 addr, peer_id, U16_MAX,
-					 tipc_link_min_win(snd_l),
-					 tipc_link_max_win(snd_l),
-					 n->capabilities,
-					 &n->bc_entry.inputq1,
-					 &n->bc_entry.namedq, snd_l,
-					 &n->bc_entry.link)) {
-			pr_warn("Broadcast rcv link creation failed, no mem\n");
-			tipc_node_write_unlock_fast(n);
-			tipc_node_put(n);
-			return;
-		}
-	}
 
 	le = &n->links[b->identity];
 
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 17f8c523e33b..f1c3b8eb4b3d 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -502,6 +502,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
 	sock_init_data(sock, sk);
 	tipc_set_sk_state(sk, TIPC_OPEN);
 	if (tipc_sk_insert(tsk)) {
+		sk_free(sk);
 		pr_warn("Socket create failed; port number exhausted\n");
 		return -EINVAL;
 	}
@@ -516,7 +517,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
 	timer_setup(&sk->sk_timer, tipc_sk_timeout, 0);
 	sk->sk_shutdown = 0;
 	sk->sk_backlog_rcv = tipc_sk_backlog_rcv;
-	sk->sk_rcvbuf = sysctl_tipc_rmem[1];
+	sk->sk_rcvbuf = READ_ONCE(sysctl_tipc_rmem[1]);
 	sk->sk_data_ready = tipc_data_ready;
 	sk->sk_write_space = tipc_write_space;
 	sk->sk_destruct = tipc_sock_destruct;
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index f3e3d009cf1c..cf75969375cf 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -97,13 +97,16 @@ static void tls_device_queue_ctx_destruction(struct tls_context *ctx)
 	unsigned long flags;
 
 	spin_lock_irqsave(&tls_device_lock, flags);
+	if (unlikely(!refcount_dec_and_test(&ctx->refcount)))
+		goto unlock;
+
 	list_move_tail(&ctx->list, &tls_device_gc_list);
 
 	/* schedule_work inside the spinlock
 	 * to make sure tls_device_down waits for that work.
 	 */
 	schedule_work(&tls_device_gc_work);
-
+unlock:
 	spin_unlock_irqrestore(&tls_device_lock, flags);
 }
 
@@ -194,8 +197,7 @@ void tls_device_sk_destruct(struct sock *sk)
 		clean_acked_data_disable(inet_csk(sk));
 	}
 
-	if (refcount_dec_and_test(&tls_ctx->refcount))
-		tls_device_queue_ctx_destruction(tls_ctx);
+	tls_device_queue_ctx_destruction(tls_ctx);
 }
 EXPORT_SYMBOL_GPL(tls_device_sk_destruct);
 
@@ -1349,8 +1351,13 @@ static int tls_device_down(struct net_device *netdev)
 		 * by tls_device_free_ctx. rx_conf and tx_conf stay in TLS_HW.
 		 * Now release the ref taken above.
 		 */
-		if (refcount_dec_and_test(&ctx->refcount))
+		if (refcount_dec_and_test(&ctx->refcount)) {
+			/* sk_destruct ran after tls_device_down took a ref, and
+			 * it returned early. Complete the destruction here.
+			 */
+			list_del(&ctx->list);
 			tls_device_free_ctx(ctx);
+		}
 	}
 
 	up_write(&device_offload_lock);
@@ -1394,9 +1401,9 @@ static struct notifier_block tls_dev_notifier = {
 	.notifier_call	= tls_dev_event,
 };
 
-void __init tls_device_init(void)
+int __init tls_device_init(void)
 {
-	register_netdevice_notifier(&tls_dev_notifier);
+	return register_netdevice_notifier(&tls_dev_notifier);
 }
 
 void __exit tls_device_cleanup(void)
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 62b1c5e32bbd..a947cfb100bd 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -910,7 +910,12 @@ static int __init tls_register(void)
 	if (err)
 		return err;
 
-	tls_device_init();
+	err = tls_device_init();
+	if (err) {
+		unregister_pernet_subsys(&tls_proc_ops);
+		return err;
+	}
+
 	tcp_register_ulp(&tcp_tls_ulp_ops);
 
 	return 0;
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 5df530e89e5a..5d46036f3ad7 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1285,6 +1285,7 @@ static void vsock_connect_timeout(struct work_struct *work)
 	if (sk->sk_state == TCP_SYN_SENT &&
 	    (sk->sk_shutdown != SHUTDOWN_MASK)) {
 		sk->sk_state = TCP_CLOSE;
+		sk->sk_socket->state = SS_UNCONNECTED;
 		sk->sk_err = ETIMEDOUT;
 		sk_error_report(sk);
 		vsock_transport_cancel_pkt(vsk);
@@ -1390,7 +1391,14 @@ static int vsock_connect(struct socket *sock, struct sockaddr *addr,
 			 * timeout fires.
 			 */
 			sock_hold(sk);
-			schedule_delayed_work(&vsk->connect_work, timeout);
+
+			/* If the timeout function is already scheduled,
+			 * reschedule it, then ungrab the socket refcount to
+			 * keep it balanced.
+			 */
+			if (mod_delayed_work(system_wq, &vsk->connect_work,
+					     timeout))
+				sock_put(sk);
 
 			/* Skip ahead to preserve error code set above. */
 			goto out_wait;
diff --git a/net/wireless/debugfs.c b/net/wireless/debugfs.c
index aab43469a2f0..0878b162890a 100644
--- a/net/wireless/debugfs.c
+++ b/net/wireless/debugfs.c
@@ -65,9 +65,10 @@ static ssize_t ht40allow_map_read(struct file *file,
 {
 	struct wiphy *wiphy = file->private_data;
 	char *buf;
-	unsigned int offset = 0, buf_size = PAGE_SIZE, i, r;
+	unsigned int offset = 0, buf_size = PAGE_SIZE, i;
 	enum nl80211_band band;
 	struct ieee80211_supported_band *sband;
+	ssize_t r;
 
 	buf = kzalloc(buf_size, GFP_KERNEL);
 	if (!buf)
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 630047a2c79b..2728d6aadef2 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -327,6 +327,7 @@ static void __xp_dma_unmap(struct xsk_dma_map *dma_map, unsigned long attrs)
 	for (i = 0; i < dma_map->dma_pages_cnt; i++) {
 		dma = &dma_map->dma_pages[i];
 		if (*dma) {
+			*dma &= ~XSK_NEXT_PG_CONTIG_MASK;
 			dma_unmap_page_attrs(dma_map->dev, *dma, PAGE_SIZE,
 					     DMA_BIDIRECTIONAL, attrs);
 			*dma = 0;
diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c
index 1f08ebf7d80c..24ca49ecebea 100644
--- a/net/xfrm/espintcp.c
+++ b/net/xfrm/espintcp.c
@@ -170,7 +170,7 @@ int espintcp_queue_out(struct sock *sk, struct sk_buff *skb)
 {
 	struct espintcp_ctx *ctx = espintcp_getctx(sk);
 
-	if (skb_queue_len(&ctx->out_queue) >= netdev_max_backlog)
+	if (skb_queue_len(&ctx->out_queue) >= READ_ONCE(netdev_max_backlog))
 		return -ENOBUFS;
 
 	__skb_queue_tail(&ctx->out_queue, skb);
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 3df0861d4390..5f34bc378fdc 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -782,7 +782,7 @@ int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb,
 
 	trans = this_cpu_ptr(&xfrm_trans_tasklet);
 
-	if (skb_queue_len(&trans->queue) >= netdev_max_backlog)
+	if (skb_queue_len(&trans->queue) >= READ_ONCE(netdev_max_backlog))
 		return -ENOBUFS;
 
 	BUILD_BUG_ON(sizeof(struct xfrm_trans_cb) > sizeof(skb->cb));
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index a6271b955e11..ba58b963f482 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2678,8 +2678,10 @@ static int xfrm_expand_policies(const struct flowi *fl, u16 family,
 		*num_xfrms = 0;
 		return 0;
 	}
-	if (IS_ERR(pols[0]))
+	if (IS_ERR(pols[0])) {
+		*num_pols = 0;
 		return PTR_ERR(pols[0]);
+	}
 
 	*num_xfrms = pols[0]->xfrm_nr;
 
@@ -2694,6 +2696,7 @@ static int xfrm_expand_policies(const struct flowi *fl, u16 family,
 		if (pols[1]) {
 			if (IS_ERR(pols[1])) {
 				xfrm_pols_put(pols, *num_pols);
+				*num_pols = 0;
 				return PTR_ERR(pols[1]);
 			}
 			(*num_pols)++;
@@ -3159,7 +3162,7 @@ ok:
 	return dst;
 
 nopol:
-	if (!(dst_orig->dev->flags & IFF_LOOPBACK) &&
+	if ((!dst_orig->dev || !(dst_orig->dev->flags & IFF_LOOPBACK)) &&
 	    net->xfrm.policy_default[dir] == XFRM_USERPOLICY_BLOCK) {
 		err = -EPERM;
 		goto error;
@@ -3597,6 +3600,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 		if (pols[1]) {
 			if (IS_ERR(pols[1])) {
 				XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR);
+				xfrm_pol_put(pols[0]);
 				return 0;
 			}
 			pols[1]->curlft.use_time = ktime_get_real_seconds();
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index f7bfa1916968..15132b080614 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1591,6 +1591,7 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig,
 	x->replay = orig->replay;
 	x->preplay = orig->preplay;
 	x->mapping_maxage = orig->mapping_maxage;
+	x->lastused = orig->lastused;
 	x->new_mapping = 0;
 	x->new_mapping_sport = 0;
 
@@ -2619,7 +2620,7 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload)
 	int err;
 
 	if (family == AF_INET &&
-	    xs_net(x)->ipv4.sysctl_ip_no_pmtu_disc)
+	    READ_ONCE(xs_net(x)->ipv4.sysctl_ip_no_pmtu_disc))
 		x->props.flags |= XFRM_STATE_NOPMTUDISC;
 
 	err = -EPROTONOSUPPORT;
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 2b988b6ccacb..17aa8ef2d52a 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -231,6 +231,7 @@ objtool_args =								\
 	$(if $(CONFIG_FRAME_POINTER),, --no-fp)				\
 	$(if $(CONFIG_GCOV_KERNEL)$(CONFIG_LTO_CLANG), --no-unreachable)\
 	$(if $(CONFIG_RETPOLINE), --retpoline)				\
+	$(if $(CONFIG_RETHUNK), --rethunk)				\
 	$(if $(CONFIG_X86_SMAP), --uaccess)				\
 	$(if $(CONFIG_FTRACE_MCOUNT_USE_OBJTOOL), --mcount)		\
 	$(if $(CONFIG_SLS), --sls)
diff --git a/scripts/Makefile.gcc-plugins b/scripts/Makefile.gcc-plugins
index 4aad28480035..36814be80264 100644
--- a/scripts/Makefile.gcc-plugins
+++ b/scripts/Makefile.gcc-plugins
@@ -6,7 +6,7 @@ gcc-plugin-$(CONFIG_GCC_PLUGIN_LATENT_ENTROPY)	+= latent_entropy_plugin.so
 gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_LATENT_ENTROPY)		\
 		+= -DLATENT_ENTROPY_PLUGIN
 ifdef CONFIG_GCC_PLUGIN_LATENT_ENTROPY
-    DISABLE_LATENT_ENTROPY_PLUGIN += -fplugin-arg-latent_entropy_plugin-disable
+    DISABLE_LATENT_ENTROPY_PLUGIN += -fplugin-arg-latent_entropy_plugin-disable -ULATENT_ENTROPY_PLUGIN
 endif
 export DISABLE_LATENT_ENTROPY_PLUGIN
 
diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal
index ff805777431c..ce9661d968a3 100644
--- a/scripts/Makefile.modfinal
+++ b/scripts/Makefile.modfinal
@@ -40,7 +40,7 @@ quiet_cmd_ld_ko_o = LD [M]  $@
 quiet_cmd_btf_ko = BTF [M] $@
       cmd_btf_ko = 							\
 	if [ -f vmlinux ]; then						\
-		LLVM_OBJCOPY="$(OBJCOPY)" $(PAHOLE) -J --btf_base vmlinux $@; \
+		LLVM_OBJCOPY="$(OBJCOPY)" $(PAHOLE) -J $(PAHOLE_FLAGS) --btf_base vmlinux $@; \
 	else								\
 		printf "Skipping BTF generation for %s due to unavailability of vmlinux\n" $@ 1>&2; \
 	fi;
diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost
index 48585c4d04ad..0273bf7375e2 100644
--- a/scripts/Makefile.modpost
+++ b/scripts/Makefile.modpost
@@ -87,8 +87,7 @@ obj := $(KBUILD_EXTMOD)
 src := $(obj)
 
 # Include the module's Makefile to find KBUILD_EXTRA_SYMBOLS
-include $(if $(wildcard $(KBUILD_EXTMOD)/Kbuild), \
-             $(KBUILD_EXTMOD)/Kbuild, $(KBUILD_EXTMOD)/Makefile)
+include $(if $(wildcard $(src)/Kbuild), $(src)/Kbuild, $(src)/Makefile)
 
 # modpost option for external modules
 MODPOST += -e
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index c27d2312cfc3..88cb294dc447 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -489,7 +489,8 @@ our $Attribute	= qr{
 			____cacheline_aligned|
 			____cacheline_aligned_in_smp|
 			____cacheline_internodealigned_in_smp|
-			__weak
+			__weak|
+			__alloc_size\s*\(\s*\d+\s*(?:,\s*\d+\s*)?\)
 		  }x;
 our $Modifier;
 our $Inline	= qr{inline|__always_inline|noinline|__inline|__inline__};
diff --git a/scripts/dummy-tools/dummy-plugin-dir/include/plugin-version.h b/scripts/dummy-tools/dummy-plugin-dir/include/plugin-version.h
new file mode 100644
index 000000000000..e69de29bb2d1
--- /dev/null
+++ b/scripts/dummy-tools/dummy-plugin-dir/include/plugin-version.h
diff --git a/scripts/dummy-tools/gcc b/scripts/dummy-tools/gcc
index b2483149bbe5..7db825843435 100755
--- a/scripts/dummy-tools/gcc
+++ b/scripts/dummy-tools/gcc
@@ -96,12 +96,8 @@ fi
 
 # To set GCC_PLUGINS
 if arg_contain -print-file-name=plugin "$@"; then
-	plugin_dir=$(mktemp -d)
-
-	mkdir -p $plugin_dir/include
-	touch $plugin_dir/include/plugin-version.h
-
-	echo $plugin_dir
+	# Use $0 to find the in-tree dummy directory
+	echo "$(dirname "$(readlink -f "$0")")/dummy-plugin-dir"
 	exit 0
 fi
 
diff --git a/scripts/faddr2line b/scripts/faddr2line
index 94ed98dd899f..57099687e5e1 100755
--- a/scripts/faddr2line
+++ b/scripts/faddr2line
@@ -112,7 +112,9 @@ __faddr2line() {
 	# section offsets.
 	local file_type=$(${READELF} --file-header $objfile |
 		${AWK} '$1 == "Type:" { print $2; exit }')
-	[[ $file_type = "EXEC" ]] && is_vmlinux=1
+	if [[ $file_type = "EXEC" ]] || [[ $file_type == "DYN" ]]; then
+		is_vmlinux=1
+	fi
 
 	# Go through each of the object's symbols which match the func name.
 	# In rare cases there might be duplicates, in which case we print all
diff --git a/scripts/gdb/linux/dmesg.py b/scripts/gdb/linux/dmesg.py
index a92c55bd8de5..c771831eb077 100644
--- a/scripts/gdb/linux/dmesg.py
+++ b/scripts/gdb/linux/dmesg.py
@@ -22,7 +22,6 @@ prb_desc_type = utils.CachedType("struct prb_desc")
 prb_desc_ring_type = utils.CachedType("struct prb_desc_ring")
 prb_data_ring_type = utils.CachedType("struct prb_data_ring")
 printk_ringbuffer_type = utils.CachedType("struct printk_ringbuffer")
-atomic_long_type = utils.CachedType("atomic_long_t")
 
 class LxDmesg(gdb.Command):
     """Print Linux kernel log buffer."""
@@ -44,19 +43,17 @@ class LxDmesg(gdb.Command):
         sz = prb_desc_ring_type.get_type().sizeof
         desc_ring = utils.read_memoryview(inf, addr, sz).tobytes()
 
-        # read in descriptor array
+        # read in descriptor count, size, and address
         off = prb_desc_ring_type.get_type()['count_bits'].bitpos // 8
         desc_ring_count = 1 << utils.read_u32(desc_ring, off)
         desc_sz = prb_desc_type.get_type().sizeof
         off = prb_desc_ring_type.get_type()['descs'].bitpos // 8
-        addr = utils.read_ulong(desc_ring, off)
-        descs = utils.read_memoryview(inf, addr, desc_sz * desc_ring_count).tobytes()
+        desc_addr = utils.read_ulong(desc_ring, off)
 
-        # read in info array
+        # read in info size and address
         info_sz = printk_info_type.get_type().sizeof
         off = prb_desc_ring_type.get_type()['infos'].bitpos // 8
-        addr = utils.read_ulong(desc_ring, off)
-        infos = utils.read_memoryview(inf, addr, info_sz * desc_ring_count).tobytes()
+        info_addr = utils.read_ulong(desc_ring, off)
 
         # read in text data ring structure
         off = printk_ringbuffer_type.get_type()['text_data_ring'].bitpos // 8
@@ -64,14 +61,11 @@ class LxDmesg(gdb.Command):
         sz = prb_data_ring_type.get_type().sizeof
         text_data_ring = utils.read_memoryview(inf, addr, sz).tobytes()
 
-        # read in text data
+        # read in text data size and address
         off = prb_data_ring_type.get_type()['size_bits'].bitpos // 8
         text_data_sz = 1 << utils.read_u32(text_data_ring, off)
         off = prb_data_ring_type.get_type()['data'].bitpos // 8
-        addr = utils.read_ulong(text_data_ring, off)
-        text_data = utils.read_memoryview(inf, addr, text_data_sz).tobytes()
-
-        counter_off = atomic_long_type.get_type()['counter'].bitpos // 8
+        text_data_addr = utils.read_ulong(text_data_ring, off)
 
         sv_off = prb_desc_type.get_type()['state_var'].bitpos // 8
 
@@ -92,9 +86,9 @@ class LxDmesg(gdb.Command):
 
         # read in tail and head descriptor ids
         off = prb_desc_ring_type.get_type()['tail_id'].bitpos // 8
-        tail_id = utils.read_u64(desc_ring, off + counter_off)
+        tail_id = utils.read_atomic_long(desc_ring, off)
         off = prb_desc_ring_type.get_type()['head_id'].bitpos // 8
-        head_id = utils.read_u64(desc_ring, off + counter_off)
+        head_id = utils.read_atomic_long(desc_ring, off)
 
         did = tail_id
         while True:
@@ -102,17 +96,20 @@ class LxDmesg(gdb.Command):
             desc_off = desc_sz * ind
             info_off = info_sz * ind
 
+            desc = utils.read_memoryview(inf, desc_addr + desc_off, desc_sz).tobytes()
+
             # skip non-committed record
-            state = 3 & (utils.read_u64(descs, desc_off + sv_off +
-                                        counter_off) >> desc_flags_shift)
+            state = 3 & (utils.read_atomic_long(desc, sv_off) >> desc_flags_shift)
             if state != desc_committed and state != desc_finalized:
                 if did == head_id:
                     break
                 did = (did + 1) & desc_id_mask
                 continue
 
-            begin = utils.read_ulong(descs, desc_off + begin_off) % text_data_sz
-            end = utils.read_ulong(descs, desc_off + next_off) % text_data_sz
+            begin = utils.read_ulong(desc, begin_off) % text_data_sz
+            end = utils.read_ulong(desc, next_off) % text_data_sz
+
+            info = utils.read_memoryview(inf, info_addr + info_off, info_sz).tobytes()
 
             # handle data-less record
             if begin & 1 == 1:
@@ -125,16 +122,17 @@ class LxDmesg(gdb.Command):
                 # skip over descriptor id
                 text_start = begin + utils.get_long_type().sizeof
 
-                text_len = utils.read_u16(infos, info_off + len_off)
+                text_len = utils.read_u16(info, len_off)
 
                 # handle truncated message
                 if end - text_start < text_len:
                     text_len = end - text_start
 
-                text = text_data[text_start:text_start + text_len].decode(
-                    encoding='utf8', errors='replace')
+                text_data = utils.read_memoryview(inf, text_data_addr + text_start,
+                                                  text_len).tobytes()
+                text = text_data[0:text_len].decode(encoding='utf8', errors='replace')
 
-            time_stamp = utils.read_u64(infos, info_off + ts_off)
+            time_stamp = utils.read_u64(info, ts_off)
 
             for line in text.splitlines():
                 msg = u"[{time:12.6f}] {line}\n".format(
diff --git a/scripts/gdb/linux/utils.py b/scripts/gdb/linux/utils.py
index ff7c1799d588..1553f68716cc 100644
--- a/scripts/gdb/linux/utils.py
+++ b/scripts/gdb/linux/utils.py
@@ -35,13 +35,12 @@ class CachedType:
 
 
 long_type = CachedType("long")
-
+atomic_long_type = CachedType("atomic_long_t")
 
 def get_long_type():
     global long_type
     return long_type.get_type()
 
-
 def offset_of(typeobj, field):
     element = gdb.Value(0).cast(typeobj)
     return int(str(element[field].address).split()[0], 16)
@@ -129,6 +128,17 @@ def read_ulong(buffer, offset):
     else:
         return read_u32(buffer, offset)
 
+atomic_long_counter_offset = atomic_long_type.get_type()['counter'].bitpos
+atomic_long_counter_sizeof = atomic_long_type.get_type()['counter'].type.sizeof
+
+def read_atomic_long(buffer, offset):
+    global atomic_long_counter_offset
+    global atomic_long_counter_sizeof
+
+    if atomic_long_counter_sizeof == 8:
+        return read_u64(buffer, offset + atomic_long_counter_offset)
+    else:
+        return read_u32(buffer, offset + atomic_long_counter_offset)
 
 target_arch = None
 
diff --git a/scripts/kernel-doc b/scripts/kernel-doc
index cfcb60737957..5d54b57ff90c 100755
--- a/scripts/kernel-doc
+++ b/scripts/kernel-doc
@@ -1245,6 +1245,13 @@ sub dump_struct($$) {
 	$members =~ s/\s*CRYPTO_MINALIGN_ATTR/ /gos;
 	$members =~ s/\s*____cacheline_aligned_in_smp/ /gos;
 	$members =~ s/\s*____cacheline_aligned/ /gos;
+	# unwrap struct_group():
+	# - first eat non-declaration parameters and rewrite for final match
+	# - then remove macro, outer parens, and trailing semicolon
+	$members =~ s/\bstruct_group\s*\(([^,]*,)/STRUCT_GROUP(/gos;
+	$members =~ s/\bstruct_group_(attr|tagged)\s*\(([^,]*,){2}/STRUCT_GROUP(/gos;
+	$members =~ s/\b__struct_group\s*\(([^,]*,){3}/STRUCT_GROUP(/gos;
+	$members =~ s/\bSTRUCT_GROUP(\(((?:(?>[^)(]+)|(?1))*)\))[^;]*;/$2/gos;
 
 	my $args = qr{([^,)]+)};
 	# replace DECLARE_BITMAP
@@ -1256,6 +1263,8 @@ sub dump_struct($$) {
 	$members =~ s/DECLARE_KFIFO\s*\($args,\s*$args,\s*$args\)/$2 \*$1/gos;
 	# replace DECLARE_KFIFO_PTR
 	$members =~ s/DECLARE_KFIFO_PTR\s*\($args,\s*$args\)/$2 \*$1/gos;
+	# replace DECLARE_FLEX_ARRAY
+	$members =~ s/(?:__)?DECLARE_FLEX_ARRAY\s*\($args,\s*$args\)/$1 $2\[\]/gos;
 	my $declaration = $members;
 
 	# Split nested struct/union elements as newer ones
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index 59a3df87907e..57ef6accbb40 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -120,6 +120,9 @@ objtool_link()
 
 	if [ -n "${CONFIG_VMLINUX_VALIDATION}" ]; then
 		objtoolopt="${objtoolopt} --noinstr"
+		if is_enabled CONFIG_CPU_UNRET_ENTRY; then
+			objtoolopt="${objtoolopt} --unret"
+		fi
 	fi
 
 	if [ -n "${objtoolopt}" ]; then
@@ -208,7 +211,6 @@ vmlinux_link()
 gen_btf()
 {
 	local pahole_ver
-	local extra_paholeopt=
 
 	if ! [ -x "$(command -v ${PAHOLE})" ]; then
 		echo >&2 "BTF: ${1}: pahole (${PAHOLE}) is not available"
@@ -223,16 +225,8 @@ gen_btf()
 
 	vmlinux_link ${1}
 
-	if [ "${pahole_ver}" -ge "118" ] && [ "${pahole_ver}" -le "121" ]; then
-		# pahole 1.18 through 1.21 can't handle zero-sized per-CPU vars
-		extra_paholeopt="${extra_paholeopt} --skip_encoding_btf_vars"
-	fi
-	if [ "${pahole_ver}" -ge "121" ]; then
-		extra_paholeopt="${extra_paholeopt} --btf_gen_floats"
-	fi
-
 	info "BTF" ${2}
-	LLVM_OBJCOPY="${OBJCOPY}" ${PAHOLE} -J ${extra_paholeopt} ${1}
+	LLVM_OBJCOPY="${OBJCOPY}" ${PAHOLE} -J ${PAHOLE_FLAGS} ${1}
 
 	# Create ${2} which contains just .BTF section but no symbols. Add
 	# SHF_ALLOC because .BTF will be part of the vmlinux image. --strip-all
diff --git a/scripts/mksysmap b/scripts/mksysmap
index 9aa23d15862a..ad8bbc52267d 100755
--- a/scripts/mksysmap
+++ b/scripts/mksysmap
@@ -41,4 +41,4 @@
 # so we just ignore them to let readprofile continue to work.
 # (At least sparc64 has __crc_ in the middle).
 
-$NM -n $1 | grep -v '\( [aNUw] \)\|\(__crc_\)\|\( \$[adt]\)\|\( \.L\)' > $2
+$NM -n $1 | grep -v '\( [aNUw] \)\|\(__crc_\)\|\( \$[adt]\)\|\( \.L\)\|\( L0\)' > $2
diff --git a/scripts/module.lds.S b/scripts/module.lds.S
index 1d0e1e4dc3d2..3a3aa2354ed8 100644
--- a/scripts/module.lds.S
+++ b/scripts/module.lds.S
@@ -27,6 +27,8 @@ SECTIONS {
 	.ctors			0 : ALIGN(8) { *(SORT(.ctors.*)) *(.ctors) }
 	.init_array		0 : ALIGN(8) { *(SORT(.init_array.*)) *(.init_array) }
 
+	.altinstructions	0 : ALIGN(8) { KEEP(*(.altinstructions)) }
+	__bug_table		0 : ALIGN(8) { KEEP(*(__bug_table)) }
 	__jump_table		0 : ALIGN(8) { KEEP(*(__jump_table)) }
 
 	__patchable_function_entries : { *(__patchable_function_entries) }
diff --git a/scripts/pahole-flags.sh b/scripts/pahole-flags.sh
new file mode 100755
index 000000000000..7acee326aa6c
--- /dev/null
+++ b/scripts/pahole-flags.sh
@@ -0,0 +1,24 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+extra_paholeopt=
+
+if ! [ -x "$(command -v ${PAHOLE})" ]; then
+	exit 0
+fi
+
+pahole_ver=$(${PAHOLE} --version | sed -E 's/v([0-9]+)\.([0-9]+)/\1\2/')
+
+if [ "${pahole_ver}" -ge "118" ] && [ "${pahole_ver}" -le "121" ]; then
+	# pahole 1.18 through 1.21 can't handle zero-sized per-CPU vars
+	extra_paholeopt="${extra_paholeopt} --skip_encoding_btf_vars"
+fi
+if [ "${pahole_ver}" -ge "121" ]; then
+	extra_paholeopt="${extra_paholeopt} --btf_gen_floats"
+fi
+
+if [ "${pahole_ver}" -ge "124" ]; then
+	extra_paholeopt="${extra_paholeopt} --skip_encoding_btf_enum64"
+fi
+
+echo ${extra_paholeopt}
diff --git a/scripts/sorttable.c b/scripts/sorttable.c
index 6ee4fa882919..278bb53b325c 100644
--- a/scripts/sorttable.c
+++ b/scripts/sorttable.c
@@ -240,7 +240,7 @@ static void x86_sort_relative_table(char *extab_image, int image_size)
 
 		w(r(loc) + i, loc);
 		w(r(loc + 1) + i + 4, loc + 1);
-		w(r(loc + 2) + i + 8, loc + 2);
+		/* Don't touch the fixup type */
 
 		i += sizeof(uint32_t) * 3;
 	}
@@ -253,7 +253,7 @@ static void x86_sort_relative_table(char *extab_image, int image_size)
 
 		w(r(loc) - i, loc);
 		w(r(loc + 1) - (i + 4), loc + 1);
-		w(r(loc + 2) - (i + 8), loc + 2);
+		/* Don't touch the fixup type */
 
 		i += sizeof(uint32_t) * 3;
 	}
diff --git a/security/Kconfig b/security/Kconfig
index fe6c0395fa02..5d412b3ddc49 100644
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -54,17 +54,6 @@ config SECURITY_NETWORK
 	  implement socket and networking access controls.
 	  If you are unsure how to answer this question, answer N.
 
-config PAGE_TABLE_ISOLATION
-	bool "Remove the kernel mapping in user mode"
-	default y
-	depends on (X86_64 || X86_PAE) && !UML
-	help
-	  This feature reduces the number of hardware side channels by
-	  ensuring that the majority of kernel addresses are not mapped
-	  into userspace.
-
-	  See Documentation/x86/pti.rst for more details.
-
 config SECURITY_INFINIBAND
 	bool "Infiniband Security Hooks"
 	depends on SECURITY && INFINIBAND
diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
index 2ee3b3d29f10..a891705b1d57 100644
--- a/security/apparmor/apparmorfs.c
+++ b/security/apparmor/apparmorfs.c
@@ -401,7 +401,7 @@ static struct aa_loaddata *aa_simple_write_to_buffer(const char __user *userbuf,
 
 	data->size = copy_size;
 	if (copy_from_user(data->data, userbuf, copy_size)) {
-		kvfree(data);
+		aa_put_loaddata(data);
 		return ERR_PTR(-EFAULT);
 	}
 
diff --git a/security/apparmor/audit.c b/security/apparmor/audit.c
index f7e97c7e80f3..704b0c895605 100644
--- a/security/apparmor/audit.c
+++ b/security/apparmor/audit.c
@@ -137,7 +137,7 @@ int aa_audit(int type, struct aa_profile *profile, struct common_audit_data *sa,
 	}
 	if (AUDIT_MODE(profile) == AUDIT_QUIET ||
 	    (type == AUDIT_APPARMOR_DENIED &&
-	     AUDIT_MODE(profile) == AUDIT_QUIET))
+	     AUDIT_MODE(profile) == AUDIT_QUIET_DENIED))
 		return aad(sa)->error;
 
 	if (KILL_MODE(profile) && type == AUDIT_APPARMOR_DENIED)
diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c
index 583680f6cd81..a7b3d8e58ed8 100644
--- a/security/apparmor/domain.c
+++ b/security/apparmor/domain.c
@@ -467,7 +467,7 @@ restart:
 				 * xattrs, or a longer match
 				 */
 				candidate = profile;
-				candidate_len = profile->xmatch_len;
+				candidate_len = max(count, profile->xmatch_len);
 				candidate_xattrs = ret;
 				conflict = false;
 			}
diff --git a/security/apparmor/include/lib.h b/security/apparmor/include/lib.h
index 7d27db740bc2..ac5054899f6f 100644
--- a/security/apparmor/include/lib.h
+++ b/security/apparmor/include/lib.h
@@ -22,6 +22,11 @@
  */
 
 #define DEBUG_ON (aa_g_debug)
+/*
+ * split individual debug cases out in preparation for finer grained
+ * debug controls in the future.
+ */
+#define AA_DEBUG_LABEL DEBUG_ON
 #define dbg_printk(__fmt, __args...) pr_debug(__fmt, ##__args)
 #define AA_DEBUG(fmt, args...)						\
 	do {								\
diff --git a/security/apparmor/include/policy.h b/security/apparmor/include/policy.h
index b5b4b8190e65..b5aa4231af68 100644
--- a/security/apparmor/include/policy.h
+++ b/security/apparmor/include/policy.h
@@ -135,7 +135,7 @@ struct aa_profile {
 
 	const char *attach;
 	struct aa_dfa *xmatch;
-	int xmatch_len;
+	unsigned int xmatch_len;
 	enum audit_mode audit;
 	long mode;
 	u32 path_flags;
diff --git a/security/apparmor/label.c b/security/apparmor/label.c
index 6222fdfebe4e..66bc4704f804 100644
--- a/security/apparmor/label.c
+++ b/security/apparmor/label.c
@@ -1632,9 +1632,9 @@ int aa_label_snxprint(char *str, size_t size, struct aa_ns *ns,
 	AA_BUG(!str && size != 0);
 	AA_BUG(!label);
 
-	if (flags & FLAG_ABS_ROOT) {
+	if (AA_DEBUG_LABEL && (flags & FLAG_ABS_ROOT)) {
 		ns = root_ns;
-		len = snprintf(str, size, "=");
+		len = snprintf(str, size, "_");
 		update_for_len(total, len, size, str);
 	} else if (!ns) {
 		ns = labels_ns(label);
@@ -1745,7 +1745,7 @@ void aa_label_xaudit(struct audit_buffer *ab, struct aa_ns *ns,
 	if (!use_label_hname(ns, label, flags) ||
 	    display_mode(ns, label, flags)) {
 		len  = aa_label_asxprint(&name, ns, label, flags, gfp);
-		if (len == -1) {
+		if (len < 0) {
 			AA_DEBUG("label print error");
 			return;
 		}
@@ -1773,7 +1773,7 @@ void aa_label_seq_xprint(struct seq_file *f, struct aa_ns *ns,
 		int len;
 
 		len = aa_label_asxprint(&str, ns, label, flags, gfp);
-		if (len == -1) {
+		if (len < 0) {
 			AA_DEBUG("label print error");
 			return;
 		}
@@ -1796,7 +1796,7 @@ void aa_label_xprintk(struct aa_ns *ns, struct aa_label *label, int flags,
 		int len;
 
 		len = aa_label_asxprint(&str, ns, label, flags, gfp);
-		if (len == -1) {
+		if (len < 0) {
 			AA_DEBUG("label print error");
 			return;
 		}
@@ -1896,7 +1896,8 @@ struct aa_label *aa_label_strn_parse(struct aa_label *base, const char *str,
 	AA_BUG(!str);
 
 	str = skipn_spaces(str, n);
-	if (str == NULL || (*str == '=' && base != &root_ns->unconfined->label))
+	if (str == NULL || (AA_DEBUG_LABEL && *str == '_' &&
+			    base != &root_ns->unconfined->label))
 		return ERR_PTR(-EINVAL);
 
 	len = label_count_strn_entries(str, end - str);
diff --git a/security/apparmor/mount.c b/security/apparmor/mount.c
index aa6fcfde3051..f7bb47daf2ad 100644
--- a/security/apparmor/mount.c
+++ b/security/apparmor/mount.c
@@ -229,7 +229,8 @@ static const char * const mnt_info_table[] = {
 	"failed srcname match",
 	"failed type match",
 	"failed flags match",
-	"failed data match"
+	"failed data match",
+	"failed perms check"
 };
 
 /*
@@ -284,8 +285,8 @@ static int do_match_mnt(struct aa_dfa *dfa, unsigned int start,
 			return 0;
 	}
 
-	/* failed at end of flags match */
-	return 4;
+	/* failed at perms check, don't confuse with flags match */
+	return 6;
 }
 
 
@@ -718,6 +719,7 @@ int aa_pivotroot(struct aa_label *label, const struct path *old_path,
 			aa_put_label(target);
 			goto out;
 		}
+		aa_put_label(target);
 	} else
 		/* already audited error */
 		error = PTR_ERR(target);
diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c
index 4e1f96b216a8..03c9609ca407 100644
--- a/security/apparmor/policy_unpack.c
+++ b/security/apparmor/policy_unpack.c
@@ -746,16 +746,18 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name)
 		profile->label.flags |= FLAG_HAT;
 	if (!unpack_u32(e, &tmp, NULL))
 		goto fail;
-	if (tmp == PACKED_MODE_COMPLAIN || (e->version & FORCE_COMPLAIN_FLAG))
+	if (tmp == PACKED_MODE_COMPLAIN || (e->version & FORCE_COMPLAIN_FLAG)) {
 		profile->mode = APPARMOR_COMPLAIN;
-	else if (tmp == PACKED_MODE_ENFORCE)
+	} else if (tmp == PACKED_MODE_ENFORCE) {
 		profile->mode = APPARMOR_ENFORCE;
-	else if (tmp == PACKED_MODE_KILL)
+	} else if (tmp == PACKED_MODE_KILL) {
 		profile->mode = APPARMOR_KILL;
-	else if (tmp == PACKED_MODE_UNCONFINED)
+	} else if (tmp == PACKED_MODE_UNCONFINED) {
 		profile->mode = APPARMOR_UNCONFINED;
-	else
+		profile->label.flags |= FLAG_UNCONFINED;
+	} else {
 		goto fail;
+	}
 	if (!unpack_u32(e, &tmp, NULL))
 		goto fail;
 	if (tmp)
diff --git a/security/integrity/evm/evm_crypto.c b/security/integrity/evm/evm_crypto.c
index 0450d79afdc8..b862f0f919bf 100644
--- a/security/integrity/evm/evm_crypto.c
+++ b/security/integrity/evm/evm_crypto.c
@@ -75,7 +75,7 @@ static struct shash_desc *init_desc(char type, uint8_t hash_algo)
 {
 	long rc;
 	const char *algo;
-	struct crypto_shash **tfm, *tmp_tfm = NULL;
+	struct crypto_shash **tfm, *tmp_tfm;
 	struct shash_desc *desc;
 
 	if (type == EVM_XATTR_HMAC) {
@@ -120,16 +120,13 @@ unlock:
 alloc:
 	desc = kmalloc(sizeof(*desc) + crypto_shash_descsize(*tfm),
 			GFP_KERNEL);
-	if (!desc) {
-		crypto_free_shash(tmp_tfm);
+	if (!desc)
 		return ERR_PTR(-ENOMEM);
-	}
 
 	desc->tfm = *tfm;
 
 	rc = crypto_shash_init(desc);
 	if (rc) {
-		crypto_free_shash(tmp_tfm);
 		kfree(desc);
 		return ERR_PTR(rc);
 	}
diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c
index dbba51583e7c..ed04bb7c7512 100644
--- a/security/integrity/ima/ima_appraise.c
+++ b/security/integrity/ima/ima_appraise.c
@@ -408,7 +408,8 @@ int ima_appraise_measurement(enum ima_hooks func,
 		goto out;
 	}
 
-	status = evm_verifyxattr(dentry, XATTR_NAME_IMA, xattr_value, rc, iint);
+	status = evm_verifyxattr(dentry, XATTR_NAME_IMA, xattr_value,
+				 rc < 0 ? 0 : rc, iint);
 	switch (status) {
 	case INTEGRITY_PASS:
 	case INTEGRITY_PASS_IMMUTABLE:
diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c
index a7206cc1d7d1..64499056648a 100644
--- a/security/integrity/ima/ima_crypto.c
+++ b/security/integrity/ima/ima_crypto.c
@@ -205,6 +205,7 @@ out_array:
 
 		crypto_free_shash(ima_algo_array[i].tfm);
 	}
+	kfree(ima_algo_array);
 out:
 	crypto_free_shash(ima_shash_tfm);
 	return rc;
diff --git a/security/integrity/ima/ima_efi.c b/security/integrity/ima/ima_efi.c
index 71786d01946f..9db66fe310d4 100644
--- a/security/integrity/ima/ima_efi.c
+++ b/security/integrity/ima/ima_efi.c
@@ -67,6 +67,8 @@ const char * const *arch_get_ima_policy(void)
 	if (IS_ENABLED(CONFIG_IMA_ARCH_POLICY) && arch_ima_get_secureboot()) {
 		if (IS_ENABLED(CONFIG_MODULE_SIG))
 			set_module_sig_enforced();
+		if (IS_ENABLED(CONFIG_KEXEC_SIG))
+			set_kexec_sig_enforced();
 		return sb_arch_rules;
 	}
 	return NULL;
diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c
index fa5a93dbe5d2..748b97a2582a 100644
--- a/security/integrity/ima/ima_policy.c
+++ b/security/integrity/ima/ima_policy.c
@@ -2034,6 +2034,10 @@ bool ima_appraise_signature(enum kernel_read_file_id id)
 	if (id >= READING_MAX_ID)
 		return false;
 
+	if (id == READING_KEXEC_IMAGE && !(ima_appraise & IMA_APPRAISE_ENFORCE)
+	    && security_locked_down(LOCKDOWN_KEXEC))
+		return false;
+
 	func = read_idmap[id] ?: FILE_CHECK;
 
 	rcu_read_lock();
diff --git a/security/selinux/ss/policydb.h b/security/selinux/ss/policydb.h
index c24d4e1063ea..ffc4e7bad205 100644
--- a/security/selinux/ss/policydb.h
+++ b/security/selinux/ss/policydb.h
@@ -370,6 +370,8 @@ static inline int put_entry(const void *buf, size_t bytes, int num, struct polic
 {
 	size_t len = bytes * num;
 
+	if (len > fp->len)
+		return -EINVAL;
 	memcpy(fp->data, buf, len);
 	fp->data += len;
 	fp->len -= len;
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index c4931bf6f92a..e8035e4876df 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -4045,6 +4045,7 @@ int security_read_policy(struct selinux_state *state,
 int security_read_state_kernel(struct selinux_state *state,
 			       void **data, size_t *len)
 {
+	int err;
 	struct selinux_policy *policy;
 
 	policy = rcu_dereference_protected(
@@ -4057,5 +4058,11 @@ int security_read_state_kernel(struct selinux_state *state,
 	if (!*data)
 		return -ENOMEM;
 
-	return __security_read_policy(policy, *data, len);
+	err = __security_read_policy(policy, *data, len);
+	if (err) {
+		vfree(*data);
+		*data = NULL;
+		*len = 0;
+	}
+	return err;
 }
diff --git a/sound/core/control.c b/sound/core/control.c
index a25c0d64d104..f66fe4be30d3 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -127,6 +127,7 @@ static int snd_ctl_release(struct inode *inode, struct file *file)
 			if (control->vd[idx].owner == ctl)
 				control->vd[idx].owner = NULL;
 	up_write(&card->controls_rwsem);
+	snd_fasync_free(ctl->fasync);
 	snd_ctl_empty_read_queue(ctl);
 	put_pid(ctl->pid);
 	kfree(ctl);
@@ -181,7 +182,7 @@ void snd_ctl_notify(struct snd_card *card, unsigned int mask,
 	_found:
 		wake_up(&ctl->change_sleep);
 		spin_unlock(&ctl->read_lock);
-		kill_fasync(&ctl->fasync, SIGIO, POLL_IN);
+		snd_kill_fasync(ctl->fasync, SIGIO, POLL_IN);
 	}
 	read_unlock_irqrestore(&card->ctl_files_rwlock, flags);
 }
@@ -2002,7 +2003,7 @@ static int snd_ctl_fasync(int fd, struct file * file, int on)
 	struct snd_ctl_file *ctl;
 
 	ctl = file->private_data;
-	return fasync_helper(fd, file, on, &ctl->fasync);
+	return snd_fasync_helper(fd, file, on, &ctl->fasync);
 }
 
 /* return the preferred subdevice number if already assigned;
@@ -2170,7 +2171,7 @@ static int snd_ctl_dev_disconnect(struct snd_device *device)
 	read_lock_irqsave(&card->ctl_files_rwlock, flags);
 	list_for_each_entry(ctl, &card->ctl_files, list) {
 		wake_up(&ctl->change_sleep);
-		kill_fasync(&ctl->fasync, SIGIO, POLL_ERR);
+		snd_kill_fasync(ctl->fasync, SIGIO, POLL_ERR);
 	}
 	read_unlock_irqrestore(&card->ctl_files_rwlock, flags);
 
diff --git a/sound/core/info.c b/sound/core/info.c
index a451b24199c3..9f6714e29bbc 100644
--- a/sound/core/info.c
+++ b/sound/core/info.c
@@ -111,9 +111,9 @@ static loff_t snd_info_entry_llseek(struct file *file, loff_t offset, int orig)
 	entry = data->entry;
 	mutex_lock(&entry->access);
 	if (entry->c.ops->llseek) {
-		offset = entry->c.ops->llseek(entry,
-					      data->file_private_data,
-					      file, offset, orig);
+		ret = entry->c.ops->llseek(entry,
+					   data->file_private_data,
+					   file, offset, orig);
 		goto out;
 	}
 
diff --git a/sound/core/misc.c b/sound/core/misc.c
index 50e4aaa6270d..d32a19976a2b 100644
--- a/sound/core/misc.c
+++ b/sound/core/misc.c
@@ -10,6 +10,7 @@
 #include <linux/time.h>
 #include <linux/slab.h>
 #include <linux/ioport.h>
+#include <linux/fs.h>
 #include <sound/core.h>
 
 #ifdef CONFIG_SND_DEBUG
@@ -145,3 +146,96 @@ snd_pci_quirk_lookup(struct pci_dev *pci, const struct snd_pci_quirk *list)
 }
 EXPORT_SYMBOL(snd_pci_quirk_lookup);
 #endif
+
+/*
+ * Deferred async signal helpers
+ *
+ * Below are a few helper functions to wrap the async signal handling
+ * in the deferred work.  The main purpose is to avoid the messy deadlock
+ * around tasklist_lock and co at the kill_fasync() invocation.
+ * fasync_helper() and kill_fasync() are replaced with snd_fasync_helper()
+ * and snd_kill_fasync(), respectively.  In addition, snd_fasync_free() has
+ * to be called at releasing the relevant file object.
+ */
+struct snd_fasync {
+	struct fasync_struct *fasync;
+	int signal;
+	int poll;
+	int on;
+	struct list_head list;
+};
+
+static DEFINE_SPINLOCK(snd_fasync_lock);
+static LIST_HEAD(snd_fasync_list);
+
+static void snd_fasync_work_fn(struct work_struct *work)
+{
+	struct snd_fasync *fasync;
+
+	spin_lock_irq(&snd_fasync_lock);
+	while (!list_empty(&snd_fasync_list)) {
+		fasync = list_first_entry(&snd_fasync_list, struct snd_fasync, list);
+		list_del_init(&fasync->list);
+		spin_unlock_irq(&snd_fasync_lock);
+		if (fasync->on)
+			kill_fasync(&fasync->fasync, fasync->signal, fasync->poll);
+		spin_lock_irq(&snd_fasync_lock);
+	}
+	spin_unlock_irq(&snd_fasync_lock);
+}
+
+static DECLARE_WORK(snd_fasync_work, snd_fasync_work_fn);
+
+int snd_fasync_helper(int fd, struct file *file, int on,
+		      struct snd_fasync **fasyncp)
+{
+	struct snd_fasync *fasync = NULL;
+
+	if (on) {
+		fasync = kzalloc(sizeof(*fasync), GFP_KERNEL);
+		if (!fasync)
+			return -ENOMEM;
+		INIT_LIST_HEAD(&fasync->list);
+	}
+
+	spin_lock_irq(&snd_fasync_lock);
+	if (*fasyncp) {
+		kfree(fasync);
+		fasync = *fasyncp;
+	} else {
+		if (!fasync) {
+			spin_unlock_irq(&snd_fasync_lock);
+			return 0;
+		}
+		*fasyncp = fasync;
+	}
+	fasync->on = on;
+	spin_unlock_irq(&snd_fasync_lock);
+	return fasync_helper(fd, file, on, &fasync->fasync);
+}
+EXPORT_SYMBOL_GPL(snd_fasync_helper);
+
+void snd_kill_fasync(struct snd_fasync *fasync, int signal, int poll)
+{
+	unsigned long flags;
+
+	if (!fasync || !fasync->on)
+		return;
+	spin_lock_irqsave(&snd_fasync_lock, flags);
+	fasync->signal = signal;
+	fasync->poll = poll;
+	list_move(&fasync->list, &snd_fasync_list);
+	schedule_work(&snd_fasync_work);
+	spin_unlock_irqrestore(&snd_fasync_lock, flags);
+}
+EXPORT_SYMBOL_GPL(snd_kill_fasync);
+
+void snd_fasync_free(struct snd_fasync *fasync)
+{
+	if (!fasync)
+		return;
+	fasync->on = 0;
+	flush_work(&snd_fasync_work);
+	kfree(fasync);
+}
+EXPORT_SYMBOL_GPL(snd_fasync_free);
diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c
index f158f0abd25d..ca4a692fe1c3 100644
--- a/sound/core/oss/pcm_oss.c
+++ b/sound/core/oss/pcm_oss.c
@@ -1664,14 +1664,14 @@ static int snd_pcm_oss_sync(struct snd_pcm_oss_file *pcm_oss_file)
 		runtime = substream->runtime;
 		if (atomic_read(&substream->mmap_count))
 			goto __direct;
-		err = snd_pcm_oss_make_ready(substream);
-		if (err < 0)
-			return err;
 		atomic_inc(&runtime->oss.rw_ref);
 		if (mutex_lock_interruptible(&runtime->oss.params_lock)) {
 			atomic_dec(&runtime->oss.rw_ref);
 			return -ERESTARTSYS;
 		}
+		err = snd_pcm_oss_make_ready_locked(substream);
+		if (err < 0)
+			goto unlock;
 		format = snd_pcm_oss_format_from(runtime->oss.format);
 		width = snd_pcm_format_physical_width(format);
 		if (runtime->oss.buffer_used > 0) {
diff --git a/sound/core/seq/oss/seq_oss_midi.c b/sound/core/seq/oss/seq_oss_midi.c
index 1e3bf086f867..07efb38f58ac 100644
--- a/sound/core/seq/oss/seq_oss_midi.c
+++ b/sound/core/seq/oss/seq_oss_midi.c
@@ -270,7 +270,9 @@ snd_seq_oss_midi_clear_all(void)
 void
 snd_seq_oss_midi_setup(struct seq_oss_devinfo *dp)
 {
+	spin_lock_irq(&register_lock);
 	dp->max_mididev = max_midi_devs;
+	spin_unlock_irq(&register_lock);
 }
 
 /*
diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c
index 2e9d695d336c..2d707afa1ef1 100644
--- a/sound/core/seq/seq_clientmgr.c
+++ b/sound/core/seq/seq_clientmgr.c
@@ -121,13 +121,13 @@ struct snd_seq_client *snd_seq_client_use_ptr(int clientid)
 	spin_unlock_irqrestore(&clients_lock, flags);
 #ifdef CONFIG_MODULES
 	if (!in_interrupt()) {
-		static char client_requested[SNDRV_SEQ_GLOBAL_CLIENTS];
-		static char card_requested[SNDRV_CARDS];
+		static DECLARE_BITMAP(client_requested, SNDRV_SEQ_GLOBAL_CLIENTS);
+		static DECLARE_BITMAP(card_requested, SNDRV_CARDS);
+
 		if (clientid < SNDRV_SEQ_GLOBAL_CLIENTS) {
 			int idx;
 			
-			if (!client_requested[clientid]) {
-				client_requested[clientid] = 1;
+			if (!test_and_set_bit(clientid, client_requested)) {
 				for (idx = 0; idx < 15; idx++) {
 					if (seq_client_load[idx] < 0)
 						break;
@@ -142,10 +142,8 @@ struct snd_seq_client *snd_seq_client_use_ptr(int clientid)
 			int card = (clientid - SNDRV_SEQ_GLOBAL_CLIENTS) /
 				SNDRV_SEQ_CLIENTS_PER_CARD;
 			if (card < snd_ecards_limit) {
-				if (! card_requested[card]) {
-					card_requested[card] = 1;
+				if (!test_and_set_bit(card, card_requested))
 					snd_request_card(card);
-				}
 				snd_seq_device_load_drivers();
 			}
 		}
diff --git a/sound/core/timer.c b/sound/core/timer.c
index b3214baa8919..e08a37c23add 100644
--- a/sound/core/timer.c
+++ b/sound/core/timer.c
@@ -83,7 +83,7 @@ struct snd_timer_user {
 	unsigned int filter;
 	struct timespec64 tstamp;		/* trigger tstamp */
 	wait_queue_head_t qchange_sleep;
-	struct fasync_struct *fasync;
+	struct snd_fasync *fasync;
 	struct mutex ioctl_lock;
 };
 
@@ -1345,7 +1345,7 @@ static void snd_timer_user_interrupt(struct snd_timer_instance *timeri,
 	}
       __wake:
 	spin_unlock(&tu->qlock);
-	kill_fasync(&tu->fasync, SIGIO, POLL_IN);
+	snd_kill_fasync(tu->fasync, SIGIO, POLL_IN);
 	wake_up(&tu->qchange_sleep);
 }
 
@@ -1383,7 +1383,7 @@ static void snd_timer_user_ccallback(struct snd_timer_instance *timeri,
 	spin_lock_irqsave(&tu->qlock, flags);
 	snd_timer_user_append_to_tqueue(tu, &r1);
 	spin_unlock_irqrestore(&tu->qlock, flags);
-	kill_fasync(&tu->fasync, SIGIO, POLL_IN);
+	snd_kill_fasync(tu->fasync, SIGIO, POLL_IN);
 	wake_up(&tu->qchange_sleep);
 }
 
@@ -1453,7 +1453,7 @@ static void snd_timer_user_tinterrupt(struct snd_timer_instance *timeri,
 	spin_unlock(&tu->qlock);
 	if (append == 0)
 		return;
-	kill_fasync(&tu->fasync, SIGIO, POLL_IN);
+	snd_kill_fasync(tu->fasync, SIGIO, POLL_IN);
 	wake_up(&tu->qchange_sleep);
 }
 
@@ -1521,6 +1521,7 @@ static int snd_timer_user_release(struct inode *inode, struct file *file)
 			snd_timer_instance_free(tu->timeri);
 		}
 		mutex_unlock(&tu->ioctl_lock);
+		snd_fasync_free(tu->fasync);
 		kfree(tu->queue);
 		kfree(tu->tqueue);
 		kfree(tu);
@@ -2135,7 +2136,7 @@ static int snd_timer_user_fasync(int fd, struct file * file, int on)
 	struct snd_timer_user *tu;
 
 	tu = file->private_data;
-	return fasync_helper(fd, file, on, &tu->fasync);
+	return snd_fasync_helper(fd, file, on, &tu->fasync);
 }
 
 static ssize_t snd_timer_user_read(struct file *file, char __user *buffer,
diff --git a/sound/drivers/aloop.c b/sound/drivers/aloop.c
index 9b4a7cdb103a..12f12a294df5 100644
--- a/sound/drivers/aloop.c
+++ b/sound/drivers/aloop.c
@@ -605,17 +605,18 @@ static unsigned int loopback_jiffies_timer_pos_update
 			cable->streams[SNDRV_PCM_STREAM_PLAYBACK];
 	struct loopback_pcm *dpcm_capt =
 			cable->streams[SNDRV_PCM_STREAM_CAPTURE];
-	unsigned long delta_play = 0, delta_capt = 0;
+	unsigned long delta_play = 0, delta_capt = 0, cur_jiffies;
 	unsigned int running, count1, count2;
 
+	cur_jiffies = jiffies;
 	running = cable->running ^ cable->pause;
 	if (running & (1 << SNDRV_PCM_STREAM_PLAYBACK)) {
-		delta_play = jiffies - dpcm_play->last_jiffies;
+		delta_play = cur_jiffies - dpcm_play->last_jiffies;
 		dpcm_play->last_jiffies += delta_play;
 	}
 
 	if (running & (1 << SNDRV_PCM_STREAM_CAPTURE)) {
-		delta_capt = jiffies - dpcm_capt->last_jiffies;
+		delta_capt = cur_jiffies - dpcm_capt->last_jiffies;
 		dpcm_capt->last_jiffies += delta_capt;
 	}
 
diff --git a/sound/hda/intel-nhlt.c b/sound/hda/intel-nhlt.c
index e2237239d922..8714891f50b0 100644
--- a/sound/hda/intel-nhlt.c
+++ b/sound/hda/intel-nhlt.c
@@ -55,20 +55,26 @@ int intel_nhlt_get_dmic_geo(struct device *dev, struct nhlt_acpi_table *nhlt)
 
 		/* find max number of channels based on format_configuration */
 		if (fmt_configs->fmt_count) {
-			dev_dbg(dev, "%s: found %d format definitions\n",
-				__func__, fmt_configs->fmt_count);
+			struct nhlt_fmt_cfg *fmt_cfg = fmt_configs->fmt_config;
+
+			dev_dbg(dev, "found %d format definitions\n",
+				fmt_configs->fmt_count);
 
 			for (i = 0; i < fmt_configs->fmt_count; i++) {
 				struct wav_fmt_ext *fmt_ext;
 
-				fmt_ext = &fmt_configs->fmt_config[i].fmt_ext;
+				fmt_ext = &fmt_cfg->fmt_ext;
 
 				if (fmt_ext->fmt.channels > max_ch)
 					max_ch = fmt_ext->fmt.channels;
+
+				/* Move to the next nhlt_fmt_cfg */
+				fmt_cfg = (struct nhlt_fmt_cfg *)(fmt_cfg->config.caps +
+								  fmt_cfg->config.size);
 			}
-			dev_dbg(dev, "%s: max channels found %d\n", __func__, max_ch);
+			dev_dbg(dev, "max channels found %d\n", max_ch);
 		} else {
-			dev_dbg(dev, "%s: No format information found\n", __func__);
+			dev_dbg(dev, "No format information found\n");
 		}
 
 		if (cfg->device_config.config_type != NHLT_CONFIG_TYPE_MIC_ARRAY) {
@@ -95,17 +101,16 @@ int intel_nhlt_get_dmic_geo(struct device *dev, struct nhlt_acpi_table *nhlt)
 			}
 
 			if (dmic_geo > 0) {
-				dev_dbg(dev, "%s: Array with %d dmics\n", __func__, dmic_geo);
+				dev_dbg(dev, "Array with %d dmics\n", dmic_geo);
 			}
 			if (max_ch > dmic_geo) {
-				dev_dbg(dev, "%s: max channels %d exceed dmic number %d\n",
-					__func__, max_ch, dmic_geo);
+				dev_dbg(dev, "max channels %d exceed dmic number %d\n",
+					max_ch, dmic_geo);
 			}
 		}
 	}
 
-	dev_dbg(dev, "%s: dmic number %d max_ch %d\n",
-		__func__, dmic_geo, max_ch);
+	dev_dbg(dev, "dmic number %d max_ch %d\n", dmic_geo, max_ch);
 
 	return dmic_geo;
 }
diff --git a/sound/pci/cs46xx/cs46xx.c b/sound/pci/cs46xx/cs46xx.c
index bd60308769ff..8634004a606b 100644
--- a/sound/pci/cs46xx/cs46xx.c
+++ b/sound/pci/cs46xx/cs46xx.c
@@ -74,36 +74,36 @@ static int snd_card_cs46xx_probe(struct pci_dev *pci,
 	err = snd_cs46xx_create(card, pci,
 				external_amp[dev], thinkpad[dev]);
 	if (err < 0)
-		return err;
+		goto error;
 	card->private_data = chip;
 	chip->accept_valid = mmap_valid[dev];
 	err = snd_cs46xx_pcm(chip, 0);
 	if (err < 0)
-		return err;
+		goto error;
 #ifdef CONFIG_SND_CS46XX_NEW_DSP
 	err = snd_cs46xx_pcm_rear(chip, 1);
 	if (err < 0)
-		return err;
+		goto error;
 	err = snd_cs46xx_pcm_iec958(chip, 2);
 	if (err < 0)
-		return err;
+		goto error;
 #endif
 	err = snd_cs46xx_mixer(chip, 2);
 	if (err < 0)
-		return err;
+		goto error;
 #ifdef CONFIG_SND_CS46XX_NEW_DSP
 	if (chip->nr_ac97_codecs ==2) {
 		err = snd_cs46xx_pcm_center_lfe(chip, 3);
 		if (err < 0)
-			return err;
+			goto error;
 	}
 #endif
 	err = snd_cs46xx_midi(chip, 0);
 	if (err < 0)
-		return err;
+		goto error;
 	err = snd_cs46xx_start_dsp(chip);
 	if (err < 0)
-		return err;
+		goto error;
 
 	snd_cs46xx_gameport(chip);
 
@@ -117,11 +117,15 @@ static int snd_card_cs46xx_probe(struct pci_dev *pci,
 
 	err = snd_card_register(card);
 	if (err < 0)
-		return err;
+		goto error;
 
 	pci_set_drvdata(pci, card);
 	dev++;
 	return 0;
+
+ error:
+	snd_card_free(card);
+	return err;
 }
 
 static struct pci_driver cs46xx_driver = {
diff --git a/sound/pci/emu10k1/emupcm.c b/sound/pci/emu10k1/emupcm.c
index b2701a4452d8..48af77ae8020 100644
--- a/sound/pci/emu10k1/emupcm.c
+++ b/sound/pci/emu10k1/emupcm.c
@@ -124,7 +124,7 @@ static int snd_emu10k1_pcm_channel_alloc(struct snd_emu10k1_pcm * epcm, int voic
 	epcm->voices[0]->epcm = epcm;
 	if (voices > 1) {
 		for (i = 1; i < voices; i++) {
-			epcm->voices[i] = &epcm->emu->voices[epcm->voices[0]->number + i];
+			epcm->voices[i] = &epcm->emu->voices[(epcm->voices[0]->number + i) % NUM_G];
 			epcm->voices[i]->epcm = epcm;
 		}
 	}
diff --git a/sound/pci/hda/hda_tegra.c b/sound/pci/hda/hda_tegra.c
index 773f4903550a..f0e556f2ccf6 100644
--- a/sound/pci/hda/hda_tegra.c
+++ b/sound/pci/hda/hda_tegra.c
@@ -451,7 +451,8 @@ MODULE_DEVICE_TABLE(of, hda_tegra_match);
 static int hda_tegra_probe(struct platform_device *pdev)
 {
 	const unsigned int driver_flags = AZX_DCAPS_CORBRP_SELF_CLEAR |
-					  AZX_DCAPS_PM_RUNTIME;
+					  AZX_DCAPS_PM_RUNTIME |
+					  AZX_DCAPS_4K_BDLE_BOUNDARY;
 	struct snd_card *card;
 	struct azx *chip;
 	struct hda_tegra *hda;
diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c
index 678fbcaf2a3b..6807b4708a17 100644
--- a/sound/pci/hda/patch_cirrus.c
+++ b/sound/pci/hda/patch_cirrus.c
@@ -395,6 +395,7 @@ static const struct snd_pci_quirk cs420x_fixup_tbl[] = {
 
 	/* codec SSID */
 	SND_PCI_QUIRK(0x106b, 0x0600, "iMac 14,1", CS420X_IMAC27_122),
+	SND_PCI_QUIRK(0x106b, 0x0900, "iMac 12,1", CS420X_IMAC27_122),
 	SND_PCI_QUIRK(0x106b, 0x1c00, "MacBookPro 8,1", CS420X_MBP81),
 	SND_PCI_QUIRK(0x106b, 0x2000, "iMac 12,2", CS420X_IMAC27_122),
 	SND_PCI_QUIRK(0x106b, 0x2800, "MacBookPro 10,1", CS420X_MBP101),
diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index 0b7d500249f6..2bc9274e0960 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -222,6 +222,7 @@ enum {
 	CXT_PINCFG_LEMOTE_A1205,
 	CXT_PINCFG_COMPAQ_CQ60,
 	CXT_FIXUP_STEREO_DMIC,
+	CXT_PINCFG_LENOVO_NOTEBOOK,
 	CXT_FIXUP_INC_MIC_BOOST,
 	CXT_FIXUP_HEADPHONE_MIC_PIN,
 	CXT_FIXUP_HEADPHONE_MIC,
@@ -772,6 +773,14 @@ static const struct hda_fixup cxt_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = cxt_fixup_stereo_dmic,
 	},
+	[CXT_PINCFG_LENOVO_NOTEBOOK] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x1a, 0x05d71030 },
+			{ }
+		},
+		.chain_id = CXT_FIXUP_STEREO_DMIC,
+	},
 	[CXT_FIXUP_INC_MIC_BOOST] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = cxt5066_increase_mic_boost,
@@ -944,6 +953,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = {
 	SND_PCI_QUIRK(0x103c, 0x828c, "HP EliteBook 840 G4", CXT_FIXUP_HP_DOCK),
 	SND_PCI_QUIRK(0x103c, 0x8299, "HP 800 G3 SFF", CXT_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x829a, "HP 800 G3 DM", CXT_FIXUP_HP_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x103c, 0x82b4, "HP ProDesk 600 G3", CXT_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x836e, "HP ProBook 455 G5", CXT_FIXUP_MUTE_LED_GPIO),
 	SND_PCI_QUIRK(0x103c, 0x837f, "HP ProBook 470 G5", CXT_FIXUP_MUTE_LED_GPIO),
 	SND_PCI_QUIRK(0x103c, 0x83b2, "HP EliteBook 840 G5", CXT_FIXUP_HP_DOCK),
@@ -970,7 +980,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = {
 	SND_PCI_QUIRK(0x17aa, 0x3905, "Lenovo G50-30", CXT_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK(0x17aa, 0x390b, "Lenovo G50-80", CXT_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK(0x17aa, 0x3975, "Lenovo U300s", CXT_FIXUP_STEREO_DMIC),
-	SND_PCI_QUIRK(0x17aa, 0x3977, "Lenovo IdeaPad U310", CXT_FIXUP_STEREO_DMIC),
+	SND_PCI_QUIRK(0x17aa, 0x3977, "Lenovo IdeaPad U310", CXT_PINCFG_LENOVO_NOTEBOOK),
 	SND_PCI_QUIRK(0x17aa, 0x3978, "Lenovo G50-70", CXT_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK(0x17aa, 0x397b, "Lenovo S205", CXT_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK_VENDOR(0x17aa, "Thinkpad", CXT_FIXUP_THINKPAD_ACPI),
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 70664c9832d6..45b8ebda284d 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4684,6 +4684,48 @@ static void alc236_fixup_hp_mute_led_micmute_vref(struct hda_codec *codec,
 	alc236_fixup_hp_micmute_led_vref(codec, fix, action);
 }
 
+static inline void alc298_samsung_write_coef_pack(struct hda_codec *codec,
+						  const unsigned short coefs[2])
+{
+	alc_write_coef_idx(codec, 0x23, coefs[0]);
+	alc_write_coef_idx(codec, 0x25, coefs[1]);
+	alc_write_coef_idx(codec, 0x26, 0xb011);
+}
+
+struct alc298_samsung_amp_desc {
+	unsigned char nid;
+	unsigned short init_seq[2][2];
+};
+
+static void alc298_fixup_samsung_amp(struct hda_codec *codec,
+				     const struct hda_fixup *fix, int action)
+{
+	int i, j;
+	static const unsigned short init_seq[][2] = {
+		{ 0x19, 0x00 }, { 0x20, 0xc0 }, { 0x22, 0x44 }, { 0x23, 0x08 },
+		{ 0x24, 0x85 }, { 0x25, 0x41 }, { 0x35, 0x40 }, { 0x36, 0x01 },
+		{ 0x38, 0x81 }, { 0x3a, 0x03 }, { 0x3b, 0x81 }, { 0x40, 0x3e },
+		{ 0x41, 0x07 }, { 0x400, 0x1 }
+	};
+	static const struct alc298_samsung_amp_desc amps[] = {
+		{ 0x3a, { { 0x18, 0x1 }, { 0x26, 0x0 } } },
+		{ 0x39, { { 0x18, 0x2 }, { 0x26, 0x1 } } }
+	};
+
+	if (action != HDA_FIXUP_ACT_INIT)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(amps); i++) {
+		alc_write_coef_idx(codec, 0x22, amps[i].nid);
+
+		for (j = 0; j < ARRAY_SIZE(amps[i].init_seq); j++)
+			alc298_samsung_write_coef_pack(codec, amps[i].init_seq[j]);
+
+		for (j = 0; j < ARRAY_SIZE(init_seq); j++)
+			alc298_samsung_write_coef_pack(codec, init_seq[j]);
+	}
+}
+
 #if IS_REACHABLE(CONFIG_INPUT)
 static void gpio2_mic_hotkey_event(struct hda_codec *codec,
 				   struct hda_jack_callback *event)
@@ -6721,6 +6763,7 @@ enum {
 	ALC269_FIXUP_LIMIT_INT_MIC_BOOST,
 	ALC269VB_FIXUP_ASUS_ZENBOOK,
 	ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A,
+	ALC269VB_FIXUP_ASUS_MIC_NO_PRESENCE,
 	ALC269_FIXUP_LIMIT_INT_MIC_BOOST_MUTE_LED,
 	ALC269VB_FIXUP_ORDISSIMO_EVE2,
 	ALC283_FIXUP_CHROME_BOOK,
@@ -6780,6 +6823,7 @@ enum {
 	ALC298_FIXUP_LENOVO_SPK_VOLUME,
 	ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER,
 	ALC269_FIXUP_ATIV_BOOK_8,
+	ALC221_FIXUP_HP_288PRO_MIC_NO_PRESENCE,
 	ALC221_FIXUP_HP_MIC_NO_PRESENCE,
 	ALC256_FIXUP_ASUS_HEADSET_MODE,
 	ALC256_FIXUP_ASUS_MIC,
@@ -6840,6 +6884,7 @@ enum {
 	ALC236_FIXUP_HP_GPIO_LED,
 	ALC236_FIXUP_HP_MUTE_LED,
 	ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF,
+	ALC298_FIXUP_SAMSUNG_AMP,
 	ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET,
 	ALC256_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET,
 	ALC295_FIXUP_ASUS_MIC_NO_PRESENCE,
@@ -7296,6 +7341,15 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC269VB_FIXUP_ASUS_ZENBOOK,
 	},
+	[ALC269VB_FIXUP_ASUS_MIC_NO_PRESENCE] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x18, 0x01a110f0 },  /* use as headset mic */
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC269_FIXUP_HEADSET_MIC
+	},
 	[ALC269_FIXUP_LIMIT_INT_MIC_BOOST_MUTE_LED] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc269_fixup_limit_int_mic_boost,
@@ -7707,6 +7761,16 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC269_FIXUP_NO_SHUTUP
 	},
+	[ALC221_FIXUP_HP_288PRO_MIC_NO_PRESENCE] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x19, 0x01a1913c }, /* use as headset mic, without its own jack detect */
+			{ 0x1a, 0x01813030 }, /* use as headphone mic, without its own jack detect */
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC269_FIXUP_HEADSET_MODE
+	},
 	[ALC221_FIXUP_HP_MIC_NO_PRESENCE] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
@@ -8175,6 +8239,12 @@ static const struct hda_fixup alc269_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc236_fixup_hp_mute_led_micmute_vref,
 	},
+	[ALC298_FIXUP_SAMSUNG_AMP] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc298_fixup_samsung_amp,
+		.chained = true,
+		.chain_id = ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET
+	},
 	[ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET] = {
 		.type = HDA_FIXUP_VERBS,
 		.v.verbs = (const struct hda_verb[]) {
@@ -8695,6 +8765,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1025, 0x1290, "Acer Veriton Z4860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x1291, "Acer Veriton Z4660G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x129c, "Acer SWIFT SF314-55", ALC256_FIXUP_ACER_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1025, 0x129d, "Acer SWIFT SF313-51", ALC256_FIXUP_ACER_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1025, 0x1300, "Acer SWIFT SF314-56", ALC256_FIXUP_ACER_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1025, 0x1308, "Acer Aspire Z24-890", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x132a, "Acer TravelMate B114-21", ALC233_FIXUP_ACER_HEADSET_MIC),
@@ -8704,6 +8775,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1025, 0x1430, "Acer TravelMate B311R-31", ALC256_FIXUP_ACER_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1025, 0x1466, "Acer Aspire A515-56", ALC255_FIXUP_ACER_HEADPHONE_AND_MIC),
 	SND_PCI_QUIRK(0x1028, 0x0470, "Dell M101z", ALC269_FIXUP_DELL_M101Z),
+	SND_PCI_QUIRK(0x1028, 0x053c, "Dell Latitude E5430", ALC292_FIXUP_DELL_E7X),
 	SND_PCI_QUIRK(0x1028, 0x054b, "Dell XPS one 2710", ALC275_FIXUP_DELL_XPS),
 	SND_PCI_QUIRK(0x1028, 0x05bd, "Dell Latitude E6440", ALC292_FIXUP_DELL_E7X),
 	SND_PCI_QUIRK(0x1028, 0x05be, "Dell Latitude E6540", ALC292_FIXUP_DELL_E7X),
@@ -8818,6 +8890,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x2335, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2336, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2337, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2b5e, "HP 288 Pro G2 MT", ALC221_FIXUP_HP_288PRO_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x802e, "HP Z240 SFF", ALC221_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x802f, "HP Z240", ALC221_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x8077, "HP", ALC256_FIXUP_HP_HEADSET_MIC),
@@ -8838,6 +8911,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x861f, "HP Elite Dragonfly G1", ALC285_FIXUP_HP_GPIO_AMP_INIT),
 	SND_PCI_QUIRK(0x103c, 0x869d, "HP", ALC236_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x86c7, "HP Envy AiO 32", ALC274_FIXUP_HP_ENVY_GPIO),
+	SND_PCI_QUIRK(0x103c, 0x86e7, "HP Spectre x360 15-eb0xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1),
+	SND_PCI_QUIRK(0x103c, 0x86e8, "HP Spectre x360 15-eb0xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1),
 	SND_PCI_QUIRK(0x103c, 0x8716, "HP Elite Dragonfly G2 Notebook PC", ALC285_FIXUP_HP_GPIO_AMP_INIT),
 	SND_PCI_QUIRK(0x103c, 0x8720, "HP EliteBook x360 1040 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_AMP_INIT),
 	SND_PCI_QUIRK(0x103c, 0x8724, "HP EliteBook 850 G7", ALC285_FIXUP_HP_GPIO_LED),
@@ -8853,6 +8928,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 		      ALC285_FIXUP_HP_GPIO_AMP_INIT),
 	SND_PCI_QUIRK(0x103c, 0x8783, "HP ZBook Fury 15 G7 Mobile Workstation",
 		      ALC285_FIXUP_HP_GPIO_AMP_INIT),
+	SND_PCI_QUIRK(0x103c, 0x8786, "HP OMEN 15", ALC285_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x8787, "HP OMEN 15", ALC285_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x8788, "HP OMEN 15", ALC285_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x87c8, "HP", ALC287_FIXUP_HP_GPIO_LED),
@@ -8885,6 +8961,10 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x89c3, "HP", ALC285_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x89ca, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
 	SND_PCI_QUIRK(0x103c, 0x8a78, "HP Dev One", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST),
+	SND_PCI_QUIRK(0x103c, 0x8aa0, "HP ProBook 440 G9 (MB 8A9E)", ALC236_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8aa3, "HP ProBook 450 G9 (MB 8AA1)", ALC236_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8aa8, "HP EliteBook 640 G9 (MB 8AA6)", ALC236_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8aab, "HP EliteBook 650 G9 (MB 8AA9)", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
 	SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
@@ -8899,6 +8979,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x12a0, "ASUS X441UV", ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x12e0, "ASUS X541SA", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x12f0, "ASUS X541UV", ALC256_FIXUP_ASUS_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1313, "Asus K42JZ", ALC269VB_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x13b0, "ASUS Z550SA", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK),
 	SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A),
@@ -8953,13 +9034,13 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x10ec, 0x1254, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK),
 	SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_HEADSET_MODE),
 	SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC),
-	SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET),
-	SND_PCI_QUIRK(0x144d, 0xc176, "Samsung Notebook 9 Pro (NP930MBE-K04US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET),
-	SND_PCI_QUIRK(0x144d, 0xc189, "Samsung Galaxy Flex Book (NT950QCG-X716)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET),
-	SND_PCI_QUIRK(0x144d, 0xc18a, "Samsung Galaxy Book Ion (NP930XCJ-K01US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET),
+	SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_AMP),
+	SND_PCI_QUIRK(0x144d, 0xc176, "Samsung Notebook 9 Pro (NP930MBE-K04US)", ALC298_FIXUP_SAMSUNG_AMP),
+	SND_PCI_QUIRK(0x144d, 0xc189, "Samsung Galaxy Flex Book (NT950QCG-X716)", ALC298_FIXUP_SAMSUNG_AMP),
+	SND_PCI_QUIRK(0x144d, 0xc18a, "Samsung Galaxy Book Ion (NP930XCJ-K01US)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc740, "Samsung Ativ book 8 (NP870Z5G)", ALC269_FIXUP_ATIV_BOOK_8),
-	SND_PCI_QUIRK(0x144d, 0xc812, "Samsung Notebook Pen S (NT950SBE-X58)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET),
-	SND_PCI_QUIRK(0x144d, 0xc830, "Samsung Galaxy Book Ion (NT950XCJ-X716A)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET),
+	SND_PCI_QUIRK(0x144d, 0xc812, "Samsung Notebook Pen S (NT950SBE-X58)", ALC298_FIXUP_SAMSUNG_AMP),
+	SND_PCI_QUIRK(0x144d, 0xc830, "Samsung Galaxy Book Ion (NT950XCJ-X716A)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc832, "Samsung Galaxy Book Flex Alpha (NP730QCJ)", ALC256_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET),
 	SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC),
@@ -8974,6 +9055,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1558, 0x4018, "Clevo NV40M[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x4019, "Clevo NV40MZ", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x4020, "Clevo NV40MB", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1558, 0x4041, "Clevo NV4[15]PZ", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x40a1, "Clevo NL40GU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x40c1, "Clevo NL40[CZ]U", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x40d1, "Clevo NL41DU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
@@ -9001,6 +9083,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1558, 0x70f4, "Clevo NH77EPY", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x70f6, "Clevo NH77DPQ-Y", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x7716, "Clevo NS50PU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1558, 0x7717, "Clevo NS70PU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1558, 0x7718, "Clevo L140PU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x8228, "Clevo NR40BU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x8520, "Clevo NH50D[CD]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x8521, "Clevo NH77D[CD]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
@@ -9139,6 +9223,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1d72, 0x1701, "XiaomiNotebook Pro", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1d72, 0x1945, "Redmi G", ALC256_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1d72, 0x1947, "RedmiBook Air", ALC255_FIXUP_XIAOMI_HEADSET_MIC),
 	SND_PCI_QUIRK(0x8086, 0x2074, "Intel NUC 8", ALC233_FIXUP_INTEL_NUC8_DMIC),
 	SND_PCI_QUIRK(0x8086, 0x2080, "Intel NUC 8 Rugged", ALC256_FIXUP_INTEL_NUC8_RUGGED),
@@ -9315,7 +9400,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
 	{.id = ALC299_FIXUP_PREDATOR_SPK, .name = "predator-spk"},
 	{.id = ALC298_FIXUP_HUAWEI_MBX_STEREO, .name = "huawei-mbx-stereo"},
 	{.id = ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE, .name = "alc256-medion-headset"},
-	{.id = ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET, .name = "alc298-samsung-headphone"},
+	{.id = ALC298_FIXUP_SAMSUNG_AMP, .name = "alc298-samsung-amp"},
 	{.id = ALC256_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET, .name = "alc256-samsung-headphone"},
 	{.id = ALC255_FIXUP_XIAOMI_HEADSET_MIC, .name = "alc255-xiaomi-headset"},
 	{.id = ALC274_FIXUP_HP_MIC, .name = "alc274-hp-mic-detect"},
@@ -11000,6 +11085,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x1632, "HP RP5800", ALC662_FIXUP_HP_RP5800),
 	SND_PCI_QUIRK(0x103c, 0x8719, "HP", ALC897_FIXUP_HP_HSMIC_VERB),
 	SND_PCI_QUIRK(0x103c, 0x873e, "HP", ALC671_FIXUP_HP_HEADSET_MIC2),
+	SND_PCI_QUIRK(0x103c, 0x877e, "HP 288 Pro G6", ALC671_FIXUP_HP_HEADSET_MIC2),
 	SND_PCI_QUIRK(0x103c, 0x885f, "HP 288 Pro G8", ALC671_FIXUP_HP_HEADSET_MIC2),
 	SND_PCI_QUIRK(0x1043, 0x1080, "Asus UX501VW", ALC668_FIXUP_HEADSET_MODE),
 	SND_PCI_QUIRK(0x1043, 0x11cd, "Asus N550", ALC662_FIXUP_ASUS_Nx50),
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 61df4d33c48f..7f340f18599c 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -209,6 +209,7 @@ struct sigmatel_spec {
 
 	/* beep widgets */
 	hda_nid_t anabeep_nid;
+	bool beep_power_on;
 
 	/* SPDIF-out mux */
 	const char * const *spdif_labels;
@@ -4443,6 +4444,28 @@ static int stac_suspend(struct hda_codec *codec)
 
 	return 0;
 }
+
+static int stac_check_power_status(struct hda_codec *codec, hda_nid_t nid)
+{
+#ifdef CONFIG_SND_HDA_INPUT_BEEP
+	struct sigmatel_spec *spec = codec->spec;
+#endif
+	int ret = snd_hda_gen_check_power_status(codec, nid);
+
+#ifdef CONFIG_SND_HDA_INPUT_BEEP
+	if (nid == spec->gen.beep_nid && codec->beep) {
+		if (codec->beep->enabled != spec->beep_power_on) {
+			spec->beep_power_on = codec->beep->enabled;
+			if (spec->beep_power_on)
+				snd_hda_power_up_pm(codec);
+			else
+				snd_hda_power_down_pm(codec);
+		}
+		ret |= spec->beep_power_on;
+	}
+#endif
+	return ret;
+}
 #else
 #define stac_suspend		NULL
 #endif /* CONFIG_PM */
@@ -4455,6 +4478,7 @@ static const struct hda_codec_ops stac_patch_ops = {
 	.unsol_event = snd_hda_jack_unsol_event,
 #ifdef CONFIG_PM
 	.suspend = stac_suspend,
+	.check_power_status = stac_check_power_status,
 #endif
 };
 
diff --git a/sound/soc/atmel/mchp-spdifrx.c b/sound/soc/atmel/mchp-spdifrx.c
index bcd4f3e4fb0f..2a62d9a2fa0d 100644
--- a/sound/soc/atmel/mchp-spdifrx.c
+++ b/sound/soc/atmel/mchp-spdifrx.c
@@ -288,15 +288,17 @@ static void mchp_spdifrx_isr_blockend_en(struct mchp_spdifrx_dev *dev)
 	spin_unlock_irqrestore(&dev->blockend_lock, flags);
 }
 
-/* called from atomic context only */
+/* called from atomic/non-atomic context */
 static void mchp_spdifrx_isr_blockend_dis(struct mchp_spdifrx_dev *dev)
 {
-	spin_lock(&dev->blockend_lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->blockend_lock, flags);
 	dev->blockend_refcount--;
 	/* don't enable BLOCKEND interrupt if it's already enabled */
 	if (dev->blockend_refcount == 0)
 		regmap_write(dev->regmap, SPDIFRX_IDR, SPDIFRX_IR_BLOCKEND);
-	spin_unlock(&dev->blockend_lock);
+	spin_unlock_irqrestore(&dev->blockend_lock, flags);
 }
 
 static irqreturn_t mchp_spdif_interrupt(int irq, void *dev_id)
@@ -575,6 +577,7 @@ static int mchp_spdifrx_subcode_ch_get(struct mchp_spdifrx_dev *dev,
 	if (ret <= 0) {
 		dev_dbg(dev->dev, "user data for channel %d timeout\n",
 			channel);
+		mchp_spdifrx_isr_blockend_dis(dev);
 		return ret;
 	}
 
diff --git a/sound/soc/atmel/mchp-spdiftx.c b/sound/soc/atmel/mchp-spdiftx.c
index d24380046435..bcca1cf3cd7b 100644
--- a/sound/soc/atmel/mchp-spdiftx.c
+++ b/sound/soc/atmel/mchp-spdiftx.c
@@ -196,8 +196,7 @@ struct mchp_spdiftx_dev {
 	struct clk				*pclk;
 	struct clk				*gclk;
 	unsigned int				fmt;
-	const struct mchp_i2s_caps		*caps;
-	int					gclk_enabled:1;
+	unsigned int				gclk_enabled:1;
 };
 
 static inline int mchp_spdiftx_is_running(struct mchp_spdiftx_dev *dev)
@@ -766,8 +765,6 @@ static const struct of_device_id mchp_spdiftx_dt_ids[] = {
 MODULE_DEVICE_TABLE(of, mchp_spdiftx_dt_ids);
 static int mchp_spdiftx_probe(struct platform_device *pdev)
 {
-	struct device_node *np = pdev->dev.of_node;
-	const struct of_device_id *match;
 	struct mchp_spdiftx_dev *dev;
 	struct resource *mem;
 	struct regmap *regmap;
@@ -781,11 +778,6 @@ static int mchp_spdiftx_probe(struct platform_device *pdev)
 	if (!dev)
 		return -ENOMEM;
 
-	/* Get hardware capabilities. */
-	match = of_match_node(mchp_spdiftx_dt_ids, np);
-	if (match)
-		dev->caps = match->data;
-
 	/* Map I/O registers. */
 	base = devm_platform_get_and_ioremap_resource(pdev, 0, &mem);
 	if (IS_ERR(base))
diff --git a/sound/soc/codecs/cros_ec_codec.c b/sound/soc/codecs/cros_ec_codec.c
index a201d652aca2..8823edc35113 100644
--- a/sound/soc/codecs/cros_ec_codec.c
+++ b/sound/soc/codecs/cros_ec_codec.c
@@ -994,6 +994,7 @@ static int cros_ec_codec_platform_probe(struct platform_device *pdev)
 			dev_dbg(dev, "ap_shm_phys_addr=%#llx len=%#x\n",
 				priv->ap_shm_phys_addr, priv->ap_shm_len);
 		}
+		of_node_put(node);
 	}
 #endif
 
diff --git a/sound/soc/codecs/cs47l15.c b/sound/soc/codecs/cs47l15.c
index 1ee83160b83f..ac9ccdea15b5 100644
--- a/sound/soc/codecs/cs47l15.c
+++ b/sound/soc/codecs/cs47l15.c
@@ -122,6 +122,9 @@ static int cs47l15_in1_adc_put(struct snd_kcontrol *kcontrol,
 		snd_soc_kcontrol_component(kcontrol);
 	struct cs47l15 *cs47l15 = snd_soc_component_get_drvdata(component);
 
+	if (!!ucontrol->value.integer.value[0] == cs47l15->in1_lp_mode)
+		return 0;
+
 	switch (ucontrol->value.integer.value[0]) {
 	case 0:
 		/* Set IN1 to normal mode */
@@ -150,7 +153,7 @@ static int cs47l15_in1_adc_put(struct snd_kcontrol *kcontrol,
 		break;
 	}
 
-	return 0;
+	return 1;
 }
 
 static const struct snd_kcontrol_new cs47l15_snd_controls[] = {
diff --git a/sound/soc/codecs/da7210.c b/sound/soc/codecs/da7210.c
index 8af344b2fdbf..d75d15006f64 100644
--- a/sound/soc/codecs/da7210.c
+++ b/sound/soc/codecs/da7210.c
@@ -1336,6 +1336,8 @@ static int __init da7210_modinit(void)
 	int ret = 0;
 #if IS_ENABLED(CONFIG_I2C)
 	ret = i2c_add_driver(&da7210_i2c_driver);
+	if (ret)
+		return ret;
 #endif
 #if defined(CONFIG_SPI_MASTER)
 	ret = spi_register_driver(&da7210_spi_driver);
diff --git a/sound/soc/codecs/madera.c b/sound/soc/codecs/madera.c
index f4ed7e04673f..fd4fa1d5d2d1 100644
--- a/sound/soc/codecs/madera.c
+++ b/sound/soc/codecs/madera.c
@@ -618,7 +618,13 @@ int madera_out1_demux_put(struct snd_kcontrol *kcontrol,
 end:
 	snd_soc_dapm_mutex_unlock(dapm);
 
-	return snd_soc_dapm_mux_update_power(dapm, kcontrol, mux, e, NULL);
+	ret = snd_soc_dapm_mux_update_power(dapm, kcontrol, mux, e, NULL);
+	if (ret < 0) {
+		dev_err(madera->dev, "Failed to update demux power state: %d\n", ret);
+		return ret;
+	}
+
+	return change;
 }
 EXPORT_SYMBOL_GPL(madera_out1_demux_put);
 
@@ -893,7 +899,7 @@ static int madera_adsp_rate_put(struct snd_kcontrol *kcontrol,
 	struct soc_enum *e = (struct soc_enum *)kcontrol->private_value;
 	const int adsp_num = e->shift_l;
 	const unsigned int item = ucontrol->value.enumerated.item[0];
-	int ret;
+	int ret = 0;
 
 	if (item >= e->items)
 		return -EINVAL;
@@ -910,10 +916,10 @@ static int madera_adsp_rate_put(struct snd_kcontrol *kcontrol,
 			 "Cannot change '%s' while in use by active audio paths\n",
 			 kcontrol->id.name);
 		ret = -EBUSY;
-	} else {
+	} else if (priv->adsp_rate_cache[adsp_num] != e->values[item]) {
 		/* Volatile register so defer until the codec is powered up */
 		priv->adsp_rate_cache[adsp_num] = e->values[item];
-		ret = 0;
+		ret = 1;
 	}
 
 	mutex_unlock(&priv->rate_lock);
diff --git a/sound/soc/codecs/max98373-sdw.c b/sound/soc/codecs/max98373-sdw.c
index dc520effc61c..12323d4b5bfa 100644
--- a/sound/soc/codecs/max98373-sdw.c
+++ b/sound/soc/codecs/max98373-sdw.c
@@ -862,6 +862,16 @@ static int max98373_sdw_probe(struct sdw_slave *slave,
 	return max98373_init(slave, regmap);
 }
 
+static int max98373_sdw_remove(struct sdw_slave *slave)
+{
+	struct max98373_priv *max98373 = dev_get_drvdata(&slave->dev);
+
+	if (max98373->first_hw_init)
+		pm_runtime_disable(&slave->dev);
+
+	return 0;
+}
+
 #if defined(CONFIG_OF)
 static const struct of_device_id max98373_of_match[] = {
 	{ .compatible = "maxim,max98373", },
@@ -893,7 +903,7 @@ static struct sdw_driver max98373_sdw_driver = {
 		.pm = &max98373_pm,
 	},
 	.probe = max98373_sdw_probe,
-	.remove = NULL,
+	.remove = max98373_sdw_remove,
 	.ops = &max98373_slave_ops,
 	.id_table = max98373_id,
 };
diff --git a/sound/soc/codecs/msm8916-wcd-digital.c b/sound/soc/codecs/msm8916-wcd-digital.c
index 20a07c92b2fc..098a58990f07 100644
--- a/sound/soc/codecs/msm8916-wcd-digital.c
+++ b/sound/soc/codecs/msm8916-wcd-digital.c
@@ -328,8 +328,8 @@ static const struct snd_kcontrol_new rx1_mix2_inp1_mux = SOC_DAPM_ENUM(
 static const struct snd_kcontrol_new rx2_mix2_inp1_mux = SOC_DAPM_ENUM(
 				"RX2 MIX2 INP1 Mux", rx2_mix2_inp1_chain_enum);
 
-/* Digital Gain control -38.4 dB to +38.4 dB in 0.3 dB steps */
-static const DECLARE_TLV_DB_SCALE(digital_gain, -3840, 30, 0);
+/* Digital Gain control -84 dB to +40 dB in 1 dB steps */
+static const DECLARE_TLV_DB_SCALE(digital_gain, -8400, 100, -8400);
 
 /* Cutoff Freq for High Pass Filter at -3dB */
 static const char * const hpf_cutoff_text[] = {
@@ -510,15 +510,15 @@ static int wcd_iir_filter_info(struct snd_kcontrol *kcontrol,
 
 static const struct snd_kcontrol_new msm8916_wcd_digital_snd_controls[] = {
 	SOC_SINGLE_S8_TLV("RX1 Digital Volume", LPASS_CDC_RX1_VOL_CTL_B2_CTL,
-			  -128, 127, digital_gain),
+			-84, 40, digital_gain),
 	SOC_SINGLE_S8_TLV("RX2 Digital Volume", LPASS_CDC_RX2_VOL_CTL_B2_CTL,
-			  -128, 127, digital_gain),
+			-84, 40, digital_gain),
 	SOC_SINGLE_S8_TLV("RX3 Digital Volume", LPASS_CDC_RX3_VOL_CTL_B2_CTL,
-			  -128, 127, digital_gain),
+			-84, 40, digital_gain),
 	SOC_SINGLE_S8_TLV("TX1 Digital Volume", LPASS_CDC_TX1_VOL_CTL_GAIN,
-			  -128, 127, digital_gain),
+			-84, 40, digital_gain),
 	SOC_SINGLE_S8_TLV("TX2 Digital Volume", LPASS_CDC_TX2_VOL_CTL_GAIN,
-			  -128, 127, digital_gain),
+			-84, 40, digital_gain),
 	SOC_ENUM("TX1 HPF Cutoff", tx1_hpf_cutoff_enum),
 	SOC_ENUM("TX2 HPF Cutoff", tx2_hpf_cutoff_enum),
 	SOC_SINGLE("TX1 HPF Switch", LPASS_CDC_TX1_MUX_CTL, 3, 1, 0),
@@ -553,22 +553,22 @@ static const struct snd_kcontrol_new msm8916_wcd_digital_snd_controls[] = {
 	WCD_IIR_FILTER_CTL("IIR2 Band3", IIR2, BAND3),
 	WCD_IIR_FILTER_CTL("IIR2 Band4", IIR2, BAND4),
 	WCD_IIR_FILTER_CTL("IIR2 Band5", IIR2, BAND5),
-	SOC_SINGLE_SX_TLV("IIR1 INP1 Volume", LPASS_CDC_IIR1_GAIN_B1_CTL,
-			0,  -84, 40, digital_gain),
-	SOC_SINGLE_SX_TLV("IIR1 INP2 Volume", LPASS_CDC_IIR1_GAIN_B2_CTL,
-			0,  -84, 40, digital_gain),
-	SOC_SINGLE_SX_TLV("IIR1 INP3 Volume", LPASS_CDC_IIR1_GAIN_B3_CTL,
-			0,  -84, 40, digital_gain),
-	SOC_SINGLE_SX_TLV("IIR1 INP4 Volume", LPASS_CDC_IIR1_GAIN_B4_CTL,
-			0,  -84,	40, digital_gain),
-	SOC_SINGLE_SX_TLV("IIR2 INP1 Volume", LPASS_CDC_IIR2_GAIN_B1_CTL,
-			0,  -84, 40, digital_gain),
-	SOC_SINGLE_SX_TLV("IIR2 INP2 Volume", LPASS_CDC_IIR2_GAIN_B2_CTL,
-			0,  -84, 40, digital_gain),
-	SOC_SINGLE_SX_TLV("IIR2 INP3 Volume", LPASS_CDC_IIR2_GAIN_B3_CTL,
-			0,  -84, 40, digital_gain),
-	SOC_SINGLE_SX_TLV("IIR2 INP4 Volume", LPASS_CDC_IIR2_GAIN_B4_CTL,
-			0,  -84, 40, digital_gain),
+	SOC_SINGLE_S8_TLV("IIR1 INP1 Volume", LPASS_CDC_IIR1_GAIN_B1_CTL,
+			-84, 40, digital_gain),
+	SOC_SINGLE_S8_TLV("IIR1 INP2 Volume", LPASS_CDC_IIR1_GAIN_B2_CTL,
+			-84, 40, digital_gain),
+	SOC_SINGLE_S8_TLV("IIR1 INP3 Volume", LPASS_CDC_IIR1_GAIN_B3_CTL,
+			-84, 40, digital_gain),
+	SOC_SINGLE_S8_TLV("IIR1 INP4 Volume", LPASS_CDC_IIR1_GAIN_B4_CTL,
+			-84, 40, digital_gain),
+	SOC_SINGLE_S8_TLV("IIR2 INP1 Volume", LPASS_CDC_IIR2_GAIN_B1_CTL,
+			-84, 40, digital_gain),
+	SOC_SINGLE_S8_TLV("IIR2 INP2 Volume", LPASS_CDC_IIR2_GAIN_B2_CTL,
+			-84, 40, digital_gain),
+	SOC_SINGLE_S8_TLV("IIR2 INP3 Volume", LPASS_CDC_IIR2_GAIN_B3_CTL,
+			-84, 40, digital_gain),
+	SOC_SINGLE_S8_TLV("IIR2 INP4 Volume", LPASS_CDC_IIR2_GAIN_B4_CTL,
+			-84, 40, digital_gain),
 
 };
 
diff --git a/sound/soc/codecs/mt6359-accdet.c b/sound/soc/codecs/mt6359-accdet.c
index 6d3d170144a0..c190628e2905 100644
--- a/sound/soc/codecs/mt6359-accdet.c
+++ b/sound/soc/codecs/mt6359-accdet.c
@@ -675,6 +675,7 @@ static int mt6359_accdet_parse_dt(struct mt6359_accdet *priv)
 			       sizeof(struct three_key_threshold));
 	}
 
+	of_node_put(node);
 	dev_warn(priv->dev, "accdet caps=%x\n", priv->caps);
 
 	return 0;
diff --git a/sound/soc/codecs/mt6359.c b/sound/soc/codecs/mt6359.c
index 2d6a4a29b850..cf1febe54bcd 100644
--- a/sound/soc/codecs/mt6359.c
+++ b/sound/soc/codecs/mt6359.c
@@ -2780,6 +2780,7 @@ static int mt6359_parse_dt(struct mt6359_priv *priv)
 
 	ret = of_property_read_u32(np, "mediatek,mic-type-2",
 				   &priv->mux_select[MUX_MIC_TYPE_2]);
+	of_node_put(np);
 	if (ret) {
 		dev_info(priv->dev,
 			 "%s() failed to read mic-type-2, use default (%d)\n",
diff --git a/sound/soc/codecs/nau8824.c b/sound/soc/codecs/nau8824.c
index f7018f2dd21f..27589900f4fb 100644
--- a/sound/soc/codecs/nau8824.c
+++ b/sound/soc/codecs/nau8824.c
@@ -1042,6 +1042,7 @@ static int nau8824_hw_params(struct snd_pcm_substream *substream,
 	struct snd_soc_component *component = dai->component;
 	struct nau8824 *nau8824 = snd_soc_component_get_drvdata(component);
 	unsigned int val_len = 0, osr, ctrl_val, bclk_fs, bclk_div;
+	int err = -EINVAL;
 
 	nau8824_sema_acquire(nau8824, HZ);
 
@@ -1058,7 +1059,7 @@ static int nau8824_hw_params(struct snd_pcm_substream *substream,
 		osr &= NAU8824_DAC_OVERSAMPLE_MASK;
 		if (nau8824_clock_check(nau8824, substream->stream,
 			nau8824->fs, osr))
-			return -EINVAL;
+			goto error;
 		regmap_update_bits(nau8824->regmap, NAU8824_REG_CLK_DIVIDER,
 			NAU8824_CLK_DAC_SRC_MASK,
 			osr_dac_sel[osr].clk_src << NAU8824_CLK_DAC_SRC_SFT);
@@ -1068,7 +1069,7 @@ static int nau8824_hw_params(struct snd_pcm_substream *substream,
 		osr &= NAU8824_ADC_SYNC_DOWN_MASK;
 		if (nau8824_clock_check(nau8824, substream->stream,
 			nau8824->fs, osr))
-			return -EINVAL;
+			goto error;
 		regmap_update_bits(nau8824->regmap, NAU8824_REG_CLK_DIVIDER,
 			NAU8824_CLK_ADC_SRC_MASK,
 			osr_adc_sel[osr].clk_src << NAU8824_CLK_ADC_SRC_SFT);
@@ -1089,7 +1090,7 @@ static int nau8824_hw_params(struct snd_pcm_substream *substream,
 		else if (bclk_fs <= 256)
 			bclk_div = 0;
 		else
-			return -EINVAL;
+			goto error;
 		regmap_update_bits(nau8824->regmap,
 			NAU8824_REG_PORT0_I2S_PCM_CTRL_2,
 			NAU8824_I2S_LRC_DIV_MASK | NAU8824_I2S_BLK_DIV_MASK,
@@ -1110,15 +1111,17 @@ static int nau8824_hw_params(struct snd_pcm_substream *substream,
 		val_len |= NAU8824_I2S_DL_32;
 		break;
 	default:
-		return -EINVAL;
+		goto error;
 	}
 
 	regmap_update_bits(nau8824->regmap, NAU8824_REG_PORT0_I2S_PCM_CTRL_1,
 		NAU8824_I2S_DL_MASK, val_len);
+	err = 0;
 
+ error:
 	nau8824_sema_release(nau8824);
 
-	return 0;
+	return err;
 }
 
 static int nau8824_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
@@ -1127,8 +1130,6 @@ static int nau8824_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 	struct nau8824 *nau8824 = snd_soc_component_get_drvdata(component);
 	unsigned int ctrl1_val = 0, ctrl2_val = 0;
 
-	nau8824_sema_acquire(nau8824, HZ);
-
 	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
 	case SND_SOC_DAIFMT_CBM_CFM:
 		ctrl2_val |= NAU8824_I2S_MS_MASTER;
@@ -1170,6 +1171,8 @@ static int nau8824_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 		return -EINVAL;
 	}
 
+	nau8824_sema_acquire(nau8824, HZ);
+
 	regmap_update_bits(nau8824->regmap, NAU8824_REG_PORT0_I2S_PCM_CTRL_1,
 		NAU8824_I2S_DF_MASK | NAU8824_I2S_BP_MASK |
 		NAU8824_I2S_PCMB_EN, ctrl1_val);
diff --git a/sound/soc/codecs/rt1308-sdw.c b/sound/soc/codecs/rt1308-sdw.c
index f716668de640..8472d855c325 100644
--- a/sound/soc/codecs/rt1308-sdw.c
+++ b/sound/soc/codecs/rt1308-sdw.c
@@ -683,6 +683,16 @@ static int rt1308_sdw_probe(struct sdw_slave *slave,
 	return 0;
 }
 
+static int rt1308_sdw_remove(struct sdw_slave *slave)
+{
+	struct rt1308_sdw_priv *rt1308 = dev_get_drvdata(&slave->dev);
+
+	if (rt1308->first_hw_init)
+		pm_runtime_disable(&slave->dev);
+
+	return 0;
+}
+
 static const struct sdw_device_id rt1308_id[] = {
 	SDW_SLAVE_ENTRY_EXT(0x025d, 0x1308, 0x2, 0, 0),
 	{},
@@ -742,6 +752,7 @@ static struct sdw_driver rt1308_sdw_driver = {
 		.pm = &rt1308_pm,
 	},
 	.probe = rt1308_sdw_probe,
+	.remove = rt1308_sdw_remove,
 	.ops = &rt1308_slave_ops,
 	.id_table = rt1308_id,
 };
diff --git a/sound/soc/codecs/rt1316-sdw.c b/sound/soc/codecs/rt1316-sdw.c
index 09b4914bba1b..09cf3ca86fa4 100644
--- a/sound/soc/codecs/rt1316-sdw.c
+++ b/sound/soc/codecs/rt1316-sdw.c
@@ -675,6 +675,16 @@ static int rt1316_sdw_probe(struct sdw_slave *slave,
 	return rt1316_sdw_init(&slave->dev, regmap, slave);
 }
 
+static int rt1316_sdw_remove(struct sdw_slave *slave)
+{
+	struct rt1316_sdw_priv *rt1316 = dev_get_drvdata(&slave->dev);
+
+	if (rt1316->first_hw_init)
+		pm_runtime_disable(&slave->dev);
+
+	return 0;
+}
+
 static const struct sdw_device_id rt1316_id[] = {
 	SDW_SLAVE_ENTRY_EXT(0x025d, 0x1316, 0x3, 0x1, 0),
 	{},
@@ -734,6 +744,7 @@ static struct sdw_driver rt1316_sdw_driver = {
 		.pm = &rt1316_pm,
 	},
 	.probe = rt1316_sdw_probe,
+	.remove = rt1316_sdw_remove,
 	.ops = &rt1316_slave_ops,
 	.id_table = rt1316_id,
 };
diff --git a/sound/soc/codecs/rt5682-i2c.c b/sound/soc/codecs/rt5682-i2c.c
index b9d5d7a0975b..3d2d7c9ce66d 100644
--- a/sound/soc/codecs/rt5682-i2c.c
+++ b/sound/soc/codecs/rt5682-i2c.c
@@ -59,18 +59,12 @@ static void rt5682_jd_check_handler(struct work_struct *work)
 	struct rt5682_priv *rt5682 = container_of(work, struct rt5682_priv,
 		jd_check_work.work);
 
-	if (snd_soc_component_read(rt5682->component, RT5682_AJD1_CTRL)
-		& RT5682_JDH_RS_MASK) {
+	if (snd_soc_component_read(rt5682->component, RT5682_AJD1_CTRL) & RT5682_JDH_RS_MASK)
 		/* jack out */
-		rt5682->jack_type = rt5682_headset_detect(rt5682->component, 0);
-
-		snd_soc_jack_report(rt5682->hs_jack, rt5682->jack_type,
-			SND_JACK_HEADSET |
-			SND_JACK_BTN_0 | SND_JACK_BTN_1 |
-			SND_JACK_BTN_2 | SND_JACK_BTN_3);
-	} else {
+		mod_delayed_work(system_power_efficient_wq,
+				 &rt5682->jack_detect_work, 0);
+	else
 		schedule_delayed_work(&rt5682->jd_check_work, 500);
-	}
 }
 
 static irqreturn_t rt5682_irq(int irq, void *data)
@@ -139,6 +133,8 @@ static int rt5682_i2c_probe(struct i2c_client *i2c,
 
 	i2c_set_clientdata(i2c, rt5682);
 
+	rt5682->i2c_dev = &i2c->dev;
+
 	rt5682->pdata = i2s_default_platform_data;
 
 	if (pdata)
@@ -276,6 +272,26 @@ static int rt5682_i2c_probe(struct i2c_client *i2c,
 			dev_err(&i2c->dev, "Failed to reguest IRQ: %d\n", ret);
 	}
 
+#ifdef CONFIG_COMMON_CLK
+	/* Check if MCLK provided */
+	rt5682->mclk = devm_clk_get(&i2c->dev, "mclk");
+	if (IS_ERR(rt5682->mclk)) {
+		if (PTR_ERR(rt5682->mclk) != -ENOENT) {
+			ret = PTR_ERR(rt5682->mclk);
+			return ret;
+		}
+		rt5682->mclk = NULL;
+	}
+
+	/* Register CCF DAI clock control */
+	ret = rt5682_register_dai_clks(rt5682);
+	if (ret)
+		return ret;
+
+	/* Initial setup for CCF */
+	rt5682->lrck[RT5682_AIF1] = 48000;
+#endif
+
 	return devm_snd_soc_register_component(&i2c->dev,
 					       &rt5682_soc_component_dev,
 					       rt5682_dai, ARRAY_SIZE(rt5682_dai));
diff --git a/sound/soc/codecs/rt5682-sdw.c b/sound/soc/codecs/rt5682-sdw.c
index 31a4f286043e..a030c9987b92 100644
--- a/sound/soc/codecs/rt5682-sdw.c
+++ b/sound/soc/codecs/rt5682-sdw.c
@@ -719,9 +719,12 @@ static int rt5682_sdw_remove(struct sdw_slave *slave)
 {
 	struct rt5682_priv *rt5682 = dev_get_drvdata(&slave->dev);
 
-	if (rt5682 && rt5682->hw_init)
+	if (rt5682->hw_init)
 		cancel_delayed_work_sync(&rt5682->jack_detect_work);
 
+	if (rt5682->first_hw_init)
+		pm_runtime_disable(&slave->dev);
+
 	return 0;
 }
 
diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c
index 6ad3159eceb9..8a9e1a4fa03e 100644
--- a/sound/soc/codecs/rt5682.c
+++ b/sound/soc/codecs/rt5682.c
@@ -48,6 +48,8 @@ static const struct reg_sequence patch_list[] = {
 	{RT5682_SAR_IL_CMD_6, 0x0110},
 	{RT5682_CHARGE_PUMP_1, 0x0210},
 	{RT5682_HP_LOGIC_CTRL_2, 0x0007},
+	{RT5682_SAR_IL_CMD_2, 0xac00},
+	{RT5682_CBJ_CTRL_7, 0x0104},
 };
 
 void rt5682_apply_patch_list(struct rt5682_priv *rt5682, struct device *dev)
@@ -920,15 +922,13 @@ static void rt5682_enable_push_button_irq(struct snd_soc_component *component,
  *
  * Returns detect status.
  */
-int rt5682_headset_detect(struct snd_soc_component *component, int jack_insert)
+static int rt5682_headset_detect(struct snd_soc_component *component, int jack_insert)
 {
 	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
 	struct snd_soc_dapm_context *dapm = &component->dapm;
 	unsigned int val, count;
 
 	if (jack_insert) {
-		snd_soc_dapm_mutex_lock(dapm);
-
 		snd_soc_component_update_bits(component, RT5682_PWR_ANLG_1,
 			RT5682_PWR_VREF2 | RT5682_PWR_MB,
 			RT5682_PWR_VREF2 | RT5682_PWR_MB);
@@ -942,6 +942,10 @@ int rt5682_headset_detect(struct snd_soc_component *component, int jack_insert)
 		snd_soc_component_update_bits(component,
 			RT5682_HP_CHARGE_PUMP_1,
 			RT5682_OSW_L_MASK | RT5682_OSW_R_MASK, 0);
+		rt5682_enable_push_button_irq(component, false);
+		snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1,
+			RT5682_TRIG_JD_MASK, RT5682_TRIG_JD_LOW);
+		usleep_range(55000, 60000);
 		snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1,
 			RT5682_TRIG_JD_MASK, RT5682_TRIG_JD_HIGH);
 
@@ -975,8 +979,6 @@ int rt5682_headset_detect(struct snd_soc_component *component, int jack_insert)
 		snd_soc_component_update_bits(component, RT5682_MICBIAS_2,
 			RT5682_PWR_CLK25M_MASK | RT5682_PWR_CLK1M_MASK,
 			RT5682_PWR_CLK25M_PU | RT5682_PWR_CLK1M_PU);
-
-		snd_soc_dapm_mutex_unlock(dapm);
 	} else {
 		rt5682_enable_push_button_irq(component, false);
 		snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1,
@@ -1005,7 +1007,6 @@ int rt5682_headset_detect(struct snd_soc_component *component, int jack_insert)
 	dev_dbg(component->dev, "jack_type = %d\n", rt5682->jack_type);
 	return rt5682->jack_type;
 }
-EXPORT_SYMBOL_GPL(rt5682_headset_detect);
 
 static int rt5682_set_jack_detect(struct snd_soc_component *component,
 		struct snd_soc_jack *hs_jack, void *data)
@@ -1088,6 +1089,7 @@ void rt5682_jack_detect_handler(struct work_struct *work)
 {
 	struct rt5682_priv *rt5682 =
 		container_of(work, struct rt5682_priv, jack_detect_work.work);
+	struct snd_soc_dapm_context *dapm;
 	int val, btn_type;
 
 	if (!rt5682->component || !rt5682->component->card ||
@@ -1098,6 +1100,9 @@ void rt5682_jack_detect_handler(struct work_struct *work)
 		return;
 	}
 
+	dapm = snd_soc_component_get_dapm(rt5682->component);
+
+	snd_soc_dapm_mutex_lock(dapm);
 	mutex_lock(&rt5682->calibrate_mutex);
 
 	val = snd_soc_component_read(rt5682->component, RT5682_AJD1_CTRL)
@@ -1157,6 +1162,9 @@ void rt5682_jack_detect_handler(struct work_struct *work)
 		rt5682->irq_work_delay_time = 50;
 	}
 
+	mutex_unlock(&rt5682->calibrate_mutex);
+	snd_soc_dapm_mutex_unlock(dapm);
+
 	snd_soc_jack_report(rt5682->hs_jack, rt5682->jack_type,
 		SND_JACK_HEADSET |
 		SND_JACK_BTN_0 | SND_JACK_BTN_1 |
@@ -1169,8 +1177,6 @@ void rt5682_jack_detect_handler(struct work_struct *work)
 		else
 			cancel_delayed_work_sync(&rt5682->jd_check_work);
 	}
-
-	mutex_unlock(&rt5682->calibrate_mutex);
 }
 EXPORT_SYMBOL_GPL(rt5682_jack_detect_handler);
 
@@ -2556,7 +2562,7 @@ static int rt5682_set_bias_level(struct snd_soc_component *component,
 static bool rt5682_clk_check(struct rt5682_priv *rt5682)
 {
 	if (!rt5682->master[RT5682_AIF1]) {
-		dev_dbg(rt5682->component->dev, "sysclk/dai not set correctly\n");
+		dev_dbg(rt5682->i2c_dev, "sysclk/dai not set correctly\n");
 		return false;
 	}
 	return true;
@@ -2567,13 +2573,15 @@ static int rt5682_wclk_prepare(struct clk_hw *hw)
 	struct rt5682_priv *rt5682 =
 		container_of(hw, struct rt5682_priv,
 			     dai_clks_hw[RT5682_DAI_WCLK_IDX]);
-	struct snd_soc_component *component = rt5682->component;
-	struct snd_soc_dapm_context *dapm =
-			snd_soc_component_get_dapm(component);
+	struct snd_soc_component *component;
+	struct snd_soc_dapm_context *dapm;
 
 	if (!rt5682_clk_check(rt5682))
 		return -EINVAL;
 
+	component = rt5682->component;
+	dapm = snd_soc_component_get_dapm(component);
+
 	snd_soc_dapm_mutex_lock(dapm);
 
 	snd_soc_dapm_force_enable_pin_unlocked(dapm, "MICBIAS");
@@ -2603,13 +2611,15 @@ static void rt5682_wclk_unprepare(struct clk_hw *hw)
 	struct rt5682_priv *rt5682 =
 		container_of(hw, struct rt5682_priv,
 			     dai_clks_hw[RT5682_DAI_WCLK_IDX]);
-	struct snd_soc_component *component = rt5682->component;
-	struct snd_soc_dapm_context *dapm =
-			snd_soc_component_get_dapm(component);
+	struct snd_soc_component *component;
+	struct snd_soc_dapm_context *dapm;
 
 	if (!rt5682_clk_check(rt5682))
 		return;
 
+	component = rt5682->component;
+	dapm = snd_soc_component_get_dapm(component);
+
 	snd_soc_dapm_mutex_lock(dapm);
 
 	snd_soc_dapm_disable_pin_unlocked(dapm, "MICBIAS");
@@ -2633,7 +2643,6 @@ static unsigned long rt5682_wclk_recalc_rate(struct clk_hw *hw,
 	struct rt5682_priv *rt5682 =
 		container_of(hw, struct rt5682_priv,
 			     dai_clks_hw[RT5682_DAI_WCLK_IDX]);
-	struct snd_soc_component *component = rt5682->component;
 	const char * const clk_name = clk_hw_get_name(hw);
 
 	if (!rt5682_clk_check(rt5682))
@@ -2643,7 +2652,7 @@ static unsigned long rt5682_wclk_recalc_rate(struct clk_hw *hw,
 	 */
 	if (rt5682->lrck[RT5682_AIF1] != CLK_48 &&
 	    rt5682->lrck[RT5682_AIF1] != CLK_44) {
-		dev_warn(component->dev, "%s: clk %s only support %d or %d Hz output\n",
+		dev_warn(rt5682->i2c_dev, "%s: clk %s only support %d or %d Hz output\n",
 			__func__, clk_name, CLK_44, CLK_48);
 		return 0;
 	}
@@ -2657,7 +2666,6 @@ static long rt5682_wclk_round_rate(struct clk_hw *hw, unsigned long rate,
 	struct rt5682_priv *rt5682 =
 		container_of(hw, struct rt5682_priv,
 			     dai_clks_hw[RT5682_DAI_WCLK_IDX]);
-	struct snd_soc_component *component = rt5682->component;
 	const char * const clk_name = clk_hw_get_name(hw);
 
 	if (!rt5682_clk_check(rt5682))
@@ -2667,7 +2675,7 @@ static long rt5682_wclk_round_rate(struct clk_hw *hw, unsigned long rate,
 	 * It will force to 48kHz if not both.
 	 */
 	if (rate != CLK_48 && rate != CLK_44) {
-		dev_warn(component->dev, "%s: clk %s only support %d or %d Hz output\n",
+		dev_warn(rt5682->i2c_dev, "%s: clk %s only support %d or %d Hz output\n",
 			__func__, clk_name, CLK_44, CLK_48);
 		rate = CLK_48;
 	}
@@ -2681,7 +2689,7 @@ static int rt5682_wclk_set_rate(struct clk_hw *hw, unsigned long rate,
 	struct rt5682_priv *rt5682 =
 		container_of(hw, struct rt5682_priv,
 			     dai_clks_hw[RT5682_DAI_WCLK_IDX]);
-	struct snd_soc_component *component = rt5682->component;
+	struct snd_soc_component *component;
 	struct clk_hw *parent_hw;
 	const char * const clk_name = clk_hw_get_name(hw);
 	int pre_div;
@@ -2690,6 +2698,8 @@ static int rt5682_wclk_set_rate(struct clk_hw *hw, unsigned long rate,
 	if (!rt5682_clk_check(rt5682))
 		return -EINVAL;
 
+	component = rt5682->component;
+
 	/*
 	 * Whether the wclk's parent clk (mclk) exists or not, please ensure
 	 * it is fixed or set to 48MHz before setting wclk rate. It's a
@@ -2699,12 +2709,12 @@ static int rt5682_wclk_set_rate(struct clk_hw *hw, unsigned long rate,
 	 */
 	parent_hw = clk_hw_get_parent(hw);
 	if (!parent_hw)
-		dev_warn(component->dev,
+		dev_warn(rt5682->i2c_dev,
 			"Parent mclk of wclk not acquired in driver. Please ensure mclk was provided as %d Hz.\n",
 			CLK_PLL2_FIN);
 
 	if (parent_rate != CLK_PLL2_FIN)
-		dev_warn(component->dev, "clk %s only support %d Hz input\n",
+		dev_warn(rt5682->i2c_dev, "clk %s only support %d Hz input\n",
 			clk_name, CLK_PLL2_FIN);
 
 	/*
@@ -2736,10 +2746,9 @@ static unsigned long rt5682_bclk_recalc_rate(struct clk_hw *hw,
 	struct rt5682_priv *rt5682 =
 		container_of(hw, struct rt5682_priv,
 			     dai_clks_hw[RT5682_DAI_BCLK_IDX]);
-	struct snd_soc_component *component = rt5682->component;
 	unsigned int bclks_per_wclk;
 
-	bclks_per_wclk = snd_soc_component_read(component, RT5682_TDM_TCON_CTRL);
+	regmap_read(rt5682->regmap, RT5682_TDM_TCON_CTRL, &bclks_per_wclk);
 
 	switch (bclks_per_wclk & RT5682_TDM_BCLK_MS1_MASK) {
 	case RT5682_TDM_BCLK_MS1_256:
@@ -2800,25 +2809,24 @@ static int rt5682_bclk_set_rate(struct clk_hw *hw, unsigned long rate,
 	struct rt5682_priv *rt5682 =
 		container_of(hw, struct rt5682_priv,
 			     dai_clks_hw[RT5682_DAI_BCLK_IDX]);
-	struct snd_soc_component *component = rt5682->component;
+	struct snd_soc_component *component;
 	struct snd_soc_dai *dai;
 	unsigned long factor;
 
 	if (!rt5682_clk_check(rt5682))
 		return -EINVAL;
 
+	component = rt5682->component;
+
 	factor = rt5682_bclk_get_factor(rate, parent_rate);
 
 	for_each_component_dais(component, dai)
 		if (dai->id == RT5682_AIF1)
-			break;
-	if (!dai) {
-		dev_err(component->dev, "dai %d not found in component\n",
-			RT5682_AIF1);
-		return -ENODEV;
-	}
+			return rt5682_set_bclk1_ratio(dai, factor);
 
-	return rt5682_set_bclk1_ratio(dai, factor);
+	dev_err(rt5682->i2c_dev, "dai %d not found in component\n",
+		RT5682_AIF1);
+	return -ENODEV;
 }
 
 static const struct clk_ops rt5682_dai_clk_ops[RT5682_DAI_NUM_CLKS] = {
@@ -2836,10 +2844,9 @@ static const struct clk_ops rt5682_dai_clk_ops[RT5682_DAI_NUM_CLKS] = {
 	},
 };
 
-static int rt5682_register_dai_clks(struct snd_soc_component *component)
+int rt5682_register_dai_clks(struct rt5682_priv *rt5682)
 {
-	struct device *dev = component->dev;
-	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
+	struct device *dev = rt5682->i2c_dev;
 	struct rt5682_platform_data *pdata = &rt5682->pdata;
 	struct clk_hw *dai_clk_hw;
 	int i, ret;
@@ -2899,6 +2906,7 @@ static int rt5682_register_dai_clks(struct snd_soc_component *component)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(rt5682_register_dai_clks);
 #endif /* CONFIG_COMMON_CLK */
 
 static int rt5682_probe(struct snd_soc_component *component)
@@ -2908,9 +2916,6 @@ static int rt5682_probe(struct snd_soc_component *component)
 	unsigned long time;
 	struct snd_soc_dapm_context *dapm = &component->dapm;
 
-#ifdef CONFIG_COMMON_CLK
-	int ret;
-#endif
 	rt5682->component = component;
 
 	if (rt5682->is_sdw) {
@@ -2922,26 +2927,6 @@ static int rt5682_probe(struct snd_soc_component *component)
 			dev_err(&slave->dev, "Initialization not complete, timed out\n");
 			return -ETIMEDOUT;
 		}
-	} else {
-#ifdef CONFIG_COMMON_CLK
-		/* Check if MCLK provided */
-		rt5682->mclk = devm_clk_get(component->dev, "mclk");
-		if (IS_ERR(rt5682->mclk)) {
-			if (PTR_ERR(rt5682->mclk) != -ENOENT) {
-				ret = PTR_ERR(rt5682->mclk);
-				return ret;
-			}
-			rt5682->mclk = NULL;
-		}
-
-		/* Register CCF DAI clock control */
-		ret = rt5682_register_dai_clks(component);
-		if (ret)
-			return ret;
-
-		/* Initial setup for CCF */
-		rt5682->lrck[RT5682_AIF1] = CLK_48;
-#endif
 	}
 
 	snd_soc_dapm_disable_pin(dapm, "MICBIAS");
@@ -2968,10 +2953,7 @@ static int rt5682_suspend(struct snd_soc_component *component)
 
 	cancel_delayed_work_sync(&rt5682->jack_detect_work);
 	cancel_delayed_work_sync(&rt5682->jd_check_work);
-	if (rt5682->hs_jack && rt5682->jack_type == SND_JACK_HEADSET) {
-		snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1,
-			RT5682_MB1_PATH_MASK | RT5682_MB2_PATH_MASK,
-			RT5682_CTRL_MB1_REG | RT5682_CTRL_MB2_REG);
+	if (rt5682->hs_jack && (rt5682->jack_type & SND_JACK_HEADSET) == SND_JACK_HEADSET) {
 		val = snd_soc_component_read(component,
 				RT5682_CBJ_CTRL_2) & RT5682_JACK_TYPE_MASK;
 
@@ -2993,10 +2975,17 @@ static int rt5682_suspend(struct snd_soc_component *component)
 		/* enter SAR ADC power saving mode */
 		snd_soc_component_update_bits(component, RT5682_SAR_IL_CMD_1,
 			RT5682_SAR_BUTT_DET_MASK | RT5682_SAR_BUTDET_MODE_MASK |
-			RT5682_SAR_BUTDET_RST_MASK | RT5682_SAR_SEL_MB1_MB2_MASK, 0);
+			RT5682_SAR_SEL_MB1_MB2_MASK, 0);
+		usleep_range(5000, 6000);
+		snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1,
+			RT5682_MB1_PATH_MASK | RT5682_MB2_PATH_MASK,
+			RT5682_CTRL_MB1_REG | RT5682_CTRL_MB2_REG);
+		usleep_range(10000, 12000);
 		snd_soc_component_update_bits(component, RT5682_SAR_IL_CMD_1,
-			RT5682_SAR_BUTT_DET_MASK | RT5682_SAR_BUTDET_MODE_MASK | RT5682_SAR_BUTDET_RST_MASK,
-			RT5682_SAR_BUTT_DET_EN | RT5682_SAR_BUTDET_POW_SAV | RT5682_SAR_BUTDET_RST_NORMAL);
+			RT5682_SAR_BUTT_DET_MASK | RT5682_SAR_BUTDET_MODE_MASK,
+			RT5682_SAR_BUTT_DET_EN | RT5682_SAR_BUTDET_POW_SAV);
+		snd_soc_component_update_bits(component, RT5682_HP_CHARGE_PUMP_1,
+			RT5682_OSW_L_MASK | RT5682_OSW_R_MASK, 0);
 	}
 
 	regcache_cache_only(rt5682->regmap, true);
@@ -3014,10 +3003,11 @@ static int rt5682_resume(struct snd_soc_component *component)
 	regcache_cache_only(rt5682->regmap, false);
 	regcache_sync(rt5682->regmap);
 
-	if (rt5682->hs_jack && rt5682->jack_type == SND_JACK_HEADSET) {
+	if (rt5682->hs_jack && (rt5682->jack_type & SND_JACK_HEADSET) == SND_JACK_HEADSET) {
 		snd_soc_component_update_bits(component, RT5682_SAR_IL_CMD_1,
 			RT5682_SAR_BUTDET_MODE_MASK | RT5682_SAR_SEL_MB1_MB2_MASK,
 			RT5682_SAR_BUTDET_POW_NORM | RT5682_SAR_SEL_MB1_MB2_AUTO);
+		usleep_range(5000, 6000);
 		snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1,
 			RT5682_MB1_PATH_MASK | RT5682_MB2_PATH_MASK,
 			RT5682_CTRL_MB1_FSM | RT5682_CTRL_MB2_FSM);
@@ -3025,8 +3015,9 @@ static int rt5682_resume(struct snd_soc_component *component)
 			RT5682_PWR_CBJ, RT5682_PWR_CBJ);
 	}
 
+	rt5682->jack_type = 0;
 	mod_delayed_work(system_power_efficient_wq,
-		&rt5682->jack_detect_work, msecs_to_jiffies(250));
+		&rt5682->jack_detect_work, msecs_to_jiffies(0));
 
 	return 0;
 }
diff --git a/sound/soc/codecs/rt5682.h b/sound/soc/codecs/rt5682.h
index 8e3244a62c16..52ff0d9c36c5 100644
--- a/sound/soc/codecs/rt5682.h
+++ b/sound/soc/codecs/rt5682.h
@@ -1428,6 +1428,7 @@ enum {
 
 struct rt5682_priv {
 	struct snd_soc_component *component;
+	struct device *i2c_dev;
 	struct rt5682_platform_data pdata;
 	struct regmap *regmap;
 	struct regmap *sdw_regmap;
@@ -1471,7 +1472,6 @@ int rt5682_sel_asrc_clk_src(struct snd_soc_component *component,
 
 void rt5682_apply_patch_list(struct rt5682_priv *rt5682, struct device *dev);
 
-int rt5682_headset_detect(struct snd_soc_component *component, int jack_insert);
 void rt5682_jack_detect_handler(struct work_struct *work);
 
 bool rt5682_volatile_register(struct device *dev, unsigned int reg);
@@ -1482,6 +1482,8 @@ void rt5682_calibrate(struct rt5682_priv *rt5682);
 void rt5682_reset(struct rt5682_priv *rt5682);
 int rt5682_parse_dt(struct rt5682_priv *rt5682, struct device *dev);
 
+int rt5682_register_dai_clks(struct rt5682_priv *rt5682);
+
 #define RT5682_REG_NUM 318
 extern const struct reg_default rt5682_reg[RT5682_REG_NUM];
 
diff --git a/sound/soc/codecs/rt700-sdw.c b/sound/soc/codecs/rt700-sdw.c
index bda594899664..f7439e40ca8b 100644
--- a/sound/soc/codecs/rt700-sdw.c
+++ b/sound/soc/codecs/rt700-sdw.c
@@ -13,6 +13,7 @@
 #include <linux/soundwire/sdw_type.h>
 #include <linux/soundwire/sdw_registers.h>
 #include <linux/module.h>
+#include <linux/pm_runtime.h>
 #include <linux/regmap.h>
 #include <sound/soc.h>
 #include "rt700.h"
@@ -463,11 +464,14 @@ static int rt700_sdw_remove(struct sdw_slave *slave)
 {
 	struct rt700_priv *rt700 = dev_get_drvdata(&slave->dev);
 
-	if (rt700 && rt700->hw_init) {
+	if (rt700->hw_init) {
 		cancel_delayed_work_sync(&rt700->jack_detect_work);
 		cancel_delayed_work_sync(&rt700->jack_btn_check_work);
 	}
 
+	if (rt700->first_hw_init)
+		pm_runtime_disable(&slave->dev);
+
 	return 0;
 }
 
diff --git a/sound/soc/codecs/rt700.c b/sound/soc/codecs/rt700.c
index 921382724f9c..e049d672ccfd 100644
--- a/sound/soc/codecs/rt700.c
+++ b/sound/soc/codecs/rt700.c
@@ -162,7 +162,7 @@ static void rt700_jack_detect_handler(struct work_struct *work)
 	if (!rt700->hs_jack)
 		return;
 
-	if (!rt700->component->card->instantiated)
+	if (!rt700->component->card || !rt700->component->card->instantiated)
 		return;
 
 	reg = RT700_VERB_GET_PIN_SENSE | RT700_HP_OUT;
@@ -315,17 +315,27 @@ static int rt700_set_jack_detect(struct snd_soc_component *component,
 	struct snd_soc_jack *hs_jack, void *data)
 {
 	struct rt700_priv *rt700 = snd_soc_component_get_drvdata(component);
+	int ret;
 
 	rt700->hs_jack = hs_jack;
 
-	if (!rt700->hw_init) {
-		dev_dbg(&rt700->slave->dev,
-			"%s hw_init not ready yet\n", __func__);
+	ret = pm_runtime_resume_and_get(component->dev);
+	if (ret < 0) {
+		if (ret != -EACCES) {
+			dev_err(component->dev, "%s: failed to resume %d\n", __func__, ret);
+			return ret;
+		}
+
+		/* pm_runtime not enabled yet */
+		dev_dbg(component->dev,	"%s: skipping jack init for now\n", __func__);
 		return 0;
 	}
 
 	rt700_jack_init(rt700);
 
+	pm_runtime_mark_last_busy(component->dev);
+	pm_runtime_put_autosuspend(component->dev);
+
 	return 0;
 }
 
@@ -1114,6 +1124,11 @@ int rt700_init(struct device *dev, struct regmap *sdw_regmap,
 
 	mutex_init(&rt700->disable_irq_lock);
 
+	INIT_DELAYED_WORK(&rt700->jack_detect_work,
+			  rt700_jack_detect_handler);
+	INIT_DELAYED_WORK(&rt700->jack_btn_check_work,
+			  rt700_btn_check_handler);
+
 	/*
 	 * Mark hw_init to false
 	 * HW init will be performed when device reports present
@@ -1208,13 +1223,6 @@ int rt700_io_init(struct device *dev, struct sdw_slave *slave)
 	/* Finish Initial Settings, set power to D3 */
 	regmap_write(rt700->regmap, RT700_SET_AUDIO_POWER_STATE, AC_PWRST_D3);
 
-	if (!rt700->first_hw_init) {
-		INIT_DELAYED_WORK(&rt700->jack_detect_work,
-			rt700_jack_detect_handler);
-		INIT_DELAYED_WORK(&rt700->jack_btn_check_work,
-			rt700_btn_check_handler);
-	}
-
 	/*
 	 * if set_jack callback occurred early than io_init,
 	 * we set up the jack detection function now
diff --git a/sound/soc/codecs/rt711-sdca-sdw.c b/sound/soc/codecs/rt711-sdca-sdw.c
index aaf5af153d3f..a085b2f530aa 100644
--- a/sound/soc/codecs/rt711-sdca-sdw.c
+++ b/sound/soc/codecs/rt711-sdca-sdw.c
@@ -11,6 +11,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/soundwire/sdw_registers.h>
 #include <linux/module.h>
+#include <linux/pm_runtime.h>
 
 #include "rt711-sdca.h"
 #include "rt711-sdca-sdw.h"
@@ -364,11 +365,17 @@ static int rt711_sdca_sdw_remove(struct sdw_slave *slave)
 {
 	struct rt711_sdca_priv *rt711 = dev_get_drvdata(&slave->dev);
 
-	if (rt711 && rt711->hw_init) {
+	if (rt711->hw_init) {
 		cancel_delayed_work_sync(&rt711->jack_detect_work);
 		cancel_delayed_work_sync(&rt711->jack_btn_check_work);
 	}
 
+	if (rt711->first_hw_init)
+		pm_runtime_disable(&slave->dev);
+
+	mutex_destroy(&rt711->calibrate_mutex);
+	mutex_destroy(&rt711->disable_irq_lock);
+
 	return 0;
 }
 
diff --git a/sound/soc/codecs/rt711-sdca.c b/sound/soc/codecs/rt711-sdca.c
index 2e992589f1e4..3b5df3ea2f60 100644
--- a/sound/soc/codecs/rt711-sdca.c
+++ b/sound/soc/codecs/rt711-sdca.c
@@ -34,7 +34,7 @@ static int rt711_sdca_index_write(struct rt711_sdca_priv *rt711,
 
 	ret = regmap_write(regmap, addr, value);
 	if (ret < 0)
-		dev_err(rt711->component->dev,
+		dev_err(&rt711->slave->dev,
 			"Failed to set private value: %06x <= %04x ret=%d\n",
 			addr, value, ret);
 
@@ -50,7 +50,7 @@ static int rt711_sdca_index_read(struct rt711_sdca_priv *rt711,
 
 	ret = regmap_read(regmap, addr, value);
 	if (ret < 0)
-		dev_err(rt711->component->dev,
+		dev_err(&rt711->slave->dev,
 			"Failed to get private value: %06x => %04x ret=%d\n",
 			addr, *value, ret);
 
@@ -294,7 +294,7 @@ static void rt711_sdca_jack_detect_handler(struct work_struct *work)
 	if (!rt711->hs_jack)
 		return;
 
-	if (!rt711->component->card->instantiated)
+	if (!rt711->component->card || !rt711->component->card->instantiated)
 		return;
 
 	/* SDW_SCP_SDCA_INT_SDCA_0 is used for jack detection */
@@ -487,16 +487,27 @@ static int rt711_sdca_set_jack_detect(struct snd_soc_component *component,
 	struct snd_soc_jack *hs_jack, void *data)
 {
 	struct rt711_sdca_priv *rt711 = snd_soc_component_get_drvdata(component);
+	int ret;
 
 	rt711->hs_jack = hs_jack;
 
-	if (!rt711->hw_init) {
-		dev_dbg(&rt711->slave->dev,
-			"%s hw_init not ready yet\n", __func__);
+	ret = pm_runtime_resume_and_get(component->dev);
+	if (ret < 0) {
+		if (ret != -EACCES) {
+			dev_err(component->dev, "%s: failed to resume %d\n", __func__, ret);
+			return ret;
+		}
+
+		/* pm_runtime not enabled yet */
+		dev_dbg(component->dev,	"%s: skipping jack init for now\n", __func__);
 		return 0;
 	}
 
 	rt711_sdca_jack_init(rt711);
+
+	pm_runtime_mark_last_busy(component->dev);
+	pm_runtime_put_autosuspend(component->dev);
+
 	return 0;
 }
 
@@ -1190,14 +1201,6 @@ static int rt711_sdca_probe(struct snd_soc_component *component)
 	return 0;
 }
 
-static void rt711_sdca_remove(struct snd_soc_component *component)
-{
-	struct rt711_sdca_priv *rt711 = snd_soc_component_get_drvdata(component);
-
-	regcache_cache_only(rt711->regmap, true);
-	regcache_cache_only(rt711->mbq_regmap, true);
-}
-
 static const struct snd_soc_component_driver soc_sdca_dev_rt711 = {
 	.probe = rt711_sdca_probe,
 	.controls = rt711_sdca_snd_controls,
@@ -1207,7 +1210,7 @@ static const struct snd_soc_component_driver soc_sdca_dev_rt711 = {
 	.dapm_routes = rt711_sdca_audio_map,
 	.num_dapm_routes = ARRAY_SIZE(rt711_sdca_audio_map),
 	.set_jack = rt711_sdca_set_jack_detect,
-	.remove = rt711_sdca_remove,
+	.endianness = 1,
 };
 
 static int rt711_sdca_set_sdw_stream(struct snd_soc_dai *dai, void *sdw_stream,
@@ -1411,8 +1414,12 @@ int rt711_sdca_init(struct device *dev, struct regmap *regmap,
 	rt711->regmap = regmap;
 	rt711->mbq_regmap = mbq_regmap;
 
+	mutex_init(&rt711->calibrate_mutex);
 	mutex_init(&rt711->disable_irq_lock);
 
+	INIT_DELAYED_WORK(&rt711->jack_detect_work, rt711_sdca_jack_detect_handler);
+	INIT_DELAYED_WORK(&rt711->jack_btn_check_work, rt711_sdca_btn_check_handler);
+
 	/*
 	 * Mark hw_init to false
 	 * HW init will be performed when device reports present
@@ -1544,14 +1551,6 @@ int rt711_sdca_io_init(struct device *dev, struct sdw_slave *slave)
 	rt711_sdca_index_update_bits(rt711, RT711_VENDOR_HDA_CTL,
 		RT711_PUSH_BTN_INT_CTL0, 0x20, 0x00);
 
-	if (!rt711->first_hw_init) {
-		INIT_DELAYED_WORK(&rt711->jack_detect_work,
-			rt711_sdca_jack_detect_handler);
-		INIT_DELAYED_WORK(&rt711->jack_btn_check_work,
-			rt711_sdca_btn_check_handler);
-		mutex_init(&rt711->calibrate_mutex);
-	}
-
 	/* calibration */
 	ret = rt711_sdca_calibration(rt711);
 	if (ret < 0)
diff --git a/sound/soc/codecs/rt711-sdw.c b/sound/soc/codecs/rt711-sdw.c
index bda2cc9439c9..4fe68bcf2a7c 100644
--- a/sound/soc/codecs/rt711-sdw.c
+++ b/sound/soc/codecs/rt711-sdw.c
@@ -13,6 +13,7 @@
 #include <linux/soundwire/sdw_type.h>
 #include <linux/soundwire/sdw_registers.h>
 #include <linux/module.h>
+#include <linux/pm_runtime.h>
 #include <linux/regmap.h>
 #include <sound/soc.h>
 #include "rt711.h"
@@ -464,12 +465,18 @@ static int rt711_sdw_remove(struct sdw_slave *slave)
 {
 	struct rt711_priv *rt711 = dev_get_drvdata(&slave->dev);
 
-	if (rt711 && rt711->hw_init) {
+	if (rt711->hw_init) {
 		cancel_delayed_work_sync(&rt711->jack_detect_work);
 		cancel_delayed_work_sync(&rt711->jack_btn_check_work);
 		cancel_work_sync(&rt711->calibration_work);
 	}
 
+	if (rt711->first_hw_init)
+		pm_runtime_disable(&slave->dev);
+
+	mutex_destroy(&rt711->calibrate_mutex);
+	mutex_destroy(&rt711->disable_irq_lock);
+
 	return 0;
 }
 
diff --git a/sound/soc/codecs/rt711.c b/sound/soc/codecs/rt711.c
index a7c5608a0ef8..51a98e730fc8 100644
--- a/sound/soc/codecs/rt711.c
+++ b/sound/soc/codecs/rt711.c
@@ -242,7 +242,7 @@ static void rt711_jack_detect_handler(struct work_struct *work)
 	if (!rt711->hs_jack)
 		return;
 
-	if (!rt711->component->card->instantiated)
+	if (!rt711->component->card || !rt711->component->card->instantiated)
 		return;
 
 	reg = RT711_VERB_GET_PIN_SENSE | RT711_HP_OUT;
@@ -450,17 +450,27 @@ static int rt711_set_jack_detect(struct snd_soc_component *component,
 	struct snd_soc_jack *hs_jack, void *data)
 {
 	struct rt711_priv *rt711 = snd_soc_component_get_drvdata(component);
+	int ret;
 
 	rt711->hs_jack = hs_jack;
 
-	if (!rt711->hw_init) {
-		dev_dbg(&rt711->slave->dev,
-			"%s hw_init not ready yet\n", __func__);
+	ret = pm_runtime_resume_and_get(component->dev);
+	if (ret < 0) {
+		if (ret != -EACCES) {
+			dev_err(component->dev, "%s: failed to resume %d\n", __func__, ret);
+			return ret;
+		}
+
+		/* pm_runtime not enabled yet */
+		dev_dbg(component->dev,	"%s: skipping jack init for now\n", __func__);
 		return 0;
 	}
 
 	rt711_jack_init(rt711);
 
+	pm_runtime_mark_last_busy(component->dev);
+	pm_runtime_put_autosuspend(component->dev);
+
 	return 0;
 }
 
@@ -925,13 +935,6 @@ static int rt711_probe(struct snd_soc_component *component)
 	return 0;
 }
 
-static void rt711_remove(struct snd_soc_component *component)
-{
-	struct rt711_priv *rt711 = snd_soc_component_get_drvdata(component);
-
-	regcache_cache_only(rt711->regmap, true);
-}
-
 static const struct snd_soc_component_driver soc_codec_dev_rt711 = {
 	.probe = rt711_probe,
 	.set_bias_level = rt711_set_bias_level,
@@ -942,7 +945,7 @@ static const struct snd_soc_component_driver soc_codec_dev_rt711 = {
 	.dapm_routes = rt711_audio_map,
 	.num_dapm_routes = ARRAY_SIZE(rt711_audio_map),
 	.set_jack = rt711_set_jack_detect,
-	.remove = rt711_remove,
+	.endianness = 1,
 };
 
 static int rt711_set_sdw_stream(struct snd_soc_dai *dai, void *sdw_stream,
@@ -1196,8 +1199,13 @@ int rt711_init(struct device *dev, struct regmap *sdw_regmap,
 	rt711->sdw_regmap = sdw_regmap;
 	rt711->regmap = regmap;
 
+	mutex_init(&rt711->calibrate_mutex);
 	mutex_init(&rt711->disable_irq_lock);
 
+	INIT_DELAYED_WORK(&rt711->jack_detect_work, rt711_jack_detect_handler);
+	INIT_DELAYED_WORK(&rt711->jack_btn_check_work, rt711_btn_check_handler);
+	INIT_WORK(&rt711->calibration_work, rt711_calibration_work);
+
 	/*
 	 * Mark hw_init to false
 	 * HW init will be performed when device reports present
@@ -1305,15 +1313,8 @@ int rt711_io_init(struct device *dev, struct sdw_slave *slave)
 
 	if (rt711->first_hw_init)
 		rt711_calibration(rt711);
-	else {
-		INIT_DELAYED_WORK(&rt711->jack_detect_work,
-			rt711_jack_detect_handler);
-		INIT_DELAYED_WORK(&rt711->jack_btn_check_work,
-			rt711_btn_check_handler);
-		mutex_init(&rt711->calibrate_mutex);
-		INIT_WORK(&rt711->calibration_work, rt711_calibration_work);
+	else
 		schedule_work(&rt711->calibration_work);
-	}
 
 	/*
 	 * if set_jack callback occurred early than io_init,
diff --git a/sound/soc/codecs/rt715-sdca-sdw.c b/sound/soc/codecs/rt715-sdca-sdw.c
index a5c673f43d82..0f4354eafef2 100644
--- a/sound/soc/codecs/rt715-sdca-sdw.c
+++ b/sound/soc/codecs/rt715-sdca-sdw.c
@@ -13,6 +13,7 @@
 #include <linux/soundwire/sdw_type.h>
 #include <linux/soundwire/sdw_registers.h>
 #include <linux/module.h>
+#include <linux/pm_runtime.h>
 #include <linux/regmap.h>
 #include <sound/soc.h>
 #include "rt715-sdca.h"
@@ -195,6 +196,16 @@ static int rt715_sdca_sdw_probe(struct sdw_slave *slave,
 	return rt715_sdca_init(&slave->dev, mbq_regmap, regmap, slave);
 }
 
+static int rt715_sdca_sdw_remove(struct sdw_slave *slave)
+{
+	struct rt715_sdca_priv *rt715 = dev_get_drvdata(&slave->dev);
+
+	if (rt715->first_hw_init)
+		pm_runtime_disable(&slave->dev);
+
+	return 0;
+}
+
 static const struct sdw_device_id rt715_sdca_id[] = {
 	SDW_SLAVE_ENTRY_EXT(0x025d, 0x715, 0x3, 0x1, 0),
 	SDW_SLAVE_ENTRY_EXT(0x025d, 0x714, 0x3, 0x1, 0),
@@ -269,6 +280,7 @@ static struct sdw_driver rt715_sdw_driver = {
 		.pm = &rt715_pm,
 	},
 	.probe = rt715_sdca_sdw_probe,
+	.remove = rt715_sdca_sdw_remove,
 	.ops = &rt715_sdca_slave_ops,
 	.id_table = rt715_sdca_id,
 };
diff --git a/sound/soc/codecs/rt715-sdw.c b/sound/soc/codecs/rt715-sdw.c
index a7b21b03c08b..b047bf87a100 100644
--- a/sound/soc/codecs/rt715-sdw.c
+++ b/sound/soc/codecs/rt715-sdw.c
@@ -14,6 +14,7 @@
 #include <linux/soundwire/sdw_type.h>
 #include <linux/soundwire/sdw_registers.h>
 #include <linux/module.h>
+#include <linux/pm_runtime.h>
 #include <linux/of.h>
 #include <linux/regmap.h>
 #include <sound/soc.h>
@@ -514,6 +515,16 @@ static int rt715_sdw_probe(struct sdw_slave *slave,
 	return 0;
 }
 
+static int rt715_sdw_remove(struct sdw_slave *slave)
+{
+	struct rt715_priv *rt715 = dev_get_drvdata(&slave->dev);
+
+	if (rt715->first_hw_init)
+		pm_runtime_disable(&slave->dev);
+
+	return 0;
+}
+
 static const struct sdw_device_id rt715_id[] = {
 	SDW_SLAVE_ENTRY_EXT(0x025d, 0x714, 0x2, 0, 0),
 	SDW_SLAVE_ENTRY_EXT(0x025d, 0x715, 0x2, 0, 0),
@@ -575,6 +586,7 @@ static struct sdw_driver rt715_sdw_driver = {
 		   .pm = &rt715_pm,
 		   },
 	.probe = rt715_sdw_probe,
+	.remove = rt715_sdw_remove,
 	.ops = &rt715_slave_ops,
 	.id_table = rt715_id,
 };
diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c
index 97bf1f222805..dc56e6c6b668 100644
--- a/sound/soc/codecs/sgtl5000.c
+++ b/sound/soc/codecs/sgtl5000.c
@@ -1797,6 +1797,9 @@ static int sgtl5000_i2c_remove(struct i2c_client *client)
 {
 	struct sgtl5000_priv *sgtl5000 = i2c_get_clientdata(client);
 
+	regmap_write(sgtl5000->regmap, SGTL5000_CHIP_DIG_POWER, SGTL5000_DIG_POWER_DEFAULT);
+	regmap_write(sgtl5000->regmap, SGTL5000_CHIP_ANA_POWER, SGTL5000_ANA_POWER_DEFAULT);
+
 	clk_disable_unprepare(sgtl5000->mclk);
 	regulator_bulk_disable(sgtl5000->num_supplies, sgtl5000->supplies);
 	regulator_bulk_free(sgtl5000->num_supplies, sgtl5000->supplies);
@@ -1804,6 +1807,11 @@ static int sgtl5000_i2c_remove(struct i2c_client *client)
 	return 0;
 }
 
+static void sgtl5000_i2c_shutdown(struct i2c_client *client)
+{
+	sgtl5000_i2c_remove(client);
+}
+
 static const struct i2c_device_id sgtl5000_id[] = {
 	{"sgtl5000", 0},
 	{},
@@ -1824,6 +1832,7 @@ static struct i2c_driver sgtl5000_i2c_driver = {
 	},
 	.probe = sgtl5000_i2c_probe,
 	.remove = sgtl5000_i2c_remove,
+	.shutdown = sgtl5000_i2c_shutdown,
 	.id_table = sgtl5000_id,
 };
 
diff --git a/sound/soc/codecs/sgtl5000.h b/sound/soc/codecs/sgtl5000.h
index 56ec5863f250..3a808c762299 100644
--- a/sound/soc/codecs/sgtl5000.h
+++ b/sound/soc/codecs/sgtl5000.h
@@ -80,6 +80,7 @@
 /*
  * SGTL5000_CHIP_DIG_POWER
  */
+#define SGTL5000_DIG_POWER_DEFAULT		0x0000
 #define SGTL5000_ADC_EN				0x0040
 #define SGTL5000_DAC_EN				0x0020
 #define SGTL5000_DAP_POWERUP			0x0010
diff --git a/sound/soc/codecs/tas2764.c b/sound/soc/codecs/tas2764.c
index 9265af41c235..ec13ba01e522 100644
--- a/sound/soc/codecs/tas2764.c
+++ b/sound/soc/codecs/tas2764.c
@@ -42,10 +42,12 @@ static void tas2764_reset(struct tas2764_priv *tas2764)
 		gpiod_set_value_cansleep(tas2764->reset_gpio, 0);
 		msleep(20);
 		gpiod_set_value_cansleep(tas2764->reset_gpio, 1);
+		usleep_range(1000, 2000);
 	}
 
 	snd_soc_component_write(tas2764->component, TAS2764_SW_RST,
 				TAS2764_RST);
+	usleep_range(1000, 2000);
 }
 
 static int tas2764_set_bias_level(struct snd_soc_component *component,
@@ -107,8 +109,10 @@ static int tas2764_codec_resume(struct snd_soc_component *component)
 	struct tas2764_priv *tas2764 = snd_soc_component_get_drvdata(component);
 	int ret;
 
-	if (tas2764->sdz_gpio)
+	if (tas2764->sdz_gpio) {
 		gpiod_set_value_cansleep(tas2764->sdz_gpio, 1);
+		usleep_range(1000, 2000);
+	}
 
 	ret = snd_soc_component_update_bits(component, TAS2764_PWR_CTRL,
 					    TAS2764_PWR_CTRL_MASK,
@@ -131,7 +135,8 @@ static const char * const tas2764_ASI1_src[] = {
 };
 
 static SOC_ENUM_SINGLE_DECL(
-	tas2764_ASI1_src_enum, TAS2764_TDM_CFG2, 4, tas2764_ASI1_src);
+	tas2764_ASI1_src_enum, TAS2764_TDM_CFG2, TAS2764_TDM_CFG2_SCFG_SHIFT,
+	tas2764_ASI1_src);
 
 static const struct snd_kcontrol_new tas2764_asi1_mux =
 	SOC_DAPM_ENUM("ASI1 Source", tas2764_ASI1_src_enum);
@@ -329,20 +334,22 @@ static int tas2764_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 {
 	struct snd_soc_component *component = dai->component;
 	struct tas2764_priv *tas2764 = snd_soc_component_get_drvdata(component);
-	u8 tdm_rx_start_slot = 0, asi_cfg_1 = 0;
-	int iface;
+	u8 tdm_rx_start_slot = 0, asi_cfg_0 = 0, asi_cfg_1 = 0;
 	int ret;
 
 	switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
+	case SND_SOC_DAIFMT_NB_IF:
+		asi_cfg_0 ^= TAS2764_TDM_CFG0_FRAME_START;
+		fallthrough;
 	case SND_SOC_DAIFMT_NB_NF:
 		asi_cfg_1 = TAS2764_TDM_CFG1_RX_RISING;
 		break;
+	case SND_SOC_DAIFMT_IB_IF:
+		asi_cfg_0 ^= TAS2764_TDM_CFG0_FRAME_START;
+		fallthrough;
 	case SND_SOC_DAIFMT_IB_NF:
 		asi_cfg_1 = TAS2764_TDM_CFG1_RX_FALLING;
 		break;
-	default:
-		dev_err(tas2764->dev, "ASI format Inverse is not found\n");
-		return -EINVAL;
 	}
 
 	ret = snd_soc_component_update_bits(component, TAS2764_TDM_CFG1,
@@ -353,13 +360,13 @@ static int tas2764_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 
 	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
 	case SND_SOC_DAIFMT_I2S:
+		asi_cfg_0 ^= TAS2764_TDM_CFG0_FRAME_START;
+		fallthrough;
 	case SND_SOC_DAIFMT_DSP_A:
-		iface = TAS2764_TDM_CFG2_SCFG_I2S;
 		tdm_rx_start_slot = 1;
 		break;
 	case SND_SOC_DAIFMT_DSP_B:
 	case SND_SOC_DAIFMT_LEFT_J:
-		iface = TAS2764_TDM_CFG2_SCFG_LEFT_J;
 		tdm_rx_start_slot = 0;
 		break;
 	default:
@@ -368,14 +375,15 @@ static int tas2764_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 		return -EINVAL;
 	}
 
-	ret = snd_soc_component_update_bits(component, TAS2764_TDM_CFG1,
-					    TAS2764_TDM_CFG1_MASK,
-					    (tdm_rx_start_slot << TAS2764_TDM_CFG1_51_SHIFT));
+	ret = snd_soc_component_update_bits(component, TAS2764_TDM_CFG0,
+					    TAS2764_TDM_CFG0_FRAME_START,
+					    asi_cfg_0);
 	if (ret < 0)
 		return ret;
 
-	ret = snd_soc_component_update_bits(component, TAS2764_TDM_CFG2,
-					    TAS2764_TDM_CFG2_SCFG_MASK, iface);
+	ret = snd_soc_component_update_bits(component, TAS2764_TDM_CFG1,
+					    TAS2764_TDM_CFG1_MASK,
+					    (tdm_rx_start_slot << TAS2764_TDM_CFG1_51_SHIFT));
 	if (ret < 0)
 		return ret;
 
@@ -501,8 +509,10 @@ static int tas2764_codec_probe(struct snd_soc_component *component)
 
 	tas2764->component = component;
 
-	if (tas2764->sdz_gpio)
+	if (tas2764->sdz_gpio) {
 		gpiod_set_value_cansleep(tas2764->sdz_gpio, 1);
+		usleep_range(1000, 2000);
+	}
 
 	tas2764_reset(tas2764);
 
@@ -526,12 +536,12 @@ static int tas2764_codec_probe(struct snd_soc_component *component)
 }
 
 static DECLARE_TLV_DB_SCALE(tas2764_digital_tlv, 1100, 50, 0);
-static DECLARE_TLV_DB_SCALE(tas2764_playback_volume, -10000, 50, 0);
+static DECLARE_TLV_DB_SCALE(tas2764_playback_volume, -10050, 50, 1);
 
 static const struct snd_kcontrol_new tas2764_snd_controls[] = {
 	SOC_SINGLE_TLV("Speaker Volume", TAS2764_DVC, 0,
 		       TAS2764_DVC_MAX, 1, tas2764_playback_volume),
-	SOC_SINGLE_TLV("Amp Gain Volume", TAS2764_CHNL_0, 0, 0x14, 0,
+	SOC_SINGLE_TLV("Amp Gain Volume", TAS2764_CHNL_0, 1, 0x14, 0,
 		       tas2764_digital_tlv),
 };
 
@@ -556,7 +566,7 @@ static const struct reg_default tas2764_reg_defaults[] = {
 	{ TAS2764_SW_RST, 0x00 },
 	{ TAS2764_PWR_CTRL, 0x1a },
 	{ TAS2764_DVC, 0x00 },
-	{ TAS2764_CHNL_0, 0x00 },
+	{ TAS2764_CHNL_0, 0x28 },
 	{ TAS2764_TDM_CFG0, 0x09 },
 	{ TAS2764_TDM_CFG1, 0x02 },
 	{ TAS2764_TDM_CFG2, 0x0a },
diff --git a/sound/soc/codecs/tas2764.h b/sound/soc/codecs/tas2764.h
index 67d6fd903c42..f015f22a083b 100644
--- a/sound/soc/codecs/tas2764.h
+++ b/sound/soc/codecs/tas2764.h
@@ -47,6 +47,7 @@
 #define TAS2764_TDM_CFG0_MASK		GENMASK(3, 1)
 #define TAS2764_TDM_CFG0_44_1_48KHZ	BIT(3)
 #define TAS2764_TDM_CFG0_88_2_96KHZ	(BIT(3) | BIT(1))
+#define TAS2764_TDM_CFG0_FRAME_START	BIT(0)
 
 /* TDM Configuration Reg1 */
 #define TAS2764_TDM_CFG1		TAS2764_REG(0X0, 0x09)
@@ -66,10 +67,7 @@
 #define TAS2764_TDM_CFG2_RXS_16BITS	0x0
 #define TAS2764_TDM_CFG2_RXS_24BITS	BIT(0)
 #define TAS2764_TDM_CFG2_RXS_32BITS	BIT(1)
-#define TAS2764_TDM_CFG2_SCFG_MASK	GENMASK(5, 4)
-#define TAS2764_TDM_CFG2_SCFG_I2S	0x0
-#define TAS2764_TDM_CFG2_SCFG_LEFT_J	BIT(4)
-#define TAS2764_TDM_CFG2_SCFG_RIGHT_J	BIT(5)
+#define TAS2764_TDM_CFG2_SCFG_SHIFT	4
 
 /* TDM Configuration Reg3 */
 #define TAS2764_TDM_CFG3		TAS2764_REG(0X0, 0x0c)
diff --git a/sound/soc/codecs/tas2770.c b/sound/soc/codecs/tas2770.c
index c5ea3b115966..b8cda6b14b49 100644
--- a/sound/soc/codecs/tas2770.c
+++ b/sound/soc/codecs/tas2770.c
@@ -46,34 +46,22 @@ static void tas2770_reset(struct tas2770_priv *tas2770)
 	usleep_range(1000, 2000);
 }
 
-static int tas2770_set_bias_level(struct snd_soc_component *component,
-				 enum snd_soc_bias_level level)
+static int tas2770_update_pwr_ctrl(struct tas2770_priv *tas2770)
 {
-	struct tas2770_priv *tas2770 =
-			snd_soc_component_get_drvdata(component);
+	struct snd_soc_component *component = tas2770->component;
+	unsigned int val;
+	int ret;
 
-	switch (level) {
-	case SND_SOC_BIAS_ON:
-		snd_soc_component_update_bits(component, TAS2770_PWR_CTRL,
-					      TAS2770_PWR_CTRL_MASK,
-					      TAS2770_PWR_CTRL_ACTIVE);
-		break;
-	case SND_SOC_BIAS_STANDBY:
-	case SND_SOC_BIAS_PREPARE:
-		snd_soc_component_update_bits(component, TAS2770_PWR_CTRL,
-					      TAS2770_PWR_CTRL_MASK,
-					      TAS2770_PWR_CTRL_MUTE);
-		break;
-	case SND_SOC_BIAS_OFF:
-		snd_soc_component_update_bits(component, TAS2770_PWR_CTRL,
-					      TAS2770_PWR_CTRL_MASK,
-					      TAS2770_PWR_CTRL_SHUTDOWN);
-		break;
+	if (tas2770->dac_powered)
+		val = tas2770->unmuted ?
+			TAS2770_PWR_CTRL_ACTIVE : TAS2770_PWR_CTRL_MUTE;
+	else
+		val = TAS2770_PWR_CTRL_SHUTDOWN;
 
-	default:
-		dev_err(tas2770->dev, "wrong power level setting %d\n", level);
-		return -EINVAL;
-	}
+	ret = snd_soc_component_update_bits(component, TAS2770_PWR_CTRL,
+					    TAS2770_PWR_CTRL_MASK, val);
+	if (ret < 0)
+		return ret;
 
 	return 0;
 }
@@ -114,9 +102,7 @@ static int tas2770_codec_resume(struct snd_soc_component *component)
 		gpiod_set_value_cansleep(tas2770->sdz_gpio, 1);
 		usleep_range(1000, 2000);
 	} else {
-		ret = snd_soc_component_update_bits(component, TAS2770_PWR_CTRL,
-						    TAS2770_PWR_CTRL_MASK,
-						    TAS2770_PWR_CTRL_ACTIVE);
+		ret = tas2770_update_pwr_ctrl(tas2770);
 		if (ret < 0)
 			return ret;
 	}
@@ -152,24 +138,19 @@ static int tas2770_dac_event(struct snd_soc_dapm_widget *w,
 
 	switch (event) {
 	case SND_SOC_DAPM_POST_PMU:
-		ret = snd_soc_component_update_bits(component, TAS2770_PWR_CTRL,
-						    TAS2770_PWR_CTRL_MASK,
-						    TAS2770_PWR_CTRL_MUTE);
+		tas2770->dac_powered = 1;
+		ret = tas2770_update_pwr_ctrl(tas2770);
 		break;
 	case SND_SOC_DAPM_PRE_PMD:
-		ret = snd_soc_component_update_bits(component, TAS2770_PWR_CTRL,
-						    TAS2770_PWR_CTRL_MASK,
-						    TAS2770_PWR_CTRL_SHUTDOWN);
+		tas2770->dac_powered = 0;
+		ret = tas2770_update_pwr_ctrl(tas2770);
 		break;
 	default:
 		dev_err(tas2770->dev, "Not supported evevt\n");
 		return -EINVAL;
 	}
 
-	if (ret < 0)
-		return ret;
-
-	return 0;
+	return ret;
 }
 
 static const struct snd_kcontrol_new isense_switch =
@@ -203,21 +184,11 @@ static const struct snd_soc_dapm_route tas2770_audio_map[] = {
 static int tas2770_mute(struct snd_soc_dai *dai, int mute, int direction)
 {
 	struct snd_soc_component *component = dai->component;
-	int ret;
-
-	if (mute)
-		ret = snd_soc_component_update_bits(component, TAS2770_PWR_CTRL,
-						    TAS2770_PWR_CTRL_MASK,
-						    TAS2770_PWR_CTRL_MUTE);
-	else
-		ret = snd_soc_component_update_bits(component, TAS2770_PWR_CTRL,
-						    TAS2770_PWR_CTRL_MASK,
-						    TAS2770_PWR_CTRL_ACTIVE);
-
-	if (ret < 0)
-		return ret;
+	struct tas2770_priv *tas2770 =
+			snd_soc_component_get_drvdata(component);
 
-	return 0;
+	tas2770->unmuted = !mute;
+	return tas2770_update_pwr_ctrl(tas2770);
 }
 
 static int tas2770_set_bitwidth(struct tas2770_priv *tas2770, int bitwidth)
@@ -337,7 +308,7 @@ static int tas2770_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 	struct snd_soc_component *component = dai->component;
 	struct tas2770_priv *tas2770 =
 			snd_soc_component_get_drvdata(component);
-	u8 tdm_rx_start_slot = 0, asi_cfg_1 = 0;
+	u8 tdm_rx_start_slot = 0, invert_fpol = 0, fpol_preinv = 0, asi_cfg_1 = 0;
 	int ret;
 
 	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
@@ -349,9 +320,15 @@ static int tas2770_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 	}
 
 	switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
+	case SND_SOC_DAIFMT_NB_IF:
+		invert_fpol = 1;
+		fallthrough;
 	case SND_SOC_DAIFMT_NB_NF:
 		asi_cfg_1 |= TAS2770_TDM_CFG_REG1_RX_RSING;
 		break;
+	case SND_SOC_DAIFMT_IB_IF:
+		invert_fpol = 1;
+		fallthrough;
 	case SND_SOC_DAIFMT_IB_NF:
 		asi_cfg_1 |= TAS2770_TDM_CFG_REG1_RX_FALING;
 		break;
@@ -369,15 +346,19 @@ static int tas2770_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
 	case SND_SOC_DAIFMT_I2S:
 		tdm_rx_start_slot = 1;
+		fpol_preinv = 0;
 		break;
 	case SND_SOC_DAIFMT_DSP_A:
 		tdm_rx_start_slot = 0;
+		fpol_preinv = 1;
 		break;
 	case SND_SOC_DAIFMT_DSP_B:
 		tdm_rx_start_slot = 1;
+		fpol_preinv = 1;
 		break;
 	case SND_SOC_DAIFMT_LEFT_J:
 		tdm_rx_start_slot = 0;
+		fpol_preinv = 1;
 		break;
 	default:
 		dev_err(tas2770->dev,
@@ -391,6 +372,14 @@ static int tas2770_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 	if (ret < 0)
 		return ret;
 
+	ret = snd_soc_component_update_bits(component, TAS2770_TDM_CFG_REG0,
+					    TAS2770_TDM_CFG_REG0_FPOL_MASK,
+					    (fpol_preinv ^ invert_fpol)
+					     ? TAS2770_TDM_CFG_REG0_FPOL_RSING
+					     : TAS2770_TDM_CFG_REG0_FPOL_FALING);
+	if (ret < 0)
+		return ret;
+
 	return 0;
 }
 
@@ -489,7 +478,7 @@ static struct snd_soc_dai_driver tas2770_dai_driver[] = {
 		.id = 0,
 		.playback = {
 			.stream_name    = "ASI1 Playback",
-			.channels_min   = 2,
+			.channels_min   = 1,
 			.channels_max   = 2,
 			.rates      = TAS2770_RATES,
 			.formats    = TAS2770_FORMATS,
@@ -537,7 +526,6 @@ static const struct snd_soc_component_driver soc_component_driver_tas2770 = {
 	.probe			= tas2770_codec_probe,
 	.suspend		= tas2770_codec_suspend,
 	.resume			= tas2770_codec_resume,
-	.set_bias_level = tas2770_set_bias_level,
 	.controls		= tas2770_snd_controls,
 	.num_controls		= ARRAY_SIZE(tas2770_snd_controls),
 	.dapm_widgets		= tas2770_dapm_widgets,
diff --git a/sound/soc/codecs/tas2770.h b/sound/soc/codecs/tas2770.h
index d156666bcc55..f75f40781ab1 100644
--- a/sound/soc/codecs/tas2770.h
+++ b/sound/soc/codecs/tas2770.h
@@ -41,6 +41,9 @@
 #define TAS2770_TDM_CFG_REG0_31_44_1_48KHZ  0x6
 #define TAS2770_TDM_CFG_REG0_31_88_2_96KHZ  0x8
 #define TAS2770_TDM_CFG_REG0_31_176_4_192KHZ  0xa
+#define TAS2770_TDM_CFG_REG0_FPOL_MASK  BIT(0)
+#define TAS2770_TDM_CFG_REG0_FPOL_RSING  0
+#define TAS2770_TDM_CFG_REG0_FPOL_FALING  1
     /* TDM Configuration Reg1 */
 #define TAS2770_TDM_CFG_REG1  TAS2770_REG(0X0, 0x0B)
 #define TAS2770_TDM_CFG_REG1_MASK	GENMASK(5, 1)
@@ -135,6 +138,8 @@ struct tas2770_priv {
 	struct device *dev;
 	int v_sense_slot;
 	int i_sense_slot;
+	bool dac_powered;
+	bool unmuted;
 };
 
 #endif /* __TAS2770__ */
diff --git a/sound/soc/codecs/tlv320aic32x4.c b/sound/soc/codecs/tlv320aic32x4.c
index d39c7d52ecfd..9f4a629b032b 100644
--- a/sound/soc/codecs/tlv320aic32x4.c
+++ b/sound/soc/codecs/tlv320aic32x4.c
@@ -49,6 +49,8 @@ struct aic32x4_priv {
 	struct aic32x4_setup_data *setup;
 	struct device *dev;
 	enum aic32x4_type type;
+
+	unsigned int fmt;
 };
 
 static int aic32x4_reset_adc(struct snd_soc_dapm_widget *w,
@@ -611,6 +613,7 @@ static int aic32x4_set_dai_sysclk(struct snd_soc_dai *codec_dai,
 static int aic32x4_set_dai_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt)
 {
 	struct snd_soc_component *component = codec_dai->component;
+	struct aic32x4_priv *aic32x4 = snd_soc_component_get_drvdata(component);
 	u8 iface_reg_1 = 0;
 	u8 iface_reg_2 = 0;
 	u8 iface_reg_3 = 0;
@@ -654,6 +657,8 @@ static int aic32x4_set_dai_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt)
 		return -EINVAL;
 	}
 
+	aic32x4->fmt = fmt;
+
 	snd_soc_component_update_bits(component, AIC32X4_IFACE1,
 				AIC32X4_IFACE1_DATATYPE_MASK |
 				AIC32X4_IFACE1_MASTER_MASK, iface_reg_1);
@@ -758,6 +763,10 @@ static int aic32x4_setup_clocks(struct snd_soc_component *component,
 		return -EINVAL;
 	}
 
+	/* PCM over I2S is always 2-channel */
+	if ((aic32x4->fmt & SND_SOC_DAIFMT_FORMAT_MASK) == SND_SOC_DAIFMT_I2S)
+		channels = 2;
+
 	madc = DIV_ROUND_UP((32 * adc_resource_class), aosr);
 	max_dosr = (AIC32X4_MAX_DOSR_FREQ / sample_rate / dosr_increment) *
 			dosr_increment;
diff --git a/sound/soc/codecs/wcd9335.c b/sound/soc/codecs/wcd9335.c
index bc5d68c53e5a..3a13afbfb74b 100644
--- a/sound/soc/codecs/wcd9335.c
+++ b/sound/soc/codecs/wcd9335.c
@@ -2252,51 +2252,42 @@ static int wcd9335_rx_hph_mode_put(struct snd_kcontrol *kc,
 
 static const struct snd_kcontrol_new wcd9335_snd_controls[] = {
 	/* -84dB min - 40dB max */
-	SOC_SINGLE_SX_TLV("RX0 Digital Volume", WCD9335_CDC_RX0_RX_VOL_CTL,
-		0, -84, 40, digital_gain),
-	SOC_SINGLE_SX_TLV("RX1 Digital Volume", WCD9335_CDC_RX1_RX_VOL_CTL,
-		0, -84, 40, digital_gain),
-	SOC_SINGLE_SX_TLV("RX2 Digital Volume", WCD9335_CDC_RX2_RX_VOL_CTL,
-		0, -84, 40, digital_gain),
-	SOC_SINGLE_SX_TLV("RX3 Digital Volume", WCD9335_CDC_RX3_RX_VOL_CTL,
-		0, -84, 40, digital_gain),
-	SOC_SINGLE_SX_TLV("RX4 Digital Volume", WCD9335_CDC_RX4_RX_VOL_CTL,
-		0, -84, 40, digital_gain),
-	SOC_SINGLE_SX_TLV("RX5 Digital Volume", WCD9335_CDC_RX5_RX_VOL_CTL,
-		0, -84, 40, digital_gain),
-	SOC_SINGLE_SX_TLV("RX6 Digital Volume", WCD9335_CDC_RX6_RX_VOL_CTL,
-		0, -84, 40, digital_gain),
-	SOC_SINGLE_SX_TLV("RX7 Digital Volume", WCD9335_CDC_RX7_RX_VOL_CTL,
-		0, -84, 40, digital_gain),
-	SOC_SINGLE_SX_TLV("RX8 Digital Volume", WCD9335_CDC_RX8_RX_VOL_CTL,
-		0, -84, 40, digital_gain),
-	SOC_SINGLE_SX_TLV("RX0 Mix Digital Volume",
-			  WCD9335_CDC_RX0_RX_VOL_MIX_CTL,
-			  0, -84, 40, digital_gain),
-	SOC_SINGLE_SX_TLV("RX1 Mix Digital Volume",
-			  WCD9335_CDC_RX1_RX_VOL_MIX_CTL,
-			  0, -84, 40, digital_gain),
-	SOC_SINGLE_SX_TLV("RX2 Mix Digital Volume",
-			  WCD9335_CDC_RX2_RX_VOL_MIX_CTL,
-			  0, -84, 40, digital_gain),
-	SOC_SINGLE_SX_TLV("RX3 Mix Digital Volume",
-			  WCD9335_CDC_RX3_RX_VOL_MIX_CTL,
-			  0, -84, 40, digital_gain),
-	SOC_SINGLE_SX_TLV("RX4 Mix Digital Volume",
-			  WCD9335_CDC_RX4_RX_VOL_MIX_CTL,
-			  0, -84, 40, digital_gain),
-	SOC_SINGLE_SX_TLV("RX5 Mix Digital Volume",
-			  WCD9335_CDC_RX5_RX_VOL_MIX_CTL,
-			  0, -84, 40, digital_gain),
-	SOC_SINGLE_SX_TLV("RX6 Mix Digital Volume",
-			  WCD9335_CDC_RX6_RX_VOL_MIX_CTL,
-			  0, -84, 40, digital_gain),
-	SOC_SINGLE_SX_TLV("RX7 Mix Digital Volume",
-			  WCD9335_CDC_RX7_RX_VOL_MIX_CTL,
-			  0, -84, 40, digital_gain),
-	SOC_SINGLE_SX_TLV("RX8 Mix Digital Volume",
-			  WCD9335_CDC_RX8_RX_VOL_MIX_CTL,
-			  0, -84, 40, digital_gain),
+	SOC_SINGLE_S8_TLV("RX0 Digital Volume", WCD9335_CDC_RX0_RX_VOL_CTL,
+			-84, 40, digital_gain),
+	SOC_SINGLE_S8_TLV("RX1 Digital Volume", WCD9335_CDC_RX1_RX_VOL_CTL,
+			-84, 40, digital_gain),
+	SOC_SINGLE_S8_TLV("RX2 Digital Volume", WCD9335_CDC_RX2_RX_VOL_CTL,
+			-84, 40, digital_gain),
+	SOC_SINGLE_S8_TLV("RX3 Digital Volume", WCD9335_CDC_RX3_RX_VOL_CTL,
+			-84, 40, digital_gain),
+	SOC_SINGLE_S8_TLV("RX4 Digital Volume", WCD9335_CDC_RX4_RX_VOL_CTL,
+			-84, 40, digital_gain),
+	SOC_SINGLE_S8_TLV("RX5 Digital Volume", WCD9335_CDC_RX5_RX_VOL_CTL,
+			-84, 40, digital_gain),
+	SOC_SINGLE_S8_TLV("RX6 Digital Volume", WCD9335_CDC_RX6_RX_VOL_CTL,
+			-84, 40, digital_gain),
+	SOC_SINGLE_S8_TLV("RX7 Digital Volume", WCD9335_CDC_RX7_RX_VOL_CTL,
+			-84, 40, digital_gain),
+	SOC_SINGLE_S8_TLV("RX8 Digital Volume", WCD9335_CDC_RX8_RX_VOL_CTL,
+			-84, 40, digital_gain),
+	SOC_SINGLE_S8_TLV("RX0 Mix Digital Volume", WCD9335_CDC_RX0_RX_VOL_MIX_CTL,
+			-84, 40, digital_gain),
+	SOC_SINGLE_S8_TLV("RX1 Mix Digital Volume", WCD9335_CDC_RX1_RX_VOL_MIX_CTL,
+			-84, 40, digital_gain),
+	SOC_SINGLE_S8_TLV("RX2 Mix Digital Volume", WCD9335_CDC_RX2_RX_VOL_MIX_CTL,
+			-84, 40, digital_gain),
+	SOC_SINGLE_S8_TLV("RX3 Mix Digital Volume", WCD9335_CDC_RX3_RX_VOL_MIX_CTL,
+			-84, 40, digital_gain),
+	SOC_SINGLE_S8_TLV("RX4 Mix Digital Volume", WCD9335_CDC_RX4_RX_VOL_MIX_CTL,
+			-84, 40, digital_gain),
+	SOC_SINGLE_S8_TLV("RX5 Mix Digital Volume", WCD9335_CDC_RX5_RX_VOL_MIX_CTL,
+			-84, 40, digital_gain),
+	SOC_SINGLE_S8_TLV("RX6 Mix Digital Volume", WCD9335_CDC_RX6_RX_VOL_MIX_CTL,
+			-84, 40, digital_gain),
+	SOC_SINGLE_S8_TLV("RX7 Mix Digital Volume", WCD9335_CDC_RX7_RX_VOL_MIX_CTL,
+			-84, 40, digital_gain),
+	SOC_SINGLE_S8_TLV("RX8 Mix Digital Volume", WCD9335_CDC_RX8_RX_VOL_MIX_CTL,
+			-84, 40, digital_gain),
 	SOC_ENUM("RX INT0_1 HPF cut off", cf_int0_1_enum),
 	SOC_ENUM("RX INT0_2 HPF cut off", cf_int0_2_enum),
 	SOC_ENUM("RX INT1_1 HPF cut off", cf_int1_1_enum),
diff --git a/sound/soc/codecs/wcd938x.c b/sound/soc/codecs/wcd938x.c
index 4480c118ed5d..8cdc45e669f2 100644
--- a/sound/soc/codecs/wcd938x.c
+++ b/sound/soc/codecs/wcd938x.c
@@ -2517,6 +2517,9 @@ static int wcd938x_tx_mode_put(struct snd_kcontrol *kcontrol,
 	struct soc_enum *e = (struct soc_enum *)kcontrol->private_value;
 	int path = e->shift_l;
 
+	if (wcd938x->tx_mode[path] == ucontrol->value.enumerated.item[0])
+		return 0;
+
 	wcd938x->tx_mode[path] = ucontrol->value.enumerated.item[0];
 
 	return 1;
@@ -2539,6 +2542,9 @@ static int wcd938x_rx_hph_mode_put(struct snd_kcontrol *kcontrol,
 	struct snd_soc_component *component = snd_soc_kcontrol_component(kcontrol);
 	struct wcd938x_priv *wcd938x = snd_soc_component_get_drvdata(component);
 
+	if (wcd938x->hph_mode == ucontrol->value.enumerated.item[0])
+		return 0;
+
 	wcd938x->hph_mode = ucontrol->value.enumerated.item[0];
 
 	return 1;
@@ -2630,6 +2636,9 @@ static int wcd938x_ldoh_put(struct snd_kcontrol *kcontrol,
 	struct snd_soc_component *component = snd_soc_kcontrol_component(kcontrol);
 	struct wcd938x_priv *wcd938x = snd_soc_component_get_drvdata(component);
 
+	if (wcd938x->ldoh == ucontrol->value.integer.value[0])
+		return 0;
+
 	wcd938x->ldoh = ucontrol->value.integer.value[0];
 
 	return 1;
@@ -2652,6 +2661,9 @@ static int wcd938x_bcs_put(struct snd_kcontrol *kcontrol,
 	struct snd_soc_component *component = snd_soc_kcontrol_component(kcontrol);
 	struct wcd938x_priv *wcd938x = snd_soc_component_get_drvdata(component);
 
+	if (wcd938x->bcs_dis == ucontrol->value.integer.value[0])
+		return 0;
+
 	wcd938x->bcs_dis = ucontrol->value.integer.value[0];
 
 	return 1;
diff --git a/sound/soc/codecs/wm5110.c b/sound/soc/codecs/wm5110.c
index 5c2d45d05c97..7c6e01720d65 100644
--- a/sound/soc/codecs/wm5110.c
+++ b/sound/soc/codecs/wm5110.c
@@ -413,6 +413,7 @@ static int wm5110_put_dre(struct snd_kcontrol *kcontrol,
 	unsigned int rnew = (!!ucontrol->value.integer.value[1]) << mc->rshift;
 	unsigned int lold, rold;
 	unsigned int lena, rena;
+	bool change = false;
 	int ret;
 
 	snd_soc_dapm_mutex_lock(dapm);
@@ -440,8 +441,8 @@ static int wm5110_put_dre(struct snd_kcontrol *kcontrol,
 		goto err;
 	}
 
-	ret = regmap_update_bits(arizona->regmap, ARIZONA_DRE_ENABLE,
-				 mask, lnew | rnew);
+	ret = regmap_update_bits_check(arizona->regmap, ARIZONA_DRE_ENABLE,
+				       mask, lnew | rnew, &change);
 	if (ret) {
 		dev_err(arizona->dev, "Failed to set DRE: %d\n", ret);
 		goto err;
@@ -454,6 +455,9 @@ static int wm5110_put_dre(struct snd_kcontrol *kcontrol,
 	if (!rnew && rold)
 		wm5110_clear_pga_volume(arizona, mc->rshift);
 
+	if (change)
+		ret = 1;
+
 err:
 	snd_soc_dapm_mutex_unlock(dapm);
 
diff --git a/sound/soc/fsl/fsl-asoc-card.c b/sound/soc/fsl/fsl-asoc-card.c
index 0aaf8aa88794..0f3a6290403d 100644
--- a/sound/soc/fsl/fsl-asoc-card.c
+++ b/sound/soc/fsl/fsl-asoc-card.c
@@ -700,6 +700,7 @@ static int fsl_asoc_card_probe(struct platform_device *pdev)
 	struct platform_device *client_pdev[2];
 	const char *codec_dai_name;
 	const char *codec_dev_name;
+	u32 asrc_fmt = 0;
 	u32 width;
 	int ret;
 
@@ -1013,8 +1014,8 @@ static int fsl_asoc_card_probe(struct platform_device *pdev)
 			goto asrc_fail;
 		}
 
-		ret = of_property_read_u32(asrc_np, "fsl,asrc-format",
-					   &priv->asrc_format);
+		ret = of_property_read_u32(asrc_np, "fsl,asrc-format", &asrc_fmt);
+		priv->asrc_format = (__force snd_pcm_format_t)asrc_fmt;
 		if (ret) {
 			/* Fallback to old binding; translate to asrc_format */
 			ret = of_property_read_u32(asrc_np, "fsl,asrc-width",
diff --git a/sound/soc/fsl/fsl_asrc.c b/sound/soc/fsl/fsl_asrc.c
index b05fdfb7d336..3538c9268ab4 100644
--- a/sound/soc/fsl/fsl_asrc.c
+++ b/sound/soc/fsl/fsl_asrc.c
@@ -1075,6 +1075,7 @@ static int fsl_asrc_probe(struct platform_device *pdev)
 	struct resource *res;
 	void __iomem *regs;
 	int irq, ret, i;
+	u32 asrc_fmt = 0;
 	u32 map_idx;
 	char tmp[16];
 	u32 width;
@@ -1195,7 +1196,8 @@ static int fsl_asrc_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	ret = of_property_read_u32(np, "fsl,asrc-format", &asrc->asrc_format);
+	ret = of_property_read_u32(np, "fsl,asrc-format", &asrc_fmt);
+	asrc->asrc_format = (__force snd_pcm_format_t)asrc_fmt;
 	if (ret) {
 		ret = of_property_read_u32(np, "fsl,asrc-width", &width);
 		if (ret) {
@@ -1218,7 +1220,7 @@ static int fsl_asrc_probe(struct platform_device *pdev)
 		}
 	}
 
-	if (!(FSL_ASRC_FORMATS & (1ULL << asrc->asrc_format))) {
+	if (!(FSL_ASRC_FORMATS & pcm_format_to_bits(asrc->asrc_format))) {
 		dev_warn(&pdev->dev, "unsupported width, use default S24_LE\n");
 		asrc->asrc_format = SNDRV_PCM_FORMAT_S24_LE;
 	}
diff --git a/sound/soc/fsl/fsl_easrc.c b/sound/soc/fsl/fsl_easrc.c
index 442015b86e46..91d0b833970f 100644
--- a/sound/soc/fsl/fsl_easrc.c
+++ b/sound/soc/fsl/fsl_easrc.c
@@ -476,7 +476,8 @@ static int fsl_easrc_prefilter_config(struct fsl_asrc *easrc,
 	struct fsl_asrc_pair *ctx;
 	struct device *dev;
 	u32 inrate, outrate, offset = 0;
-	u32 in_s_rate, out_s_rate, in_s_fmt, out_s_fmt;
+	u32 in_s_rate, out_s_rate;
+	snd_pcm_format_t in_s_fmt, out_s_fmt;
 	int ret, i;
 
 	if (!easrc)
@@ -1875,6 +1876,7 @@ static int fsl_easrc_probe(struct platform_device *pdev)
 	struct resource *res;
 	struct device_node *np;
 	void __iomem *regs;
+	u32 asrc_fmt = 0;
 	int ret, irq;
 	int width;
 
@@ -1936,7 +1938,8 @@ static int fsl_easrc_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	ret = of_property_read_u32(np, "fsl,asrc-format", &easrc->asrc_format);
+	ret = of_property_read_u32(np, "fsl,asrc-format", &asrc_fmt);
+	easrc->asrc_format = (__force snd_pcm_format_t)asrc_fmt;
 	if (ret) {
 		ret = of_property_read_u32(np, "fsl,asrc-width", &width);
 		if (ret) {
@@ -1959,7 +1962,7 @@ static int fsl_easrc_probe(struct platform_device *pdev)
 		}
 	}
 
-	if (!(FSL_EASRC_FORMATS & (1ULL << easrc->asrc_format))) {
+	if (!(FSL_EASRC_FORMATS & (pcm_format_to_bits(easrc->asrc_format)))) {
 		dev_warn(dev, "unsupported format, switching to S24_LE\n");
 		easrc->asrc_format = SNDRV_PCM_FORMAT_S24_LE;
 	}
diff --git a/sound/soc/fsl/fsl_easrc.h b/sound/soc/fsl/fsl_easrc.h
index 30620d56252c..5b8469757c12 100644
--- a/sound/soc/fsl/fsl_easrc.h
+++ b/sound/soc/fsl/fsl_easrc.h
@@ -569,7 +569,7 @@ struct fsl_easrc_io_params {
 	unsigned int access_len;
 	unsigned int fifo_wtmk;
 	unsigned int sample_rate;
-	unsigned int sample_format;
+	snd_pcm_format_t sample_format;
 	unsigned int norm_rate;
 };
 
diff --git a/sound/soc/fsl/imx-audmux.c b/sound/soc/fsl/imx-audmux.c
index dfa05d40b276..a8e5e0f57faf 100644
--- a/sound/soc/fsl/imx-audmux.c
+++ b/sound/soc/fsl/imx-audmux.c
@@ -298,7 +298,7 @@ static int imx_audmux_probe(struct platform_device *pdev)
 		audmux_clk = NULL;
 	}
 
-	audmux_type = (enum imx_audmux_type)of_device_get_match_data(&pdev->dev);
+	audmux_type = (uintptr_t)of_device_get_match_data(&pdev->dev);
 
 	switch (audmux_type) {
 	case IMX31_AUDMUX:
diff --git a/sound/soc/fsl/imx-card.c b/sound/soc/fsl/imx-card.c
index da48eff86287..36b54675ce7f 100644
--- a/sound/soc/fsl/imx-card.c
+++ b/sound/soc/fsl/imx-card.c
@@ -17,6 +17,9 @@
 
 #include "fsl_sai.h"
 
+#define IMX_CARD_MCLK_22P5792MHZ  22579200
+#define IMX_CARD_MCLK_24P576MHZ   24576000
+
 enum codec_type {
 	CODEC_DUMMY = 0,
 	CODEC_AK5558 = 1,
@@ -115,7 +118,7 @@ struct imx_card_data {
 	struct snd_soc_card card;
 	int num_dapm_routes;
 	u32 asrc_rate;
-	u32 asrc_format;
+	snd_pcm_format_t asrc_format;
 };
 
 static struct imx_akcodec_fs_mul ak4458_fs_mul[] = {
@@ -353,12 +356,13 @@ static int imx_aif_hw_params(struct snd_pcm_substream *substream,
 		mclk_freq = akcodec_get_mclk_rate(substream, params, slots, slot_width);
 	else
 		mclk_freq = params_rate(params) * slots * slot_width;
-	/* Use the maximum freq from DSD512 (512*44100 = 22579200) */
+
 	if (format_is_dsd(params)) {
-		if (params_rate(params) % 11025 == 0)
-			mclk_freq = 22579200;
+		/* Use the maximum freq from DSD512 (512*44100 = 22579200) */
+		if (!(params_rate(params) % 11025))
+			mclk_freq = IMX_CARD_MCLK_22P5792MHZ;
 		else
-			mclk_freq = 24576000;
+			mclk_freq = IMX_CARD_MCLK_24P576MHZ;
 	}
 
 	ret = snd_soc_dai_set_sysclk(cpu_dai, link_data->cpu_sysclk_id, mclk_freq,
@@ -475,7 +479,7 @@ static int be_hw_params_fixup(struct snd_soc_pcm_runtime *rtd,
 
 	mask = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT);
 	snd_mask_none(mask);
-	snd_mask_set(mask, data->asrc_format);
+	snd_mask_set(mask, (__force unsigned int)data->asrc_format);
 
 	return 0;
 }
@@ -494,6 +498,7 @@ static int imx_card_parse_of(struct imx_card_data *data)
 	struct dai_link_data *link_data;
 	struct of_phandle_args args;
 	int ret, num_links;
+	u32 asrc_fmt = 0;
 	u32 width;
 
 	ret = snd_soc_of_parse_card_name(card, "model");
@@ -640,7 +645,8 @@ static int imx_card_parse_of(struct imx_card_data *data)
 				goto err;
 			}
 
-			ret = of_property_read_u32(args.np, "fsl,asrc-format", &data->asrc_format);
+			ret = of_property_read_u32(args.np, "fsl,asrc-format", &asrc_fmt);
+			data->asrc_format = (__force snd_pcm_format_t)asrc_fmt;
 			if (ret) {
 				/* Fallback to old binding; translate to asrc_format */
 				ret = of_property_read_u32(args.np, "fsl,asrc-width", &width);
diff --git a/sound/soc/generic/audio-graph-card.c b/sound/soc/generic/audio-graph-card.c
index 546f6fd0609e..28cbcdb56857 100644
--- a/sound/soc/generic/audio-graph-card.c
+++ b/sound/soc/generic/audio-graph-card.c
@@ -158,8 +158,10 @@ static int asoc_simple_parse_dai(struct device_node *ep,
 	 *    if he unbinded CPU or Codec.
 	 */
 	ret = snd_soc_get_dai_name(&args, &dlc->dai_name);
-	if (ret < 0)
+	if (ret < 0) {
+		of_node_put(node);
 		return ret;
+	}
 
 	dlc->of_node = node;
 
diff --git a/sound/soc/intel/boards/bytcr_wm5102.c b/sound/soc/intel/boards/bytcr_wm5102.c
index 580d5fddae5a..bb669d58eb8b 100644
--- a/sound/soc/intel/boards/bytcr_wm5102.c
+++ b/sound/soc/intel/boards/bytcr_wm5102.c
@@ -421,8 +421,17 @@ static int snd_byt_wm5102_mc_probe(struct platform_device *pdev)
 	priv->spkvdd_en_gpio = gpiod_get(codec_dev, "wlf,spkvdd-ena", GPIOD_OUT_LOW);
 	put_device(codec_dev);
 
-	if (IS_ERR(priv->spkvdd_en_gpio))
-		return dev_err_probe(dev, PTR_ERR(priv->spkvdd_en_gpio), "getting spkvdd-GPIO\n");
+	if (IS_ERR(priv->spkvdd_en_gpio)) {
+		ret = PTR_ERR(priv->spkvdd_en_gpio);
+		/*
+		 * The spkvdd gpio-lookup is registered by: drivers/mfd/arizona-spi.c,
+		 * so -ENOENT means that arizona-spi hasn't probed yet.
+		 */
+		if (ret == -ENOENT)
+			ret = -EPROBE_DEFER;
+
+		return dev_err_probe(dev, ret, "getting spkvdd-GPIO\n");
+	}
 
 	/* override platform name, if required */
 	byt_wm5102_card.dev = dev;
diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c
index 0bf3e56e1d58..abe39a0ef14b 100644
--- a/sound/soc/intel/boards/sof_sdw.c
+++ b/sound/soc/intel/boards/sof_sdw.c
@@ -1323,6 +1323,33 @@ static struct snd_soc_card card_sof_sdw = {
 	.late_probe = sof_sdw_card_late_probe,
 };
 
+static void mc_dailink_exit_loop(struct snd_soc_card *card)
+{
+	struct snd_soc_dai_link *link;
+	int ret;
+	int i, j;
+
+	for (i = 0; i < ARRAY_SIZE(codec_info_list); i++) {
+		if (!codec_info_list[i].exit)
+			continue;
+		/*
+		 * We don't need to call .exit function if there is no matched
+		 * dai link found.
+		 */
+		for_each_card_prelinks(card, j, link) {
+			if (!strcmp(link->codecs[0].dai_name,
+				    codec_info_list[i].dai_name)) {
+				ret = codec_info_list[i].exit(card, link);
+				if (ret)
+					dev_warn(card->dev,
+						 "codec exit failed %d\n",
+						 ret);
+				break;
+			}
+		}
+	}
+}
+
 static int mc_probe(struct platform_device *pdev)
 {
 	struct snd_soc_card *card = &card_sof_sdw;
@@ -1387,6 +1414,7 @@ static int mc_probe(struct platform_device *pdev)
 	ret = devm_snd_soc_register_card(&pdev->dev, card);
 	if (ret) {
 		dev_err(card->dev, "snd_soc_register_card failed %d\n", ret);
+		mc_dailink_exit_loop(card);
 		return ret;
 	}
 
@@ -1398,29 +1426,8 @@ static int mc_probe(struct platform_device *pdev)
 static int mc_remove(struct platform_device *pdev)
 {
 	struct snd_soc_card *card = platform_get_drvdata(pdev);
-	struct snd_soc_dai_link *link;
-	int ret;
-	int i, j;
 
-	for (i = 0; i < ARRAY_SIZE(codec_info_list); i++) {
-		if (!codec_info_list[i].exit)
-			continue;
-		/*
-		 * We don't need to call .exit function if there is no matched
-		 * dai link found.
-		 */
-		for_each_card_prelinks(card, j, link) {
-			if (!strcmp(link->codecs[0].dai_name,
-				    codec_info_list[i].dai_name)) {
-				ret = codec_info_list[i].exit(card, link);
-				if (ret)
-					dev_warn(&pdev->dev,
-						 "codec exit failed %d\n",
-						 ret);
-				break;
-			}
-		}
-	}
+	mc_dailink_exit_loop(card);
 
 	return 0;
 }
diff --git a/sound/soc/intel/skylake/skl-nhlt.c b/sound/soc/intel/skylake/skl-nhlt.c
index 64226072f0ee..74f60f5dfaef 100644
--- a/sound/soc/intel/skylake/skl-nhlt.c
+++ b/sound/soc/intel/skylake/skl-nhlt.c
@@ -201,7 +201,6 @@ static void skl_get_ssp_clks(struct skl_dev *skl, struct skl_ssp_clk *ssp_clks,
 	struct nhlt_fmt_cfg *fmt_cfg;
 	struct wav_fmt_ext *wav_fmt;
 	unsigned long rate;
-	bool present = false;
 	int rate_index = 0;
 	u16 channels, bps;
 	u8 clk_src;
@@ -214,9 +213,12 @@ static void skl_get_ssp_clks(struct skl_dev *skl, struct skl_ssp_clk *ssp_clks,
 	if (fmt->fmt_count == 0)
 		return;
 
+	fmt_cfg = (struct nhlt_fmt_cfg *)fmt->fmt_config;
 	for (i = 0; i < fmt->fmt_count; i++) {
-		fmt_cfg = &fmt->fmt_config[i];
-		wav_fmt = &fmt_cfg->fmt_ext;
+		struct nhlt_fmt_cfg *saved_fmt_cfg = fmt_cfg;
+		bool present = false;
+
+		wav_fmt = &saved_fmt_cfg->fmt_ext;
 
 		channels = wav_fmt->fmt.channels;
 		bps = wav_fmt->fmt.bits_per_sample;
@@ -234,12 +236,18 @@ static void skl_get_ssp_clks(struct skl_dev *skl, struct skl_ssp_clk *ssp_clks,
 		 * derive the rate.
 		 */
 		for (j = i; j < fmt->fmt_count; j++) {
-			fmt_cfg = &fmt->fmt_config[j];
-			wav_fmt = &fmt_cfg->fmt_ext;
+			struct nhlt_fmt_cfg *tmp_fmt_cfg = fmt_cfg;
+
+			wav_fmt = &tmp_fmt_cfg->fmt_ext;
 			if ((fs == wav_fmt->fmt.samples_per_sec) &&
-			   (bps == wav_fmt->fmt.bits_per_sample))
+			   (bps == wav_fmt->fmt.bits_per_sample)) {
 				channels = max_t(u16, channels,
 						wav_fmt->fmt.channels);
+				saved_fmt_cfg = tmp_fmt_cfg;
+			}
+			/* Move to the next nhlt_fmt_cfg */
+			tmp_fmt_cfg = (struct nhlt_fmt_cfg *)(tmp_fmt_cfg->config.caps +
+							      tmp_fmt_cfg->config.size);
 		}
 
 		rate = channels * bps * fs;
@@ -255,8 +263,11 @@ static void skl_get_ssp_clks(struct skl_dev *skl, struct skl_ssp_clk *ssp_clks,
 
 		/* Fill rate and parent for sclk/sclkfs */
 		if (!present) {
+			struct nhlt_fmt_cfg *first_fmt_cfg;
+
+			first_fmt_cfg = (struct nhlt_fmt_cfg *)fmt->fmt_config;
 			i2s_config_ext = (struct skl_i2s_config_blob_ext *)
-						fmt->fmt_config[0].config.caps;
+						first_fmt_cfg->config.caps;
 
 			/* MCLK Divider Source Select */
 			if (is_legacy_blob(i2s_config_ext->hdr.sig)) {
@@ -270,6 +281,9 @@ static void skl_get_ssp_clks(struct skl_dev *skl, struct skl_ssp_clk *ssp_clks,
 
 			parent = skl_get_parent_clk(clk_src);
 
+			/* Move to the next nhlt_fmt_cfg */
+			fmt_cfg = (struct nhlt_fmt_cfg *)(fmt_cfg->config.caps +
+							  fmt_cfg->config.size);
 			/*
 			 * Do not copy the config data if there is no parent
 			 * clock available for this clock source select
@@ -278,9 +292,9 @@ static void skl_get_ssp_clks(struct skl_dev *skl, struct skl_ssp_clk *ssp_clks,
 				continue;
 
 			sclk[id].rate_cfg[rate_index].rate = rate;
-			sclk[id].rate_cfg[rate_index].config = fmt_cfg;
+			sclk[id].rate_cfg[rate_index].config = saved_fmt_cfg;
 			sclkfs[id].rate_cfg[rate_index].rate = rate;
-			sclkfs[id].rate_cfg[rate_index].config = fmt_cfg;
+			sclkfs[id].rate_cfg[rate_index].config = saved_fmt_cfg;
 			sclk[id].parent_name = parent->name;
 			sclkfs[id].parent_name = parent->name;
 
@@ -294,13 +308,13 @@ static void skl_get_mclk(struct skl_dev *skl, struct skl_ssp_clk *mclk,
 {
 	struct skl_i2s_config_blob_ext *i2s_config_ext;
 	struct skl_i2s_config_blob_legacy *i2s_config;
-	struct nhlt_specific_cfg *fmt_cfg;
+	struct nhlt_fmt_cfg *fmt_cfg;
 	struct skl_clk_parent_src *parent;
 	u32 clkdiv, div_ratio;
 	u8 clk_src;
 
-	fmt_cfg = &fmt->fmt_config[0].config;
-	i2s_config_ext = (struct skl_i2s_config_blob_ext *)fmt_cfg->caps;
+	fmt_cfg = (struct nhlt_fmt_cfg *)fmt->fmt_config;
+	i2s_config_ext = (struct skl_i2s_config_blob_ext *)fmt_cfg->config.caps;
 
 	/* MCLK Divider Source Select and divider */
 	if (is_legacy_blob(i2s_config_ext->hdr.sig)) {
@@ -329,7 +343,7 @@ static void skl_get_mclk(struct skl_dev *skl, struct skl_ssp_clk *mclk,
 		return;
 
 	mclk[id].rate_cfg[0].rate = parent->rate/div_ratio;
-	mclk[id].rate_cfg[0].config = &fmt->fmt_config[0];
+	mclk[id].rate_cfg[0].config = fmt_cfg;
 	mclk[id].parent_name = parent->name;
 }
 
diff --git a/sound/soc/mediatek/mt6797/mt6797-mt6351.c b/sound/soc/mediatek/mt6797/mt6797-mt6351.c
index 496f32bcfb5e..d2f6213a6bfc 100644
--- a/sound/soc/mediatek/mt6797/mt6797-mt6351.c
+++ b/sound/soc/mediatek/mt6797/mt6797-mt6351.c
@@ -217,7 +217,8 @@ static int mt6797_mt6351_dev_probe(struct platform_device *pdev)
 	if (!codec_node) {
 		dev_err(&pdev->dev,
 			"Property 'audio-codec' missing or invalid\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto put_platform_node;
 	}
 	for_each_card_prelinks(card, i, dai_link) {
 		if (dai_link->codecs->name)
@@ -230,6 +231,9 @@ static int mt6797_mt6351_dev_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev, "%s snd_soc_register_card fail %d\n",
 			__func__, ret);
 
+	of_node_put(codec_node);
+put_platform_node:
+	of_node_put(platform_node);
 	return ret;
 }
 
diff --git a/sound/soc/mediatek/mt8173/mt8173-rt5650-rt5676.c b/sound/soc/mediatek/mt8173/mt8173-rt5650-rt5676.c
index c8e4e85e1057..94a9bbf144d1 100644
--- a/sound/soc/mediatek/mt8173/mt8173-rt5650-rt5676.c
+++ b/sound/soc/mediatek/mt8173/mt8173-rt5650-rt5676.c
@@ -256,14 +256,16 @@ static int mt8173_rt5650_rt5676_dev_probe(struct platform_device *pdev)
 	if (!mt8173_rt5650_rt5676_dais[DAI_LINK_CODEC_I2S].codecs[0].of_node) {
 		dev_err(&pdev->dev,
 			"Property 'audio-codec' missing or invalid\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto put_node;
 	}
 	mt8173_rt5650_rt5676_dais[DAI_LINK_CODEC_I2S].codecs[1].of_node =
 		of_parse_phandle(pdev->dev.of_node, "mediatek,audio-codec", 1);
 	if (!mt8173_rt5650_rt5676_dais[DAI_LINK_CODEC_I2S].codecs[1].of_node) {
 		dev_err(&pdev->dev,
 			"Property 'audio-codec' missing or invalid\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto put_node;
 	}
 	mt8173_rt5650_rt5676_codec_conf[0].dlc.of_node =
 		mt8173_rt5650_rt5676_dais[DAI_LINK_CODEC_I2S].codecs[1].of_node;
@@ -276,7 +278,8 @@ static int mt8173_rt5650_rt5676_dev_probe(struct platform_device *pdev)
 	if (!mt8173_rt5650_rt5676_dais[DAI_LINK_HDMI_I2S].codecs->of_node) {
 		dev_err(&pdev->dev,
 			"Property 'audio-codec' missing or invalid\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto put_node;
 	}
 
 	card->dev = &pdev->dev;
@@ -286,6 +289,7 @@ static int mt8173_rt5650_rt5676_dev_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev, "%s snd_soc_register_card fail %d\n",
 			__func__, ret);
 
+put_node:
 	of_node_put(platform_node);
 	return ret;
 }
diff --git a/sound/soc/mediatek/mt8173/mt8173-rt5650.c b/sound/soc/mediatek/mt8173/mt8173-rt5650.c
index e168d31f4445..1de9dab218c6 100644
--- a/sound/soc/mediatek/mt8173/mt8173-rt5650.c
+++ b/sound/soc/mediatek/mt8173/mt8173-rt5650.c
@@ -280,7 +280,8 @@ static int mt8173_rt5650_dev_probe(struct platform_device *pdev)
 	if (!mt8173_rt5650_dais[DAI_LINK_CODEC_I2S].codecs[0].of_node) {
 		dev_err(&pdev->dev,
 			"Property 'audio-codec' missing or invalid\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto put_platform_node;
 	}
 	mt8173_rt5650_dais[DAI_LINK_CODEC_I2S].codecs[1].of_node =
 		mt8173_rt5650_dais[DAI_LINK_CODEC_I2S].codecs[0].of_node;
@@ -293,7 +294,7 @@ static int mt8173_rt5650_dev_probe(struct platform_device *pdev)
 			dev_err(&pdev->dev,
 				"%s codec_capture_dai name fail %d\n",
 				__func__, ret);
-			return ret;
+			goto put_platform_node;
 		}
 		mt8173_rt5650_dais[DAI_LINK_CODEC_I2S].codecs[1].dai_name =
 			codec_capture_dai;
@@ -315,7 +316,8 @@ static int mt8173_rt5650_dev_probe(struct platform_device *pdev)
 	if (!mt8173_rt5650_dais[DAI_LINK_HDMI_I2S].codecs->of_node) {
 		dev_err(&pdev->dev,
 			"Property 'audio-codec' missing or invalid\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto put_platform_node;
 	}
 	card->dev = &pdev->dev;
 
@@ -324,6 +326,7 @@ static int mt8173_rt5650_dev_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev, "%s snd_soc_register_card fail %d\n",
 			__func__, ret);
 
+put_platform_node:
 	of_node_put(platform_node);
 	return ret;
 }
diff --git a/sound/soc/qcom/lpass-cpu.c b/sound/soc/qcom/lpass-cpu.c
index 3bd9eb3cc688..5e89d280e355 100644
--- a/sound/soc/qcom/lpass-cpu.c
+++ b/sound/soc/qcom/lpass-cpu.c
@@ -880,6 +880,7 @@ int asoc_qcom_lpass_cpu_platform_probe(struct platform_device *pdev)
 	dsp_of_node = of_parse_phandle(pdev->dev.of_node, "qcom,adsp", 0);
 	if (dsp_of_node) {
 		dev_err(dev, "DSP exists and holds audio resources\n");
+		of_node_put(dsp_of_node);
 		return -EBUSY;
 	}
 
diff --git a/sound/soc/qcom/qdsp6/q6adm.c b/sound/soc/qcom/qdsp6/q6adm.c
index 3d831b635524..4ae97afe9062 100644
--- a/sound/soc/qcom/qdsp6/q6adm.c
+++ b/sound/soc/qcom/qdsp6/q6adm.c
@@ -217,7 +217,7 @@ static struct q6copp *q6adm_alloc_copp(struct q6adm *adm, int port_idx)
 	idx = find_first_zero_bit(&adm->copp_bitmap[port_idx],
 				  MAX_COPPS_PER_PORT);
 
-	if (idx > MAX_COPPS_PER_PORT)
+	if (idx >= MAX_COPPS_PER_PORT)
 		return ERR_PTR(-EBUSY);
 
 	c = kzalloc(sizeof(*c), GFP_ATOMIC);
diff --git a/sound/soc/qcom/sm8250.c b/sound/soc/qcom/sm8250.c
index fe8fd7367e21..e5190aa588c6 100644
--- a/sound/soc/qcom/sm8250.c
+++ b/sound/soc/qcom/sm8250.c
@@ -191,6 +191,7 @@ static int sm8250_platform_probe(struct platform_device *pdev)
 	if (!card)
 		return -ENOMEM;
 
+	card->owner = THIS_MODULE;
 	/* Allocate the private data */
 	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
diff --git a/sound/soc/samsung/aries_wm8994.c b/sound/soc/samsung/aries_wm8994.c
index 83acbe57b248..a0825da9fff9 100644
--- a/sound/soc/samsung/aries_wm8994.c
+++ b/sound/soc/samsung/aries_wm8994.c
@@ -628,8 +628,10 @@ static int aries_audio_probe(struct platform_device *pdev)
 		return -EINVAL;
 
 	codec = of_get_child_by_name(dev->of_node, "codec");
-	if (!codec)
-		return -EINVAL;
+	if (!codec) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	for_each_card_prelinks(card, i, dai_link) {
 		dai_link->codecs->of_node = of_parse_phandle(codec,
diff --git a/sound/soc/samsung/h1940_uda1380.c b/sound/soc/samsung/h1940_uda1380.c
index c994e67d1eaf..ca086243fcfd 100644
--- a/sound/soc/samsung/h1940_uda1380.c
+++ b/sound/soc/samsung/h1940_uda1380.c
@@ -8,7 +8,7 @@
 // Based on version from Arnaud Patard <arnaud.patard@rtp-net.org>
 
 #include <linux/types.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/module.h>
 
 #include <sound/soc.h>
diff --git a/sound/soc/samsung/rx1950_uda1380.c b/sound/soc/samsung/rx1950_uda1380.c
index 6ea1c8cc9167..2820097b00b9 100644
--- a/sound/soc/samsung/rx1950_uda1380.c
+++ b/sound/soc/samsung/rx1950_uda1380.c
@@ -128,7 +128,7 @@ static int rx1950_startup(struct snd_pcm_substream *substream)
 					&hw_rates);
 }
 
-struct gpio_desc *gpiod_speaker_power;
+static struct gpio_desc *gpiod_speaker_power;
 
 static int rx1950_spk_power(struct snd_soc_dapm_widget *w,
 				struct snd_kcontrol *kcontrol, int event)
@@ -227,7 +227,7 @@ static int rx1950_probe(struct platform_device *pdev)
 	return devm_snd_soc_register_card(dev, &rx1950_asoc);
 }
 
-struct platform_driver rx1950_audio = {
+static struct platform_driver rx1950_audio = {
 	.driver = {
 		.name = "rx1950-audio",
 		.pm = &snd_soc_pm_ops,
diff --git a/sound/soc/sh/rcar/ssiu.c b/sound/soc/sh/rcar/ssiu.c
index 4b8a63e336c7..d7f4646ee029 100644
--- a/sound/soc/sh/rcar/ssiu.c
+++ b/sound/soc/sh/rcar/ssiu.c
@@ -67,6 +67,8 @@ static void rsnd_ssiu_busif_err_irq_ctrl(struct rsnd_mod *mod, int enable)
 		shift  = 1;
 		offset = 1;
 		break;
+	default:
+		return;
 	}
 
 	for (i = 0; i < 4; i++) {
diff --git a/sound/soc/sh/rz-ssi.c b/sound/soc/sh/rz-ssi.c
index 6d794eaaf4c3..2e33a1fa0a6f 100644
--- a/sound/soc/sh/rz-ssi.c
+++ b/sound/soc/sh/rz-ssi.c
@@ -1022,32 +1022,36 @@ static int rz_ssi_probe(struct platform_device *pdev)
 
 	ssi->rstc = devm_reset_control_get_exclusive(&pdev->dev, NULL);
 	if (IS_ERR(ssi->rstc)) {
-		rz_ssi_release_dma_channels(ssi);
-		return PTR_ERR(ssi->rstc);
+		ret = PTR_ERR(ssi->rstc);
+		goto err_reset;
 	}
 
 	reset_control_deassert(ssi->rstc);
 	pm_runtime_enable(&pdev->dev);
 	ret = pm_runtime_resume_and_get(&pdev->dev);
 	if (ret < 0) {
-		rz_ssi_release_dma_channels(ssi);
-		pm_runtime_disable(ssi->dev);
-		reset_control_assert(ssi->rstc);
-		return dev_err_probe(ssi->dev, ret, "pm_runtime_resume_and_get failed\n");
+		dev_err(&pdev->dev, "pm_runtime_resume_and_get failed\n");
+		goto err_pm;
 	}
 
 	ret = devm_snd_soc_register_component(&pdev->dev, &rz_ssi_soc_component,
 					      rz_ssi_soc_dai,
 					      ARRAY_SIZE(rz_ssi_soc_dai));
 	if (ret < 0) {
-		rz_ssi_release_dma_channels(ssi);
-
-		pm_runtime_put(ssi->dev);
-		pm_runtime_disable(ssi->dev);
-		reset_control_assert(ssi->rstc);
 		dev_err(&pdev->dev, "failed to register snd component\n");
+		goto err_snd_soc;
 	}
 
+	return 0;
+
+err_snd_soc:
+	pm_runtime_put(ssi->dev);
+err_pm:
+	pm_runtime_disable(ssi->dev);
+	reset_control_assert(ssi->rstc);
+err_reset:
+	rz_ssi_release_dma_channels(ssi);
+
 	return ret;
 }
 
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 47b85ba5b7d6..b957049bae33 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -62,6 +62,8 @@ struct snd_soc_dapm_widget *
 snd_soc_dapm_new_control_unlocked(struct snd_soc_dapm_context *dapm,
 			 const struct snd_soc_dapm_widget *widget);
 
+static unsigned int soc_dapm_read(struct snd_soc_dapm_context *dapm, int reg);
+
 /* dapm power sequences - make this per codec in the future */
 static int dapm_up_seq[] = {
 	[snd_soc_dapm_pre] = 1,
@@ -442,6 +444,9 @@ static int dapm_kcontrol_data_alloc(struct snd_soc_dapm_widget *widget,
 
 			snd_soc_dapm_add_path(widget->dapm, data->widget,
 					      widget, NULL, NULL);
+		} else if (e->reg != SND_SOC_NOPM) {
+			data->value = soc_dapm_read(widget->dapm, e->reg) &
+				      (e->mask << e->shift_l);
 		}
 		break;
 	default:
diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c
index f32ba64c5dda..e73360e9de8f 100644
--- a/sound/soc/soc-ops.c
+++ b/sound/soc/soc-ops.c
@@ -526,7 +526,7 @@ int snd_soc_put_volsw_range(struct snd_kcontrol *kcontrol,
 		return -EINVAL;
 	if (mc->platform_max && tmp > mc->platform_max)
 		return -EINVAL;
-	if (tmp > mc->max - mc->min + 1)
+	if (tmp > mc->max - mc->min)
 		return -EINVAL;
 
 	if (invert)
@@ -547,7 +547,7 @@ int snd_soc_put_volsw_range(struct snd_kcontrol *kcontrol,
 			return -EINVAL;
 		if (mc->platform_max && tmp > mc->platform_max)
 			return -EINVAL;
-		if (tmp > mc->max - mc->min + 1)
+		if (tmp > mc->max - mc->min)
 			return -EINVAL;
 
 		if (invert)
diff --git a/sound/soc/sof/debug.c b/sound/soc/sof/debug.c
index a51a928ea40a..5f780ef9581a 100644
--- a/sound/soc/sof/debug.c
+++ b/sound/soc/sof/debug.c
@@ -668,9 +668,9 @@ static int memory_info_update(struct snd_sof_dev *sdev, char *buf, size_t buff_s
 	}
 
 	for (i = 0, len = 0; i < reply->num_elems; i++) {
-		ret = snprintf(buf + len, buff_size - len, "zone %d.%d used %#8x free %#8x\n",
-			       reply->elems[i].zone, reply->elems[i].id,
-			       reply->elems[i].used, reply->elems[i].free);
+		ret = scnprintf(buf + len, buff_size - len, "zone %d.%d used %#8x free %#8x\n",
+				reply->elems[i].zone, reply->elems[i].id,
+				reply->elems[i].used, reply->elems[i].free);
 		if (ret < 0)
 			goto error;
 		len += ret;
diff --git a/sound/soc/sof/intel/apl.c b/sound/soc/sof/intel/apl.c
index c7ed2b3d6abc..0a42034c4655 100644
--- a/sound/soc/sof/intel/apl.c
+++ b/sound/soc/sof/intel/apl.c
@@ -139,6 +139,7 @@ const struct sof_intel_dsp_desc apl_chip_info = {
 	.ipc_ack = HDA_DSP_REG_HIPCIE,
 	.ipc_ack_mask = HDA_DSP_REG_HIPCIE_DONE,
 	.ipc_ctl = HDA_DSP_REG_HIPCCTL,
+	.rom_status_reg = HDA_DSP_SRAM_REG_ROM_STATUS,
 	.rom_init_timeout	= 150,
 	.ssp_count = APL_SSP_COUNT,
 	.ssp_base_offset = APL_SSP_BASE_OFFSET,
diff --git a/sound/soc/sof/intel/cnl.c b/sound/soc/sof/intel/cnl.c
index e115e12a856f..a63b235763ed 100644
--- a/sound/soc/sof/intel/cnl.c
+++ b/sound/soc/sof/intel/cnl.c
@@ -344,6 +344,7 @@ const struct sof_intel_dsp_desc cnl_chip_info = {
 	.ipc_ack = CNL_DSP_REG_HIPCIDA,
 	.ipc_ack_mask = CNL_DSP_REG_HIPCIDA_DONE,
 	.ipc_ctl = CNL_DSP_REG_HIPCCTL,
+	.rom_status_reg = HDA_DSP_SRAM_REG_ROM_STATUS,
 	.rom_init_timeout	= 300,
 	.ssp_count = CNL_SSP_COUNT,
 	.ssp_base_offset = CNL_SSP_BASE_OFFSET,
@@ -363,6 +364,7 @@ const struct sof_intel_dsp_desc jsl_chip_info = {
 	.ipc_ack = CNL_DSP_REG_HIPCIDA,
 	.ipc_ack_mask = CNL_DSP_REG_HIPCIDA_DONE,
 	.ipc_ctl = CNL_DSP_REG_HIPCCTL,
+	.rom_status_reg = HDA_DSP_SRAM_REG_ROM_STATUS,
 	.rom_init_timeout	= 300,
 	.ssp_count = ICL_SSP_COUNT,
 	.ssp_base_offset = CNL_SSP_BASE_OFFSET,
diff --git a/sound/soc/sof/intel/hda-loader.c b/sound/soc/sof/intel/hda-loader.c
index 14469e087b00..439cb33d2a71 100644
--- a/sound/soc/sof/intel/hda-loader.c
+++ b/sound/soc/sof/intel/hda-loader.c
@@ -80,9 +80,9 @@ out_put:
 }
 
 /*
- * first boot sequence has some extra steps. core 0 waits for power
- * status on core 1, so power up core 1 also momentarily, keep it in
- * reset/stall and then turn it off
+ * first boot sequence has some extra steps.
+ * power on all host managed cores and only unstall/run the boot core to boot the
+ * DSP then turn off all non boot cores (if any) is powered on.
  */
 static int cl_dsp_init(struct snd_sof_dev *sdev, int stream_tag)
 {
@@ -117,7 +117,7 @@ static int cl_dsp_init(struct snd_sof_dev *sdev, int stream_tag)
 			  ((stream_tag - 1) << 9)));
 
 	/* step 3: unset core 0 reset state & unstall/run core 0 */
-	ret = hda_dsp_core_run(sdev, BIT(0));
+	ret = hda_dsp_core_run(sdev, chip->init_core_mask);
 	if (ret < 0) {
 		if (hda->boot_iteration == HDA_FW_BOOT_ATTEMPTS)
 			dev_err(sdev->dev,
@@ -163,7 +163,7 @@ static int cl_dsp_init(struct snd_sof_dev *sdev, int stream_tag)
 
 	/* step 7: wait for ROM init */
 	ret = snd_sof_dsp_read_poll_timeout(sdev, HDA_DSP_BAR,
-					HDA_DSP_SRAM_REG_ROM_STATUS, status,
+					chip->rom_status_reg, status,
 					((status & HDA_DSP_ROM_STS_MASK)
 						== HDA_DSP_ROM_INIT),
 					HDA_DSP_REG_POLL_INTERVAL_US,
@@ -174,8 +174,8 @@ static int cl_dsp_init(struct snd_sof_dev *sdev, int stream_tag)
 
 	if (hda->boot_iteration == HDA_FW_BOOT_ATTEMPTS)
 		dev_err(sdev->dev,
-			"error: %s: timeout HDA_DSP_SRAM_REG_ROM_STATUS read\n",
-			__func__);
+			"%s: timeout with rom_status_reg (%#x) read\n",
+			__func__, chip->rom_status_reg);
 
 err:
 	flags = SOF_DBG_DUMP_REGS | SOF_DBG_DUMP_PCI | SOF_DBG_DUMP_MBOX;
@@ -251,6 +251,8 @@ static int cl_cleanup(struct snd_sof_dev *sdev, struct snd_dma_buffer *dmab,
 
 static int cl_copy_fw(struct snd_sof_dev *sdev, struct hdac_ext_stream *stream)
 {
+	struct sof_intel_hda_dev *hda = sdev->pdata->hw_pdata;
+	const struct sof_intel_dsp_desc *chip = hda->desc;
 	unsigned int reg;
 	int ret, status;
 
@@ -261,7 +263,7 @@ static int cl_copy_fw(struct snd_sof_dev *sdev, struct hdac_ext_stream *stream)
 	}
 
 	status = snd_sof_dsp_read_poll_timeout(sdev, HDA_DSP_BAR,
-					HDA_DSP_SRAM_REG_ROM_STATUS, reg,
+					chip->rom_status_reg, reg,
 					((reg & HDA_DSP_ROM_STS_MASK)
 						== HDA_DSP_ROM_FW_ENTERED),
 					HDA_DSP_REG_POLL_INTERVAL_US,
@@ -274,8 +276,8 @@ static int cl_copy_fw(struct snd_sof_dev *sdev, struct hdac_ext_stream *stream)
 
 	if (status < 0) {
 		dev_err(sdev->dev,
-			"error: %s: timeout HDA_DSP_SRAM_REG_ROM_STATUS read\n",
-			__func__);
+			"%s: timeout with rom_status_reg (%#x) read\n",
+			__func__, chip->rom_status_reg);
 	}
 
 	ret = cl_trigger(sdev, stream, SNDRV_PCM_TRIGGER_STOP);
diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c
index ddf70902e53c..35cbef171f4a 100644
--- a/sound/soc/sof/intel/hda.c
+++ b/sound/soc/sof/intel/hda.c
@@ -353,11 +353,13 @@ static const struct hda_dsp_msg_code hda_dsp_rom_msg[] = {
 
 static void hda_dsp_get_status(struct snd_sof_dev *sdev)
 {
+	const struct sof_intel_dsp_desc *chip;
 	u32 status;
 	int i;
 
+	chip = get_chip_info(sdev->pdata);
 	status = snd_sof_dsp_read(sdev, HDA_DSP_BAR,
-				  HDA_DSP_SRAM_REG_ROM_STATUS);
+				  chip->rom_status_reg);
 
 	for (i = 0; i < ARRAY_SIZE(hda_dsp_rom_msg); i++) {
 		if (status == hda_dsp_rom_msg[i].code) {
@@ -402,14 +404,16 @@ static void hda_dsp_get_registers(struct snd_sof_dev *sdev,
 /* dump the first 8 dwords representing the extended ROM status */
 static void hda_dsp_dump_ext_rom_status(struct snd_sof_dev *sdev, u32 flags)
 {
+	const struct sof_intel_dsp_desc *chip;
 	char msg[128];
 	int len = 0;
 	u32 value;
 	int i;
 
+	chip = get_chip_info(sdev->pdata);
 	for (i = 0; i < HDA_EXT_ROM_STATUS_SIZE; i++) {
-		value = snd_sof_dsp_read(sdev, HDA_DSP_BAR, HDA_DSP_SRAM_REG_ROM_STATUS + i * 0x4);
-		len += snprintf(msg + len, sizeof(msg) - len, " 0x%x", value);
+		value = snd_sof_dsp_read(sdev, HDA_DSP_BAR, chip->rom_status_reg + i * 0x4);
+		len += scnprintf(msg + len, sizeof(msg) - len, " 0x%x", value);
 	}
 
 	sof_dev_dbg_or_err(sdev->dev, flags & SOF_DBG_DUMP_FORCE_ERR_LEVEL,
diff --git a/sound/soc/sof/intel/icl.c b/sound/soc/sof/intel/icl.c
index ee095b8f2d01..4065c4d3912a 100644
--- a/sound/soc/sof/intel/icl.c
+++ b/sound/soc/sof/intel/icl.c
@@ -139,6 +139,7 @@ const struct sof_intel_dsp_desc icl_chip_info = {
 	.ipc_ack = CNL_DSP_REG_HIPCIDA,
 	.ipc_ack_mask = CNL_DSP_REG_HIPCIDA_DONE,
 	.ipc_ctl = CNL_DSP_REG_HIPCCTL,
+	.rom_status_reg = HDA_DSP_SRAM_REG_ROM_STATUS,
 	.rom_init_timeout	= 300,
 	.ssp_count = ICL_SSP_COUNT,
 	.ssp_base_offset = CNL_SSP_BASE_OFFSET,
diff --git a/sound/soc/sof/intel/shim.h b/sound/soc/sof/intel/shim.h
index e9f7d4d7fcce..96707758ebc5 100644
--- a/sound/soc/sof/intel/shim.h
+++ b/sound/soc/sof/intel/shim.h
@@ -161,6 +161,7 @@ struct sof_intel_dsp_desc {
 	int ipc_ack;
 	int ipc_ack_mask;
 	int ipc_ctl;
+	int rom_status_reg;
 	int rom_init_timeout;
 	int ssp_count;			/* ssp count of the platform */
 	int ssp_base_offset;		/* base address of the SSPs */
diff --git a/sound/soc/sof/intel/tgl.c b/sound/soc/sof/intel/tgl.c
index 199d41a7dc9b..aba52d8628aa 100644
--- a/sound/soc/sof/intel/tgl.c
+++ b/sound/soc/sof/intel/tgl.c
@@ -134,6 +134,7 @@ const struct sof_intel_dsp_desc tgl_chip_info = {
 	.ipc_ack = CNL_DSP_REG_HIPCIDA,
 	.ipc_ack_mask = CNL_DSP_REG_HIPCIDA_DONE,
 	.ipc_ctl = CNL_DSP_REG_HIPCCTL,
+	.rom_status_reg = HDA_DSP_SRAM_REG_ROM_STATUS,
 	.rom_init_timeout	= 300,
 	.ssp_count = ICL_SSP_COUNT,
 	.ssp_base_offset = CNL_SSP_BASE_OFFSET,
@@ -153,6 +154,7 @@ const struct sof_intel_dsp_desc tglh_chip_info = {
 	.ipc_ack = CNL_DSP_REG_HIPCIDA,
 	.ipc_ack_mask = CNL_DSP_REG_HIPCIDA_DONE,
 	.ipc_ctl = CNL_DSP_REG_HIPCCTL,
+	.rom_status_reg = HDA_DSP_SRAM_REG_ROM_STATUS,
 	.rom_init_timeout	= 300,
 	.ssp_count = ICL_SSP_COUNT,
 	.ssp_base_offset = CNL_SSP_BASE_OFFSET,
@@ -172,6 +174,7 @@ const struct sof_intel_dsp_desc ehl_chip_info = {
 	.ipc_ack = CNL_DSP_REG_HIPCIDA,
 	.ipc_ack_mask = CNL_DSP_REG_HIPCIDA_DONE,
 	.ipc_ctl = CNL_DSP_REG_HIPCCTL,
+	.rom_status_reg = HDA_DSP_SRAM_REG_ROM_STATUS,
 	.rom_init_timeout	= 300,
 	.ssp_count = ICL_SSP_COUNT,
 	.ssp_base_offset = CNL_SSP_BASE_OFFSET,
@@ -191,6 +194,7 @@ const struct sof_intel_dsp_desc adls_chip_info = {
 	.ipc_ack = CNL_DSP_REG_HIPCIDA,
 	.ipc_ack_mask = CNL_DSP_REG_HIPCIDA_DONE,
 	.ipc_ctl = CNL_DSP_REG_HIPCCTL,
+	.rom_status_reg = HDA_DSP_SRAM_REG_ROM_STATUS,
 	.rom_init_timeout	= 300,
 	.ssp_count = ICL_SSP_COUNT,
 	.ssp_base_offset = CNL_SSP_BASE_OFFSET,
diff --git a/sound/usb/bcd2000/bcd2000.c b/sound/usb/bcd2000/bcd2000.c
index cd4a0bc6d278..7aec0a95c609 100644
--- a/sound/usb/bcd2000/bcd2000.c
+++ b/sound/usb/bcd2000/bcd2000.c
@@ -348,7 +348,8 @@ static int bcd2000_init_midi(struct bcd2000 *bcd2k)
 static void bcd2000_free_usb_related_resources(struct bcd2000 *bcd2k,
 						struct usb_interface *interface)
 {
-	/* usb_kill_urb not necessary, urb is aborted automatically */
+	usb_kill_urb(bcd2k->midi_out_urb);
+	usb_kill_urb(bcd2k->midi_in_urb);
 
 	usb_free_urb(bcd2k->midi_out_urb);
 	usb_free_urb(bcd2k->midi_in_urb);
diff --git a/sound/usb/card.c b/sound/usb/card.c
index 1764b9302d46..713b84d8d42f 100644
--- a/sound/usb/card.c
+++ b/sound/usb/card.c
@@ -387,6 +387,14 @@ static const struct usb_audio_device_name usb_audio_names[] = {
 	DEVICE_NAME(0x05e1, 0x0408, "Syntek", "STK1160"),
 	DEVICE_NAME(0x05e1, 0x0480, "Hauppauge", "Woodbury"),
 
+	/* ASUS ROG Zenith II: this machine has also two devices, one for
+	 * the front headphone and another for the rest
+	 */
+	PROFILE_NAME(0x0b05, 0x1915, "ASUS", "Zenith II Front Headphone",
+		     "Zenith-II-Front-Headphone"),
+	PROFILE_NAME(0x0b05, 0x1916, "ASUS", "Zenith II Main Audio",
+		     "Zenith-II-Main-Audio"),
+
 	/* ASUS ROG Strix */
 	PROFILE_NAME(0x0b05, 0x1917,
 		     "Realtek", "ALC1220-VB-DT", "Realtek-ALC1220-VB-Desktop"),
@@ -690,7 +698,7 @@ static bool check_delayed_register_option(struct snd_usb_audio *chip, int iface)
 		if (delayed_register[i] &&
 		    sscanf(delayed_register[i], "%x:%x", &id, &inum) == 2 &&
 		    id == chip->usb_id)
-			return inum != iface;
+			return iface < inum;
 	}
 
 	return false;
diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c
index 743b8287cfcd..11fa7745c017 100644
--- a/sound/usb/endpoint.c
+++ b/sound/usb/endpoint.c
@@ -731,7 +731,8 @@ bool snd_usb_endpoint_compatible(struct snd_usb_audio *chip,
  * The endpoint needs to be closed via snd_usb_endpoint_close() later.
  *
  * Note that this function doesn't configure the endpoint.  The substream
- * needs to set it up later via snd_usb_endpoint_configure().
+ * needs to set it up later via snd_usb_endpoint_set_params() and
+ * snd_usb_endpoint_prepare().
  */
 struct snd_usb_endpoint *
 snd_usb_endpoint_open(struct snd_usb_audio *chip,
@@ -1254,12 +1255,13 @@ out_of_memory:
 /*
  * snd_usb_endpoint_set_params: configure an snd_usb_endpoint
  *
+ * It's called either from hw_params callback.
  * Determine the number of URBs to be used on this endpoint.
  * An endpoint must be configured before it can be started.
  * An endpoint that is already running can not be reconfigured.
  */
-static int snd_usb_endpoint_set_params(struct snd_usb_audio *chip,
-				       struct snd_usb_endpoint *ep)
+int snd_usb_endpoint_set_params(struct snd_usb_audio *chip,
+				struct snd_usb_endpoint *ep)
 {
 	const struct audioformat *fmt = ep->cur_audiofmt;
 	int err;
@@ -1315,18 +1317,18 @@ static int snd_usb_endpoint_set_params(struct snd_usb_audio *chip,
 }
 
 /*
- * snd_usb_endpoint_configure: Configure the endpoint
+ * snd_usb_endpoint_prepare: Prepare the endpoint
  *
  * This function sets up the EP to be fully usable state.
- * It's called either from hw_params or prepare callback.
+ * It's called either from prepare callback.
  * The function checks need_setup flag, and performs nothing unless needed,
  * so it's safe to call this multiple times.
  *
  * This returns zero if unchanged, 1 if the configuration has changed,
  * or a negative error code.
  */
-int snd_usb_endpoint_configure(struct snd_usb_audio *chip,
-			       struct snd_usb_endpoint *ep)
+int snd_usb_endpoint_prepare(struct snd_usb_audio *chip,
+			     struct snd_usb_endpoint *ep)
 {
 	bool iface_first;
 	int err = 0;
@@ -1348,9 +1350,6 @@ int snd_usb_endpoint_configure(struct snd_usb_audio *chip,
 			if (err < 0)
 				goto unlock;
 		}
-		err = snd_usb_endpoint_set_params(chip, ep);
-		if (err < 0)
-			goto unlock;
 		goto done;
 	}
 
@@ -1378,10 +1377,6 @@ int snd_usb_endpoint_configure(struct snd_usb_audio *chip,
 	if (err < 0)
 		goto unlock;
 
-	err = snd_usb_endpoint_set_params(chip, ep);
-	if (err < 0)
-		goto unlock;
-
 	err = snd_usb_select_mode_quirk(chip, ep->cur_audiofmt);
 	if (err < 0)
 		goto unlock;
diff --git a/sound/usb/endpoint.h b/sound/usb/endpoint.h
index 6a9af04cf175..e67ea28faa54 100644
--- a/sound/usb/endpoint.h
+++ b/sound/usb/endpoint.h
@@ -17,8 +17,10 @@ snd_usb_endpoint_open(struct snd_usb_audio *chip,
 		      bool is_sync_ep);
 void snd_usb_endpoint_close(struct snd_usb_audio *chip,
 			    struct snd_usb_endpoint *ep);
-int snd_usb_endpoint_configure(struct snd_usb_audio *chip,
-			       struct snd_usb_endpoint *ep);
+int snd_usb_endpoint_set_params(struct snd_usb_audio *chip,
+				struct snd_usb_endpoint *ep);
+int snd_usb_endpoint_prepare(struct snd_usb_audio *chip,
+			     struct snd_usb_endpoint *ep);
 int snd_usb_endpoint_get_clock_rate(struct snd_usb_audio *chip, int clock);
 
 bool snd_usb_endpoint_compatible(struct snd_usb_audio *chip,
diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c
index 6ffd23f2ee65..3f8f6056ff6a 100644
--- a/sound/usb/mixer_maps.c
+++ b/sound/usb/mixer_maps.c
@@ -366,13 +366,28 @@ static const struct usbmix_name_map corsair_virtuoso_map[] = {
 	{ 0 }
 };
 
-/* Some mobos shipped with a dummy HD-audio show the invalid GET_MIN/GET_MAX
- * response for Input Gain Pad (id=19, control=12) and the connector status
- * for SPDIF terminal (id=18).  Skip them.
- */
-static const struct usbmix_name_map asus_rog_map[] = {
-	{ 18, NULL }, /* OT, connector control */
-	{ 19, NULL, 12 }, /* FU, Input Gain Pad */
+/* ASUS ROG Zenith II with Realtek ALC1220-VB */
+static const struct usbmix_name_map asus_zenith_ii_map[] = {
+	{ 19, NULL, 12 }, /* FU, Input Gain Pad - broken response, disabled */
+	{ 16, "Speaker" },		/* OT */
+	{ 22, "Speaker Playback" },	/* FU */
+	{ 7, "Line" },			/* IT */
+	{ 19, "Line Capture" },		/* FU */
+	{ 8, "Mic" },			/* IT */
+	{ 20, "Mic Capture" },		/* FU */
+	{ 9, "Front Mic" },		/* IT */
+	{ 21, "Front Mic Capture" },	/* FU */
+	{ 17, "IEC958" },		/* OT */
+	{ 23, "IEC958 Playback" },	/* FU */
+	{}
+};
+
+static const struct usbmix_connector_map asus_zenith_ii_connector_map[] = {
+	{ 10, 16 },	/* (Back) Speaker */
+	{ 11, 17 },	/* SPDIF */
+	{ 13, 7 },	/* Line */
+	{ 14, 8 },	/* Mic */
+	{ 15, 9 },	/* Front Mic */
 	{}
 };
 
@@ -423,6 +438,14 @@ static const struct usbmix_name_map aorus_master_alc1220vb_map[] = {
 	{}
 };
 
+/* MSI MPG X570S Carbon Max Wifi with ALC4080  */
+static const struct usbmix_name_map msi_mpg_x570s_carbon_max_wifi_alc4080_map[] = {
+	{ 29, "Speaker Playback" },
+	{ 30, "Front Headphone Playback" },
+	{ 32, "IEC958 Playback" },
+	{}
+};
+
 /*
  * Control map entries
  */
@@ -560,9 +583,10 @@ static const struct usbmix_ctl_map usbmix_ctl_maps[] = {
 		.map = trx40_mobo_map,
 		.connector_map = trx40_mobo_connector_map,
 	},
-	{	/* ASUS ROG Zenith II */
+	{	/* ASUS ROG Zenith II (main audio) */
 		.id = USB_ID(0x0b05, 0x1916),
-		.map = asus_rog_map,
+		.map = asus_zenith_ii_map,
+		.connector_map = asus_zenith_ii_connector_map,
 	},
 	{	/* ASUS ROG Strix */
 		.id = USB_ID(0x0b05, 0x1917),
@@ -574,6 +598,14 @@ static const struct usbmix_ctl_map usbmix_ctl_maps[] = {
 		.map = trx40_mobo_map,
 		.connector_map = trx40_mobo_connector_map,
 	},
+	{	/* MSI MPG X570S Carbon Max Wifi */
+		.id = USB_ID(0x0db0, 0x419c),
+		.map = msi_mpg_x570s_carbon_max_wifi_alc4080_map,
+	},
+	{	/* MSI MAG X570S Torpedo Max */
+		.id = USB_ID(0x0db0, 0xa073),
+		.map = msi_mpg_x570s_carbon_max_wifi_alc4080_map,
+	},
 	{	/* MSI TRX40 */
 		.id = USB_ID(0x0db0, 0x543d),
 		.map = trx40_mobo_map,
diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index b6cd43c5ea3e..2d60e6d1f8df 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -443,17 +443,17 @@ static int configure_endpoints(struct snd_usb_audio *chip,
 		if (stop_endpoints(subs, false))
 			sync_pending_stops(subs);
 		if (subs->sync_endpoint) {
-			err = snd_usb_endpoint_configure(chip, subs->sync_endpoint);
+			err = snd_usb_endpoint_prepare(chip, subs->sync_endpoint);
 			if (err < 0)
 				return err;
 		}
-		err = snd_usb_endpoint_configure(chip, subs->data_endpoint);
+		err = snd_usb_endpoint_prepare(chip, subs->data_endpoint);
 		if (err < 0)
 			return err;
 		snd_usb_set_format_quirk(subs, subs->cur_audiofmt);
 	} else {
 		if (subs->sync_endpoint) {
-			err = snd_usb_endpoint_configure(chip, subs->sync_endpoint);
+			err = snd_usb_endpoint_prepare(chip, subs->sync_endpoint);
 			if (err < 0)
 				return err;
 		}
@@ -551,7 +551,13 @@ static int snd_usb_hw_params(struct snd_pcm_substream *substream,
 	subs->cur_audiofmt = fmt;
 	mutex_unlock(&chip->mutex);
 
-	ret = configure_endpoints(chip, subs);
+	if (subs->sync_endpoint) {
+		ret = snd_usb_endpoint_set_params(chip, subs->sync_endpoint);
+		if (ret < 0)
+			goto unlock;
+	}
+
+	ret = snd_usb_endpoint_set_params(chip, subs->data_endpoint);
 
  unlock:
 	if (ret < 0)
diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
index 4f56e1784932..f93201a830b5 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -3803,6 +3803,54 @@ YAMAHA_DEVICE(0x7010, "UB99"),
 },
 
 /*
+ * MacroSilicon MS2100/MS2106 based AV capture cards
+ *
+ * These claim 96kHz 1ch in the descriptors, but are actually 48kHz 2ch.
+ * They also need QUIRK_FLAG_ALIGN_TRANSFER, which makes one wonder if
+ * they pretend to be 96kHz mono as a workaround for stereo being broken
+ * by that...
+ *
+ * They also have an issue with initial stream alignment that causes the
+ * channels to be swapped and out of phase, which is dealt with in quirks.c.
+ */
+{
+	USB_AUDIO_DEVICE(0x534d, 0x0021),
+	.driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
+		.vendor_name = "MacroSilicon",
+		.product_name = "MS210x",
+		.ifnum = QUIRK_ANY_INTERFACE,
+		.type = QUIRK_COMPOSITE,
+		.data = &(const struct snd_usb_audio_quirk[]) {
+			{
+				.ifnum = 2,
+				.type = QUIRK_AUDIO_STANDARD_MIXER,
+			},
+			{
+				.ifnum = 3,
+				.type = QUIRK_AUDIO_FIXED_ENDPOINT,
+				.data = &(const struct audioformat) {
+					.formats = SNDRV_PCM_FMTBIT_S16_LE,
+					.channels = 2,
+					.iface = 3,
+					.altsetting = 1,
+					.altset_idx = 1,
+					.attributes = 0,
+					.endpoint = 0x82,
+					.ep_attr = USB_ENDPOINT_XFER_ISOC |
+						USB_ENDPOINT_SYNC_ASYNC,
+					.rates = SNDRV_PCM_RATE_CONTINUOUS,
+					.rate_min = 48000,
+					.rate_max = 48000,
+				}
+			},
+			{
+				.ifnum = -1
+			}
+		}
+	}
+},
+
+/*
  * MacroSilicon MS2109 based HDMI capture cards
  *
  * These claim 96kHz 1ch in the descriptors, but are actually 48kHz 2ch.
@@ -4119,6 +4167,206 @@ YAMAHA_DEVICE(0x7010, "UB99"),
 		}
 	}
 },
+{
+	/*
+	 * Fiero SC-01 (firmware v1.0.0 @ 48 kHz)
+	 */
+	USB_DEVICE(0x2b53, 0x0023),
+	.driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
+		.vendor_name = "Fiero",
+		.product_name = "SC-01",
+		.ifnum = QUIRK_ANY_INTERFACE,
+		.type = QUIRK_COMPOSITE,
+		.data = &(const struct snd_usb_audio_quirk[]) {
+			{
+				.ifnum = 0,
+				.type = QUIRK_AUDIO_STANDARD_INTERFACE
+			},
+			/* Playback */
+			{
+				.ifnum = 1,
+				.type = QUIRK_AUDIO_FIXED_ENDPOINT,
+				.data = &(const struct audioformat) {
+					.formats = SNDRV_PCM_FMTBIT_S32_LE,
+					.channels = 2,
+					.fmt_bits = 24,
+					.iface = 1,
+					.altsetting = 1,
+					.altset_idx = 1,
+					.endpoint = 0x01,
+					.ep_attr = USB_ENDPOINT_XFER_ISOC |
+						   USB_ENDPOINT_SYNC_ASYNC,
+					.rates = SNDRV_PCM_RATE_48000,
+					.rate_min = 48000,
+					.rate_max = 48000,
+					.nr_rates = 1,
+					.rate_table = (unsigned int[]) { 48000 },
+					.clock = 0x29
+				}
+			},
+			/* Capture */
+			{
+				.ifnum = 2,
+				.type = QUIRK_AUDIO_FIXED_ENDPOINT,
+				.data = &(const struct audioformat) {
+					.formats = SNDRV_PCM_FMTBIT_S32_LE,
+					.channels = 2,
+					.fmt_bits = 24,
+					.iface = 2,
+					.altsetting = 1,
+					.altset_idx = 1,
+					.endpoint = 0x82,
+					.ep_attr = USB_ENDPOINT_XFER_ISOC |
+						   USB_ENDPOINT_SYNC_ASYNC |
+						   USB_ENDPOINT_USAGE_IMPLICIT_FB,
+					.rates = SNDRV_PCM_RATE_48000,
+					.rate_min = 48000,
+					.rate_max = 48000,
+					.nr_rates = 1,
+					.rate_table = (unsigned int[]) { 48000 },
+					.clock = 0x29
+				}
+			},
+			{
+				.ifnum = -1
+			}
+		}
+	}
+},
+{
+	/*
+	 * Fiero SC-01 (firmware v1.0.0 @ 96 kHz)
+	 */
+	USB_DEVICE(0x2b53, 0x0024),
+	.driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
+		.vendor_name = "Fiero",
+		.product_name = "SC-01",
+		.ifnum = QUIRK_ANY_INTERFACE,
+		.type = QUIRK_COMPOSITE,
+		.data = &(const struct snd_usb_audio_quirk[]) {
+			{
+				.ifnum = 0,
+				.type = QUIRK_AUDIO_STANDARD_INTERFACE
+			},
+			/* Playback */
+			{
+				.ifnum = 1,
+				.type = QUIRK_AUDIO_FIXED_ENDPOINT,
+				.data = &(const struct audioformat) {
+					.formats = SNDRV_PCM_FMTBIT_S32_LE,
+					.channels = 2,
+					.fmt_bits = 24,
+					.iface = 1,
+					.altsetting = 1,
+					.altset_idx = 1,
+					.endpoint = 0x01,
+					.ep_attr = USB_ENDPOINT_XFER_ISOC |
+						   USB_ENDPOINT_SYNC_ASYNC,
+					.rates = SNDRV_PCM_RATE_96000,
+					.rate_min = 96000,
+					.rate_max = 96000,
+					.nr_rates = 1,
+					.rate_table = (unsigned int[]) { 96000 },
+					.clock = 0x29
+				}
+			},
+			/* Capture */
+			{
+				.ifnum = 2,
+				.type = QUIRK_AUDIO_FIXED_ENDPOINT,
+				.data = &(const struct audioformat) {
+					.formats = SNDRV_PCM_FMTBIT_S32_LE,
+					.channels = 2,
+					.fmt_bits = 24,
+					.iface = 2,
+					.altsetting = 1,
+					.altset_idx = 1,
+					.endpoint = 0x82,
+					.ep_attr = USB_ENDPOINT_XFER_ISOC |
+						   USB_ENDPOINT_SYNC_ASYNC |
+						   USB_ENDPOINT_USAGE_IMPLICIT_FB,
+					.rates = SNDRV_PCM_RATE_96000,
+					.rate_min = 96000,
+					.rate_max = 96000,
+					.nr_rates = 1,
+					.rate_table = (unsigned int[]) { 96000 },
+					.clock = 0x29
+				}
+			},
+			{
+				.ifnum = -1
+			}
+		}
+	}
+},
+{
+	/*
+	 * Fiero SC-01 (firmware v1.1.0)
+	 */
+	USB_DEVICE(0x2b53, 0x0031),
+	.driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
+		.vendor_name = "Fiero",
+		.product_name = "SC-01",
+		.ifnum = QUIRK_ANY_INTERFACE,
+		.type = QUIRK_COMPOSITE,
+		.data = &(const struct snd_usb_audio_quirk[]) {
+			{
+				.ifnum = 0,
+				.type = QUIRK_AUDIO_STANDARD_INTERFACE
+			},
+			/* Playback */
+			{
+				.ifnum = 1,
+				.type = QUIRK_AUDIO_FIXED_ENDPOINT,
+				.data = &(const struct audioformat) {
+					.formats = SNDRV_PCM_FMTBIT_S32_LE,
+					.channels = 2,
+					.fmt_bits = 24,
+					.iface = 1,
+					.altsetting = 1,
+					.altset_idx = 1,
+					.endpoint = 0x01,
+					.ep_attr = USB_ENDPOINT_XFER_ISOC |
+						   USB_ENDPOINT_SYNC_ASYNC,
+					.rates = SNDRV_PCM_RATE_48000 |
+						 SNDRV_PCM_RATE_96000,
+					.rate_min = 48000,
+					.rate_max = 96000,
+					.nr_rates = 2,
+					.rate_table = (unsigned int[]) { 48000, 96000 },
+					.clock = 0x29
+				}
+			},
+			/* Capture */
+			{
+				.ifnum = 2,
+				.type = QUIRK_AUDIO_FIXED_ENDPOINT,
+				.data = &(const struct audioformat) {
+					.formats = SNDRV_PCM_FMTBIT_S32_LE,
+					.channels = 2,
+					.fmt_bits = 24,
+					.iface = 2,
+					.altsetting = 1,
+					.altset_idx = 1,
+					.endpoint = 0x82,
+					.ep_attr = USB_ENDPOINT_XFER_ISOC |
+						   USB_ENDPOINT_SYNC_ASYNC |
+						   USB_ENDPOINT_USAGE_IMPLICIT_FB,
+					.rates = SNDRV_PCM_RATE_48000 |
+						 SNDRV_PCM_RATE_96000,
+					.rate_min = 48000,
+					.rate_max = 96000,
+					.nr_rates = 2,
+					.rate_table = (unsigned int[]) { 48000, 96000 },
+					.clock = 0x29
+				}
+			},
+			{
+				.ifnum = -1
+			}
+		}
+	}
+},
 
 #undef USB_DEVICE_VENDOR_SPEC
 #undef USB_AUDIO_DEVICE
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index e8468f9b007d..5b4d8f5eade2 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1478,6 +1478,7 @@ void snd_usb_set_format_quirk(struct snd_usb_substream *subs,
 	case USB_ID(0x041e, 0x3f19): /* E-Mu 0204 USB */
 		set_format_emu_quirk(subs, fmt);
 		break;
+	case USB_ID(0x534d, 0x0021): /* MacroSilicon MS2100/MS2106 */
 	case USB_ID(0x534d, 0x2109): /* MacroSilicon MS2109 */
 		subs->stream_offset_adj = 2;
 		break;
@@ -1763,7 +1764,7 @@ bool snd_usb_registration_quirk(struct snd_usb_audio *chip, int iface)
 
 	for (q = registration_quirks; q->usb_id; q++)
 		if (chip->usb_id == q->usb_id)
-			return iface != q->interface;
+			return iface < q->interface;
 
 	/* Register as normal */
 	return false;
@@ -1842,6 +1843,12 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER),
 	DEVICE_FLG(0x1395, 0x740a, /* Sennheiser DECT */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
+	DEVICE_FLG(0x1397, 0x0507, /* Behringer UMC202HD */
+		   QUIRK_FLAG_PLAYBACK_FIRST | QUIRK_FLAG_GENERIC_IMPLICIT_FB),
+	DEVICE_FLG(0x1397, 0x0508, /* Behringer UMC204HD */
+		   QUIRK_FLAG_PLAYBACK_FIRST | QUIRK_FLAG_GENERIC_IMPLICIT_FB),
+	DEVICE_FLG(0x1397, 0x0509, /* Behringer UMC404HD */
+		   QUIRK_FLAG_PLAYBACK_FIRST | QUIRK_FLAG_GENERIC_IMPLICIT_FB),
 	DEVICE_FLG(0x13e5, 0x0001, /* Serato Phono */
 		   QUIRK_FLAG_IGNORE_CTL_ERROR),
 	DEVICE_FLG(0x154e, 0x1002, /* Denon DCD-1500RE */
@@ -1896,6 +1903,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER),
 	DEVICE_FLG(0x21b4, 0x0081, /* AudioQuest DragonFly */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
+	DEVICE_FLG(0x2522, 0x0007, /* LH Labs Geek Out HD Audio 1V5 */
+		   QUIRK_FLAG_SET_IFACE_FIRST),
 	DEVICE_FLG(0x2708, 0x0002, /* Audient iD14 */
 		   QUIRK_FLAG_IGNORE_CTL_ERROR),
 	DEVICE_FLG(0x2912, 0x30c8, /* Audioengine D1 */
@@ -1904,10 +1913,18 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_IGNORE_CTL_ERROR),
 	DEVICE_FLG(0x413c, 0xa506, /* Dell AE515 sound bar */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
+	DEVICE_FLG(0x534d, 0x0021, /* MacroSilicon MS2100/MS2106 */
+		   QUIRK_FLAG_ALIGN_TRANSFER),
 	DEVICE_FLG(0x534d, 0x2109, /* MacroSilicon MS2109 */
 		   QUIRK_FLAG_ALIGN_TRANSFER),
 	DEVICE_FLG(0x1224, 0x2a25, /* Jieli Technology USB PHY 2.0 */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
+	DEVICE_FLG(0x2b53, 0x0023, /* Fiero SC-01 (firmware v1.0.0 @ 48 kHz) */
+		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
+	DEVICE_FLG(0x2b53, 0x0024, /* Fiero SC-01 (firmware v1.0.0 @ 96 kHz) */
+		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
+	DEVICE_FLG(0x2b53, 0x0031, /* Fiero SC-01 (firmware v1.1.0) */
+		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
 
 	/* Vendor matches */
 	VENDOR_FLG(0x045e, /* MS Lifecam */
diff --git a/sound/usb/stream.c b/sound/usb/stream.c
index ceb93d798182..f10f4e6d3fb8 100644
--- a/sound/usb/stream.c
+++ b/sound/usb/stream.c
@@ -495,6 +495,10 @@ static int __snd_usb_add_audio_stream(struct snd_usb_audio *chip,
 			return 0;
 		}
 	}
+
+	if (chip->card->registered)
+		chip->need_delayed_register = true;
+
 	/* look for an empty stream */
 	list_for_each_entry(as, &chip->pcm_list, list) {
 		if (as->fmt_type != fp->fmt_type)
@@ -502,9 +506,6 @@ static int __snd_usb_add_audio_stream(struct snd_usb_audio *chip,
 		subs = &as->substream[stream];
 		if (subs->ep_num)
 			continue;
-		if (snd_device_get_state(chip->card, as->pcm) !=
-		    SNDRV_DEV_BUILD)
-			chip->need_delayed_register = true;
 		err = snd_pcm_new_stream(as->pcm, stream, 1);
 		if (err < 0)
 			return err;
@@ -1105,7 +1106,7 @@ static int __snd_usb_parse_audio_interface(struct snd_usb_audio *chip,
 	 * Dallas DS4201 workaround: It presents 5 altsettings, but the last
 	 * one misses syncpipe, and does not produce any sound.
 	 */
-	if (chip->usb_id == USB_ID(0x04fa, 0x4201))
+	if (chip->usb_id == USB_ID(0x04fa, 0x4201) && num >= 4)
 		num = 4;
 
 	for (i = 0; i < num; i++) {
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 96eefc05387a..bcaedfe60572 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -203,8 +203,8 @@
 #define X86_FEATURE_PROC_FEEDBACK	( 7*32+ 9) /* AMD ProcFeedbackInterface */
 /* FREE!                                ( 7*32+10) */
 #define X86_FEATURE_PTI			( 7*32+11) /* Kernel Page Table Isolation enabled */
-#define X86_FEATURE_RETPOLINE		( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */
-#define X86_FEATURE_RETPOLINE_LFENCE	( 7*32+13) /* "" Use LFENCEs for Spectre variant 2 */
+#define X86_FEATURE_KERNEL_IBRS		( 7*32+12) /* "" Set/clear IBRS on kernel entry/exit */
+#define X86_FEATURE_RSB_VMEXIT		( 7*32+13) /* "" Fill RSB on VM-Exit */
 #define X86_FEATURE_INTEL_PPIN		( 7*32+14) /* Intel Processor Inventory Number */
 #define X86_FEATURE_CDP_L2		( 7*32+15) /* Code and Data Prioritization L2 */
 #define X86_FEATURE_MSR_SPEC_CTRL	( 7*32+16) /* "" MSR SPEC_CTRL is implemented */
@@ -294,6 +294,13 @@
 #define X86_FEATURE_PER_THREAD_MBA	(11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */
 #define X86_FEATURE_SGX1		(11*32+ 8) /* "" Basic SGX */
 #define X86_FEATURE_SGX2		(11*32+ 9) /* "" SGX Enclave Dynamic Memory Management (EDMM) */
+#define X86_FEATURE_ENTRY_IBPB		(11*32+10) /* "" Issue an IBPB on kernel entry */
+#define X86_FEATURE_RRSBA_CTRL		(11*32+11) /* "" RET prediction control */
+#define X86_FEATURE_RETPOLINE		(11*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */
+#define X86_FEATURE_RETPOLINE_LFENCE	(11*32+13) /* "" Use LFENCE for Spectre variant 2 */
+#define X86_FEATURE_RETHUNK		(11*32+14) /* "" Use REturn THUNK */
+#define X86_FEATURE_UNRET		(11*32+15) /* "" AMD BTB untrain return */
+#define X86_FEATURE_RSB_VMEXIT_LITE	(11*32+17) /* "" Fill RSB on VM-Exit when EIBRS is enabled */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
@@ -313,6 +320,7 @@
 #define X86_FEATURE_AMD_SSBD		(13*32+24) /* "" Speculative Store Bypass Disable */
 #define X86_FEATURE_VIRT_SSBD		(13*32+25) /* Virtualized Speculative Store Bypass Disable */
 #define X86_FEATURE_AMD_SSB_NO		(13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */
+#define X86_FEATURE_BTC_NO		(13*32+29) /* "" Not vulnerable to Branch Type Confusion */
 
 /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
 #define X86_FEATURE_DTHERM		(14*32+ 0) /* Digital Thermal Sensor */
@@ -437,5 +445,6 @@
 #define X86_BUG_ITLB_MULTIHIT		X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */
 #define X86_BUG_SRBDS			X86_BUG(24) /* CPU may leak RNG bits if not mitigated */
 #define X86_BUG_MMIO_STALE_DATA		X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */
+#define X86_BUG_RETBLEED		X86_BUG(26) /* CPU is affected by RETBleed */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index 8f28fafa98b3..834a3b6d81e1 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -56,6 +56,25 @@
 # define DISABLE_PTI		(1 << (X86_FEATURE_PTI & 31))
 #endif
 
+#ifdef CONFIG_RETPOLINE
+# define DISABLE_RETPOLINE	0
+#else
+# define DISABLE_RETPOLINE	((1 << (X86_FEATURE_RETPOLINE & 31)) | \
+				 (1 << (X86_FEATURE_RETPOLINE_LFENCE & 31)))
+#endif
+
+#ifdef CONFIG_RETHUNK
+# define DISABLE_RETHUNK	0
+#else
+# define DISABLE_RETHUNK	(1 << (X86_FEATURE_RETHUNK & 31))
+#endif
+
+#ifdef CONFIG_CPU_UNRET_ENTRY
+# define DISABLE_UNRET		0
+#else
+# define DISABLE_UNRET		(1 << (X86_FEATURE_UNRET & 31))
+#endif
+
 /* Force disable because it's broken beyond repair */
 #define DISABLE_ENQCMD		(1 << (X86_FEATURE_ENQCMD & 31))
 
@@ -79,7 +98,7 @@
 #define DISABLED_MASK8	0
 #define DISABLED_MASK9	(DISABLE_SMAP|DISABLE_SGX)
 #define DISABLED_MASK10	0
-#define DISABLED_MASK11	0
+#define DISABLED_MASK11	(DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET)
 #define DISABLED_MASK12	0
 #define DISABLED_MASK13	0
 #define DISABLED_MASK14	0
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 7dc5a3306f37..8f38265bc81d 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -51,6 +51,8 @@
 #define SPEC_CTRL_STIBP			BIT(SPEC_CTRL_STIBP_SHIFT)	/* STIBP mask */
 #define SPEC_CTRL_SSBD_SHIFT		2	   /* Speculative Store Bypass Disable bit */
 #define SPEC_CTRL_SSBD			BIT(SPEC_CTRL_SSBD_SHIFT)	/* Speculative Store Bypass Disable */
+#define SPEC_CTRL_RRSBA_DIS_S_SHIFT	6	   /* Disable RRSBA behavior */
+#define SPEC_CTRL_RRSBA_DIS_S		BIT(SPEC_CTRL_RRSBA_DIS_S_SHIFT)
 
 #define MSR_IA32_PRED_CMD		0x00000049 /* Prediction Command */
 #define PRED_CMD_IBPB			BIT(0)	   /* Indirect Branch Prediction Barrier */
@@ -91,6 +93,7 @@
 #define MSR_IA32_ARCH_CAPABILITIES	0x0000010a
 #define ARCH_CAP_RDCL_NO		BIT(0)	/* Not susceptible to Meltdown */
 #define ARCH_CAP_IBRS_ALL		BIT(1)	/* Enhanced IBRS support */
+#define ARCH_CAP_RSBA			BIT(2)	/* RET may use alternative branch predictors */
 #define ARCH_CAP_SKIP_VMENTRY_L1DFLUSH	BIT(3)	/* Skip L1D flush on vmentry */
 #define ARCH_CAP_SSB_NO			BIT(4)	/*
 						 * Not susceptible to Speculative Store Bypass
@@ -138,6 +141,17 @@
 						 * bit available to control VERW
 						 * behavior.
 						 */
+#define ARCH_CAP_RRSBA			BIT(19)	/*
+						 * Indicates RET may use predictors
+						 * other than the RSB. With eIBRS
+						 * enabled predictions in kernel mode
+						 * are restricted to targets in
+						 * kernel.
+						 */
+#define ARCH_CAP_PBRSB_NO		BIT(24)	/*
+						 * Not susceptible to Post-Barrier
+						 * Return Stack Buffer Predictions.
+						 */
 
 #define MSR_IA32_FLUSH_CMD		0x0000010b
 #define L1D_FLUSH			BIT(0)	/*
@@ -514,6 +528,9 @@
 /* Fam 17h MSRs */
 #define MSR_F17H_IRPERF			0xc00000e9
 
+#define MSR_ZEN2_SPECTRAL_CHICKEN	0xc00110e3
+#define MSR_ZEN2_SPECTRAL_CHICKEN_BIT	BIT_ULL(1)
+
 /* Fam 16h MSRs */
 #define MSR_F16H_L2I_PERF_CTL		0xc0010230
 #define MSR_F16H_L2I_PERF_CTR		0xc0010231
diff --git a/tools/build/feature/test-libcrypto.c b/tools/build/feature/test-libcrypto.c
index a98174e0569c..bc34a5bbb504 100644
--- a/tools/build/feature/test-libcrypto.c
+++ b/tools/build/feature/test-libcrypto.c
@@ -1,16 +1,23 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <openssl/evp.h>
 #include <openssl/sha.h>
 #include <openssl/md5.h>
 
 int main(void)
 {
-	MD5_CTX context;
+	EVP_MD_CTX *mdctx;
 	unsigned char md[MD5_DIGEST_LENGTH + SHA_DIGEST_LENGTH];
 	unsigned char dat[] = "12345";
+	unsigned int digest_len;
 
-	MD5_Init(&context);
-	MD5_Update(&context, &dat[0], sizeof(dat));
-	MD5_Final(&md[0], &context);
+	mdctx = EVP_MD_CTX_new();
+	if (!mdctx)
+		return 0;
+
+	EVP_DigestInit_ex(mdctx, EVP_md5(), NULL);
+	EVP_DigestUpdate(mdctx, &dat[0], sizeof(dat));
+	EVP_DigestFinal_ex(mdctx, &md[0], &digest_len);
+	EVP_MD_CTX_free(mdctx);
 
 	SHA1(&dat[0], sizeof(dat), &md[0]);
 
diff --git a/tools/include/linux/objtool.h b/tools/include/linux/objtool.h
index 7e72d975cb76..a2042c418686 100644
--- a/tools/include/linux/objtool.h
+++ b/tools/include/linux/objtool.h
@@ -32,11 +32,16 @@ struct unwind_hint {
  *
  * UNWIND_HINT_FUNC: Generate the unwind metadata of a callable function.
  * Useful for code which doesn't have an ELF function annotation.
+ *
+ * UNWIND_HINT_ENTRY: machine entry without stack, SYSCALL/SYSENTER etc.
  */
 #define UNWIND_HINT_TYPE_CALL		0
 #define UNWIND_HINT_TYPE_REGS		1
 #define UNWIND_HINT_TYPE_REGS_PARTIAL	2
 #define UNWIND_HINT_TYPE_FUNC		3
+#define UNWIND_HINT_TYPE_ENTRY		4
+#define UNWIND_HINT_TYPE_SAVE		5
+#define UNWIND_HINT_TYPE_RESTORE	6
 
 #ifdef CONFIG_STACK_VALIDATION
 
@@ -99,7 +104,7 @@ struct unwind_hint {
  * the debuginfo as necessary.  It will also warn if it sees any
  * inconsistencies.
  */
-.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0
+.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 end=0
 .Lunwind_hint_ip_\@:
 	.pushsection .discard.unwind_hints
 		/* struct unwind_hint */
@@ -129,7 +134,7 @@ struct unwind_hint {
 #define STACK_FRAME_NON_STANDARD(func)
 #else
 #define ANNOTATE_INTRA_FUNCTION_CALL
-.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0
+.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 end=0
 .endm
 .macro STACK_FRAME_NON_STANDARD func:req
 .endm
diff --git a/tools/include/uapi/asm/errno.h b/tools/include/uapi/asm/errno.h
index d30439b4b8ab..869379f91fe4 100644
--- a/tools/include/uapi/asm/errno.h
+++ b/tools/include/uapi/asm/errno.h
@@ -9,8 +9,8 @@
 #include "../../../arch/alpha/include/uapi/asm/errno.h"
 #elif defined(__mips__)
 #include "../../../arch/mips/include/uapi/asm/errno.h"
-#elif defined(__xtensa__)
-#include "../../../arch/xtensa/include/uapi/asm/errno.h"
+#elif defined(__hppa__)
+#include "../../../arch/parisc/include/uapi/asm/errno.h"
 #else
 #include <asm-generic/errno.h>
 #endif
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e2c8f946c541..8330e3ca8fbf 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -5347,7 +5347,8 @@ struct bpf_sock {
 	__u32 src_ip4;
 	__u32 src_ip6[4];
 	__u32 src_port;		/* host byte order */
-	__u32 dst_port;		/* network byte order */
+	__be16 dst_port;	/* network byte order */
+	__u16 :16;		/* zero padding */
 	__u32 dst_ip4;
 	__u32 dst_ip6[4];
 	__u32 state;
diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat
index 5a5bd74f55bd..9c366b3a676d 100755
--- a/tools/kvm/kvm_stat/kvm_stat
+++ b/tools/kvm/kvm_stat/kvm_stat
@@ -1646,7 +1646,8 @@ Press any other key to refresh statistics immediately.
                          .format(values))
             if len(pids) > 1:
                 sys.exit('Error: Multiple processes found (pids: {}). Use "-p"'
-                         ' to specify the desired pid'.format(" ".join(pids)))
+                         ' to specify the desired pid'
+                         .format(" ".join(map(str, pids))))
             namespace.pid = pids[0]
 
     argparser = argparse.ArgumentParser(description=description_text,
diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c
index 33c19590ee43..4435c09fe132 100644
--- a/tools/lib/bpf/gen_loader.c
+++ b/tools/lib/bpf/gen_loader.c
@@ -480,7 +480,7 @@ void bpf_gen__record_attach_target(struct bpf_gen *gen, const char *attach_name,
 	gen->attach_kind = kind;
 	ret = snprintf(gen->attach_target, sizeof(gen->attach_target), "%s%s",
 		       prefix, attach_name);
-	if (ret == sizeof(gen->attach_target))
+	if (ret >= sizeof(gen->attach_target))
 		gen->error = -ENOSPC;
 }
 
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 1ba2dd3523f8..050622649797 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -3942,7 +3942,7 @@ static int bpf_get_map_info_from_fdinfo(int fd, struct bpf_map_info *info)
 int bpf_map__reuse_fd(struct bpf_map *map, int fd)
 {
 	struct bpf_map_info info = {};
-	__u32 len = sizeof(info);
+	__u32 len = sizeof(info), name_len;
 	int new_fd, err;
 	char *new_name;
 
@@ -3952,7 +3952,12 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd)
 	if (err)
 		return libbpf_err(err);
 
-	new_name = strdup(info.name);
+	name_len = strlen(info.name);
+	if (name_len == BPF_OBJ_NAME_LEN - 1 && strncmp(map->name, info.name, name_len) == 0)
+		new_name = strdup(map->name);
+	else
+		new_name = strdup(info.name);
+
 	if (!new_name)
 		return libbpf_err(-errno);
 
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 9f45115f5f64..5ed45841e86f 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -1168,8 +1168,6 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 		goto out_mmap_tx;
 	}
 
-	ctx->prog_fd = -1;
-
 	if (!(xsk->config.libbpf_flags & XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)) {
 		err = __xsk_setup_xdp_prog(xsk, NULL);
 		if (err)
@@ -1250,7 +1248,10 @@ void xsk_socket__delete(struct xsk_socket *xsk)
 
 	ctx = xsk->ctx;
 	umem = ctx->umem;
-	if (ctx->prog_fd != -1) {
+
+	xsk_put_ctx(ctx, true);
+
+	if (!ctx->refcount) {
 		xsk_delete_bpf_maps(xsk);
 		close(ctx->prog_fd);
 		if (ctx->has_bpf_link)
@@ -1269,8 +1270,6 @@ void xsk_socket__delete(struct xsk_socket *xsk)
 		}
 	}
 
-	xsk_put_ctx(ctx, true);
-
 	umem->refcount--;
 	/* Do not close an fd that also has an associated umem connected
 	 * to it.
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 63ffbc36dacc..f62db0e006e9 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -684,154 +684,32 @@ const char *arch_ret_insn(int len)
 	return ret[len-1];
 }
 
-/* asm/alternative.h ? */
-
-#define ALTINSTR_FLAG_INV	(1 << 15)
-#define ALT_NOT(feat)		((feat) | ALTINSTR_FLAG_INV)
-
-struct alt_instr {
-	s32 instr_offset;	/* original instruction */
-	s32 repl_offset;	/* offset to replacement instruction */
-	u16 cpuid;		/* cpuid bit set for replacement */
-	u8  instrlen;		/* length of original instruction */
-	u8  replacementlen;	/* length of new instruction */
-} __packed;
-
-static int elf_add_alternative(struct elf *elf,
-			       struct instruction *orig, struct symbol *sym,
-			       int cpuid, u8 orig_len, u8 repl_len)
+int arch_decode_hint_reg(u8 sp_reg, int *base)
 {
-	const int size = sizeof(struct alt_instr);
-	struct alt_instr *alt;
-	struct section *sec;
-	Elf_Scn *s;
-
-	sec = find_section_by_name(elf, ".altinstructions");
-	if (!sec) {
-		sec = elf_create_section(elf, ".altinstructions",
-					 SHF_ALLOC, 0, 0);
-
-		if (!sec) {
-			WARN_ELF("elf_create_section");
-			return -1;
-		}
-	}
-
-	s = elf_getscn(elf->elf, sec->idx);
-	if (!s) {
-		WARN_ELF("elf_getscn");
-		return -1;
-	}
-
-	sec->data = elf_newdata(s);
-	if (!sec->data) {
-		WARN_ELF("elf_newdata");
-		return -1;
-	}
-
-	sec->data->d_size = size;
-	sec->data->d_align = 1;
-
-	alt = sec->data->d_buf = malloc(size);
-	if (!sec->data->d_buf) {
-		perror("malloc");
-		return -1;
-	}
-	memset(sec->data->d_buf, 0, size);
-
-	if (elf_add_reloc_to_insn(elf, sec, sec->sh.sh_size,
-				  R_X86_64_PC32, orig->sec, orig->offset)) {
-		WARN("elf_create_reloc: alt_instr::instr_offset");
-		return -1;
-	}
-
-	if (elf_add_reloc(elf, sec, sec->sh.sh_size + 4,
-			  R_X86_64_PC32, sym, 0)) {
-		WARN("elf_create_reloc: alt_instr::repl_offset");
-		return -1;
-	}
-
-	alt->cpuid = bswap_if_needed(cpuid);
-	alt->instrlen = orig_len;
-	alt->replacementlen = repl_len;
-
-	sec->sh.sh_size += size;
-	sec->changed = true;
-
-	return 0;
-}
-
-#define X86_FEATURE_RETPOLINE                ( 7*32+12)
-
-int arch_rewrite_retpolines(struct objtool_file *file)
-{
-	struct instruction *insn;
-	struct reloc *reloc;
-	struct symbol *sym;
-	char name[32] = "";
-
-	list_for_each_entry(insn, &file->retpoline_call_list, call_node) {
-
-		if (insn->type != INSN_JUMP_DYNAMIC &&
-		    insn->type != INSN_CALL_DYNAMIC)
-			continue;
-
-		if (!strcmp(insn->sec->name, ".text.__x86.indirect_thunk"))
-			continue;
-
-		reloc = insn->reloc;
-
-		sprintf(name, "__x86_indirect_alt_%s_%s",
-			insn->type == INSN_JUMP_DYNAMIC ? "jmp" : "call",
-			reloc->sym->name + 21);
-
-		sym = find_symbol_by_name(file->elf, name);
-		if (!sym) {
-			sym = elf_create_undef_symbol(file->elf, name);
-			if (!sym) {
-				WARN("elf_create_undef_symbol");
-				return -1;
-			}
-		}
-
-		if (elf_add_alternative(file->elf, insn, sym,
-					ALT_NOT(X86_FEATURE_RETPOLINE), 5, 5)) {
-			WARN("elf_add_alternative");
-			return -1;
-		}
-	}
-
-	return 0;
-}
-
-int arch_decode_hint_reg(struct instruction *insn, u8 sp_reg)
-{
-	struct cfi_reg *cfa = &insn->cfi.cfa;
-
 	switch (sp_reg) {
 	case ORC_REG_UNDEFINED:
-		cfa->base = CFI_UNDEFINED;
+		*base = CFI_UNDEFINED;
 		break;
 	case ORC_REG_SP:
-		cfa->base = CFI_SP;
+		*base = CFI_SP;
 		break;
 	case ORC_REG_BP:
-		cfa->base = CFI_BP;
+		*base = CFI_BP;
 		break;
 	case ORC_REG_SP_INDIRECT:
-		cfa->base = CFI_SP_INDIRECT;
+		*base = CFI_SP_INDIRECT;
 		break;
 	case ORC_REG_R10:
-		cfa->base = CFI_R10;
+		*base = CFI_R10;
 		break;
 	case ORC_REG_R13:
-		cfa->base = CFI_R13;
+		*base = CFI_R13;
 		break;
 	case ORC_REG_DI:
-		cfa->base = CFI_DI;
+		*base = CFI_DI;
 		break;
 	case ORC_REG_DX:
-		cfa->base = CFI_DX;
+		*base = CFI_DX;
 		break;
 	default:
 		return -1;
@@ -844,3 +722,8 @@ bool arch_is_retpoline(struct symbol *sym)
 {
 	return !strncmp(sym->name, "__x86_indirect_", 15);
 }
+
+bool arch_is_rethunk(struct symbol *sym)
+{
+	return !strcmp(sym->name, "__x86_return_thunk");
+}
diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c
index 38070f26105b..35081fe37320 100644
--- a/tools/objtool/builtin-check.c
+++ b/tools/objtool/builtin-check.c
@@ -20,7 +20,7 @@
 #include <objtool/objtool.h>
 
 bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess, stats,
-     validate_dup, vmlinux, mcount, noinstr, backup, sls;
+     validate_dup, vmlinux, mcount, noinstr, backup, sls, unret, rethunk;
 
 static const char * const check_usage[] = {
 	"objtool check [<options>] file.o",
@@ -36,6 +36,8 @@ const struct option check_options[] = {
 	OPT_BOOLEAN('f', "no-fp", &no_fp, "Skip frame pointer validation"),
 	OPT_BOOLEAN('u', "no-unreachable", &no_unreachable, "Skip 'unreachable instruction' warnings"),
 	OPT_BOOLEAN('r', "retpoline", &retpoline, "Validate retpoline assumptions"),
+	OPT_BOOLEAN(0,   "rethunk", &rethunk, "validate and annotate rethunk usage"),
+	OPT_BOOLEAN(0,   "unret", &unret, "validate entry unret placement"),
 	OPT_BOOLEAN('m', "module", &module, "Indicates the object will be part of a kernel module"),
 	OPT_BOOLEAN('b', "backtrace", &backtrace, "unwind on error"),
 	OPT_BOOLEAN('a', "uaccess", &uaccess, "enable uaccess checking"),
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 8b3435af989a..72e5d23f1ad8 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -6,6 +6,7 @@
 #include <string.h>
 #include <stdlib.h>
 #include <inttypes.h>
+#include <sys/mman.h>
 
 #include <arch/elf.h>
 #include <objtool/builtin.h>
@@ -27,7 +28,11 @@ struct alternative {
 	bool skip_orig;
 };
 
-struct cfi_init_state initial_func_cfi;
+static unsigned long nr_cfi, nr_cfi_reused, nr_cfi_cache;
+
+static struct cfi_init_state initial_func_cfi;
+static struct cfi_state init_cfi;
+static struct cfi_state func_cfi;
 
 struct instruction *find_insn(struct objtool_file *file,
 			      struct section *sec, unsigned long offset)
@@ -267,6 +272,78 @@ static void init_insn_state(struct insn_state *state, struct section *sec)
 		state->noinstr = sec->noinstr;
 }
 
+static struct cfi_state *cfi_alloc(void)
+{
+	struct cfi_state *cfi = calloc(sizeof(struct cfi_state), 1);
+	if (!cfi) {
+		WARN("calloc failed");
+		exit(1);
+	}
+	nr_cfi++;
+	return cfi;
+}
+
+static int cfi_bits;
+static struct hlist_head *cfi_hash;
+
+static inline bool cficmp(struct cfi_state *cfi1, struct cfi_state *cfi2)
+{
+	return memcmp((void *)cfi1 + sizeof(cfi1->hash),
+		      (void *)cfi2 + sizeof(cfi2->hash),
+		      sizeof(struct cfi_state) - sizeof(struct hlist_node));
+}
+
+static inline u32 cfi_key(struct cfi_state *cfi)
+{
+	return jhash((void *)cfi + sizeof(cfi->hash),
+		     sizeof(*cfi) - sizeof(cfi->hash), 0);
+}
+
+static struct cfi_state *cfi_hash_find_or_add(struct cfi_state *cfi)
+{
+	struct hlist_head *head = &cfi_hash[hash_min(cfi_key(cfi), cfi_bits)];
+	struct cfi_state *obj;
+
+	hlist_for_each_entry(obj, head, hash) {
+		if (!cficmp(cfi, obj)) {
+			nr_cfi_cache++;
+			return obj;
+		}
+	}
+
+	obj = cfi_alloc();
+	*obj = *cfi;
+	hlist_add_head(&obj->hash, head);
+
+	return obj;
+}
+
+static void cfi_hash_add(struct cfi_state *cfi)
+{
+	struct hlist_head *head = &cfi_hash[hash_min(cfi_key(cfi), cfi_bits)];
+
+	hlist_add_head(&cfi->hash, head);
+}
+
+static void *cfi_hash_alloc(unsigned long size)
+{
+	cfi_bits = max(10, ilog2(size));
+	cfi_hash = mmap(NULL, sizeof(struct hlist_head) << cfi_bits,
+			PROT_READ|PROT_WRITE,
+			MAP_PRIVATE|MAP_ANON, -1, 0);
+	if (cfi_hash == (void *)-1L) {
+		WARN("mmap fail cfi_hash");
+		cfi_hash = NULL;
+	}  else if (stats) {
+		printf("cfi_bits: %d\n", cfi_bits);
+	}
+
+	return cfi_hash;
+}
+
+static unsigned long nr_insns;
+static unsigned long nr_insns_visited;
+
 /*
  * Call the arch-specific instruction decoder for all the instructions and add
  * them to the global instruction list.
@@ -277,7 +354,6 @@ static int decode_instructions(struct objtool_file *file)
 	struct symbol *func;
 	unsigned long offset;
 	struct instruction *insn;
-	unsigned long nr_insns = 0;
 	int ret;
 
 	for_each_sec(file, sec) {
@@ -291,7 +367,8 @@ static int decode_instructions(struct objtool_file *file)
 			sec->text = true;
 
 		if (!strcmp(sec->name, ".noinstr.text") ||
-		    !strcmp(sec->name, ".entry.text"))
+		    !strcmp(sec->name, ".entry.text") ||
+		    !strncmp(sec->name, ".text.__x86.", 12))
 			sec->noinstr = true;
 
 		for (offset = 0; offset < sec->sh.sh_size; offset += insn->len) {
@@ -303,7 +380,6 @@ static int decode_instructions(struct objtool_file *file)
 			memset(insn, 0, sizeof(*insn));
 			INIT_LIST_HEAD(&insn->alts);
 			INIT_LIST_HEAD(&insn->stack_ops);
-			init_cfi_state(&insn->cfi);
 
 			insn->sec = sec;
 			insn->offset = offset;
@@ -533,6 +609,98 @@ static int create_static_call_sections(struct objtool_file *file)
 	return 0;
 }
 
+static int create_retpoline_sites_sections(struct objtool_file *file)
+{
+	struct instruction *insn;
+	struct section *sec;
+	int idx;
+
+	sec = find_section_by_name(file->elf, ".retpoline_sites");
+	if (sec) {
+		WARN("file already has .retpoline_sites, skipping");
+		return 0;
+	}
+
+	idx = 0;
+	list_for_each_entry(insn, &file->retpoline_call_list, call_node)
+		idx++;
+
+	if (!idx)
+		return 0;
+
+	sec = elf_create_section(file->elf, ".retpoline_sites", 0,
+				 sizeof(int), idx);
+	if (!sec) {
+		WARN("elf_create_section: .retpoline_sites");
+		return -1;
+	}
+
+	idx = 0;
+	list_for_each_entry(insn, &file->retpoline_call_list, call_node) {
+
+		int *site = (int *)sec->data->d_buf + idx;
+		*site = 0;
+
+		if (elf_add_reloc_to_insn(file->elf, sec,
+					  idx * sizeof(int),
+					  R_X86_64_PC32,
+					  insn->sec, insn->offset)) {
+			WARN("elf_add_reloc_to_insn: .retpoline_sites");
+			return -1;
+		}
+
+		idx++;
+	}
+
+	return 0;
+}
+
+static int create_return_sites_sections(struct objtool_file *file)
+{
+	struct instruction *insn;
+	struct section *sec;
+	int idx;
+
+	sec = find_section_by_name(file->elf, ".return_sites");
+	if (sec) {
+		WARN("file already has .return_sites, skipping");
+		return 0;
+	}
+
+	idx = 0;
+	list_for_each_entry(insn, &file->return_thunk_list, call_node)
+		idx++;
+
+	if (!idx)
+		return 0;
+
+	sec = elf_create_section(file->elf, ".return_sites", 0,
+				 sizeof(int), idx);
+	if (!sec) {
+		WARN("elf_create_section: .return_sites");
+		return -1;
+	}
+
+	idx = 0;
+	list_for_each_entry(insn, &file->return_thunk_list, call_node) {
+
+		int *site = (int *)sec->data->d_buf + idx;
+		*site = 0;
+
+		if (elf_add_reloc_to_insn(file->elf, sec,
+					  idx * sizeof(int),
+					  R_X86_64_PC32,
+					  insn->sec, insn->offset)) {
+			WARN("elf_add_reloc_to_insn: .return_sites");
+			return -1;
+		}
+
+		idx++;
+	}
+
+	return 0;
+}
+
 static int create_mcount_loc_sections(struct objtool_file *file)
 {
 	struct section *sec;
@@ -551,7 +719,7 @@ static int create_mcount_loc_sections(struct objtool_file *file)
 		return 0;
 
 	idx = 0;
-	list_for_each_entry(insn, &file->mcount_loc_list, mcount_loc_node)
+	list_for_each_entry(insn, &file->mcount_loc_list, call_node)
 		idx++;
 
 	sec = elf_create_section(file->elf, "__mcount_loc", 0, sizeof(unsigned long), idx);
@@ -559,7 +727,7 @@ static int create_mcount_loc_sections(struct objtool_file *file)
 		return -1;
 
 	idx = 0;
-	list_for_each_entry(insn, &file->mcount_loc_list, mcount_loc_node) {
+	list_for_each_entry(insn, &file->mcount_loc_list, call_node) {
 
 		loc = (unsigned long *)sec->data->d_buf + idx;
 		memset(loc, 0, sizeof(unsigned long));
@@ -811,6 +979,11 @@ __weak bool arch_is_retpoline(struct symbol *sym)
 	return false;
 }
 
+__weak bool arch_is_rethunk(struct symbol *sym)
+{
+	return false;
+}
+
 #define NEGATIVE_RELOC	((void *)-1L)
 
 static struct reloc *insn_reloc(struct objtool_file *file, struct instruction *insn)
@@ -840,18 +1013,32 @@ static void remove_insn_ops(struct instruction *insn)
 	}
 }
 
-static void add_call_dest(struct objtool_file *file, struct instruction *insn,
-			  struct symbol *dest, bool sibling)
+static void annotate_call_site(struct objtool_file *file,
+			       struct instruction *insn, bool sibling)
 {
 	struct reloc *reloc = insn_reloc(file, insn);
+	struct symbol *sym = insn->call_dest;
 
-	insn->call_dest = dest;
-	if (!dest)
+	if (!sym)
+		sym = reloc->sym;
+
+	/*
+	 * Alternative replacement code is just template code which is
+	 * sometimes copied to the original instruction. For now, don't
+	 * annotate it. (In the future we might consider annotating the
+	 * original instruction if/when it ever makes sense to do so.)
+	 */
+	if (!strcmp(insn->sec->name, ".altinstr_replacement"))
 		return;
 
-	if (insn->call_dest->static_call_tramp) {
-		list_add_tail(&insn->call_node,
-			      &file->static_call_list);
+	if (sym->static_call_tramp) {
+		list_add_tail(&insn->call_node, &file->static_call_list);
+		return;
+	}
+
+	if (sym->retpoline_thunk) {
+		list_add_tail(&insn->call_node, &file->retpoline_call_list);
+		return;
 	}
 
 	/*
@@ -859,8 +1046,7 @@ static void add_call_dest(struct objtool_file *file, struct instruction *insn,
 	 * so they need a little help, NOP out any KCOV calls from noinstr
 	 * text.
 	 */
-	if (insn->sec->noinstr &&
-	    !strncmp(insn->call_dest->name, "__sanitizer_cov_", 16)) {
+	if (insn->sec->noinstr && sym->kcov) {
 		if (reloc) {
 			reloc->type = R_NONE;
 			elf_write_reloc(file->elf, reloc);
@@ -882,9 +1068,11 @@ static void add_call_dest(struct objtool_file *file, struct instruction *insn,
 			 */
 			insn->retpoline_safe = true;
 		}
+
+		return;
 	}
 
-	if (mcount && !strcmp(insn->call_dest->name, "__fentry__")) {
+	if (mcount && sym->fentry) {
 		if (sibling)
 			WARN_FUNC("Tail call to __fentry__ !?!?", insn->sec, insn->offset);
 
@@ -899,9 +1087,17 @@ static void add_call_dest(struct objtool_file *file, struct instruction *insn,
 
 		insn->type = INSN_NOP;
 
-		list_add_tail(&insn->mcount_loc_node,
-			      &file->mcount_loc_list);
+		list_add_tail(&insn->call_node, &file->mcount_loc_list);
+		return;
 	}
+}
+
+static void add_call_dest(struct objtool_file *file, struct instruction *insn,
+			  struct symbol *dest, bool sibling)
+{
+	insn->call_dest = dest;
+	if (!dest)
+		return;
 
 	/*
 	 * Whatever stack impact regular CALLs have, should be undone
@@ -911,6 +1107,56 @@ static void add_call_dest(struct objtool_file *file, struct instruction *insn,
 	 * are converted to JUMP, see read_intra_function_calls().
 	 */
 	remove_insn_ops(insn);
+
+	annotate_call_site(file, insn, sibling);
+}
+
+static void add_retpoline_call(struct objtool_file *file, struct instruction *insn)
+{
+	/*
+	 * Retpoline calls/jumps are really dynamic calls/jumps in disguise,
+	 * so convert them accordingly.
+	 */
+	switch (insn->type) {
+	case INSN_CALL:
+		insn->type = INSN_CALL_DYNAMIC;
+		break;
+	case INSN_JUMP_UNCONDITIONAL:
+		insn->type = INSN_JUMP_DYNAMIC;
+		break;
+	case INSN_JUMP_CONDITIONAL:
+		insn->type = INSN_JUMP_DYNAMIC_CONDITIONAL;
+		break;
+	default:
+		return;
+	}
+
+	insn->retpoline_safe = true;
+
+	/*
+	 * Whatever stack impact regular CALLs have, should be undone
+	 * by the RETURN of the called function.
+	 *
+	 * Annotated intra-function calls retain the stack_ops but
+	 * are converted to JUMP, see read_intra_function_calls().
+	 */
+	remove_insn_ops(insn);
+
+	annotate_call_site(file, insn, false);
+}
+
+static void add_return_call(struct objtool_file *file, struct instruction *insn, bool add)
+{
+	/*
+	 * Return thunk tail calls are really just returns in disguise,
+	 * so convert them accordingly.
+	 */
+	insn->type = INSN_RETURN;
+	insn->retpoline_safe = true;
+
+	/* Skip the non-text sections, specially .discard ones */
+	if (add && insn->sec->text)
+		list_add_tail(&insn->call_node, &file->return_thunk_list);
 }
 
 /*
@@ -934,20 +1180,11 @@ static int add_jump_destinations(struct objtool_file *file)
 		} else if (reloc->sym->type == STT_SECTION) {
 			dest_sec = reloc->sym->sec;
 			dest_off = arch_dest_reloc_offset(reloc->addend);
-		} else if (arch_is_retpoline(reloc->sym)) {
-			/*
-			 * Retpoline jumps are really dynamic jumps in
-			 * disguise, so convert them accordingly.
-			 */
-			if (insn->type == INSN_JUMP_UNCONDITIONAL)
-				insn->type = INSN_JUMP_DYNAMIC;
-			else
-				insn->type = INSN_JUMP_DYNAMIC_CONDITIONAL;
-
-			list_add_tail(&insn->call_node,
-				      &file->retpoline_call_list);
-
-			insn->retpoline_safe = true;
+		} else if (reloc->sym->retpoline_thunk) {
+			add_retpoline_call(file, insn);
+			continue;
+		} else if (reloc->sym->return_thunk) {
+			add_return_call(file, insn, true);
 			continue;
 		} else if (insn->func) {
 			/* internal or external sibling call (with reloc) */
@@ -964,6 +1201,7 @@ static int add_jump_destinations(struct objtool_file *file)
 
 		insn->jump_dest = find_insn(file, dest_sec, dest_off);
 		if (!insn->jump_dest) {
+			struct symbol *sym = find_symbol_by_offset(dest_sec, dest_off);
 
 			/*
 			 * This is a special case where an alt instruction
@@ -973,6 +1211,19 @@ static int add_jump_destinations(struct objtool_file *file)
 			if (!strcmp(insn->sec->name, ".altinstr_replacement"))
 				continue;
 
+			/*
+			 * This is a special case for zen_untrain_ret().
+			 * It jumps to __x86_return_thunk(), but objtool
+			 * can't find the thunk's starting RET
+			 * instruction, because the RET is also in the
+			 * middle of another instruction.  Objtool only
+			 * knows about the outer instruction.
+			 */
+			if (sym && sym->return_thunk) {
+				add_return_call(file, insn, false);
+				continue;
+			}
+
 			WARN_FUNC("can't find jump dest instruction at %s+0x%lx",
 				  insn->sec, insn->offset, dest_sec->name,
 				  dest_off);
@@ -1075,19 +1326,8 @@ static int add_call_destinations(struct objtool_file *file)
 
 			add_call_dest(file, insn, dest, false);
 
-		} else if (arch_is_retpoline(reloc->sym)) {
-			/*
-			 * Retpoline calls are really dynamic calls in
-			 * disguise, so convert them accordingly.
-			 */
-			insn->type = INSN_CALL_DYNAMIC;
-			insn->retpoline_safe = true;
-
-			list_add_tail(&insn->call_node,
-				      &file->retpoline_call_list);
-
-			remove_insn_ops(insn);
-			continue;
+		} else if (reloc->sym->retpoline_thunk) {
+			add_retpoline_call(file, insn);
 
 		} else
 			add_call_dest(file, insn, reloc->sym, false);
@@ -1158,7 +1398,6 @@ static int handle_group_alt(struct objtool_file *file,
 		memset(nop, 0, sizeof(*nop));
 		INIT_LIST_HEAD(&nop->alts);
 		INIT_LIST_HEAD(&nop->stack_ops);
-		init_cfi_state(&nop->cfi);
 
 		nop->sec = special_alt->new_sec;
 		nop->offset = special_alt->new_off + special_alt->new_len;
@@ -1567,10 +1806,11 @@ static void set_func_state(struct cfi_state *state)
 
 static int read_unwind_hints(struct objtool_file *file)
 {
+	struct cfi_state cfi = init_cfi;
 	struct section *sec, *relocsec;
-	struct reloc *reloc;
 	struct unwind_hint *hint;
 	struct instruction *insn;
+	struct reloc *reloc;
 	int i;
 
 	sec = find_section_by_name(file->elf, ".discard.unwind_hints");
@@ -1607,20 +1847,49 @@ static int read_unwind_hints(struct objtool_file *file)
 
 		insn->hint = true;
 
+		if (hint->type == UNWIND_HINT_TYPE_SAVE) {
+			insn->hint = false;
+			insn->save = true;
+			continue;
+		}
+
+		if (hint->type == UNWIND_HINT_TYPE_RESTORE) {
+			insn->restore = true;
+			continue;
+		}
+
+		if (hint->type == UNWIND_HINT_TYPE_REGS_PARTIAL) {
+			struct symbol *sym = find_symbol_by_offset(insn->sec, insn->offset);
+
+			if (sym && sym->bind == STB_GLOBAL) {
+				insn->entry = 1;
+			}
+		}
+
+		if (hint->type == UNWIND_HINT_TYPE_ENTRY) {
+			hint->type = UNWIND_HINT_TYPE_CALL;
+			insn->entry = 1;
+		}
+
 		if (hint->type == UNWIND_HINT_TYPE_FUNC) {
-			set_func_state(&insn->cfi);
+			insn->cfi = &func_cfi;
 			continue;
 		}
 
-		if (arch_decode_hint_reg(insn, hint->sp_reg)) {
+		if (insn->cfi)
+			cfi = *(insn->cfi);
+
+		if (arch_decode_hint_reg(hint->sp_reg, &cfi.cfa.base)) {
 			WARN_FUNC("unsupported unwind_hint sp base reg %d",
 				  insn->sec, insn->offset, hint->sp_reg);
 			return -1;
 		}
 
-		insn->cfi.cfa.offset = bswap_if_needed(hint->sp_offset);
-		insn->cfi.type = hint->type;
-		insn->cfi.end = hint->end;
+		cfi.cfa.offset = bswap_if_needed(hint->sp_offset);
+		cfi.type = hint->type;
+		cfi.end = hint->end;
+
+		insn->cfi = cfi_hash_find_or_add(&cfi);
 	}
 
 	return 0;
@@ -1649,8 +1918,10 @@ static int read_retpoline_hints(struct objtool_file *file)
 		}
 
 		if (insn->type != INSN_JUMP_DYNAMIC &&
-		    insn->type != INSN_CALL_DYNAMIC) {
-			WARN_FUNC("retpoline_safe hint not an indirect jump/call",
+		    insn->type != INSN_CALL_DYNAMIC &&
+		    insn->type != INSN_RETURN &&
+		    insn->type != INSN_NOP) {
+			WARN_FUNC("retpoline_safe hint not an indirect jump/call/ret/nop",
 				  insn->sec, insn->offset);
 			return -1;
 		}
@@ -1759,17 +2030,31 @@ static int read_intra_function_calls(struct objtool_file *file)
 	return 0;
 }
 
-static int read_static_call_tramps(struct objtool_file *file)
+static int classify_symbols(struct objtool_file *file)
 {
 	struct section *sec;
 	struct symbol *func;
 
 	for_each_sec(file, sec) {
 		list_for_each_entry(func, &sec->symbol_list, list) {
-			if (func->bind == STB_GLOBAL &&
-			    !strncmp(func->name, STATIC_CALL_TRAMP_PREFIX_STR,
+			if (func->bind != STB_GLOBAL)
+				continue;
+
+			if (!strncmp(func->name, STATIC_CALL_TRAMP_PREFIX_STR,
 				     strlen(STATIC_CALL_TRAMP_PREFIX_STR)))
 				func->static_call_tramp = true;
+
+			if (arch_is_retpoline(func))
+				func->retpoline_thunk = true;
+
+			if (arch_is_rethunk(func))
+				func->return_thunk = true;
+
+			if (!strcmp(func->name, "__fentry__"))
+				func->fentry = true;
+
+			if (!strncmp(func->name, "__sanitizer_cov_", 16))
+				func->kcov = true;
 		}
 	}
 
@@ -1802,11 +2087,6 @@ static void mark_rodata(struct objtool_file *file)
 	file->rodata = found;
 }
 
-__weak int arch_rewrite_retpolines(struct objtool_file *file)
-{
-	return 0;
-}
-
 static int decode_sections(struct objtool_file *file)
 {
 	int ret;
@@ -1831,7 +2111,7 @@ static int decode_sections(struct objtool_file *file)
 	/*
 	 * Must be before add_{jump_call}_destination.
 	 */
-	ret = read_static_call_tramps(file);
+	ret = classify_symbols(file);
 	if (ret)
 		return ret;
 
@@ -1875,23 +2155,14 @@ static int decode_sections(struct objtool_file *file)
 	if (ret)
 		return ret;
 
-	/*
-	 * Must be after add_special_section_alts(), since this will emit
-	 * alternatives. Must be after add_{jump,call}_destination(), since
-	 * those create the call insn lists.
-	 */
-	ret = arch_rewrite_retpolines(file);
-	if (ret)
-		return ret;
-
 	return 0;
 }
 
 static bool is_fentry_call(struct instruction *insn)
 {
-	if (insn->type == INSN_CALL && insn->call_dest &&
-	    insn->call_dest->type == STT_NOTYPE &&
-	    !strcmp(insn->call_dest->name, "__fentry__"))
+	if (insn->type == INSN_CALL &&
+	    insn->call_dest &&
+	    insn->call_dest->fentry)
 		return true;
 
 	return false;
@@ -2474,13 +2745,18 @@ static int propagate_alt_cfi(struct objtool_file *file, struct instruction *insn
 	if (!insn->alt_group)
 		return 0;
 
+	if (!insn->cfi) {
+		WARN("CFI missing");
+		return -1;
+	}
+
 	alt_cfi = insn->alt_group->cfi;
 	group_off = insn->offset - insn->alt_group->first_insn->offset;
 
 	if (!alt_cfi[group_off]) {
-		alt_cfi[group_off] = &insn->cfi;
+		alt_cfi[group_off] = insn->cfi;
 	} else {
-		if (memcmp(alt_cfi[group_off], &insn->cfi, sizeof(struct cfi_state))) {
+		if (cficmp(alt_cfi[group_off], insn->cfi)) {
 			WARN_FUNC("stack layout conflict in alternatives",
 				  insn->sec, insn->offset);
 			return -1;
@@ -2531,9 +2807,14 @@ static int handle_insn_ops(struct instruction *insn,
 
 static bool insn_cfi_match(struct instruction *insn, struct cfi_state *cfi2)
 {
-	struct cfi_state *cfi1 = &insn->cfi;
+	struct cfi_state *cfi1 = insn->cfi;
 	int i;
 
+	if (!cfi1) {
+		WARN("CFI missing");
+		return false;
+	}
+
 	if (memcmp(&cfi1->cfa, &cfi2->cfa, sizeof(cfi1->cfa))) {
 
 		WARN_FUNC("stack state mismatch: cfa1=%d%+d cfa2=%d%+d",
@@ -2718,7 +2999,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
 			   struct instruction *insn, struct insn_state state)
 {
 	struct alternative *alt;
-	struct instruction *next_insn;
+	struct instruction *next_insn, *prev_insn = NULL;
 	struct section *sec;
 	u8 visited;
 	int ret;
@@ -2740,22 +3021,61 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
 			return 1;
 		}
 
-		visited = 1 << state.uaccess;
-		if (insn->visited) {
+		visited = VISITED_BRANCH << state.uaccess;
+		if (insn->visited & VISITED_BRANCH_MASK) {
 			if (!insn->hint && !insn_cfi_match(insn, &state.cfi))
 				return 1;
 
 			if (insn->visited & visited)
 				return 0;
+		} else {
+			nr_insns_visited++;
 		}
 
 		if (state.noinstr)
 			state.instr += insn->instr;
 
-		if (insn->hint)
-			state.cfi = insn->cfi;
-		else
-			insn->cfi = state.cfi;
+		if (insn->hint) {
+			if (insn->restore) {
+				struct instruction *save_insn, *i;
+
+				i = insn;
+				save_insn = NULL;
+
+				sym_for_each_insn_continue_reverse(file, func, i) {
+					if (i->save) {
+						save_insn = i;
+						break;
+					}
+				}
+
+				if (!save_insn) {
+					WARN_FUNC("no corresponding CFI save for CFI restore",
+						  sec, insn->offset);
+					return 1;
+				}
+
+				if (!save_insn->visited) {
+					WARN_FUNC("objtool isn't smart enough to handle this CFI save/restore combo",
+						  sec, insn->offset);
+					return 1;
+				}
+
+				insn->cfi = save_insn->cfi;
+				nr_cfi_reused++;
+			}
+
+			state.cfi = *insn->cfi;
+		} else {
+			/* XXX track if we actually changed state.cfi */
+
+			if (prev_insn && !cficmp(prev_insn->cfi, &state.cfi)) {
+				insn->cfi = prev_insn->cfi;
+				nr_cfi_reused++;
+			} else {
+				insn->cfi = cfi_hash_find_or_add(&state.cfi);
+			}
+		}
 
 		insn->visited |= visited;
 
@@ -2787,9 +3107,8 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
 		switch (insn->type) {
 
 		case INSN_RETURN:
-			if (next_insn && next_insn->type == INSN_TRAP) {
-				next_insn->ignore = true;
-			} else if (sls && !insn->retpoline_safe) {
+			if (sls && !insn->retpoline_safe &&
+			    next_insn && next_insn->type != INSN_TRAP) {
 				WARN_FUNC("missing int3 after ret",
 					  insn->sec, insn->offset);
 			}
@@ -2836,9 +3155,8 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
 			break;
 
 		case INSN_JUMP_DYNAMIC:
-			if (next_insn && next_insn->type == INSN_TRAP) {
-				next_insn->ignore = true;
-			} else if (sls && !insn->retpoline_safe) {
+			if (sls && !insn->retpoline_safe &&
+			    next_insn && next_insn->type != INSN_TRAP) {
 				WARN_FUNC("missing int3 after indirect jump",
 					  insn->sec, insn->offset);
 			}
@@ -2919,6 +3237,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
 			return 1;
 		}
 
+		prev_insn = insn;
 		insn = next_insn;
 	}
 
@@ -2958,6 +3277,145 @@ static int validate_unwind_hints(struct objtool_file *file, struct section *sec)
 	return warnings;
 }
 
+/*
+ * Validate rethunk entry constraint: must untrain RET before the first RET.
+ *
+ * Follow every branch (intra-function) and ensure ANNOTATE_UNRET_END comes
+ * before an actual RET instruction.
+ */
+static int validate_entry(struct objtool_file *file, struct instruction *insn)
+{
+	struct instruction *next, *dest;
+	int ret, warnings = 0;
+
+	for (;;) {
+		next = next_insn_to_validate(file, insn);
+
+		if (insn->visited & VISITED_ENTRY)
+			return 0;
+
+		insn->visited |= VISITED_ENTRY;
+
+		if (!insn->ignore_alts && !list_empty(&insn->alts)) {
+			struct alternative *alt;
+			bool skip_orig = false;
+
+			list_for_each_entry(alt, &insn->alts, list) {
+				if (alt->skip_orig)
+					skip_orig = true;
+
+				ret = validate_entry(file, alt->insn);
+				if (ret) {
+				        if (backtrace)
+						BT_FUNC("(alt)", insn);
+					return ret;
+				}
+			}
+
+			if (skip_orig)
+				return 0;
+		}
+
+		switch (insn->type) {
+
+		case INSN_CALL_DYNAMIC:
+		case INSN_JUMP_DYNAMIC:
+		case INSN_JUMP_DYNAMIC_CONDITIONAL:
+			WARN_FUNC("early indirect call", insn->sec, insn->offset);
+			return 1;
+
+		case INSN_JUMP_UNCONDITIONAL:
+		case INSN_JUMP_CONDITIONAL:
+			if (!is_sibling_call(insn)) {
+				if (!insn->jump_dest) {
+					WARN_FUNC("unresolved jump target after linking?!?",
+						  insn->sec, insn->offset);
+					return -1;
+				}
+				ret = validate_entry(file, insn->jump_dest);
+				if (ret) {
+					if (backtrace) {
+						BT_FUNC("(branch%s)", insn,
+							insn->type == INSN_JUMP_CONDITIONAL ? "-cond" : "");
+					}
+					return ret;
+				}
+
+				if (insn->type == INSN_JUMP_UNCONDITIONAL)
+					return 0;
+
+				break;
+			}
+
+			/* fallthrough */
+		case INSN_CALL:
+			dest = find_insn(file, insn->call_dest->sec,
+					 insn->call_dest->offset);
+			if (!dest) {
+				WARN("Unresolved function after linking!?: %s",
+				     insn->call_dest->name);
+				return -1;
+			}
+
+			ret = validate_entry(file, dest);
+			if (ret) {
+				if (backtrace)
+					BT_FUNC("(call)", insn);
+				return ret;
+			}
+			/*
+			 * If a call returns without error, it must have seen UNTRAIN_RET.
+			 * Therefore any non-error return is a success.
+			 */
+			return 0;
+
+		case INSN_RETURN:
+			WARN_FUNC("RET before UNTRAIN", insn->sec, insn->offset);
+			return 1;
+
+		case INSN_NOP:
+			if (insn->retpoline_safe)
+				return 0;
+			break;
+
+		default:
+			break;
+		}
+
+		if (!next) {
+			WARN_FUNC("teh end!", insn->sec, insn->offset);
+			return -1;
+		}
+		insn = next;
+	}
+
+	return warnings;
+}
+
+/*
+ * Validate that all branches starting at 'insn->entry' encounter UNRET_END
+ * before RET.
+ */
+static int validate_unret(struct objtool_file *file)
+{
+	struct instruction *insn;
+	int ret, warnings = 0;
+
+	for_each_insn(file, insn) {
+		if (!insn->entry)
+			continue;
+
+		ret = validate_entry(file, insn);
+		if (ret < 0) {
+			WARN_FUNC("Failed UNRET validation", insn->sec, insn->offset);
+			return ret;
+		}
+		warnings += ret;
+	}
+
+	return warnings;
+}
+
 static int validate_retpoline(struct objtool_file *file)
 {
 	struct instruction *insn;
@@ -2965,7 +3423,8 @@ static int validate_retpoline(struct objtool_file *file)
 
 	for_each_insn(file, insn) {
 		if (insn->type != INSN_JUMP_DYNAMIC &&
-		    insn->type != INSN_CALL_DYNAMIC)
+		    insn->type != INSN_CALL_DYNAMIC &&
+		    insn->type != INSN_RETURN)
 			continue;
 
 		if (insn->retpoline_safe)
@@ -2980,9 +3439,17 @@ static int validate_retpoline(struct objtool_file *file)
 		if (!strcmp(insn->sec->name, ".init.text") && !module)
 			continue;
 
-		WARN_FUNC("indirect %s found in RETPOLINE build",
-			  insn->sec, insn->offset,
-			  insn->type == INSN_JUMP_DYNAMIC ? "jump" : "call");
+		if (insn->type == INSN_RETURN) {
+			if (rethunk) {
+				WARN_FUNC("'naked' return found in RETHUNK build",
+					  insn->sec, insn->offset);
+			} else
+				continue;
+		} else {
+			WARN_FUNC("indirect %s found in RETPOLINE build",
+				  insn->sec, insn->offset,
+				  insn->type == INSN_JUMP_DYNAMIC ? "jump" : "call");
+		}
 
 		warnings++;
 	}
@@ -3008,7 +3475,7 @@ static bool ignore_unreachable_insn(struct objtool_file *file, struct instructio
 	int i;
 	struct instruction *prev_insn;
 
-	if (insn->ignore || insn->type == INSN_NOP)
+	if (insn->ignore || insn->type == INSN_NOP || insn->type == INSN_TRAP)
 		return true;
 
 	/*
@@ -3174,10 +3641,20 @@ int check(struct objtool_file *file)
 	int ret, warnings = 0;
 
 	arch_initial_func_cfi_state(&initial_func_cfi);
+	init_cfi_state(&init_cfi);
+	init_cfi_state(&func_cfi);
+	set_func_state(&func_cfi);
+
+	if (!cfi_hash_alloc(1UL << (file->elf->symbol_bits - 3)))
+		goto out;
+
+	cfi_hash_add(&init_cfi);
+	cfi_hash_add(&func_cfi);
 
 	ret = decode_sections(file);
 	if (ret < 0)
 		goto out;
+
 	warnings += ret;
 
 	if (list_empty(&file->insn_list))
@@ -3209,6 +3686,17 @@ int check(struct objtool_file *file)
 		goto out;
 	warnings += ret;
 
+	if (unret) {
+		/*
+		 * Must be after validate_branch() and friends, it plays
+		 * further games with insn->visited.
+		 */
+		ret = validate_unret(file);
+		if (ret < 0)
+			return ret;
+		warnings += ret;
+	}
+
 	if (!warnings) {
 		ret = validate_reachable_instructions(file);
 		if (ret < 0)
@@ -3221,6 +3709,20 @@ int check(struct objtool_file *file)
 		goto out;
 	warnings += ret;
 
+	if (retpoline) {
+		ret = create_retpoline_sites_sections(file);
+		if (ret < 0)
+			goto out;
+		warnings += ret;
+	}
+
+	if (rethunk) {
+		ret = create_return_sites_sections(file);
+		if (ret < 0)
+			goto out;
+		warnings += ret;
+	}
+
 	if (mcount) {
 		ret = create_mcount_loc_sections(file);
 		if (ret < 0)
@@ -3228,6 +3730,13 @@ int check(struct objtool_file *file)
 		warnings += ret;
 	}
 
+	if (stats) {
+		printf("nr_insns_visited: %ld\n", nr_insns_visited);
+		printf("nr_cfi: %ld\n", nr_cfi);
+		printf("nr_cfi_reused: %ld\n", nr_cfi_reused);
+		printf("nr_cfi_cache: %ld\n", nr_cfi_cache);
+	}
+
 out:
 	/*
 	 *  For now, don't fail the kernel build on fatal warnings.  These
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 2554f48c4ede..bc3005ef5af8 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -944,90 +944,6 @@ static int elf_add_string(struct elf *elf, struct section *strtab, char *str)
 	return len;
 }
 
-struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name)
-{
-	struct section *symtab, *symtab_shndx;
-	struct symbol *sym;
-	Elf_Data *data;
-	Elf_Scn *s;
-
-	sym = malloc(sizeof(*sym));
-	if (!sym) {
-		perror("malloc");
-		return NULL;
-	}
-	memset(sym, 0, sizeof(*sym));
-
-	sym->name = strdup(name);
-
-	sym->sym.st_name = elf_add_string(elf, NULL, sym->name);
-	if (sym->sym.st_name == -1)
-		return NULL;
-
-	sym->sym.st_info = GELF_ST_INFO(STB_GLOBAL, STT_NOTYPE);
-	// st_other 0
-	// st_shndx 0
-	// st_value 0
-	// st_size 0
-
-	symtab = find_section_by_name(elf, ".symtab");
-	if (!symtab) {
-		WARN("can't find .symtab");
-		return NULL;
-	}
-
-	s = elf_getscn(elf->elf, symtab->idx);
-	if (!s) {
-		WARN_ELF("elf_getscn");
-		return NULL;
-	}
-
-	data = elf_newdata(s);
-	if (!data) {
-		WARN_ELF("elf_newdata");
-		return NULL;
-	}
-
-	data->d_buf = &sym->sym;
-	data->d_size = sizeof(sym->sym);
-	data->d_align = 1;
-	data->d_type = ELF_T_SYM;
-
-	sym->idx = symtab->sh.sh_size / sizeof(sym->sym);
-
-	symtab->sh.sh_size += data->d_size;
-	symtab->changed = true;
-
-	symtab_shndx = find_section_by_name(elf, ".symtab_shndx");
-	if (symtab_shndx) {
-		s = elf_getscn(elf->elf, symtab_shndx->idx);
-		if (!s) {
-			WARN_ELF("elf_getscn");
-			return NULL;
-		}
-
-		data = elf_newdata(s);
-		if (!data) {
-			WARN_ELF("elf_newdata");
-			return NULL;
-		}
-
-		data->d_buf = &sym->sym.st_size; /* conveniently 0 */
-		data->d_size = sizeof(Elf32_Word);
-		data->d_align = 4;
-		data->d_type = ELF_T_WORD;
-
-		symtab_shndx->sh.sh_size += 4;
-		symtab_shndx->changed = true;
-	}
-
-	sym->sec = find_section_by_index(elf, 0);
-
-	elf_add_symbol(elf, sym);
-
-	return sym;
-}
-
 struct section *elf_create_section(struct elf *elf, const char *name,
 				   unsigned int sh_flags, size_t entsize, int nr)
 {
diff --git a/tools/objtool/include/objtool/arch.h b/tools/objtool/include/objtool/arch.h
index 9ca08d95e78e..8d57e3d1f763 100644
--- a/tools/objtool/include/objtool/arch.h
+++ b/tools/objtool/include/objtool/arch.h
@@ -85,9 +85,10 @@ unsigned long arch_dest_reloc_offset(int addend);
 const char *arch_nop_insn(int len);
 const char *arch_ret_insn(int len);
 
-int arch_decode_hint_reg(struct instruction *insn, u8 sp_reg);
+int arch_decode_hint_reg(u8 sp_reg, int *base);
 
 bool arch_is_retpoline(struct symbol *sym);
+bool arch_is_rethunk(struct symbol *sym);
 
 int arch_rewrite_retpolines(struct objtool_file *file);
 
diff --git a/tools/objtool/include/objtool/builtin.h b/tools/objtool/include/objtool/builtin.h
index 89ba869ed08f..66ad30ec5818 100644
--- a/tools/objtool/include/objtool/builtin.h
+++ b/tools/objtool/include/objtool/builtin.h
@@ -9,7 +9,7 @@
 
 extern const struct option check_options[];
 extern bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess, stats,
-            validate_dup, vmlinux, mcount, noinstr, backup, sls;
+            validate_dup, vmlinux, mcount, noinstr, backup, sls, unret, rethunk;
 
 extern int cmd_parse_options(int argc, const char **argv, const char * const usage[]);
 
diff --git a/tools/objtool/include/objtool/cfi.h b/tools/objtool/include/objtool/cfi.h
index fd5cb0bed9bf..f11d1ac1dadf 100644
--- a/tools/objtool/include/objtool/cfi.h
+++ b/tools/objtool/include/objtool/cfi.h
@@ -7,6 +7,7 @@
 #define _OBJTOOL_CFI_H
 
 #include <arch/cfi_regs.h>
+#include <linux/list.h>
 
 #define CFI_UNDEFINED		-1
 #define CFI_CFA			-2
@@ -24,6 +25,7 @@ struct cfi_init_state {
 };
 
 struct cfi_state {
+	struct hlist_node hash; /* must be first, cficmp() */
 	struct cfi_reg regs[CFI_NUM_REGS];
 	struct cfi_reg vals[CFI_NUM_REGS];
 	struct cfi_reg cfa;
diff --git a/tools/objtool/include/objtool/check.h b/tools/objtool/include/objtool/check.h
index 56d50bc50c10..4ba041db304f 100644
--- a/tools/objtool/include/objtool/check.h
+++ b/tools/objtool/include/objtool/check.h
@@ -40,7 +40,6 @@ struct instruction {
 	struct list_head list;
 	struct hlist_node hash;
 	struct list_head call_node;
-	struct list_head mcount_loc_node;
 	struct section *sec;
 	unsigned long offset;
 	unsigned int len;
@@ -48,7 +47,9 @@ struct instruction {
 	unsigned long immediate;
 	bool dead_end, ignore, ignore_alts;
 	bool hint;
+	bool save, restore;
 	bool retpoline_safe;
+	bool entry;
 	s8 instr;
 	u8 visited;
 	struct alt_group *alt_group;
@@ -60,9 +61,14 @@ struct instruction {
 	struct list_head alts;
 	struct symbol *func;
 	struct list_head stack_ops;
-	struct cfi_state cfi;
+	struct cfi_state *cfi;
 };
 
+#define VISITED_BRANCH		0x01
+#define VISITED_BRANCH_UACCESS	0x02
+#define VISITED_BRANCH_MASK	0x03
+#define VISITED_ENTRY		0x04
+
 static inline bool is_static_jump(struct instruction *insn)
 {
 	return insn->type == INSN_JUMP_CONDITIONAL ||
diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h
index 444365285618..6cdfa401b000 100644
--- a/tools/objtool/include/objtool/elf.h
+++ b/tools/objtool/include/objtool/elf.h
@@ -54,8 +54,12 @@ struct symbol {
 	unsigned long offset;
 	unsigned int len;
 	struct symbol *pfunc, *cfunc, *alias;
-	bool uaccess_safe;
-	bool static_call_tramp;
+	u8 uaccess_safe      : 1;
+	u8 static_call_tramp : 1;
+	u8 retpoline_thunk   : 1;
+	u8 return_thunk      : 1;
+	u8 fentry            : 1;
+	u8 kcov              : 1;
 };
 
 struct reloc {
@@ -140,7 +144,6 @@ int elf_write_insn(struct elf *elf, struct section *sec,
 		   unsigned long offset, unsigned int len,
 		   const char *insn);
 int elf_write_reloc(struct elf *elf, struct reloc *reloc);
-struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name);
 int elf_write(struct elf *elf);
 void elf_close(struct elf *elf);
 
diff --git a/tools/objtool/include/objtool/objtool.h b/tools/objtool/include/objtool/objtool.h
index 24fa83634de4..97b25a217c3a 100644
--- a/tools/objtool/include/objtool/objtool.h
+++ b/tools/objtool/include/objtool/objtool.h
@@ -19,6 +19,7 @@ struct objtool_file {
 	struct list_head insn_list;
 	DECLARE_HASHTABLE(insn_hash, 20);
 	struct list_head retpoline_call_list;
+	struct list_head return_thunk_list;
 	struct list_head static_call_list;
 	struct list_head mcount_loc_list;
 	bool ignore_unreachables, c_file, hints, rodata;
diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c
index e21db8bce493..24650d533d85 100644
--- a/tools/objtool/objtool.c
+++ b/tools/objtool/objtool.c
@@ -126,6 +126,7 @@ struct objtool_file *objtool_open_read(const char *_objname)
 	INIT_LIST_HEAD(&file.insn_list);
 	hash_init(file.insn_hash);
 	INIT_LIST_HEAD(&file.retpoline_call_list);
+	INIT_LIST_HEAD(&file.return_thunk_list);
 	INIT_LIST_HEAD(&file.static_call_list);
 	INIT_LIST_HEAD(&file.mcount_loc_list);
 	file.c_file = !vmlinux && find_section_by_name(file.elf, ".comment");
diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c
index b5865e2450cb..dd3c64af9db2 100644
--- a/tools/objtool/orc_gen.c
+++ b/tools/objtool/orc_gen.c
@@ -13,13 +13,19 @@
 #include <objtool/warn.h>
 #include <objtool/endianness.h>
 
-static int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi)
+static int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi,
+			  struct instruction *insn)
 {
-	struct instruction *insn = container_of(cfi, struct instruction, cfi);
 	struct cfi_reg *bp = &cfi->regs[CFI_BP];
 
 	memset(orc, 0, sizeof(*orc));
 
+	if (!cfi) {
+		orc->end = 0;
+		orc->sp_reg = ORC_REG_UNDEFINED;
+		return 0;
+	}
+
 	orc->end = cfi->end;
 
 	if (cfi->cfa.base == CFI_UNDEFINED) {
@@ -162,7 +168,7 @@ int orc_create(struct objtool_file *file)
 			int i;
 
 			if (!alt_group) {
-				if (init_orc_entry(&orc, &insn->cfi))
+				if (init_orc_entry(&orc, insn->cfi, insn))
 					return -1;
 				if (!memcmp(&prev_orc, &orc, sizeof(orc)))
 					continue;
@@ -186,7 +192,8 @@ int orc_create(struct objtool_file *file)
 				struct cfi_state *cfi = alt_group->cfi[i];
 				if (!cfi)
 					continue;
-				if (init_orc_entry(&orc, cfi))
+				/* errors are reported on the original insn */
+				if (init_orc_entry(&orc, cfi, insn))
 					return -1;
 				if (!memcmp(&prev_orc, &orc, sizeof(orc)))
 					continue;
diff --git a/tools/objtool/special.c b/tools/objtool/special.c
index 06c3eacab3d5..e2223dd91c37 100644
--- a/tools/objtool/special.c
+++ b/tools/objtool/special.c
@@ -109,14 +109,6 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry,
 			return -1;
 		}
 
-		/*
-		 * Skip retpoline .altinstr_replacement... we already rewrite the
-		 * instructions for retpolines anyway, see arch_is_retpoline()
-		 * usage in add_{call,jump}_destinations().
-		 */
-		if (arch_is_retpoline(new_reloc->sym))
-			return 1;
-
 		reloc_to_sec_off(new_reloc, &alt->new_sec, &alt->new_off);
 
 		/* _ASM_EXTABLE_EX hack */
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 1afc67047420..35e1f2a52435 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -263,7 +263,7 @@ endif
 # defined. get-executable-or-default fails with an error if the first argument is supplied but
 # doesn't exist.
 override PYTHON_CONFIG := $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON_AUTO))
-override PYTHON := $(call get-executable-or-default,PYTHON,$(subst -config,,$(PYTHON_AUTO)))
+override PYTHON := $(call get-executable-or-default,PYTHON,$(subst -config,,$(PYTHON_CONFIG)))
 
 grep-libs  = $(filter -l%,$(1))
 strip-libs  = $(filter-out -l%,$(1))
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index cb3d81adf5ca..c6c40191933d 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -435,6 +435,9 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session)
 	struct perf_event_attr *attr = &evsel->core.attr;
 	bool allow_user_set;
 
+	if (evsel__is_dummy_event(evsel))
+		return 0;
+
 	if (perf_header__has_feat(&session->header, HEADER_STAT))
 		return 0;
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 1a194edb5452..abf88a1ad455 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -807,6 +807,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 		return -1;
 
 	evlist__for_each_entry(evsel_list, counter) {
+		counter->reset_group = false;
 		if (bpf_counter__load(counter, &target))
 			return -1;
 		if (!evsel__is_bpf(counter))
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index 7c56bc1f4cff..89d25befb171 100644
--- a/tools/perf/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -20,8 +20,6 @@
 #include "tsc.h"
 #include "mmap.h"
 #include "tests.h"
-#include "pmu.h"
-#include "pmu-hybrid.h"
 
 #define CHECK__(x) {				\
 	while ((x) < 0) {			\
@@ -84,18 +82,8 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 
 	evlist__config(evlist, &opts, NULL);
 
-	evsel = evlist__first(evlist);
-
-	evsel->core.attr.comm = 1;
-	evsel->core.attr.disabled = 1;
-	evsel->core.attr.enable_on_exec = 0;
-
-	/*
-	 * For hybrid "cycles:u", it creates two events.
-	 * Init the second evsel here.
-	 */
-	if (perf_pmu__has_hybrid() && perf_pmu__hybrid_mounted("cpu_atom")) {
-		evsel = evsel__next(evsel);
+	/* For hybrid "cycles:u", it creates two events */
+	evlist__for_each_entry(evlist, evsel) {
 		evsel->core.attr.comm = 1;
 		evsel->core.attr.disabled = 1;
 		evsel->core.attr.enable_on_exec = 0;
@@ -141,10 +129,12 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 				goto next_event;
 
 			if (strcmp(event->comm.comm, comm1) == 0) {
+				CHECK_NOT_NULL__(evsel = evlist__event2evsel(evlist, event));
 				CHECK__(evsel__parse_sample(evsel, event, &sample));
 				comm1_time = sample.time;
 			}
 			if (strcmp(event->comm.comm, comm2) == 0) {
+				CHECK_NOT_NULL__(evsel = evlist__event2evsel(evlist, event));
 				CHECK__(evsel__parse_sample(evsel, event, &sample));
 				comm2_time = sample.time;
 			}
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index 62c0ec21aaa8..72abf5d86f71 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -324,6 +324,7 @@ out_free_nodes:
 int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	const char *sched_switch = "sched:sched_switch";
+	const char *cycles = "cycles:u";
 	struct switch_tracking switch_tracking = { .tids = NULL, };
 	struct record_opts opts = {
 		.mmap_pages	     = UINT_MAX,
@@ -372,12 +373,19 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_
 	cpu_clocks_evsel = evlist__last(evlist);
 
 	/* Second event */
-	if (perf_pmu__has_hybrid())
-		err = parse_events(evlist, "cpu_core/cycles/u", NULL);
-	else
-		err = parse_events(evlist, "cycles:u", NULL);
+	if (perf_pmu__has_hybrid()) {
+		cycles = "cpu_core/cycles/u";
+		err = parse_events(evlist, cycles, NULL);
+		if (err) {
+			cycles = "cpu_atom/cycles/u";
+			pr_debug("Trying %s\n", cycles);
+			err = parse_events(evlist, cycles, NULL);
+		}
+	} else {
+		err = parse_events(evlist, cycles, NULL);
+	}
 	if (err) {
-		pr_debug("Failed to parse event cycles:u\n");
+		pr_debug("Failed to parse event %s\n", cycles);
 		goto out_err;
 	}
 
diff --git a/tools/perf/util/dsos.c b/tools/perf/util/dsos.c
index 183a81d5b2f9..2db91121bdaf 100644
--- a/tools/perf/util/dsos.c
+++ b/tools/perf/util/dsos.c
@@ -20,8 +20,19 @@ static int __dso_id__cmp(struct dso_id *a, struct dso_id *b)
 	if (a->ino > b->ino) return -1;
 	if (a->ino < b->ino) return 1;
 
-	if (a->ino_generation > b->ino_generation) return -1;
-	if (a->ino_generation < b->ino_generation) return 1;
+	/*
+	 * Synthesized MMAP events have zero ino_generation, avoid comparing
+	 * them with MMAP events with actual ino_generation.
+	 *
+	 * I found it harmful because the mismatch resulted in a new
+	 * dso that did not have a build ID whereas the original dso did have a
+	 * build ID. The build ID was essential because the object was not found
+	 * otherwise. - Adrian
+	 */
+	if (a->ino_generation && b->ino_generation) {
+		if (a->ino_generation > b->ino_generation) return -1;
+		if (a->ino_generation < b->ino_generation) return 1;
+	}
 
 	return 0;
 }
diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c
index aed49806a09b..953338b9e887 100644
--- a/tools/perf/util/genelf.c
+++ b/tools/perf/util/genelf.c
@@ -30,7 +30,11 @@
 
 #define BUILD_ID_URANDOM /* different uuid for each run */
 
-#ifdef HAVE_LIBCRYPTO
+// FIXME, remove this and fix the deprecation warnings before its removed and
+// We'll break for good here...
+#pragma GCC diagnostic ignored "-Wdeprecated-declarations"
+
+#ifdef HAVE_LIBCRYPTO_SUPPORT
 
 #define BUILD_ID_MD5
 #undef BUILD_ID_SHA	/* does not seem to work well when linked with Java */
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 44e40bad0e33..55a041329990 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -16,6 +16,7 @@
 #include "map_symbol.h"
 #include "branch.h"
 #include "mem-events.h"
+#include "path.h"
 #include "srcline.h"
 #include "symbol.h"
 #include "sort.h"
@@ -1407,7 +1408,7 @@ static int maps__set_modules_path_dir(struct maps *maps, const char *dir_name, i
 		struct stat st;
 
 		/*sshfs might return bad dent->d_type, so we have to stat*/
-		snprintf(path, sizeof(path), "%s/%s", dir_name, dent->d_name);
+		path__join(path, sizeof(path), dir_name, dent->d_name);
 		if (stat(path, &st))
 			continue;
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 3bfe099d8643..b93a36ffeb9e 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -196,9 +196,12 @@ static int tp_event_has_id(const char *dir_path, struct dirent *evt_dir)
 void parse_events__handle_error(struct parse_events_error *err, int idx,
 				char *str, char *help)
 {
-	if (WARN(!str, "WARNING: failed to provide error string\n")) {
-		free(help);
-		return;
+	if (WARN(!str, "WARNING: failed to provide error string\n"))
+		goto out_free;
+	if (!err) {
+		/* Assume caller does not want message printed */
+		pr_debug("event syntax error: %s\n", str);
+		goto out_free;
 	}
 	switch (err->num_errors) {
 	case 0:
@@ -224,6 +227,11 @@ void parse_events__handle_error(struct parse_events_error *err, int idx,
 		break;
 	}
 	err->num_errors++;
+	return;
+
+out_free:
+	free(str);
+	free(help);
 }
 
 struct tracepoint_path *tracepoint_id_to_path(u64 config)
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index a834918a0a0d..68844c48f688 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -1775,8 +1775,10 @@ int parse_perf_probe_command(const char *cmd, struct perf_probe_event *pev)
 	if (!pev->event && pev->point.function && pev->point.line
 			&& !pev->point.lazy_line && !pev->point.offset) {
 		if (asprintf(&pev->event, "%s_L%d", pev->point.function,
-			pev->point.line) < 0)
-			return -ENOMEM;
+			pev->point.line) < 0) {
+			ret = -ENOMEM;
+			goto out;
+		}
 	}
 
 	/* Copy arguments and ensure return probe has no C argument */
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index ecd377938eea..cb7b24493782 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -233,6 +233,33 @@ Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
 	return NULL;
 }
 
+static int elf_read_program_header(Elf *elf, u64 vaddr, GElf_Phdr *phdr)
+{
+	size_t i, phdrnum;
+	u64 sz;
+
+	if (elf_getphdrnum(elf, &phdrnum))
+		return -1;
+
+	for (i = 0; i < phdrnum; i++) {
+		if (gelf_getphdr(elf, i, phdr) == NULL)
+			return -1;
+
+		if (phdr->p_type != PT_LOAD)
+			continue;
+
+		sz = max(phdr->p_memsz, phdr->p_filesz);
+		if (!sz)
+			continue;
+
+		if (vaddr >= phdr->p_vaddr && (vaddr < phdr->p_vaddr + sz))
+			return 0;
+	}
+
+	/* Not found any valid program header */
+	return -1;
+}
+
 static bool want_demangle(bool is_kernel_sym)
 {
 	return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle;
@@ -1209,6 +1236,7 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 					sym.st_value);
 			used_opd = true;
 		}
+
 		/*
 		 * When loading symbols in a data mapping, ABS symbols (which
 		 * has a value of SHN_ABS in its st_shndx) failed at
@@ -1262,11 +1290,33 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 				goto out_elf_end;
 		} else if ((used_opd && runtime_ss->adjust_symbols) ||
 			   (!used_opd && syms_ss->adjust_symbols)) {
-			pr_debug4("%s: adjusting symbol: st_value: %#" PRIx64 " "
-				  "sh_addr: %#" PRIx64 " sh_offset: %#" PRIx64 "\n", __func__,
-				  (u64)sym.st_value, (u64)shdr.sh_addr,
-				  (u64)shdr.sh_offset);
-			sym.st_value -= shdr.sh_addr - shdr.sh_offset;
+			GElf_Phdr phdr;
+
+			if (elf_read_program_header(syms_ss->elf,
+						    (u64)sym.st_value, &phdr)) {
+				pr_debug4("%s: failed to find program header for "
+					   "symbol: %s st_value: %#" PRIx64 "\n",
+					   __func__, elf_name, (u64)sym.st_value);
+				pr_debug4("%s: adjusting symbol: st_value: %#" PRIx64 " "
+					"sh_addr: %#" PRIx64 " sh_offset: %#" PRIx64 "\n",
+					__func__, (u64)sym.st_value, (u64)shdr.sh_addr,
+					(u64)shdr.sh_offset);
+				/*
+				 * Fail to find program header, let's rollback
+				 * to use shdr.sh_addr and shdr.sh_offset to
+				 * calibrate symbol's file address, though this
+				 * is not necessary for normal C ELF file, we
+				 * still need to handle java JIT symbols in this
+				 * case.
+				 */
+				sym.st_value -= shdr.sh_addr - shdr.sh_offset;
+			} else {
+				pr_debug4("%s: adjusting symbol: st_value: %#" PRIx64 " "
+					"p_vaddr: %#" PRIx64 " p_offset: %#" PRIx64 "\n",
+					__func__, (u64)sym.st_value, (u64)phdr.p_vaddr,
+					(u64)phdr.p_offset);
+				sym.st_value -= phdr.p_vaddr - phdr.p_offset;
+			}
 		}
 
 		demangled = demangle_sym(dso, kmodule, elf_name);
diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c
index ed563bdd88f3..b752ce47ead3 100644
--- a/tools/testing/nvdimm/test/iomap.c
+++ b/tools/testing/nvdimm/test/iomap.c
@@ -100,25 +100,17 @@ static void nfit_test_kill(void *_pgmap)
 {
 	struct dev_pagemap *pgmap = _pgmap;
 
-	WARN_ON(!pgmap || !pgmap->ref);
-
-	if (pgmap->ops && pgmap->ops->kill)
-		pgmap->ops->kill(pgmap);
-	else
-		percpu_ref_kill(pgmap->ref);
-
-	if (pgmap->ops && pgmap->ops->cleanup) {
-		pgmap->ops->cleanup(pgmap);
-	} else {
-		wait_for_completion(&pgmap->done);
-		percpu_ref_exit(pgmap->ref);
-	}
+	WARN_ON(!pgmap);
+
+	percpu_ref_kill(&pgmap->ref);
+
+	wait_for_completion(&pgmap->done);
+	percpu_ref_exit(&pgmap->ref);
 }
 
 static void dev_pagemap_percpu_release(struct percpu_ref *ref)
 {
-	struct dev_pagemap *pgmap =
-		container_of(ref, struct dev_pagemap, internal_ref);
+	struct dev_pagemap *pgmap = container_of(ref, struct dev_pagemap, ref);
 
 	complete(&pgmap->done);
 }
@@ -132,22 +124,11 @@ void *__wrap_devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 	if (!nfit_res)
 		return devm_memremap_pages(dev, pgmap);
 
-	if (!pgmap->ref) {
-		if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup))
-			return ERR_PTR(-EINVAL);
-
-		init_completion(&pgmap->done);
-		error = percpu_ref_init(&pgmap->internal_ref,
-				dev_pagemap_percpu_release, 0, GFP_KERNEL);
-		if (error)
-			return ERR_PTR(error);
-		pgmap->ref = &pgmap->internal_ref;
-	} else {
-		if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) {
-			WARN(1, "Missing reference count teardown definition\n");
-			return ERR_PTR(-EINVAL);
-		}
-	}
+	init_completion(&pgmap->done);
+	error = percpu_ref_init(&pgmap->ref, dev_pagemap_percpu_release, 0,
+				GFP_KERNEL);
+	if (error)
+		return ERR_PTR(error);
 
 	error = devm_add_action_or_reset(dev, nfit_test_kill, pgmap);
 	if (error)
diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c
index 649f87382c8d..50afa75bd45b 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf.c
@@ -4913,7 +4913,7 @@ static void do_test_pprint(int test_num)
 	ret = snprintf(pin_path, sizeof(pin_path), "%s/%s",
 		       "/sys/fs/bpf", test->map_name);
 
-	if (CHECK(ret == sizeof(pin_path), "pin_path %s/%s is too long",
+	if (CHECK(ret >= sizeof(pin_path), "pin_path %s/%s is too long",
 		  "/sys/fs/bpf", test->map_name)) {
 		err = -1;
 		goto done;
diff --git a/tools/testing/selftests/bpf/prog_tests/sock_fields.c b/tools/testing/selftests/bpf/prog_tests/sock_fields.c
index 577d619fb07e..197ec1d1b702 100644
--- a/tools/testing/selftests/bpf/prog_tests/sock_fields.c
+++ b/tools/testing/selftests/bpf/prog_tests/sock_fields.c
@@ -1,9 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2019 Facebook */
 
+#define _GNU_SOURCE
 #include <netinet/in.h>
 #include <arpa/inet.h>
 #include <unistd.h>
+#include <sched.h>
 #include <stdlib.h>
 #include <string.h>
 #include <errno.h>
@@ -21,6 +23,7 @@
 enum bpf_linum_array_idx {
 	EGRESS_LINUM_IDX,
 	INGRESS_LINUM_IDX,
+	READ_SK_DST_PORT_LINUM_IDX,
 	__NR_BPF_LINUM_ARRAY_IDX,
 };
 
@@ -43,8 +46,16 @@ static __u64 child_cg_id;
 static int linum_map_fd;
 static __u32 duration;
 
-static __u32 egress_linum_idx = EGRESS_LINUM_IDX;
-static __u32 ingress_linum_idx = INGRESS_LINUM_IDX;
+static bool create_netns(void)
+{
+	if (!ASSERT_OK(unshare(CLONE_NEWNET), "create netns"))
+		return false;
+
+	if (!ASSERT_OK(system("ip link set dev lo up"), "bring up lo"))
+		return false;
+
+	return true;
+}
 
 static void print_sk(const struct bpf_sock *sk, const char *prefix)
 {
@@ -92,19 +103,24 @@ static void check_result(void)
 {
 	struct bpf_tcp_sock srv_tp, cli_tp, listen_tp;
 	struct bpf_sock srv_sk, cli_sk, listen_sk;
-	__u32 ingress_linum, egress_linum;
+	__u32 idx, ingress_linum, egress_linum, linum;
 	int err;
 
-	err = bpf_map_lookup_elem(linum_map_fd, &egress_linum_idx,
-				  &egress_linum);
+	idx = EGRESS_LINUM_IDX;
+	err = bpf_map_lookup_elem(linum_map_fd, &idx, &egress_linum);
 	CHECK(err < 0, "bpf_map_lookup_elem(linum_map_fd)",
 	      "err:%d errno:%d\n", err, errno);
 
-	err = bpf_map_lookup_elem(linum_map_fd, &ingress_linum_idx,
-				  &ingress_linum);
+	idx = INGRESS_LINUM_IDX;
+	err = bpf_map_lookup_elem(linum_map_fd, &idx, &ingress_linum);
 	CHECK(err < 0, "bpf_map_lookup_elem(linum_map_fd)",
 	      "err:%d errno:%d\n", err, errno);
 
+	idx = READ_SK_DST_PORT_LINUM_IDX;
+	err = bpf_map_lookup_elem(linum_map_fd, &idx, &linum);
+	ASSERT_OK(err, "bpf_map_lookup_elem(linum_map_fd, READ_SK_DST_PORT_IDX)");
+	ASSERT_EQ(linum, 0, "failure in read_sk_dst_port on line");
+
 	memcpy(&srv_sk, &skel->bss->srv_sk, sizeof(srv_sk));
 	memcpy(&srv_tp, &skel->bss->srv_tp, sizeof(srv_tp));
 	memcpy(&cli_sk, &skel->bss->cli_sk, sizeof(cli_sk));
@@ -263,7 +279,7 @@ static void test(void)
 	char buf[DATA_LEN];
 
 	/* Prepare listen_fd */
-	listen_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0);
+	listen_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0xcafe, 0);
 	/* start_server() has logged the error details */
 	if (CHECK_FAIL(listen_fd == -1))
 		goto done;
@@ -331,8 +347,12 @@ done:
 
 void test_sock_fields(void)
 {
-	struct bpf_link *egress_link = NULL, *ingress_link = NULL;
 	int parent_cg_fd = -1, child_cg_fd = -1;
+	struct bpf_link *link;
+
+	/* Use a dedicated netns to have a fixed listen port */
+	if (!create_netns())
+		return;
 
 	/* Create a cgroup, get fd, and join it */
 	parent_cg_fd = test__join_cgroup(PARENT_CGROUP);
@@ -353,15 +373,20 @@ void test_sock_fields(void)
 	if (CHECK(!skel, "test_sock_fields__open_and_load", "failed\n"))
 		goto done;
 
-	egress_link = bpf_program__attach_cgroup(skel->progs.egress_read_sock_fields,
-						 child_cg_fd);
-	if (!ASSERT_OK_PTR(egress_link, "attach_cgroup(egress)"))
+	link = bpf_program__attach_cgroup(skel->progs.egress_read_sock_fields, child_cg_fd);
+	if (!ASSERT_OK_PTR(link, "attach_cgroup(egress_read_sock_fields)"))
+		goto done;
+	skel->links.egress_read_sock_fields = link;
+
+	link = bpf_program__attach_cgroup(skel->progs.ingress_read_sock_fields, child_cg_fd);
+	if (!ASSERT_OK_PTR(link, "attach_cgroup(ingress_read_sock_fields)"))
 		goto done;
+	skel->links.ingress_read_sock_fields = link;
 
-	ingress_link = bpf_program__attach_cgroup(skel->progs.ingress_read_sock_fields,
-						  child_cg_fd);
-	if (!ASSERT_OK_PTR(ingress_link, "attach_cgroup(ingress)"))
+	link = bpf_program__attach_cgroup(skel->progs.read_sk_dst_port, child_cg_fd);
+	if (!ASSERT_OK_PTR(link, "attach_cgroup(read_sk_dst_port"))
 		goto done;
+	skel->links.read_sk_dst_port = link;
 
 	linum_map_fd = bpf_map__fd(skel->maps.linum_map);
 	sk_pkt_out_cnt_fd = bpf_map__fd(skel->maps.sk_pkt_out_cnt);
@@ -370,8 +395,7 @@ void test_sock_fields(void)
 	test();
 
 done:
-	bpf_link__destroy(egress_link);
-	bpf_link__destroy(ingress_link);
+	test_sock_fields__detach(skel);
 	test_sock_fields__destroy(skel);
 	if (child_cg_fd >= 0)
 		close(child_cg_fd);
diff --git a/tools/testing/selftests/bpf/prog_tests/timer_crash.c b/tools/testing/selftests/bpf/prog_tests/timer_crash.c
deleted file mode 100644
index f74b82305da8..000000000000
--- a/tools/testing/selftests/bpf/prog_tests/timer_crash.c
+++ /dev/null
@@ -1,32 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <test_progs.h>
-#include "timer_crash.skel.h"
-
-enum {
-	MODE_ARRAY,
-	MODE_HASH,
-};
-
-static void test_timer_crash_mode(int mode)
-{
-	struct timer_crash *skel;
-
-	skel = timer_crash__open_and_load();
-	if (!ASSERT_OK_PTR(skel, "timer_crash__open_and_load"))
-		return;
-	skel->bss->pid = getpid();
-	skel->bss->crash_map = mode;
-	if (!ASSERT_OK(timer_crash__attach(skel), "timer_crash__attach"))
-		goto end;
-	usleep(1);
-end:
-	timer_crash__destroy(skel);
-}
-
-void test_timer_crash(void)
-{
-	if (test__start_subtest("array"))
-		test_timer_crash_mode(MODE_ARRAY);
-	if (test__start_subtest("hash"))
-		test_timer_crash_mode(MODE_HASH);
-}
diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields.c b/tools/testing/selftests/bpf/progs/test_sock_fields.c
index 7967348b11af..43b31aa1fcf7 100644
--- a/tools/testing/selftests/bpf/progs/test_sock_fields.c
+++ b/tools/testing/selftests/bpf/progs/test_sock_fields.c
@@ -12,6 +12,7 @@
 enum bpf_linum_array_idx {
 	EGRESS_LINUM_IDX,
 	INGRESS_LINUM_IDX,
+	READ_SK_DST_PORT_LINUM_IDX,
 	__NR_BPF_LINUM_ARRAY_IDX,
 };
 
@@ -250,4 +251,48 @@ int ingress_read_sock_fields(struct __sk_buff *skb)
 	return CG_OK;
 }
 
+static __noinline bool sk_dst_port__load_word(struct bpf_sock *sk)
+{
+	__u32 *word = (__u32 *)&sk->dst_port;
+	return word[0] == bpf_htonl(0xcafe0000);
+}
+
+static __noinline bool sk_dst_port__load_half(struct bpf_sock *sk)
+{
+	__u16 *half = (__u16 *)&sk->dst_port;
+	return half[0] == bpf_htons(0xcafe);
+}
+
+static __noinline bool sk_dst_port__load_byte(struct bpf_sock *sk)
+{
+	__u8 *byte = (__u8 *)&sk->dst_port;
+	return byte[0] == 0xca && byte[1] == 0xfe;
+}
+
+SEC("cgroup_skb/egress")
+int read_sk_dst_port(struct __sk_buff *skb)
+{
+	__u32 linum, linum_idx;
+	struct bpf_sock *sk;
+
+	linum_idx = READ_SK_DST_PORT_LINUM_IDX;
+
+	sk = skb->sk;
+	if (!sk)
+		RET_LOG();
+
+	/* Ignore everything but the SYN from the client socket */
+	if (sk->state != BPF_TCP_SYN_SENT)
+		return CG_OK;
+
+	if (!sk_dst_port__load_word(sk))
+		RET_LOG();
+	if (!sk_dst_port__load_half(sk))
+		RET_LOG();
+	if (!sk_dst_port__load_byte(sk))
+		RET_LOG();
+
+	return CG_OK;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/timer_crash.c b/tools/testing/selftests/bpf/progs/timer_crash.c
deleted file mode 100644
index f8f7944e70da..000000000000
--- a/tools/testing/selftests/bpf/progs/timer_crash.c
+++ /dev/null
@@ -1,54 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-#include <vmlinux.h>
-#include <bpf/bpf_tracing.h>
-#include <bpf/bpf_helpers.h>
-
-struct map_elem {
-	struct bpf_timer timer;
-	struct bpf_spin_lock lock;
-};
-
-struct {
-	__uint(type, BPF_MAP_TYPE_ARRAY);
-	__uint(max_entries, 1);
-	__type(key, int);
-	__type(value, struct map_elem);
-} amap SEC(".maps");
-
-struct {
-	__uint(type, BPF_MAP_TYPE_HASH);
-	__uint(max_entries, 1);
-	__type(key, int);
-	__type(value, struct map_elem);
-} hmap SEC(".maps");
-
-int pid = 0;
-int crash_map = 0; /* 0 for amap, 1 for hmap */
-
-SEC("fentry/do_nanosleep")
-int sys_enter(void *ctx)
-{
-	struct map_elem *e, value = {};
-	void *map = crash_map ? (void *)&hmap : (void *)&amap;
-
-	if (bpf_get_current_task_btf()->tgid != pid)
-		return 0;
-
-	*(void **)&value = (void *)0xdeadcaf3;
-
-	bpf_map_update_elem(map, &(int){0}, &value, 0);
-	/* For array map, doing bpf_map_update_elem will do a
-	 * check_and_free_timer_in_array, which will trigger the crash if timer
-	 * pointer was overwritten, for hmap we need to use bpf_timer_cancel.
-	 */
-	if (crash_map == 1) {
-		e = bpf_map_lookup_elem(map, &(int){0});
-		if (!e)
-			return 0;
-		bpf_timer_cancel(&e->timer);
-	}
-	return 0;
-}
-
-char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 3a9e332c5e36..68a9a897185c 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -31,6 +31,7 @@
 #include <linux/if_ether.h>
 #include <linux/btf.h>
 
+#include <bpf/btf.h>
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
 
@@ -63,6 +64,11 @@ static bool unpriv_disabled = false;
 static int skips;
 static bool verbose = false;
 
+struct kfunc_btf_id_pair {
+	const char *kfunc;
+	int insn_idx;
+};
+
 struct bpf_test {
 	const char *descr;
 	struct bpf_insn	insns[MAX_INSNS];
@@ -88,6 +94,7 @@ struct bpf_test {
 	int fixup_map_event_output[MAX_FIXUPS];
 	int fixup_map_reuseport_array[MAX_FIXUPS];
 	int fixup_map_ringbuf[MAX_FIXUPS];
+	struct kfunc_btf_id_pair fixup_kfunc_btf_id[MAX_FIXUPS];
 	/* Expected verifier log output for result REJECT or VERBOSE_ACCEPT.
 	 * Can be a tab-separated sequence of expected strings. An empty string
 	 * means no log verification.
@@ -718,6 +725,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
 	int *fixup_map_event_output = test->fixup_map_event_output;
 	int *fixup_map_reuseport_array = test->fixup_map_reuseport_array;
 	int *fixup_map_ringbuf = test->fixup_map_ringbuf;
+	struct kfunc_btf_id_pair *fixup_kfunc_btf_id = test->fixup_kfunc_btf_id;
 
 	if (test->fill_helper) {
 		test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn));
@@ -903,6 +911,26 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
 			fixup_map_ringbuf++;
 		} while (*fixup_map_ringbuf);
 	}
+
+	/* Patch in kfunc BTF IDs */
+	if (fixup_kfunc_btf_id->kfunc) {
+		struct btf *btf;
+		int btf_id;
+
+		do {
+			btf_id = 0;
+			btf = btf__load_vmlinux_btf();
+			if (btf) {
+				btf_id = btf__find_by_name_kind(btf,
+								fixup_kfunc_btf_id->kfunc,
+								BTF_KIND_FUNC);
+				btf_id = btf_id < 0 ? 0 : btf_id;
+			}
+			btf__free(btf);
+			prog[fixup_kfunc_btf_id->insn_idx].imm = btf_id;
+			fixup_kfunc_btf_id++;
+		} while (fixup_kfunc_btf_id->kfunc);
+	}
 }
 
 struct libcap {
diff --git a/tools/testing/selftests/bpf/verifier/sock.c b/tools/testing/selftests/bpf/verifier/sock.c
index ce13ece08d51..8c224eac93df 100644
--- a/tools/testing/selftests/bpf/verifier/sock.c
+++ b/tools/testing/selftests/bpf/verifier/sock.c
@@ -121,7 +121,25 @@
 	.result = ACCEPT,
 },
 {
-	"sk_fullsock(skb->sk): sk->dst_port [narrow load]",
+	"sk_fullsock(skb->sk): sk->dst_port [word load] (backward compatibility)",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port)),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.result = ACCEPT,
+},
+{
+	"sk_fullsock(skb->sk): sk->dst_port [half load]",
 	.insns = {
 	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
 	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
@@ -139,7 +157,64 @@
 	.result = ACCEPT,
 },
 {
-	"sk_fullsock(skb->sk): sk->dst_port [load 2nd byte]",
+	"sk_fullsock(skb->sk): sk->dst_port [half load] (invalid)",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.result = REJECT,
+	.errstr = "invalid sock access",
+},
+{
+	"sk_fullsock(skb->sk): sk->dst_port [byte load]",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_LDX_MEM(BPF_B, BPF_REG_2, BPF_REG_0, offsetof(struct bpf_sock, dst_port)),
+	BPF_LDX_MEM(BPF_B, BPF_REG_2, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 1),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.result = ACCEPT,
+},
+{
+	"sk_fullsock(skb->sk): sk->dst_port [byte load] (invalid)",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.result = REJECT,
+	.errstr = "invalid sock access",
+},
+{
+	"sk_fullsock(skb->sk): past sk->dst_port [half load] (invalid)",
 	.insns = {
 	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
 	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
@@ -149,7 +224,7 @@
 	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 1),
+	BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_0, offsetofend(struct bpf_sock, dst_port)),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc
index fa928b431555..7c02509c71d0 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc
@@ -21,7 +21,6 @@ check_error 'p:^/bar vfs_read'		# NO_GROUP_NAME
 check_error 'p:^12345678901234567890123456789012345678901234567890123456789012345/bar vfs_read'	# GROUP_TOO_LONG
 
 check_error 'p:^foo.1/bar vfs_read'	# BAD_GROUP_NAME
-check_error 'p:foo/^ vfs_read'		# NO_EVENT_NAME
 check_error 'p:foo/^12345678901234567890123456789012345678901234567890123456789012345 vfs_read'	# EVENT_TOO_LONG
 check_error 'p:foo/^bar.1 vfs_read'	# BAD_EVENT_NAME
 
diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/aarch64/ucall.c
index e0b0164e9af8..be1d9728c4ce 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/ucall.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/ucall.c
@@ -73,20 +73,19 @@ void ucall_uninit(struct kvm_vm *vm)
 
 void ucall(uint64_t cmd, int nargs, ...)
 {
-	struct ucall uc = {
-		.cmd = cmd,
-	};
+	struct ucall uc = {};
 	va_list va;
 	int i;
 
+	WRITE_ONCE(uc.cmd, cmd);
 	nargs = nargs <= UCALL_MAX_ARGS ? nargs : UCALL_MAX_ARGS;
 
 	va_start(va, nargs);
 	for (i = 0; i < nargs; ++i)
-		uc.args[i] = va_arg(va, uint64_t);
+		WRITE_ONCE(uc.args[i], va_arg(va, uint64_t));
 	va_end(va);
 
-	*ucall_exit_mmio_addr = (vm_vaddr_t)&uc;
+	WRITE_ONCE(*ucall_exit_mmio_addr, (vm_vaddr_t)&uc);
 }
 
 uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc)
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index 46057079d8bb..4f1449fa9592 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -1326,7 +1326,7 @@ uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2,
 
 	asm volatile("vmcall"
 		     : "=a"(r)
-		     : "b"(a0), "c"(a1), "d"(a2), "S"(a3));
+		     : "a"(nr), "b"(a0), "c"(a1), "d"(a2), "S"(a3));
 	return r;
 }
 
diff --git a/tools/testing/selftests/kvm/rseq_test.c b/tools/testing/selftests/kvm/rseq_test.c
index 4158da0da2bb..2237d1aac801 100644
--- a/tools/testing/selftests/kvm/rseq_test.c
+++ b/tools/testing/selftests/kvm/rseq_test.c
@@ -82,8 +82,9 @@ static int next_cpu(int cpu)
 	return cpu;
 }
 
-static void *migration_worker(void *ign)
+static void *migration_worker(void *__rseq_tid)
 {
+	pid_t rseq_tid = (pid_t)(unsigned long)__rseq_tid;
 	cpu_set_t allowed_mask;
 	int r, i, cpu;
 
@@ -106,7 +107,7 @@ static void *migration_worker(void *ign)
 		 * stable, i.e. while changing affinity is in-progress.
 		 */
 		smp_wmb();
-		r = sched_setaffinity(0, sizeof(allowed_mask), &allowed_mask);
+		r = sched_setaffinity(rseq_tid, sizeof(allowed_mask), &allowed_mask);
 		TEST_ASSERT(!r, "sched_setaffinity failed, errno = %d (%s)",
 			    errno, strerror(errno));
 		smp_wmb();
@@ -231,7 +232,8 @@ int main(int argc, char *argv[])
 	vm = vm_create_default(VCPU_ID, 0, guest_code);
 	ucall_init(vm, NULL);
 
-	pthread_create(&migration_thread, NULL, migration_worker, 0);
+	pthread_create(&migration_thread, NULL, migration_worker,
+		       (void *)(unsigned long)gettid());
 
 	for (i = 0; !done; i++) {
 		vcpu_run(vm, VCPU_ID);
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
index e0b2bb1339b1..3330fb183c68 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
@@ -44,7 +44,7 @@ static inline void nop_loop(void)
 {
 	int i;
 
-	for (i = 0; i < 1000000; i++)
+	for (i = 0; i < 100000000; i++)
 		asm volatile("nop");
 }
 
@@ -56,12 +56,14 @@ static inline void check_tsc_msr_rdtsc(void)
 	tsc_freq = rdmsr(HV_X64_MSR_TSC_FREQUENCY);
 	GUEST_ASSERT(tsc_freq > 0);
 
-	/* First, check MSR-based clocksource */
+	/* For increased accuracy, take mean rdtsc() before and afrer rdmsr() */
 	r1 = rdtsc();
 	t1 = rdmsr(HV_X64_MSR_TIME_REF_COUNT);
+	r1 = (r1 + rdtsc()) / 2;
 	nop_loop();
 	r2 = rdtsc();
 	t2 = rdmsr(HV_X64_MSR_TIME_REF_COUNT);
+	r2 = (r2 + rdtsc()) / 2;
 
 	GUEST_ASSERT(r2 > r1 && t2 > t1);
 
@@ -181,12 +183,14 @@ static void host_check_tsc_msr_rdtsc(struct kvm_vm *vm)
 	tsc_freq = vcpu_get_msr(vm, VCPU_ID, HV_X64_MSR_TSC_FREQUENCY);
 	TEST_ASSERT(tsc_freq > 0, "TSC frequency must be nonzero");
 
-	/* First, check MSR-based clocksource */
+	/* For increased accuracy, take mean rdtsc() before and afrer ioctl */
 	r1 = rdtsc();
 	t1 = vcpu_get_msr(vm, VCPU_ID, HV_X64_MSR_TIME_REF_COUNT);
+	r1 = (r1 + rdtsc()) / 2;
 	nop_loop();
 	r2 = rdtsc();
 	t2 = vcpu_get_msr(vm, VCPU_ID, HV_X64_MSR_TIME_REF_COUNT);
+	r2 = (r2 + rdtsc()) / 2;
 
 	TEST_ASSERT(t2 > t1, "Time reference MSR is not monotonic (%ld <= %ld)", t1, t2);
 
diff --git a/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh
index a15d21dc035a..56eb83d1a3bd 100755
--- a/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh
+++ b/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh
@@ -181,37 +181,43 @@ ping_ipv6()
 
 send_src_ipv4()
 {
-	$MZ $h1 -q -p 64 -A "198.51.100.2-198.51.100.253" -B 203.0.113.2 \
+	ip vrf exec v$h1 $MZ $h1 -q -p 64 \
+		-A "198.51.100.2-198.51.100.253" -B 203.0.113.2 \
 		-d 1msec -c 50 -t udp "sp=20000,dp=30000"
 }
 
 send_dst_ipv4()
 {
-	$MZ $h1 -q -p 64 -A 198.51.100.2 -B "203.0.113.2-203.0.113.253" \
+	ip vrf exec v$h1 $MZ $h1 -q -p 64 \
+		-A 198.51.100.2 -B "203.0.113.2-203.0.113.253" \
 		-d 1msec -c 50 -t udp "sp=20000,dp=30000"
 }
 
 send_src_udp4()
 {
-	$MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \
+	ip vrf exec v$h1 $MZ $h1 -q -p 64 \
+		-A 198.51.100.2 -B 203.0.113.2 \
 		-d 1msec -t udp "sp=0-32768,dp=30000"
 }
 
 send_dst_udp4()
 {
-	$MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \
+	ip vrf exec v$h1 $MZ $h1 -q -p 64 \
+		-A 198.51.100.2 -B 203.0.113.2 \
 		-d 1msec -t udp "sp=20000,dp=0-32768"
 }
 
 send_src_ipv6()
 {
-	$MZ -6 $h1 -q -p 64 -A "2001:db8:1::2-2001:db8:1::fd" -B 2001:db8:4::2 \
+	ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \
+		-A "2001:db8:1::2-2001:db8:1::fd" -B 2001:db8:4::2 \
 		-d 1msec -c 50 -t udp "sp=20000,dp=30000"
 }
 
 send_dst_ipv6()
 {
-	$MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B "2001:db8:4::2-2001:db8:4::fd" \
+	ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \
+		-A 2001:db8:1::2 -B "2001:db8:4::2-2001:db8:4::fd" \
 		-d 1msec -c 50 -t udp "sp=20000,dp=30000"
 }
 
@@ -226,13 +232,15 @@ send_flowlabel()
 
 send_src_udp6()
 {
-	$MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:4::2 \
+	ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \
+		-A 2001:db8:1::2 -B 2001:db8:4::2 \
 		-d 1msec -t udp "sp=0-32768,dp=30000"
 }
 
 send_dst_udp6()
 {
-	$MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:4::2 \
+	ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \
+		-A 2001:db8:1::2 -B 2001:db8:4::2 \
 		-d 1msec -t udp "sp=20000,dp=0-32768"
 }
 
diff --git a/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh
index a73f52efcb6c..0446db9c6f74 100755
--- a/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh
+++ b/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh
@@ -276,37 +276,43 @@ ping_ipv6()
 
 send_src_ipv4()
 {
-	$MZ $h1 -q -p 64 -A "198.51.100.2-198.51.100.253" -B 203.0.113.2 \
+	ip vrf exec v$h1 $MZ $h1 -q -p 64 \
+		-A "198.51.100.2-198.51.100.253" -B 203.0.113.2 \
 		-d 1msec -c 50 -t udp "sp=20000,dp=30000"
 }
 
 send_dst_ipv4()
 {
-	$MZ $h1 -q -p 64 -A 198.51.100.2 -B "203.0.113.2-203.0.113.253" \
+	ip vrf exec v$h1 $MZ $h1 -q -p 64 \
+		-A 198.51.100.2 -B "203.0.113.2-203.0.113.253" \
 		-d 1msec -c 50 -t udp "sp=20000,dp=30000"
 }
 
 send_src_udp4()
 {
-	$MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \
+	ip vrf exec v$h1 $MZ $h1 -q -p 64 \
+		-A 198.51.100.2 -B 203.0.113.2 \
 		-d 1msec -t udp "sp=0-32768,dp=30000"
 }
 
 send_dst_udp4()
 {
-	$MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \
+	ip vrf exec v$h1 $MZ $h1 -q -p 64 \
+		-A 198.51.100.2 -B 203.0.113.2 \
 		-d 1msec -t udp "sp=20000,dp=0-32768"
 }
 
 send_src_ipv6()
 {
-	$MZ -6 $h1 -q -p 64 -A "2001:db8:1::2-2001:db8:1::fd" -B 2001:db8:2::2 \
+	ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \
+		-A "2001:db8:1::2-2001:db8:1::fd" -B 2001:db8:2::2 \
 		-d 1msec -c 50 -t udp "sp=20000,dp=30000"
 }
 
 send_dst_ipv6()
 {
-	$MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B "2001:db8:2::2-2001:db8:2::fd" \
+	ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \
+		-A 2001:db8:1::2 -B "2001:db8:2::2-2001:db8:2::fd" \
 		-d 1msec -c 50 -t udp "sp=20000,dp=30000"
 }
 
@@ -321,13 +327,15 @@ send_flowlabel()
 
 send_src_udp6()
 {
-	$MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \
+	ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \
+		-A 2001:db8:1::2 -B 2001:db8:2::2 \
 		-d 1msec -t udp "sp=0-32768,dp=30000"
 }
 
 send_dst_udp6()
 {
-	$MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \
+	ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \
+		-A 2001:db8:1::2 -B 2001:db8:2::2 \
 		-d 1msec -t udp "sp=20000,dp=0-32768"
 }
 
diff --git a/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh
index 8fea2c2e0b25..d40183b4eccc 100755
--- a/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh
+++ b/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh
@@ -278,37 +278,43 @@ ping_ipv6()
 
 send_src_ipv4()
 {
-	$MZ $h1 -q -p 64 -A "198.51.100.2-198.51.100.253" -B 203.0.113.2 \
+	ip vrf exec v$h1 $MZ $h1 -q -p 64 \
+		-A "198.51.100.2-198.51.100.253" -B 203.0.113.2 \
 		-d 1msec -c 50 -t udp "sp=20000,dp=30000"
 }
 
 send_dst_ipv4()
 {
-	$MZ $h1 -q -p 64 -A 198.51.100.2 -B "203.0.113.2-203.0.113.253" \
+	ip vrf exec v$h1 $MZ $h1 -q -p 64 \
+		-A 198.51.100.2 -B "203.0.113.2-203.0.113.253" \
 		-d 1msec -c 50 -t udp "sp=20000,dp=30000"
 }
 
 send_src_udp4()
 {
-	$MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \
+	ip vrf exec v$h1 $MZ $h1 -q -p 64 \
+		-A 198.51.100.2 -B 203.0.113.2 \
 		-d 1msec -t udp "sp=0-32768,dp=30000"
 }
 
 send_dst_udp4()
 {
-	$MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \
+	ip vrf exec v$h1 $MZ $h1 -q -p 64 \
+		-A 198.51.100.2 -B 203.0.113.2 \
 		-d 1msec -t udp "sp=20000,dp=0-32768"
 }
 
 send_src_ipv6()
 {
-	$MZ -6 $h1 -q -p 64 -A "2001:db8:1::2-2001:db8:1::fd" -B 2001:db8:2::2 \
+	ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \
+		-A "2001:db8:1::2-2001:db8:1::fd" -B 2001:db8:2::2 \
 		-d 1msec -c 50 -t udp "sp=20000,dp=30000"
 }
 
 send_dst_ipv6()
 {
-	$MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B "2001:db8:2::2-2001:db8:2::fd" \
+	ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \
+		-A 2001:db8:1::2 -B "2001:db8:2::2-2001:db8:2::fd" \
 		-d 1msec -c 50 -t udp "sp=20000,dp=30000"
 }
 
@@ -323,13 +329,15 @@ send_flowlabel()
 
 send_src_udp6()
 {
-	$MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \
+	ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \
+		-A 2001:db8:1::2 -B 2001:db8:2::2 \
 		-d 1msec -t udp "sp=0-32768,dp=30000"
 }
 
 send_dst_udp6()
 {
-	$MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \
+	ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \
+		-A 2001:db8:1::2 -B 2001:db8:2::2 \
 		-d 1msec -t udp "sp=20000,dp=0-32768"
 }
 
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 6962ec3bcdfa..761484af55f0 100755
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -1212,6 +1212,7 @@ learning_test()
 	# FDB entry was installed.
 	bridge link set dev $br_port1 flood off
 
+	ip link set $host1_if promisc on
 	tc qdisc add dev $host1_if ingress
 	tc filter add dev $host1_if ingress protocol ip pref 1 handle 101 \
 		flower dst_mac $mac action drop
@@ -1222,7 +1223,7 @@ learning_test()
 	tc -j -s filter show dev $host1_if ingress \
 		| jq -e ".[] | select(.options.handle == 101) \
 		| select(.options.actions[0].stats.packets == 1)" &> /dev/null
-	check_fail $? "Packet reached second host when should not"
+	check_fail $? "Packet reached first host when should not"
 
 	$MZ $host1_if -c 1 -p 64 -a $mac -t ip -q
 	sleep 1
@@ -1261,6 +1262,7 @@ learning_test()
 
 	tc filter del dev $host1_if ingress protocol ip pref 1 handle 101 flower
 	tc qdisc del dev $host1_if ingress
+	ip link set $host1_if promisc off
 
 	bridge link set dev $br_port1 flood on
 
@@ -1278,6 +1280,7 @@ flood_test_do()
 
 	# Add an ACL on `host2_if` which will tell us whether the packet
 	# was flooded to it or not.
+	ip link set $host2_if promisc on
 	tc qdisc add dev $host2_if ingress
 	tc filter add dev $host2_if ingress protocol ip pref 1 handle 101 \
 		flower dst_mac $mac action drop
@@ -1295,6 +1298,7 @@ flood_test_do()
 
 	tc filter del dev $host2_if ingress protocol ip pref 1 handle 101 flower
 	tc qdisc del dev $host2_if ingress
+	ip link set $host2_if promisc off
 
 	return $err
 }
diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index ff821025d309..49dfabded1d4 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -61,6 +61,39 @@ chk_msk_nr()
 	__chk_nr "grep -c token:" $*
 }
 
+wait_msk_nr()
+{
+	local condition="grep -c token:"
+	local expected=$1
+	local timeout=20
+	local msg nr
+	local max=0
+	local i=0
+
+	shift 1
+	msg=$*
+
+	while [ $i -lt $timeout ]; do
+		nr=$(ss -inmHMN $ns | $condition)
+		[ $nr == $expected ] && break;
+		[ $nr -gt $max ] && max=$nr
+		i=$((i + 1))
+		sleep 1
+	done
+
+	printf "%-50s" "$msg"
+	if [ $i -ge $timeout ]; then
+		echo "[ fail ] timeout while expecting $expected max $max last $nr"
+		ret=$test_cnt
+	elif [ $nr != $expected ]; then
+		echo "[ fail ] expected $expected found $nr"
+		ret=$test_cnt
+	else
+		echo "[  ok  ]"
+	fi
+	test_cnt=$((test_cnt+1))
+}
+
 chk_msk_fallback_nr()
 {
 		__chk_nr "grep -c fallback" $*
@@ -109,7 +142,7 @@ ip -n $ns link set dev lo up
 echo "a" | \
 	timeout ${timeout_test} \
 		ip netns exec $ns \
-			./mptcp_connect -p 10000 -l -t ${timeout_poll} \
+			./mptcp_connect -p 10000 -l -t ${timeout_poll} -w 20 \
 				0.0.0.0 >/dev/null &
 wait_local_port_listen $ns 10000
 chk_msk_nr 0 "no msk on netns creation"
@@ -117,7 +150,7 @@ chk_msk_nr 0 "no msk on netns creation"
 echo "b" | \
 	timeout ${timeout_test} \
 		ip netns exec $ns \
-			./mptcp_connect -p 10000 -r 0 -t ${timeout_poll} \
+			./mptcp_connect -p 10000 -r 0 -t ${timeout_poll} -w 20 \
 				127.0.0.1 >/dev/null &
 wait_connected $ns 10000
 chk_msk_nr 2 "after MPC handshake "
@@ -129,13 +162,13 @@ flush_pids
 echo "a" | \
 	timeout ${timeout_test} \
 		ip netns exec $ns \
-			./mptcp_connect -p 10001 -l -s TCP -t ${timeout_poll} \
+			./mptcp_connect -p 10001 -l -s TCP -t ${timeout_poll} -w 20 \
 				0.0.0.0 >/dev/null &
 wait_local_port_listen $ns 10001
 echo "b" | \
 	timeout ${timeout_test} \
 		ip netns exec $ns \
-			./mptcp_connect -p 10001 -r 0 -t ${timeout_poll} \
+			./mptcp_connect -p 10001 -r 0 -t ${timeout_poll} -w 20 \
 				127.0.0.1 >/dev/null &
 wait_connected $ns 10001
 chk_msk_fallback_nr 1 "check fallback"
@@ -146,7 +179,7 @@ for I in `seq 1 $NR_CLIENTS`; do
 	echo "a" | \
 		timeout ${timeout_test} \
 			ip netns exec $ns \
-				./mptcp_connect -p $((I+10001)) -l -w 10 \
+				./mptcp_connect -p $((I+10001)) -l -w 20 \
 					-t ${timeout_poll} 0.0.0.0 >/dev/null &
 done
 wait_local_port_listen $ns $((NR_CLIENTS + 10001))
@@ -155,12 +188,11 @@ for I in `seq 1 $NR_CLIENTS`; do
 	echo "b" | \
 		timeout ${timeout_test} \
 			ip netns exec $ns \
-				./mptcp_connect -p $((I+10001)) -w 10 \
+				./mptcp_connect -p $((I+10001)) -w 20 \
 					-t ${timeout_poll} 127.0.0.1 >/dev/null &
 done
-sleep 1.5
 
-chk_msk_nr $((NR_CLIENTS*2)) "many msk socket present"
+wait_msk_nr $((NR_CLIENTS*2)) "many msk socket present"
 flush_pids
 
 exit $ret
diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh
index f8a19f548ae9..ebbd0b282432 100755
--- a/tools/testing/selftests/net/udpgro.sh
+++ b/tools/testing/selftests/net/udpgro.sh
@@ -34,7 +34,7 @@ cfg_veth() {
 	ip -netns "${PEER_NS}" addr add dev veth1 192.168.1.1/24
 	ip -netns "${PEER_NS}" addr add dev veth1 2001:db8::1/64 nodad
 	ip -netns "${PEER_NS}" link set dev veth1 up
-	ip -n "${PEER_NS}" link set veth1 xdp object ../bpf/xdp_dummy.o section xdp_dummy
+	ip -n "${PEER_NS}" link set veth1 xdp object ../bpf/xdp_dummy.o section xdp
 }
 
 run_one() {
diff --git a/tools/testing/selftests/net/udpgro_bench.sh b/tools/testing/selftests/net/udpgro_bench.sh
index 820bc50f6b68..fad2d1a71cac 100755
--- a/tools/testing/selftests/net/udpgro_bench.sh
+++ b/tools/testing/selftests/net/udpgro_bench.sh
@@ -34,7 +34,7 @@ run_one() {
 	ip -netns "${PEER_NS}" addr add dev veth1 2001:db8::1/64 nodad
 	ip -netns "${PEER_NS}" link set dev veth1 up
 
-	ip -n "${PEER_NS}" link set veth1 xdp object ../bpf/xdp_dummy.o section xdp_dummy
+	ip -n "${PEER_NS}" link set veth1 xdp object ../bpf/xdp_dummy.o section xdp
 	ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -r &
 	ip netns exec "${PEER_NS}" ./udpgso_bench_rx -t ${rx_args} -r &
 
diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh
index 6f05e06f6761..1bcd82e1f662 100755
--- a/tools/testing/selftests/net/udpgro_fwd.sh
+++ b/tools/testing/selftests/net/udpgro_fwd.sh
@@ -46,7 +46,7 @@ create_ns() {
 		ip -n $BASE$ns addr add dev veth$ns $BM_NET_V4$ns/24
 		ip -n $BASE$ns addr add dev veth$ns $BM_NET_V6$ns/64 nodad
 	done
-	ip -n $NS_DST link set veth$DST xdp object ../bpf/xdp_dummy.o section xdp_dummy 2>/dev/null
+	ip -n $NS_DST link set veth$DST xdp object ../bpf/xdp_dummy.o section xdp 2>/dev/null
 }
 
 create_vxlan_endpoint() {
diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh
index 80b5d352702e..dc932fd65363 100755
--- a/tools/testing/selftests/net/udpgso_bench.sh
+++ b/tools/testing/selftests/net/udpgso_bench.sh
@@ -120,7 +120,7 @@ run_all() {
 	run_udp "${ipv4_args}"
 
 	echo "ipv6"
-	run_tcp "${ipv4_args}"
+	run_tcp "${ipv6_args}"
 	run_udp "${ipv6_args}"
 }
 
diff --git a/tools/testing/selftests/net/veth.sh b/tools/testing/selftests/net/veth.sh
index 19eac3e44c06..430895d1a2b6 100755
--- a/tools/testing/selftests/net/veth.sh
+++ b/tools/testing/selftests/net/veth.sh
@@ -289,14 +289,14 @@ if [ $CPUS -gt 1 ]; then
 	ip netns exec $NS_SRC ethtool -L veth$SRC rx 1 tx 2 2>/dev/null
 	printf "%-60s" "bad setting: XDP with RX nr less than TX"
 	ip -n $NS_DST link set dev veth$DST xdp object ../bpf/xdp_dummy.o \
-		section xdp_dummy 2>/dev/null &&\
+		section xdp 2>/dev/null &&\
 		echo "fail - set operation successful ?!?" || echo " ok "
 
 	# the following tests will run with multiple channels active
 	ip netns exec $NS_SRC ethtool -L veth$SRC rx 2
 	ip netns exec $NS_DST ethtool -L veth$DST rx 2
 	ip -n $NS_DST link set dev veth$DST xdp object ../bpf/xdp_dummy.o \
-		section xdp_dummy 2>/dev/null
+		section xdp 2>/dev/null
 	printf "%-60s" "bad setting: reducing RX nr below peer TX with XDP set"
 	ip netns exec $NS_DST ethtool -L veth$DST rx 1 2>/dev/null &&\
 		echo "fail - set operation successful ?!?" || echo " ok "
@@ -311,7 +311,7 @@ if [ $CPUS -gt 2 ]; then
 	chk_channels "setting invalid channels nr" $DST 2 2
 fi
 
-ip -n $NS_DST link set dev veth$DST xdp object ../bpf/xdp_dummy.o section xdp_dummy 2>/dev/null
+ip -n $NS_DST link set dev veth$DST xdp object ../bpf/xdp_dummy.o section xdp 2>/dev/null
 chk_gro_flag "with xdp attached - gro flag" $DST on
 chk_gro_flag "        - peer gro flag" $SRC off
 chk_tso_flag "        - tso flag" $SRC off
diff --git a/tools/testing/selftests/netfilter/nft_flowtable.sh b/tools/testing/selftests/netfilter/nft_flowtable.sh
index d4ffebb989f8..c336e6c148d1 100755
--- a/tools/testing/selftests/netfilter/nft_flowtable.sh
+++ b/tools/testing/selftests/netfilter/nft_flowtable.sh
@@ -14,6 +14,11 @@
 # nft_flowtable.sh -o8000 -l1500 -r2000
 #
 
+sfx=$(mktemp -u "XXXXXXXX")
+ns1="ns1-$sfx"
+ns2="ns2-$sfx"
+nsr1="nsr1-$sfx"
+nsr2="nsr2-$sfx"
 
 # Kselftest framework requirement - SKIP code is 4.
 ksft_skip=4
@@ -36,18 +41,17 @@ checktool (){
 checktool "nft --version" "run test without nft tool"
 checktool "ip -Version" "run test without ip tool"
 checktool "which nc" "run test without nc (netcat)"
-checktool "ip netns add nsr1" "create net namespace"
+checktool "ip netns add $nsr1" "create net namespace $nsr1"
 
-ip netns add ns1
-ip netns add ns2
-
-ip netns add nsr2
+ip netns add $ns1
+ip netns add $ns2
+ip netns add $nsr2
 
 cleanup() {
-	for i in 1 2; do
-		ip netns del ns$i
-		ip netns del nsr$i
-	done
+	ip netns del $ns1
+	ip netns del $ns2
+	ip netns del $nsr1
+	ip netns del $nsr2
 
 	rm -f "$ns1in" "$ns1out"
 	rm -f "$ns2in" "$ns2out"
@@ -59,22 +63,21 @@ trap cleanup EXIT
 
 sysctl -q net.netfilter.nf_log_all_netns=1
 
-ip link add veth0 netns nsr1 type veth peer name eth0 netns ns1
-ip link add veth1 netns nsr1 type veth peer name veth0 netns nsr2
+ip link add veth0 netns $nsr1 type veth peer name eth0 netns $ns1
+ip link add veth1 netns $nsr1 type veth peer name veth0 netns $nsr2
 
-ip link add veth1 netns nsr2 type veth peer name eth0 netns ns2
+ip link add veth1 netns $nsr2 type veth peer name eth0 netns $ns2
 
 for dev in lo veth0 veth1; do
-  for i in 1 2; do
-    ip -net nsr$i link set $dev up
-  done
+    ip -net $nsr1 link set $dev up
+    ip -net $nsr2 link set $dev up
 done
 
-ip -net nsr1 addr add 10.0.1.1/24 dev veth0
-ip -net nsr1 addr add dead:1::1/64 dev veth0
+ip -net $nsr1 addr add 10.0.1.1/24 dev veth0
+ip -net $nsr1 addr add dead:1::1/64 dev veth0
 
-ip -net nsr2 addr add 10.0.2.1/24 dev veth1
-ip -net nsr2 addr add dead:2::1/64 dev veth1
+ip -net $nsr2 addr add 10.0.2.1/24 dev veth1
+ip -net $nsr2 addr add dead:2::1/64 dev veth1
 
 # set different MTUs so we need to push packets coming from ns1 (large MTU)
 # to ns2 (smaller MTU) to stack either to perform fragmentation (ip_no_pmtu_disc=1),
@@ -106,49 +109,56 @@ do
 	esac
 done
 
-if ! ip -net nsr1 link set veth0 mtu $omtu; then
+if ! ip -net $nsr1 link set veth0 mtu $omtu; then
 	exit 1
 fi
 
-ip -net ns1 link set eth0 mtu $omtu
+ip -net $ns1 link set eth0 mtu $omtu
 
-if ! ip -net nsr2 link set veth1 mtu $rmtu; then
+if ! ip -net $nsr2 link set veth1 mtu $rmtu; then
 	exit 1
 fi
 
-ip -net ns2 link set eth0 mtu $rmtu
+ip -net $ns2 link set eth0 mtu $rmtu
 
 # transfer-net between nsr1 and nsr2.
 # these addresses are not used for connections.
-ip -net nsr1 addr add 192.168.10.1/24 dev veth1
-ip -net nsr1 addr add fee1:2::1/64 dev veth1
-
-ip -net nsr2 addr add 192.168.10.2/24 dev veth0
-ip -net nsr2 addr add fee1:2::2/64 dev veth0
-
-for i in 1 2; do
-  ip netns exec nsr$i sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
-  ip netns exec nsr$i sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
-
-  ip -net ns$i link set lo up
-  ip -net ns$i link set eth0 up
-  ip -net ns$i addr add 10.0.$i.99/24 dev eth0
-  ip -net ns$i route add default via 10.0.$i.1
-  ip -net ns$i addr add dead:$i::99/64 dev eth0
-  ip -net ns$i route add default via dead:$i::1
-  if ! ip netns exec ns$i sysctl net.ipv4.tcp_no_metrics_save=1 > /dev/null; then
+ip -net $nsr1 addr add 192.168.10.1/24 dev veth1
+ip -net $nsr1 addr add fee1:2::1/64 dev veth1
+
+ip -net $nsr2 addr add 192.168.10.2/24 dev veth0
+ip -net $nsr2 addr add fee1:2::2/64 dev veth0
+
+for i in 0 1; do
+  ip netns exec $nsr1 sysctl net.ipv4.conf.veth$i.forwarding=1 > /dev/null
+  ip netns exec $nsr2 sysctl net.ipv4.conf.veth$i.forwarding=1 > /dev/null
+done
+
+for ns in $ns1 $ns2;do
+  ip -net $ns link set lo up
+  ip -net $ns link set eth0 up
+
+  if ! ip netns exec $ns sysctl net.ipv4.tcp_no_metrics_save=1 > /dev/null; then
 	echo "ERROR: Check Originator/Responder values (problem during address addition)"
 	exit 1
   fi
-
   # don't set ip DF bit for first two tests
-  ip netns exec ns$i sysctl net.ipv4.ip_no_pmtu_disc=1 > /dev/null
+  ip netns exec $ns sysctl net.ipv4.ip_no_pmtu_disc=1 > /dev/null
 done
 
-ip -net nsr1 route add default via 192.168.10.2
-ip -net nsr2 route add default via 192.168.10.1
+ip -net $ns1 addr add 10.0.1.99/24 dev eth0
+ip -net $ns2 addr add 10.0.2.99/24 dev eth0
+ip -net $ns1 route add default via 10.0.1.1
+ip -net $ns2 route add default via 10.0.2.1
+ip -net $ns1 addr add dead:1::99/64 dev eth0
+ip -net $ns2 addr add dead:2::99/64 dev eth0
+ip -net $ns1 route add default via dead:1::1
+ip -net $ns2 route add default via dead:2::1
+
+ip -net $nsr1 route add default via 192.168.10.2
+ip -net $nsr2 route add default via 192.168.10.1
 
-ip netns exec nsr1 nft -f - <<EOF
+ip netns exec $nsr1 nft -f - <<EOF
 table inet filter {
   flowtable f1 {
      hook ingress priority 0
@@ -197,18 +207,18 @@ if [ $? -ne 0 ]; then
 fi
 
 # test basic connectivity
-if ! ip netns exec ns1 ping -c 1 -q 10.0.2.99 > /dev/null; then
-  echo "ERROR: ns1 cannot reach ns2" 1>&2
+if ! ip netns exec $ns1 ping -c 1 -q 10.0.2.99 > /dev/null; then
+  echo "ERROR: $ns1 cannot reach ns2" 1>&2
   exit 1
 fi
 
-if ! ip netns exec ns2 ping -c 1 -q 10.0.1.99 > /dev/null; then
-  echo "ERROR: ns2 cannot reach ns1" 1>&2
+if ! ip netns exec $ns2 ping -c 1 -q 10.0.1.99 > /dev/null; then
+  echo "ERROR: $ns2 cannot reach $ns1" 1>&2
   exit 1
 fi
 
 if [ $ret -eq 0 ];then
-	echo "PASS: netns routing/connectivity: ns1 can reach ns2"
+	echo "PASS: netns routing/connectivity: $ns1 can reach $ns2"
 fi
 
 ns1in=$(mktemp)
@@ -312,24 +322,24 @@ make_file "$ns2in"
 
 # First test:
 # No PMTU discovery, nsr1 is expected to fragment packets from ns1 to ns2 as needed.
-if test_tcp_forwarding ns1 ns2; then
+if test_tcp_forwarding $ns1 $ns2; then
 	echo "PASS: flow offloaded for ns1/ns2"
 else
 	echo "FAIL: flow offload for ns1/ns2:" 1>&2
-	ip netns exec nsr1 nft list ruleset
+	ip netns exec $nsr1 nft list ruleset
 	ret=1
 fi
 
 # delete default route, i.e. ns2 won't be able to reach ns1 and
 # will depend on ns1 being masqueraded in nsr1.
 # expect ns1 has nsr1 address.
-ip -net ns2 route del default via 10.0.2.1
-ip -net ns2 route del default via dead:2::1
-ip -net ns2 route add 192.168.10.1 via 10.0.2.1
+ip -net $ns2 route del default via 10.0.2.1
+ip -net $ns2 route del default via dead:2::1
+ip -net $ns2 route add 192.168.10.1 via 10.0.2.1
 
 # Second test:
 # Same, but with NAT enabled.
-ip netns exec nsr1 nft -f - <<EOF
+ip netns exec $nsr1 nft -f - <<EOF
 table ip nat {
    chain prerouting {
       type nat hook prerouting priority 0; policy accept;
@@ -343,47 +353,47 @@ table ip nat {
 }
 EOF
 
-if test_tcp_forwarding_nat ns1 ns2; then
+if test_tcp_forwarding_nat $ns1 $ns2; then
 	echo "PASS: flow offloaded for ns1/ns2 with NAT"
 else
 	echo "FAIL: flow offload for ns1/ns2 with NAT" 1>&2
-	ip netns exec nsr1 nft list ruleset
+	ip netns exec $nsr1 nft list ruleset
 	ret=1
 fi
 
 # Third test:
 # Same as second test, but with PMTU discovery enabled.
-handle=$(ip netns exec nsr1 nft -a list table inet filter | grep something-to-grep-for | cut -d \# -f 2)
+handle=$(ip netns exec $nsr1 nft -a list table inet filter | grep something-to-grep-for | cut -d \# -f 2)
 
-if ! ip netns exec nsr1 nft delete rule inet filter forward $handle; then
+if ! ip netns exec $nsr1 nft delete rule inet filter forward $handle; then
 	echo "FAIL: Could not delete large-packet accept rule"
 	exit 1
 fi
 
-ip netns exec ns1 sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null
-ip netns exec ns2 sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null
+ip netns exec $ns1 sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null
+ip netns exec $ns2 sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null
 
-if test_tcp_forwarding_nat ns1 ns2; then
+if test_tcp_forwarding_nat $ns1 $ns2; then
 	echo "PASS: flow offloaded for ns1/ns2 with NAT and pmtu discovery"
 else
 	echo "FAIL: flow offload for ns1/ns2 with NAT and pmtu discovery" 1>&2
-	ip netns exec nsr1 nft list ruleset
+	ip netns exec $nsr1 nft list ruleset
 fi
 
 # Another test:
 # Add bridge interface br0 to Router1, with NAT enabled.
-ip -net nsr1 link add name br0 type bridge
-ip -net nsr1 addr flush dev veth0
-ip -net nsr1 link set up dev veth0
-ip -net nsr1 link set veth0 master br0
-ip -net nsr1 addr add 10.0.1.1/24 dev br0
-ip -net nsr1 addr add dead:1::1/64 dev br0
-ip -net nsr1 link set up dev br0
+ip -net $nsr1 link add name br0 type bridge
+ip -net $nsr1 addr flush dev veth0
+ip -net $nsr1 link set up dev veth0
+ip -net $nsr1 link set veth0 master br0
+ip -net $nsr1 addr add 10.0.1.1/24 dev br0
+ip -net $nsr1 addr add dead:1::1/64 dev br0
+ip -net $nsr1 link set up dev br0
 
-ip netns exec nsr1 sysctl net.ipv4.conf.br0.forwarding=1 > /dev/null
+ip netns exec $nsr1 sysctl net.ipv4.conf.br0.forwarding=1 > /dev/null
 
 # br0 with NAT enabled.
-ip netns exec nsr1 nft -f - <<EOF
+ip netns exec $nsr1 nft -f - <<EOF
 flush table ip nat
 table ip nat {
    chain prerouting {
@@ -398,59 +408,59 @@ table ip nat {
 }
 EOF
 
-if test_tcp_forwarding_nat ns1 ns2; then
+if test_tcp_forwarding_nat $ns1 $ns2; then
 	echo "PASS: flow offloaded for ns1/ns2 with bridge NAT"
 else
 	echo "FAIL: flow offload for ns1/ns2 with bridge NAT" 1>&2
-	ip netns exec nsr1 nft list ruleset
+	ip netns exec $nsr1 nft list ruleset
 	ret=1
 fi
 
 # Another test:
 # Add bridge interface br0 to Router1, with NAT and VLAN.
-ip -net nsr1 link set veth0 nomaster
-ip -net nsr1 link set down dev veth0
-ip -net nsr1 link add link veth0 name veth0.10 type vlan id 10
-ip -net nsr1 link set up dev veth0
-ip -net nsr1 link set up dev veth0.10
-ip -net nsr1 link set veth0.10 master br0
-
-ip -net ns1 addr flush dev eth0
-ip -net ns1 link add link eth0 name eth0.10 type vlan id 10
-ip -net ns1 link set eth0 up
-ip -net ns1 link set eth0.10 up
-ip -net ns1 addr add 10.0.1.99/24 dev eth0.10
-ip -net ns1 route add default via 10.0.1.1
-ip -net ns1 addr add dead:1::99/64 dev eth0.10
-
-if test_tcp_forwarding_nat ns1 ns2; then
+ip -net $nsr1 link set veth0 nomaster
+ip -net $nsr1 link set down dev veth0
+ip -net $nsr1 link add link veth0 name veth0.10 type vlan id 10
+ip -net $nsr1 link set up dev veth0
+ip -net $nsr1 link set up dev veth0.10
+ip -net $nsr1 link set veth0.10 master br0
+
+ip -net $ns1 addr flush dev eth0
+ip -net $ns1 link add link eth0 name eth0.10 type vlan id 10
+ip -net $ns1 link set eth0 up
+ip -net $ns1 link set eth0.10 up
+ip -net $ns1 addr add 10.0.1.99/24 dev eth0.10
+ip -net $ns1 route add default via 10.0.1.1
+ip -net $ns1 addr add dead:1::99/64 dev eth0.10
+
+if test_tcp_forwarding_nat $ns1 $ns2; then
 	echo "PASS: flow offloaded for ns1/ns2 with bridge NAT and VLAN"
 else
 	echo "FAIL: flow offload for ns1/ns2 with bridge NAT and VLAN" 1>&2
-	ip netns exec nsr1 nft list ruleset
+	ip netns exec $nsr1 nft list ruleset
 	ret=1
 fi
 
 # restore test topology (remove bridge and VLAN)
-ip -net nsr1 link set veth0 nomaster
-ip -net nsr1 link set veth0 down
-ip -net nsr1 link set veth0.10 down
-ip -net nsr1 link delete veth0.10 type vlan
-ip -net nsr1 link delete br0 type bridge
-ip -net ns1 addr flush dev eth0.10
-ip -net ns1 link set eth0.10 down
-ip -net ns1 link set eth0 down
-ip -net ns1 link delete eth0.10 type vlan
+ip -net $nsr1 link set veth0 nomaster
+ip -net $nsr1 link set veth0 down
+ip -net $nsr1 link set veth0.10 down
+ip -net $nsr1 link delete veth0.10 type vlan
+ip -net $nsr1 link delete br0 type bridge
+ip -net $ns1 addr flush dev eth0.10
+ip -net $ns1 link set eth0.10 down
+ip -net $ns1 link set eth0 down
+ip -net $ns1 link delete eth0.10 type vlan
 
 # restore address in ns1 and nsr1
-ip -net ns1 link set eth0 up
-ip -net ns1 addr add 10.0.1.99/24 dev eth0
-ip -net ns1 route add default via 10.0.1.1
-ip -net ns1 addr add dead:1::99/64 dev eth0
-ip -net ns1 route add default via dead:1::1
-ip -net nsr1 addr add 10.0.1.1/24 dev veth0
-ip -net nsr1 addr add dead:1::1/64 dev veth0
-ip -net nsr1 link set up dev veth0
+ip -net $ns1 link set eth0 up
+ip -net $ns1 addr add 10.0.1.99/24 dev eth0
+ip -net $ns1 route add default via 10.0.1.1
+ip -net $ns1 addr add dead:1::99/64 dev eth0
+ip -net $ns1 route add default via dead:1::1
+ip -net $nsr1 addr add 10.0.1.1/24 dev veth0
+ip -net $nsr1 addr add dead:1::1/64 dev veth0
+ip -net $nsr1 link set up dev veth0
 
 KEY_SHA="0x"$(ps -xaf | sha1sum | cut -d " " -f 1)
 KEY_AES="0x"$(ps -xaf | md5sum | cut -d " " -f 1)
@@ -480,23 +490,23 @@ do_esp() {
 
 }
 
-do_esp nsr1 192.168.10.1 192.168.10.2 10.0.1.0/24 10.0.2.0/24 $SPI1 $SPI2
+do_esp $nsr1 192.168.10.1 192.168.10.2 10.0.1.0/24 10.0.2.0/24 $SPI1 $SPI2
 
-do_esp nsr2 192.168.10.2 192.168.10.1 10.0.2.0/24 10.0.1.0/24 $SPI2 $SPI1
+do_esp $nsr2 192.168.10.2 192.168.10.1 10.0.2.0/24 10.0.1.0/24 $SPI2 $SPI1
 
-ip netns exec nsr1 nft delete table ip nat
+ip netns exec $nsr1 nft delete table ip nat
 
 # restore default routes
-ip -net ns2 route del 192.168.10.1 via 10.0.2.1
-ip -net ns2 route add default via 10.0.2.1
-ip -net ns2 route add default via dead:2::1
+ip -net $ns2 route del 192.168.10.1 via 10.0.2.1
+ip -net $ns2 route add default via 10.0.2.1
+ip -net $ns2 route add default via dead:2::1
 
-if test_tcp_forwarding ns1 ns2; then
+if test_tcp_forwarding $ns1 $ns2; then
 	echo "PASS: ipsec tunnel mode for ns1/ns2"
 else
 	echo "FAIL: ipsec tunnel mode for ns1/ns2"
-	ip netns exec nsr1 nft list ruleset 1>&2
-	ip netns exec nsr1 cat /proc/net/xfrm_stat 1>&2
+	ip netns exec $nsr1 nft list ruleset 1>&2
+	ip netns exec $nsr1 cat /proc/net/xfrm_stat 1>&2
 fi
 
 exit $ret
diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile
index 2af9d39a9716..215e1067f037 100644
--- a/tools/testing/selftests/rseq/Makefile
+++ b/tools/testing/selftests/rseq/Makefile
@@ -6,7 +6,7 @@ endif
 
 CFLAGS += -O2 -Wall -g -I./ -I../../../../usr/include/ -L$(OUTPUT) -Wl,-rpath=./ \
 	  $(CLANG_FLAGS)
-LDLIBS += -lpthread
+LDLIBS += -lpthread -ldl
 
 # Own dependencies because we only want to build against 1st prerequisite, but
 # still track changes to header files and depend on shared object.
diff --git a/tools/testing/selftests/rseq/basic_percpu_ops_test.c b/tools/testing/selftests/rseq/basic_percpu_ops_test.c
index eb3f6db36d36..517756afc2a4 100644
--- a/tools/testing/selftests/rseq/basic_percpu_ops_test.c
+++ b/tools/testing/selftests/rseq/basic_percpu_ops_test.c
@@ -9,10 +9,9 @@
 #include <string.h>
 #include <stddef.h>
 
+#include "../kselftest.h"
 #include "rseq.h"
 
-#define ARRAY_SIZE(arr)	(sizeof(arr) / sizeof((arr)[0]))
-
 struct percpu_lock_entry {
 	intptr_t v;
 } __attribute__((aligned(128)));
@@ -168,7 +167,7 @@ struct percpu_list_node *this_cpu_list_pop(struct percpu_list *list,
 	for (;;) {
 		struct percpu_list_node *head;
 		intptr_t *targetptr, expectnot, *load;
-		off_t offset;
+		long offset;
 		int ret, cpu;
 
 		cpu = rseq_cpu_start();
diff --git a/tools/testing/selftests/rseq/compiler.h b/tools/testing/selftests/rseq/compiler.h
new file mode 100644
index 000000000000..876eb6a7f75b
--- /dev/null
+++ b/tools/testing/selftests/rseq/compiler.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */
+/*
+ * rseq/compiler.h
+ *
+ * Work-around asm goto compiler bugs.
+ *
+ * (C) Copyright 2021 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#ifndef RSEQ_COMPILER_H
+#define RSEQ_COMPILER_H
+
+/*
+ * gcc prior to 4.8.2 miscompiles asm goto.
+ * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670
+ *
+ * gcc prior to 8.1.0 miscompiles asm goto at O1.
+ * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103908
+ *
+ * clang prior to version 13.0.1 miscompiles asm goto at O2.
+ * https://github.com/llvm/llvm-project/issues/52735
+ *
+ * Work around these issues by adding a volatile inline asm with
+ * memory clobber in the fallthrough after the asm goto and at each
+ * label target.  Emit this for all compilers in case other similar
+ * issues are found in the future.
+ */
+#define rseq_after_asm_goto()	asm volatile ("" : : : "memory")
+
+#endif  /* RSEQ_COMPILER_H_ */
diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c
index 699ad5f93c34..da23c22d5882 100644
--- a/tools/testing/selftests/rseq/param_test.c
+++ b/tools/testing/selftests/rseq/param_test.c
@@ -161,7 +161,7 @@ unsigned int yield_mod_cnt, nr_abort;
 	"	cbnz	" INJECT_ASM_REG ", 222b\n"			\
 	"333:\n"
 
-#elif __PPC__
+#elif defined(__PPC__)
 
 #define RSEQ_INJECT_INPUT \
 	, [loop_cnt_1]"m"(loop_cnt[1]) \
@@ -368,9 +368,7 @@ void *test_percpu_spinlock_thread(void *arg)
 		abort();
 	reps = thread_data->reps;
 	for (i = 0; i < reps; i++) {
-		int cpu = rseq_cpu_start();
-
-		cpu = rseq_this_cpu_lock(&data->lock);
+		int cpu = rseq_this_cpu_lock(&data->lock);
 		data->c[cpu].count++;
 		rseq_percpu_unlock(&data->lock, cpu);
 #ifndef BENCHMARK
@@ -551,7 +549,7 @@ struct percpu_list_node *this_cpu_list_pop(struct percpu_list *list,
 	for (;;) {
 		struct percpu_list_node *head;
 		intptr_t *targetptr, expectnot, *load;
-		off_t offset;
+		long offset;
 		int ret;
 
 		cpu = rseq_cpu_start();
diff --git a/tools/testing/selftests/rseq/rseq-abi.h b/tools/testing/selftests/rseq/rseq-abi.h
new file mode 100644
index 000000000000..a8c44d9af71f
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-abi.h
@@ -0,0 +1,151 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+#ifndef _RSEQ_ABI_H
+#define _RSEQ_ABI_H
+
+/*
+ * rseq-abi.h
+ *
+ * Restartable sequences system call API
+ *
+ * Copyright (c) 2015-2022 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+
+enum rseq_abi_cpu_id_state {
+	RSEQ_ABI_CPU_ID_UNINITIALIZED			= -1,
+	RSEQ_ABI_CPU_ID_REGISTRATION_FAILED		= -2,
+};
+
+enum rseq_abi_flags {
+	RSEQ_ABI_FLAG_UNREGISTER = (1 << 0),
+};
+
+enum rseq_abi_cs_flags_bit {
+	RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT	= 0,
+	RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT	= 1,
+	RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT	= 2,
+};
+
+enum rseq_abi_cs_flags {
+	RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT	=
+		(1U << RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT),
+	RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL	=
+		(1U << RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT),
+	RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE	=
+		(1U << RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT),
+};
+
+/*
+ * struct rseq_abi_cs is aligned on 4 * 8 bytes to ensure it is always
+ * contained within a single cache-line. It is usually declared as
+ * link-time constant data.
+ */
+struct rseq_abi_cs {
+	/* Version of this structure. */
+	__u32 version;
+	/* enum rseq_abi_cs_flags */
+	__u32 flags;
+	__u64 start_ip;
+	/* Offset from start_ip. */
+	__u64 post_commit_offset;
+	__u64 abort_ip;
+} __attribute__((aligned(4 * sizeof(__u64))));
+
+/*
+ * struct rseq_abi is aligned on 4 * 8 bytes to ensure it is always
+ * contained within a single cache-line.
+ *
+ * A single struct rseq_abi per thread is allowed.
+ */
+struct rseq_abi {
+	/*
+	 * Restartable sequences cpu_id_start field. Updated by the
+	 * kernel. Read by user-space with single-copy atomicity
+	 * semantics. This field should only be read by the thread which
+	 * registered this data structure. Aligned on 32-bit. Always
+	 * contains a value in the range of possible CPUs, although the
+	 * value may not be the actual current CPU (e.g. if rseq is not
+	 * initialized). This CPU number value should always be compared
+	 * against the value of the cpu_id field before performing a rseq
+	 * commit or returning a value read from a data structure indexed
+	 * using the cpu_id_start value.
+	 */
+	__u32 cpu_id_start;
+	/*
+	 * Restartable sequences cpu_id field. Updated by the kernel.
+	 * Read by user-space with single-copy atomicity semantics. This
+	 * field should only be read by the thread which registered this
+	 * data structure. Aligned on 32-bit. Values
+	 * RSEQ_CPU_ID_UNINITIALIZED and RSEQ_CPU_ID_REGISTRATION_FAILED
+	 * have a special semantic: the former means "rseq uninitialized",
+	 * and latter means "rseq initialization failed". This value is
+	 * meant to be read within rseq critical sections and compared
+	 * with the cpu_id_start value previously read, before performing
+	 * the commit instruction, or read and compared with the
+	 * cpu_id_start value before returning a value loaded from a data
+	 * structure indexed using the cpu_id_start value.
+	 */
+	__u32 cpu_id;
+	/*
+	 * Restartable sequences rseq_cs field.
+	 *
+	 * Contains NULL when no critical section is active for the current
+	 * thread, or holds a pointer to the currently active struct rseq_cs.
+	 *
+	 * Updated by user-space, which sets the address of the currently
+	 * active rseq_cs at the beginning of assembly instruction sequence
+	 * block, and set to NULL by the kernel when it restarts an assembly
+	 * instruction sequence block, as well as when the kernel detects that
+	 * it is preempting or delivering a signal outside of the range
+	 * targeted by the rseq_cs. Also needs to be set to NULL by user-space
+	 * before reclaiming memory that contains the targeted struct rseq_cs.
+	 *
+	 * Read and set by the kernel. Set by user-space with single-copy
+	 * atomicity semantics. This field should only be updated by the
+	 * thread which registered this data structure. Aligned on 64-bit.
+	 */
+	union {
+		__u64 ptr64;
+
+		/*
+		 * The "arch" field provides architecture accessor for
+		 * the ptr field based on architecture pointer size and
+		 * endianness.
+		 */
+		struct {
+#ifdef __LP64__
+			__u64 ptr;
+#elif defined(__BYTE_ORDER) ? (__BYTE_ORDER == __BIG_ENDIAN) : defined(__BIG_ENDIAN)
+			__u32 padding;		/* Initialized to zero. */
+			__u32 ptr;
+#else
+			__u32 ptr;
+			__u32 padding;		/* Initialized to zero. */
+#endif
+		} arch;
+	} rseq_cs;
+
+	/*
+	 * Restartable sequences flags field.
+	 *
+	 * This field should only be updated by the thread which
+	 * registered this data structure. Read by the kernel.
+	 * Mainly used for single-stepping through rseq critical sections
+	 * with debuggers.
+	 *
+	 * - RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT
+	 *     Inhibit instruction sequence block restart on preemption
+	 *     for this thread.
+	 * - RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL
+	 *     Inhibit instruction sequence block restart on signal
+	 *     delivery for this thread.
+	 * - RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE
+	 *     Inhibit instruction sequence block restart on migration for
+	 *     this thread.
+	 */
+	__u32 flags;
+} __attribute__((aligned(4 * sizeof(__u64))));
+
+#endif /* _RSEQ_ABI_H */
diff --git a/tools/testing/selftests/rseq/rseq-arm.h b/tools/testing/selftests/rseq/rseq-arm.h
index 5943c816c07c..893a11eca9d5 100644
--- a/tools/testing/selftests/rseq/rseq-arm.h
+++ b/tools/testing/selftests/rseq/rseq-arm.h
@@ -147,14 +147,11 @@ do {									\
 		teardown						\
 		"b %l[" __rseq_str(cmpfail_label) "]\n\t"
 
-#define rseq_workaround_gcc_asm_size_guess()	__asm__ __volatile__("")
-
 static inline __attribute__((always_inline))
 int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 {
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -185,8 +182,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		"5:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  [v]			"m" (*v),
 		  [expect]		"r" (expect),
 		  [newv]		"r" (newv)
@@ -198,30 +195,31 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		  , error1, error2
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
 
 static inline __attribute__((always_inline))
 int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
-			       off_t voffp, intptr_t *load, int cpu)
+			       long voffp, intptr_t *load, int cpu)
 {
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -255,8 +253,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		"5:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expectnot]		"r" (expectnot),
@@ -270,19 +268,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		  , error1, error2
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -292,7 +292,6 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 {
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 #ifdef RSEQ_COMPARE_TWICE
@@ -316,8 +315,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		"5:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  [v]			"m" (*v),
 		  [count]		"Ir" (count)
 		  RSEQ_INJECT_INPUT
@@ -328,14 +327,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		  , error1
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 #endif
 }
@@ -347,7 +347,6 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 {
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -381,8 +380,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		"5:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* try store input */
 		  [v2]			"m" (*v2),
 		  [newv2]		"r" (newv2),
@@ -398,19 +397,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -422,7 +423,6 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
 {
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -457,8 +457,8 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
 		"5:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* try store input */
 		  [v2]			"m" (*v2),
 		  [newv2]		"r" (newv2),
@@ -474,19 +474,21 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -498,7 +500,6 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 {
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -537,8 +538,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		"5:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* cmp2 input */
 		  [v2]			"m" (*v2),
 		  [expect2]		"r" (expect2),
@@ -554,21 +555,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2, error3
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("1st expected value comparison failed");
 error3:
+	rseq_after_asm_goto();
 	rseq_bug("2nd expected value comparison failed");
 #endif
 }
@@ -582,7 +586,6 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -657,8 +660,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 		"8:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expect]		"r" (expect),
@@ -678,21 +681,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -706,7 +709,6 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
 
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -782,8 +784,8 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
 		"8:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expect]		"r" (expect),
@@ -803,21 +805,21 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
diff --git a/tools/testing/selftests/rseq/rseq-arm64.h b/tools/testing/selftests/rseq/rseq-arm64.h
index 200dae9e4208..cbe190a4d005 100644
--- a/tools/testing/selftests/rseq/rseq-arm64.h
+++ b/tools/testing/selftests/rseq/rseq-arm64.h
@@ -230,8 +230,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"Qo" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  [v]			"Qo" (*v),
 		  [expect]		"r" (expect),
 		  [newv]		"r" (newv)
@@ -242,24 +242,28 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		  , error1, error2
 #endif
 	);
-
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
 
 static inline __attribute__((always_inline))
 int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
-			       off_t voffp, intptr_t *load, int cpu)
+			       long voffp, intptr_t *load, int cpu)
 {
 	RSEQ_INJECT_C(9)
 
@@ -287,8 +291,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"Qo" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  [v]			"Qo" (*v),
 		  [expectnot]		"r" (expectnot),
 		  [load]		"Qo" (*load),
@@ -300,16 +304,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -337,8 +346,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"Qo" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  [v]			"Qo" (*v),
 		  [count]		"r" (count)
 		  RSEQ_INJECT_INPUT
@@ -348,12 +357,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		  , error1
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 #endif
 }
@@ -388,8 +400,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"Qo" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  [expect]		"r" (expect),
 		  [v]			"Qo" (*v),
 		  [newv]		"r" (newv),
@@ -402,17 +414,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
-
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -447,8 +463,8 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"Qo" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  [expect]		"r" (expect),
 		  [v]			"Qo" (*v),
 		  [newv]		"r" (newv),
@@ -461,17 +477,21 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
-
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -508,8 +528,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"Qo" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  [v]			"Qo" (*v),
 		  [expect]		"r" (expect),
 		  [v2]			"Qo" (*v2),
@@ -522,19 +542,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2, error3
 #endif
 	);
-
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 error3:
+	rseq_after_asm_goto();
 	rseq_bug("2nd expected value comparison failed");
 #endif
 }
@@ -569,8 +594,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"Qo" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  [expect]		"r" (expect),
 		  [v]			"Qo" (*v),
 		  [newv]		"r" (newv),
@@ -584,17 +609,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
-
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -629,8 +658,8 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"Qo" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  [expect]		"r" (expect),
 		  [v]			"Qo" (*v),
 		  [newv]		"r" (newv),
@@ -644,17 +673,21 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
-
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
diff --git a/tools/testing/selftests/rseq/rseq-generic-thread-pointer.h b/tools/testing/selftests/rseq/rseq-generic-thread-pointer.h
new file mode 100644
index 000000000000..38c584661571
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-generic-thread-pointer.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */
+/*
+ * rseq-generic-thread-pointer.h
+ *
+ * (C) Copyright 2021 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#ifndef _RSEQ_GENERIC_THREAD_POINTER
+#define _RSEQ_GENERIC_THREAD_POINTER
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Use gcc builtin thread pointer. */
+static inline void *rseq_thread_pointer(void)
+{
+	return __builtin_thread_pointer();
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif
diff --git a/tools/testing/selftests/rseq/rseq-mips.h b/tools/testing/selftests/rseq/rseq-mips.h
index e989e7c14b09..878739fae2fd 100644
--- a/tools/testing/selftests/rseq/rseq-mips.h
+++ b/tools/testing/selftests/rseq/rseq-mips.h
@@ -154,14 +154,11 @@ do {									\
 		teardown \
 		"b %l[" __rseq_str(cmpfail_label) "]\n\t"
 
-#define rseq_workaround_gcc_asm_size_guess()	__asm__ __volatile__("")
-
 static inline __attribute__((always_inline))
 int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 {
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -190,8 +187,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		"5:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  [v]			"m" (*v),
 		  [expect]		"r" (expect),
 		  [newv]		"r" (newv)
@@ -203,14 +200,11 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		  , error1, error2
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
-	rseq_workaround_gcc_asm_size_guess();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
@@ -222,11 +216,10 @@ error2:
 
 static inline __attribute__((always_inline))
 int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
-			       off_t voffp, intptr_t *load, int cpu)
+			       long voffp, intptr_t *load, int cpu)
 {
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -258,8 +251,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		"5:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expectnot]		"r" (expectnot),
@@ -273,14 +266,11 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		  , error1, error2
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
-	rseq_workaround_gcc_asm_size_guess();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
@@ -295,7 +285,6 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 {
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 #ifdef RSEQ_COMPARE_TWICE
@@ -319,8 +308,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		"5:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  [v]			"m" (*v),
 		  [count]		"Ir" (count)
 		  RSEQ_INJECT_INPUT
@@ -331,10 +320,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		  , error1
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
 	RSEQ_INJECT_FAILED
 	return -1;
 #ifdef RSEQ_COMPARE_TWICE
@@ -350,7 +337,6 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 {
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -382,8 +368,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		"5:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* try store input */
 		  [v2]			"m" (*v2),
 		  [newv2]		"r" (newv2),
@@ -399,14 +385,11 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
-	rseq_workaround_gcc_asm_size_guess();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
@@ -423,7 +406,6 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
 {
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -456,8 +438,8 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
 		"5:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* try store input */
 		  [v2]			"m" (*v2),
 		  [newv2]		"r" (newv2),
@@ -473,14 +455,11 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
-	rseq_workaround_gcc_asm_size_guess();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
@@ -497,7 +476,6 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 {
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -532,8 +510,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		"5:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* cmp2 input */
 		  [v2]			"m" (*v2),
 		  [expect2]		"r" (expect2),
@@ -549,14 +527,11 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2, error3
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
-	rseq_workaround_gcc_asm_size_guess();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
@@ -577,7 +552,6 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -649,8 +623,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 		"8:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expect]		"r" (expect),
@@ -670,21 +644,16 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
-	rseq_workaround_gcc_asm_size_guess();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
-	rseq_workaround_gcc_asm_size_guess();
 	rseq_bug("cpu_id comparison failed");
 error2:
-	rseq_workaround_gcc_asm_size_guess();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -698,7 +667,6 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
 
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -771,8 +739,8 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
 		"8:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expect]		"r" (expect),
@@ -792,21 +760,16 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
-	rseq_workaround_gcc_asm_size_guess();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
-	rseq_workaround_gcc_asm_size_guess();
 	rseq_bug("cpu_id comparison failed");
 error2:
-	rseq_workaround_gcc_asm_size_guess();
 	rseq_bug("expected value comparison failed");
 #endif
 }
diff --git a/tools/testing/selftests/rseq/rseq-ppc-thread-pointer.h b/tools/testing/selftests/rseq/rseq-ppc-thread-pointer.h
new file mode 100644
index 000000000000..263eee84fb76
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-ppc-thread-pointer.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */
+/*
+ * rseq-ppc-thread-pointer.h
+ *
+ * (C) Copyright 2021 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#ifndef _RSEQ_PPC_THREAD_POINTER
+#define _RSEQ_PPC_THREAD_POINTER
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+static inline void *rseq_thread_pointer(void)
+{
+#ifdef __powerpc64__
+	register void *__result asm ("r13");
+#else
+	register void *__result asm ("r2");
+#endif
+	asm ("" : "=r" (__result));
+	return __result;
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif
diff --git a/tools/testing/selftests/rseq/rseq-ppc.h b/tools/testing/selftests/rseq/rseq-ppc.h
index 76be90196fe4..bab8e0b9fb11 100644
--- a/tools/testing/selftests/rseq/rseq-ppc.h
+++ b/tools/testing/selftests/rseq/rseq-ppc.h
@@ -47,10 +47,13 @@ do {									\
 
 #ifdef __PPC64__
 
-#define STORE_WORD	"std "
-#define LOAD_WORD	"ld "
-#define LOADX_WORD	"ldx "
-#define CMP_WORD	"cmpd "
+#define RSEQ_STORE_LONG(arg)	"std%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] "	/* To memory ("m" constraint) */
+#define RSEQ_STORE_INT(arg)	"stw%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] "	/* To memory ("m" constraint) */
+#define RSEQ_LOAD_LONG(arg)	"ld%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] "	/* From memory ("m" constraint) */
+#define RSEQ_LOAD_INT(arg)	"lwz%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] "	/* From memory ("m" constraint) */
+#define RSEQ_LOADX_LONG		"ldx "							/* From base register ("b" constraint) */
+#define RSEQ_CMP_LONG		"cmpd "
+#define RSEQ_CMP_LONG_INT	"cmpdi "
 
 #define __RSEQ_ASM_DEFINE_TABLE(label, version, flags,				\
 			start_ip, post_commit_offset, abort_ip)			\
@@ -89,10 +92,13 @@ do {									\
 
 #else /* #ifdef __PPC64__ */
 
-#define STORE_WORD	"stw "
-#define LOAD_WORD	"lwz "
-#define LOADX_WORD	"lwzx "
-#define CMP_WORD	"cmpw "
+#define RSEQ_STORE_LONG(arg)	"stw%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] "	/* To memory ("m" constraint) */
+#define RSEQ_STORE_INT(arg)	RSEQ_STORE_LONG(arg)					/* To memory ("m" constraint) */
+#define RSEQ_LOAD_LONG(arg)	"lwz%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] "	/* From memory ("m" constraint) */
+#define RSEQ_LOAD_INT(arg)	RSEQ_LOAD_LONG(arg)					/* From memory ("m" constraint) */
+#define RSEQ_LOADX_LONG		"lwzx "							/* From base register ("b" constraint) */
+#define RSEQ_CMP_LONG		"cmpw "
+#define RSEQ_CMP_LONG_INT	"cmpwi "
 
 #define __RSEQ_ASM_DEFINE_TABLE(label, version, flags,				\
 			start_ip, post_commit_offset, abort_ip)			\
@@ -125,7 +131,7 @@ do {									\
 		RSEQ_INJECT_ASM(1)						\
 		"lis %%r17, (" __rseq_str(cs_label) ")@ha\n\t"			\
 		"addi %%r17, %%r17, (" __rseq_str(cs_label) ")@l\n\t"		\
-		"stw %%r17, %[" __rseq_str(rseq_cs) "]\n\t"			\
+		RSEQ_STORE_INT(rseq_cs) "%%r17, %[" __rseq_str(rseq_cs) "]\n\t"	\
 		__rseq_str(label) ":\n\t"
 
 #endif /* #ifdef __PPC64__ */
@@ -136,7 +142,7 @@ do {									\
 
 #define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label)			\
 		RSEQ_INJECT_ASM(2)						\
-		"lwz %%r17, %[" __rseq_str(current_cpu_id) "]\n\t"		\
+		RSEQ_LOAD_INT(current_cpu_id) "%%r17, %[" __rseq_str(current_cpu_id) "]\n\t" \
 		"cmpw cr7, %[" __rseq_str(cpu_id) "], %%r17\n\t"		\
 		"bne- cr7, " __rseq_str(label) "\n\t"
 
@@ -153,25 +159,25 @@ do {									\
  * 	RSEQ_ASM_OP_* (else): doesn't have hard-code registers(unless cr7)
  */
 #define RSEQ_ASM_OP_CMPEQ(var, expect, label)					\
-		LOAD_WORD "%%r17, %[" __rseq_str(var) "]\n\t"			\
-		CMP_WORD "cr7, %%r17, %[" __rseq_str(expect) "]\n\t"		\
+		RSEQ_LOAD_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t"		\
+		RSEQ_CMP_LONG "cr7, %%r17, %[" __rseq_str(expect) "]\n\t"		\
 		"bne- cr7, " __rseq_str(label) "\n\t"
 
 #define RSEQ_ASM_OP_CMPNE(var, expectnot, label)				\
-		LOAD_WORD "%%r17, %[" __rseq_str(var) "]\n\t"			\
-		CMP_WORD "cr7, %%r17, %[" __rseq_str(expectnot) "]\n\t"		\
+		RSEQ_LOAD_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t"		\
+		RSEQ_CMP_LONG "cr7, %%r17, %[" __rseq_str(expectnot) "]\n\t"		\
 		"beq- cr7, " __rseq_str(label) "\n\t"
 
 #define RSEQ_ASM_OP_STORE(value, var)						\
-		STORE_WORD "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t"
+		RSEQ_STORE_LONG(var) "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t"
 
 /* Load @var to r17 */
 #define RSEQ_ASM_OP_R_LOAD(var)							\
-		LOAD_WORD "%%r17, %[" __rseq_str(var) "]\n\t"
+		RSEQ_LOAD_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t"
 
 /* Store r17 to @var */
 #define RSEQ_ASM_OP_R_STORE(var)						\
-		STORE_WORD "%%r17, %[" __rseq_str(var) "]\n\t"
+		RSEQ_STORE_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t"
 
 /* Add @count to r17 */
 #define RSEQ_ASM_OP_R_ADD(count)						\
@@ -179,11 +185,11 @@ do {									\
 
 /* Load (r17 + voffp) to r17 */
 #define RSEQ_ASM_OP_R_LOADX(voffp)						\
-		LOADX_WORD "%%r17, %[" __rseq_str(voffp) "], %%r17\n\t"
+		RSEQ_LOADX_LONG "%%r17, %[" __rseq_str(voffp) "], %%r17\n\t"
 
 /* TODO: implement a faster memcpy. */
 #define RSEQ_ASM_OP_R_MEMCPY() \
-		"cmpdi %%r19, 0\n\t" \
+		RSEQ_CMP_LONG_INT "%%r19, 0\n\t" \
 		"beq 333f\n\t" \
 		"addi %%r20, %%r20, -1\n\t" \
 		"addi %%r21, %%r21, -1\n\t" \
@@ -191,16 +197,16 @@ do {									\
 		"lbzu %%r18, 1(%%r20)\n\t" \
 		"stbu %%r18, 1(%%r21)\n\t" \
 		"addi %%r19, %%r19, -1\n\t" \
-		"cmpdi %%r19, 0\n\t" \
+		RSEQ_CMP_LONG_INT "%%r19, 0\n\t" \
 		"bne 222b\n\t" \
 		"333:\n\t" \
 
 #define RSEQ_ASM_OP_R_FINAL_STORE(var, post_commit_label)			\
-		STORE_WORD "%%r17, %[" __rseq_str(var) "]\n\t"			\
+		RSEQ_STORE_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t"			\
 		__rseq_str(post_commit_label) ":\n\t"
 
 #define RSEQ_ASM_OP_FINAL_STORE(value, var, post_commit_label)			\
-		STORE_WORD "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t" \
+		RSEQ_STORE_LONG(var) "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t" \
 		__rseq_str(post_commit_label) ":\n\t"
 
 static inline __attribute__((always_inline))
@@ -235,8 +241,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  [v]			"m" (*v),
 		  [expect]		"r" (expect),
 		  [newv]		"r" (newv)
@@ -248,23 +254,28 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
 
 static inline __attribute__((always_inline))
 int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
-			       off_t voffp, intptr_t *load, int cpu)
+			       long voffp, intptr_t *load, int cpu)
 {
 	RSEQ_INJECT_C(9)
 
@@ -301,8 +312,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expectnot]		"r" (expectnot),
@@ -316,16 +327,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -359,8 +375,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [count]		"r" (count)
@@ -372,12 +388,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		  , error1
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 #endif
 }
@@ -419,8 +438,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* try store input */
 		  [v2]			"m" (*v2),
 		  [newv2]		"r" (newv2),
@@ -436,16 +455,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -489,8 +513,8 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* try store input */
 		  [v2]			"m" (*v2),
 		  [newv2]		"r" (newv2),
@@ -506,16 +530,21 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -560,8 +589,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* cmp2 input */
 		  [v2]			"m" (*v2),
 		  [expect2]		"r" (expect2),
@@ -577,18 +606,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2, error3
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("1st expected value comparison failed");
 error3:
+	rseq_after_asm_goto();
 	rseq_bug("2nd expected value comparison failed");
 #endif
 }
@@ -635,8 +670,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expect]		"r" (expect),
@@ -653,16 +688,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -711,8 +751,8 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expect]		"r" (expect),
@@ -729,23 +769,23 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
 
-#undef STORE_WORD
-#undef LOAD_WORD
-#undef LOADX_WORD
-#undef CMP_WORD
-
 #endif /* !RSEQ_SKIP_FASTPATH */
diff --git a/tools/testing/selftests/rseq/rseq-s390.h b/tools/testing/selftests/rseq/rseq-s390.h
index 8ef94ad1cbb4..4e6dc5f0cb42 100644
--- a/tools/testing/selftests/rseq/rseq-s390.h
+++ b/tools/testing/selftests/rseq/rseq-s390.h
@@ -165,8 +165,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  [v]			"m" (*v),
 		  [expect]		"r" (expect),
 		  [newv]		"r" (newv)
@@ -178,16 +178,21 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -198,7 +203,7 @@ error2:
  */
 static inline __attribute__((always_inline))
 int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
-			       off_t voffp, intptr_t *load, int cpu)
+			       long voffp, intptr_t *load, int cpu)
 {
 	RSEQ_INJECT_C(9)
 
@@ -233,8 +238,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expectnot]		"r" (expectnot),
@@ -248,16 +253,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -288,8 +298,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [count]		"r" (count)
@@ -301,12 +311,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		  , error1
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 #endif
 }
@@ -347,8 +360,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* try store input */
 		  [v2]			"m" (*v2),
 		  [newv2]		"r" (newv2),
@@ -364,16 +377,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -426,8 +444,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* cmp2 input */
 		  [v2]			"m" (*v2),
 		  [expect2]		"r" (expect2),
@@ -443,18 +461,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2, error3
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("1st expected value comparison failed");
 error3:
+	rseq_after_asm_goto();
 	rseq_bug("2nd expected value comparison failed");
 #endif
 }
@@ -534,8 +558,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 #endif
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expect]		"r" (expect),
@@ -555,16 +579,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
diff --git a/tools/testing/selftests/rseq/rseq-skip.h b/tools/testing/selftests/rseq/rseq-skip.h
index 72750b5905a9..7b53dac1fcdd 100644
--- a/tools/testing/selftests/rseq/rseq-skip.h
+++ b/tools/testing/selftests/rseq/rseq-skip.h
@@ -13,7 +13,7 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 
 static inline __attribute__((always_inline))
 int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
-			       off_t voffp, intptr_t *load, int cpu)
+			       long voffp, intptr_t *load, int cpu)
 {
 	return -1;
 }
diff --git a/tools/testing/selftests/rseq/rseq-thread-pointer.h b/tools/testing/selftests/rseq/rseq-thread-pointer.h
new file mode 100644
index 000000000000..977c25d758b2
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-thread-pointer.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */
+/*
+ * rseq-thread-pointer.h
+ *
+ * (C) Copyright 2021 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#ifndef _RSEQ_THREAD_POINTER
+#define _RSEQ_THREAD_POINTER
+
+#if defined(__x86_64__) || defined(__i386__)
+#include "rseq-x86-thread-pointer.h"
+#elif defined(__PPC__)
+#include "rseq-ppc-thread-pointer.h"
+#else
+#include "rseq-generic-thread-pointer.h"
+#endif
+
+#endif
diff --git a/tools/testing/selftests/rseq/rseq-x86-thread-pointer.h b/tools/testing/selftests/rseq/rseq-x86-thread-pointer.h
new file mode 100644
index 000000000000..d3133587d996
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-x86-thread-pointer.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */
+/*
+ * rseq-x86-thread-pointer.h
+ *
+ * (C) Copyright 2021 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#ifndef _RSEQ_X86_THREAD_POINTER
+#define _RSEQ_X86_THREAD_POINTER
+
+#include <features.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#if __GNUC_PREREQ (11, 1)
+static inline void *rseq_thread_pointer(void)
+{
+	return __builtin_thread_pointer();
+}
+#else
+static inline void *rseq_thread_pointer(void)
+{
+	void *__result;
+
+# ifdef __x86_64__
+	__asm__ ("mov %%fs:0, %0" : "=r" (__result));
+# else
+	__asm__ ("mov %%gs:0, %0" : "=r" (__result));
+# endif
+	return __result;
+}
+#endif /* !GCC 11 */
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif
diff --git a/tools/testing/selftests/rseq/rseq-x86.h b/tools/testing/selftests/rseq/rseq-x86.h
index 640411518e46..bd01dc41ca13 100644
--- a/tools/testing/selftests/rseq/rseq-x86.h
+++ b/tools/testing/selftests/rseq/rseq-x86.h
@@ -28,6 +28,8 @@
 
 #ifdef __x86_64__
 
+#define RSEQ_ASM_TP_SEGMENT	%%fs
+
 #define rseq_smp_mb()	\
 	__asm__ __volatile__ ("lock; addl $0,-128(%%rsp)" ::: "memory", "cc")
 #define rseq_smp_rmb()	rseq_barrier()
@@ -123,14 +125,14 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
 #endif
 		/* Start rseq by storing table entry pointer into rseq_cs. */
-		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
 		RSEQ_INJECT_ASM(3)
 		"cmpq %[v], %[expect]\n\t"
 		"jnz %l[cmpfail]\n\t"
 		RSEQ_INJECT_ASM(4)
 #ifdef RSEQ_COMPARE_TWICE
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
 		"cmpq %[v], %[expect]\n\t"
 		"jnz %l[error2]\n\t"
 #endif
@@ -141,7 +143,7 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [rseq_abi]		"r" (&__rseq_abi),
+		  [rseq_offset]		"r" (rseq_offset),
 		  [v]			"m" (*v),
 		  [expect]		"r" (expect),
 		  [newv]		"r" (newv)
@@ -152,16 +154,21 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -172,7 +179,7 @@ error2:
  */
 static inline __attribute__((always_inline))
 int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
-			       off_t voffp, intptr_t *load, int cpu)
+			       long voffp, intptr_t *load, int cpu)
 {
 	RSEQ_INJECT_C(9)
 
@@ -184,15 +191,15 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
 #endif
 		/* Start rseq by storing table entry pointer into rseq_cs. */
-		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
 		RSEQ_INJECT_ASM(3)
 		"movq %[v], %%rbx\n\t"
 		"cmpq %%rbx, %[expectnot]\n\t"
 		"je %l[cmpfail]\n\t"
 		RSEQ_INJECT_ASM(4)
 #ifdef RSEQ_COMPARE_TWICE
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
 		"movq %[v], %%rbx\n\t"
 		"cmpq %%rbx, %[expectnot]\n\t"
 		"je %l[error2]\n\t"
@@ -207,7 +214,7 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [rseq_abi]		"r" (&__rseq_abi),
+		  [rseq_offset]		"r" (rseq_offset),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expectnot]		"r" (expectnot),
@@ -220,16 +227,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -245,11 +257,11 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
 #endif
 		/* Start rseq by storing table entry pointer into rseq_cs. */
-		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
 		RSEQ_INJECT_ASM(3)
 #ifdef RSEQ_COMPARE_TWICE
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
 #endif
 		/* final store */
 		"addq %[count], %[v]\n\t"
@@ -258,7 +270,7 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [rseq_abi]		"r" (&__rseq_abi),
+		  [rseq_offset]		"r" (rseq_offset),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [count]		"er" (count)
@@ -269,12 +281,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		  , error1
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 #endif
 }
@@ -286,7 +301,7 @@ error1:
  *  *pval += inc;
  */
 static inline __attribute__((always_inline))
-int rseq_offset_deref_addv(intptr_t *ptr, off_t off, intptr_t inc, int cpu)
+int rseq_offset_deref_addv(intptr_t *ptr, long off, intptr_t inc, int cpu)
 {
 	RSEQ_INJECT_C(9)
 
@@ -296,11 +311,11 @@ int rseq_offset_deref_addv(intptr_t *ptr, off_t off, intptr_t inc, int cpu)
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
 #endif
 		/* Start rseq by storing table entry pointer into rseq_cs. */
-		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
 		RSEQ_INJECT_ASM(3)
 #ifdef RSEQ_COMPARE_TWICE
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
 #endif
 		/* get p+v */
 		"movq %[ptr], %%rbx\n\t"
@@ -314,7 +329,7 @@ int rseq_offset_deref_addv(intptr_t *ptr, off_t off, intptr_t inc, int cpu)
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [rseq_abi]		"r" (&__rseq_abi),
+		  [rseq_offset]		"r" (rseq_offset),
 		  /* final store input */
 		  [ptr]			"m" (*ptr),
 		  [off]			"er" (off),
@@ -351,14 +366,14 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
 #endif
 		/* Start rseq by storing table entry pointer into rseq_cs. */
-		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
 		RSEQ_INJECT_ASM(3)
 		"cmpq %[v], %[expect]\n\t"
 		"jnz %l[cmpfail]\n\t"
 		RSEQ_INJECT_ASM(4)
 #ifdef RSEQ_COMPARE_TWICE
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
 		"cmpq %[v], %[expect]\n\t"
 		"jnz %l[error2]\n\t"
 #endif
@@ -372,7 +387,7 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [rseq_abi]		"r" (&__rseq_abi),
+		  [rseq_offset]		"r" (rseq_offset),
 		  /* try store input */
 		  [v2]			"m" (*v2),
 		  [newv2]		"r" (newv2),
@@ -387,16 +402,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -426,8 +446,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error3])
 #endif
 		/* Start rseq by storing table entry pointer into rseq_cs. */
-		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
 		RSEQ_INJECT_ASM(3)
 		"cmpq %[v], %[expect]\n\t"
 		"jnz %l[cmpfail]\n\t"
@@ -436,7 +456,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		"jnz %l[cmpfail]\n\t"
 		RSEQ_INJECT_ASM(5)
 #ifdef RSEQ_COMPARE_TWICE
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
 		"cmpq %[v], %[expect]\n\t"
 		"jnz %l[error2]\n\t"
 		"cmpq %[v2], %[expect2]\n\t"
@@ -449,7 +469,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [rseq_abi]		"r" (&__rseq_abi),
+		  [rseq_offset]		"r" (rseq_offset),
 		  /* cmp2 input */
 		  [v2]			"m" (*v2),
 		  [expect2]		"r" (expect2),
@@ -464,18 +484,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2, error3
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("1st expected value comparison failed");
 error3:
+	rseq_after_asm_goto();
 	rseq_bug("2nd expected value comparison failed");
 #endif
 }
@@ -500,14 +526,14 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 		"movq %[dst], %[rseq_scratch1]\n\t"
 		"movq %[len], %[rseq_scratch2]\n\t"
 		/* Start rseq by storing table entry pointer into rseq_cs. */
-		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
 		RSEQ_INJECT_ASM(3)
 		"cmpq %[v], %[expect]\n\t"
 		"jnz 5f\n\t"
 		RSEQ_INJECT_ASM(4)
 #ifdef RSEQ_COMPARE_TWICE
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 6f)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 6f)
 		"cmpq %[v], %[expect]\n\t"
 		"jnz 7f\n\t"
 #endif
@@ -555,7 +581,7 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 #endif
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [rseq_abi]		"r" (&__rseq_abi),
+		  [rseq_offset]		"r" (rseq_offset),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expect]		"r" (expect),
@@ -574,16 +600,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -600,7 +631,9 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
 
 #endif /* !RSEQ_SKIP_FASTPATH */
 
-#elif __i386__
+#elif defined(__i386__)
+
+#define RSEQ_ASM_TP_SEGMENT	%%gs
 
 #define rseq_smp_mb()	\
 	__asm__ __volatile__ ("lock; addl $0,-128(%%esp)" ::: "memory", "cc")
@@ -701,14 +734,14 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
 #endif
 		/* Start rseq by storing table entry pointer into rseq_cs. */
-		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
 		RSEQ_INJECT_ASM(3)
 		"cmpl %[v], %[expect]\n\t"
 		"jnz %l[cmpfail]\n\t"
 		RSEQ_INJECT_ASM(4)
 #ifdef RSEQ_COMPARE_TWICE
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
 		"cmpl %[v], %[expect]\n\t"
 		"jnz %l[error2]\n\t"
 #endif
@@ -719,7 +752,7 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [rseq_abi]		"r" (&__rseq_abi),
+		  [rseq_offset]		"r" (rseq_offset),
 		  [v]			"m" (*v),
 		  [expect]		"r" (expect),
 		  [newv]		"r" (newv)
@@ -730,16 +763,21 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -750,7 +788,7 @@ error2:
  */
 static inline __attribute__((always_inline))
 int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
-			       off_t voffp, intptr_t *load, int cpu)
+			       long voffp, intptr_t *load, int cpu)
 {
 	RSEQ_INJECT_C(9)
 
@@ -762,15 +800,15 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
 #endif
 		/* Start rseq by storing table entry pointer into rseq_cs. */
-		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
 		RSEQ_INJECT_ASM(3)
 		"movl %[v], %%ebx\n\t"
 		"cmpl %%ebx, %[expectnot]\n\t"
 		"je %l[cmpfail]\n\t"
 		RSEQ_INJECT_ASM(4)
 #ifdef RSEQ_COMPARE_TWICE
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
 		"movl %[v], %%ebx\n\t"
 		"cmpl %%ebx, %[expectnot]\n\t"
 		"je %l[error2]\n\t"
@@ -785,7 +823,7 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [rseq_abi]		"r" (&__rseq_abi),
+		  [rseq_offset]		"r" (rseq_offset),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expectnot]		"r" (expectnot),
@@ -798,16 +836,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -823,11 +866,11 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
 #endif
 		/* Start rseq by storing table entry pointer into rseq_cs. */
-		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
 		RSEQ_INJECT_ASM(3)
 #ifdef RSEQ_COMPARE_TWICE
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
 #endif
 		/* final store */
 		"addl %[count], %[v]\n\t"
@@ -836,7 +879,7 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [rseq_abi]		"r" (&__rseq_abi),
+		  [rseq_offset]		"r" (rseq_offset),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [count]		"ir" (count)
@@ -847,12 +890,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		  , error1
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 #endif
 }
@@ -872,14 +918,14 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
 #endif
 		/* Start rseq by storing table entry pointer into rseq_cs. */
-		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
 		RSEQ_INJECT_ASM(3)
 		"cmpl %[v], %[expect]\n\t"
 		"jnz %l[cmpfail]\n\t"
 		RSEQ_INJECT_ASM(4)
 #ifdef RSEQ_COMPARE_TWICE
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
 		"cmpl %[v], %[expect]\n\t"
 		"jnz %l[error2]\n\t"
 #endif
@@ -894,7 +940,7 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [rseq_abi]		"r" (&__rseq_abi),
+		  [rseq_offset]		"r" (rseq_offset),
 		  /* try store input */
 		  [v2]			"m" (*v2),
 		  [newv2]		"m" (newv2),
@@ -909,16 +955,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -938,15 +989,15 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
 #endif
 		/* Start rseq by storing table entry pointer into rseq_cs. */
-		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
 		RSEQ_INJECT_ASM(3)
 		"movl %[expect], %%eax\n\t"
 		"cmpl %[v], %%eax\n\t"
 		"jnz %l[cmpfail]\n\t"
 		RSEQ_INJECT_ASM(4)
 #ifdef RSEQ_COMPARE_TWICE
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
 		"movl %[expect], %%eax\n\t"
 		"cmpl %[v], %%eax\n\t"
 		"jnz %l[error2]\n\t"
@@ -962,7 +1013,7 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [rseq_abi]		"r" (&__rseq_abi),
+		  [rseq_offset]		"r" (rseq_offset),
 		  /* try store input */
 		  [v2]			"m" (*v2),
 		  [newv2]		"r" (newv2),
@@ -977,16 +1028,21 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 
@@ -1008,8 +1064,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error3])
 #endif
 		/* Start rseq by storing table entry pointer into rseq_cs. */
-		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
 		RSEQ_INJECT_ASM(3)
 		"cmpl %[v], %[expect]\n\t"
 		"jnz %l[cmpfail]\n\t"
@@ -1018,7 +1074,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		"jnz %l[cmpfail]\n\t"
 		RSEQ_INJECT_ASM(5)
 #ifdef RSEQ_COMPARE_TWICE
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
 		"cmpl %[v], %[expect]\n\t"
 		"jnz %l[error2]\n\t"
 		"cmpl %[expect2], %[v2]\n\t"
@@ -1032,7 +1088,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [rseq_abi]		"r" (&__rseq_abi),
+		  [rseq_offset]		"r" (rseq_offset),
 		  /* cmp2 input */
 		  [v2]			"m" (*v2),
 		  [expect2]		"r" (expect2),
@@ -1047,18 +1103,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2, error3
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("1st expected value comparison failed");
 error3:
+	rseq_after_asm_goto();
 	rseq_bug("2nd expected value comparison failed");
 #endif
 }
@@ -1084,15 +1146,15 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 		"movl %[dst], %[rseq_scratch1]\n\t"
 		"movl %[len], %[rseq_scratch2]\n\t"
 		/* Start rseq by storing table entry pointer into rseq_cs. */
-		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
 		RSEQ_INJECT_ASM(3)
 		"movl %[expect], %%eax\n\t"
 		"cmpl %%eax, %[v]\n\t"
 		"jnz 5f\n\t"
 		RSEQ_INJECT_ASM(4)
 #ifdef RSEQ_COMPARE_TWICE
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 6f)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 6f)
 		"movl %[expect], %%eax\n\t"
 		"cmpl %%eax, %[v]\n\t"
 		"jnz 7f\n\t"
@@ -1142,7 +1204,7 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 #endif
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [rseq_abi]		"r" (&__rseq_abi),
+		  [rseq_offset]		"r" (rseq_offset),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expect]		"m" (expect),
@@ -1161,16 +1223,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -1196,15 +1263,15 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
 		"movl %[dst], %[rseq_scratch1]\n\t"
 		"movl %[len], %[rseq_scratch2]\n\t"
 		/* Start rseq by storing table entry pointer into rseq_cs. */
-		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
 		RSEQ_INJECT_ASM(3)
 		"movl %[expect], %%eax\n\t"
 		"cmpl %%eax, %[v]\n\t"
 		"jnz 5f\n\t"
 		RSEQ_INJECT_ASM(4)
 #ifdef RSEQ_COMPARE_TWICE
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 6f)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 6f)
 		"movl %[expect], %%eax\n\t"
 		"cmpl %%eax, %[v]\n\t"
 		"jnz 7f\n\t"
@@ -1255,7 +1322,7 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
 #endif
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [rseq_abi]		"r" (&__rseq_abi),
+		  [rseq_offset]		"r" (rseq_offset),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expect]		"m" (expect),
@@ -1274,16 +1341,21 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c
index 7159eb777fd3..986b9458efb2 100644
--- a/tools/testing/selftests/rseq/rseq.c
+++ b/tools/testing/selftests/rseq/rseq.c
@@ -26,131 +26,124 @@
 #include <assert.h>
 #include <signal.h>
 #include <limits.h>
+#include <dlfcn.h>
+#include <stddef.h>
 
+#include "../kselftest.h"
 #include "rseq.h"
 
-#define ARRAY_SIZE(arr)	(sizeof(arr) / sizeof((arr)[0]))
+static const ptrdiff_t *libc_rseq_offset_p;
+static const unsigned int *libc_rseq_size_p;
+static const unsigned int *libc_rseq_flags_p;
 
-__thread volatile struct rseq __rseq_abi = {
-	.cpu_id = RSEQ_CPU_ID_UNINITIALIZED,
-};
+/* Offset from the thread pointer to the rseq area.  */
+ptrdiff_t rseq_offset;
 
-/*
- * Shared with other libraries. This library may take rseq ownership if it is
- * still 0 when executing the library constructor. Set to 1 by library
- * constructor when handling rseq. Set to 0 in destructor if handling rseq.
- */
-int __rseq_handled;
+/* Size of the registered rseq area.  0 if the registration was
+   unsuccessful.  */
+unsigned int rseq_size = -1U;
+
+/* Flags used during rseq registration.  */
+unsigned int rseq_flags;
 
-/* Whether this library have ownership of rseq registration. */
 static int rseq_ownership;
 
-static __thread volatile uint32_t __rseq_refcount;
+static
+__thread struct rseq_abi __rseq_abi __attribute__((tls_model("initial-exec"))) = {
+	.cpu_id = RSEQ_ABI_CPU_ID_UNINITIALIZED,
+};
 
-static void signal_off_save(sigset_t *oldset)
+static int sys_rseq(struct rseq_abi *rseq_abi, uint32_t rseq_len,
+		    int flags, uint32_t sig)
 {
-	sigset_t set;
-	int ret;
-
-	sigfillset(&set);
-	ret = pthread_sigmask(SIG_BLOCK, &set, oldset);
-	if (ret)
-		abort();
+	return syscall(__NR_rseq, rseq_abi, rseq_len, flags, sig);
 }
 
-static void signal_restore(sigset_t oldset)
+int rseq_available(void)
 {
-	int ret;
+	int rc;
 
-	ret = pthread_sigmask(SIG_SETMASK, &oldset, NULL);
-	if (ret)
+	rc = sys_rseq(NULL, 0, 0, 0);
+	if (rc != -1)
 		abort();
-}
-
-static int sys_rseq(volatile struct rseq *rseq_abi, uint32_t rseq_len,
-		    int flags, uint32_t sig)
-{
-	return syscall(__NR_rseq, rseq_abi, rseq_len, flags, sig);
+	switch (errno) {
+	case ENOSYS:
+		return 0;
+	case EINVAL:
+		return 1;
+	default:
+		abort();
+	}
 }
 
 int rseq_register_current_thread(void)
 {
-	int rc, ret = 0;
-	sigset_t oldset;
+	int rc;
 
-	if (!rseq_ownership)
+	if (!rseq_ownership) {
+		/* Treat libc's ownership as a successful registration. */
 		return 0;
-	signal_off_save(&oldset);
-	if (__rseq_refcount == UINT_MAX) {
-		ret = -1;
-		goto end;
-	}
-	if (__rseq_refcount++)
-		goto end;
-	rc = sys_rseq(&__rseq_abi, sizeof(struct rseq), 0, RSEQ_SIG);
-	if (!rc) {
-		assert(rseq_current_cpu_raw() >= 0);
-		goto end;
 	}
-	if (errno != EBUSY)
-		__rseq_abi.cpu_id = RSEQ_CPU_ID_REGISTRATION_FAILED;
-	ret = -1;
-	__rseq_refcount--;
-end:
-	signal_restore(oldset);
-	return ret;
+	rc = sys_rseq(&__rseq_abi, sizeof(struct rseq_abi), 0, RSEQ_SIG);
+	if (rc)
+		return -1;
+	assert(rseq_current_cpu_raw() >= 0);
+	return 0;
 }
 
 int rseq_unregister_current_thread(void)
 {
-	int rc, ret = 0;
-	sigset_t oldset;
+	int rc;
 
-	if (!rseq_ownership)
+	if (!rseq_ownership) {
+		/* Treat libc's ownership as a successful unregistration. */
 		return 0;
-	signal_off_save(&oldset);
-	if (!__rseq_refcount) {
-		ret = -1;
-		goto end;
 	}
-	if (--__rseq_refcount)
-		goto end;
-	rc = sys_rseq(&__rseq_abi, sizeof(struct rseq),
-		      RSEQ_FLAG_UNREGISTER, RSEQ_SIG);
-	if (!rc)
-		goto end;
-	__rseq_refcount = 1;
-	ret = -1;
-end:
-	signal_restore(oldset);
-	return ret;
+	rc = sys_rseq(&__rseq_abi, sizeof(struct rseq_abi), RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG);
+	if (rc)
+		return -1;
+	return 0;
 }
 
-int32_t rseq_fallback_current_cpu(void)
+static __attribute__((constructor))
+void rseq_init(void)
 {
-	int32_t cpu;
-
-	cpu = sched_getcpu();
-	if (cpu < 0) {
-		perror("sched_getcpu()");
-		abort();
+	libc_rseq_offset_p = dlsym(RTLD_NEXT, "__rseq_offset");
+	libc_rseq_size_p = dlsym(RTLD_NEXT, "__rseq_size");
+	libc_rseq_flags_p = dlsym(RTLD_NEXT, "__rseq_flags");
+	if (libc_rseq_size_p && libc_rseq_offset_p && libc_rseq_flags_p) {
+		/* rseq registration owned by glibc */
+		rseq_offset = *libc_rseq_offset_p;
+		rseq_size = *libc_rseq_size_p;
+		rseq_flags = *libc_rseq_flags_p;
+		return;
 	}
-	return cpu;
-}
-
-void __attribute__((constructor)) rseq_init(void)
-{
-	/* Check whether rseq is handled by another library. */
-	if (__rseq_handled)
+	if (!rseq_available())
 		return;
-	__rseq_handled = 1;
 	rseq_ownership = 1;
+	rseq_offset = (void *)&__rseq_abi - rseq_thread_pointer();
+	rseq_size = sizeof(struct rseq_abi);
+	rseq_flags = 0;
 }
 
-void __attribute__((destructor)) rseq_fini(void)
+static __attribute__((destructor))
+void rseq_exit(void)
 {
 	if (!rseq_ownership)
 		return;
-	__rseq_handled = 0;
+	rseq_offset = 0;
+	rseq_size = -1U;
 	rseq_ownership = 0;
 }
+
+int32_t rseq_fallback_current_cpu(void)
+{
+	int32_t cpu;
+
+	cpu = sched_getcpu();
+	if (cpu < 0) {
+		perror("sched_getcpu()");
+		abort();
+	}
+	return cpu;
+}
diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h
index 3f63eb362b92..9d850b290c2e 100644
--- a/tools/testing/selftests/rseq/rseq.h
+++ b/tools/testing/selftests/rseq/rseq.h
@@ -16,7 +16,9 @@
 #include <errno.h>
 #include <stdio.h>
 #include <stdlib.h>
-#include <linux/rseq.h>
+#include <stddef.h>
+#include "rseq-abi.h"
+#include "compiler.h"
 
 /*
  * Empty code injection macros, override when testing.
@@ -43,8 +45,20 @@
 #define RSEQ_INJECT_FAILED
 #endif
 
-extern __thread volatile struct rseq __rseq_abi;
-extern int __rseq_handled;
+#include "rseq-thread-pointer.h"
+
+/* Offset from the thread pointer to the rseq area.  */
+extern ptrdiff_t rseq_offset;
+/* Size of the registered rseq area.  0 if the registration was
+   unsuccessful.  */
+extern unsigned int rseq_size;
+/* Flags used during rseq registration.  */
+extern unsigned int rseq_flags;
+
+static inline struct rseq_abi *rseq_get_abi(void)
+{
+	return (struct rseq_abi *) ((uintptr_t) rseq_thread_pointer() + rseq_offset);
+}
 
 #define rseq_likely(x)		__builtin_expect(!!(x), 1)
 #define rseq_unlikely(x)	__builtin_expect(!!(x), 0)
@@ -108,7 +122,7 @@ int32_t rseq_fallback_current_cpu(void);
  */
 static inline int32_t rseq_current_cpu_raw(void)
 {
-	return RSEQ_ACCESS_ONCE(__rseq_abi.cpu_id);
+	return RSEQ_ACCESS_ONCE(rseq_get_abi()->cpu_id);
 }
 
 /*
@@ -124,7 +138,7 @@ static inline int32_t rseq_current_cpu_raw(void)
  */
 static inline uint32_t rseq_cpu_start(void)
 {
-	return RSEQ_ACCESS_ONCE(__rseq_abi.cpu_id_start);
+	return RSEQ_ACCESS_ONCE(rseq_get_abi()->cpu_id_start);
 }
 
 static inline uint32_t rseq_current_cpu(void)
@@ -139,11 +153,7 @@ static inline uint32_t rseq_current_cpu(void)
 
 static inline void rseq_clear_rseq_cs(void)
 {
-#ifdef __LP64__
-	__rseq_abi.rseq_cs.ptr = 0;
-#else
-	__rseq_abi.rseq_cs.ptr.ptr32 = 0;
-#endif
+	RSEQ_WRITE_ONCE(rseq_get_abi()->rseq_cs.arch.ptr, 0);
 }
 
 /*
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index 34ebd1fe5eed..ac340a9c0918 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -802,7 +802,7 @@ void kill_thread_or_group(struct __test_metadata *_metadata,
 		.len = (unsigned short)ARRAY_SIZE(filter_thread),
 		.filter = filter_thread,
 	};
-	int kill = kill_how == KILL_PROCESS ? SECCOMP_RET_KILL_PROCESS : 0xAAAAAAAAA;
+	int kill = kill_how == KILL_PROCESS ? SECCOMP_RET_KILL_PROCESS : 0xAAAAAAAA;
 	struct sock_filter filter_process[] = {
 		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
 			offsetof(struct seccomp_data, nr)),
diff --git a/tools/testing/selftests/timers/clocksource-switch.c b/tools/testing/selftests/timers/clocksource-switch.c
index ef8eb3604595..b57f0a9be490 100644
--- a/tools/testing/selftests/timers/clocksource-switch.c
+++ b/tools/testing/selftests/timers/clocksource-switch.c
@@ -110,10 +110,10 @@ int run_tests(int secs)
 
 	sprintf(buf, "./inconsistency-check -t %i", secs);
 	ret = system(buf);
-	if (ret)
-		return ret;
+	if (WIFEXITED(ret) && WEXITSTATUS(ret))
+		return WEXITSTATUS(ret);
 	ret = system("./nanosleep");
-	return ret;
+	return WIFEXITED(ret) ? WEXITSTATUS(ret) : 0;
 }
 
 
diff --git a/tools/testing/selftests/timers/valid-adjtimex.c b/tools/testing/selftests/timers/valid-adjtimex.c
index 5397de708d3c..48b9a803235a 100644
--- a/tools/testing/selftests/timers/valid-adjtimex.c
+++ b/tools/testing/selftests/timers/valid-adjtimex.c
@@ -40,7 +40,7 @@
 #define ADJ_SETOFFSET 0x0100
 
 #include <sys/syscall.h>
-static int clock_adjtime(clockid_t id, struct timex *tx)
+int clock_adjtime(clockid_t id, struct timex *tx)
 {
 	return syscall(__NR_clock_adjtime, id, tx);
 }
diff --git a/tools/testing/selftests/vm/mremap_test.c b/tools/testing/selftests/vm/mremap_test.c
index 8f4dbbd60c09..e3ce33a9954e 100644
--- a/tools/testing/selftests/vm/mremap_test.c
+++ b/tools/testing/selftests/vm/mremap_test.c
@@ -120,59 +120,6 @@ static unsigned long long get_mmap_min_addr(void)
 }
 
 /*
- * Returns false if the requested remap region overlaps with an
- * existing mapping (e.g text, stack) else returns true.
- */
-static bool is_remap_region_valid(void *addr, unsigned long long size)
-{
-	void *remap_addr = NULL;
-	bool ret = true;
-
-	/* Use MAP_FIXED_NOREPLACE flag to ensure region is not mapped */
-	remap_addr = mmap(addr, size, PROT_READ | PROT_WRITE,
-					 MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED,
-					 -1, 0);
-
-	if (remap_addr == MAP_FAILED) {
-		if (errno == EEXIST)
-			ret = false;
-	} else {
-		munmap(remap_addr, size);
-	}
-
-	return ret;
-}
-
-/* Returns mmap_min_addr sysctl tunable from procfs */
-static unsigned long long get_mmap_min_addr(void)
-{
-	FILE *fp;
-	int n_matched;
-	static unsigned long long addr;
-
-	if (addr)
-		return addr;
-
-	fp = fopen("/proc/sys/vm/mmap_min_addr", "r");
-	if (fp == NULL) {
-		ksft_print_msg("Failed to open /proc/sys/vm/mmap_min_addr: %s\n",
-			strerror(errno));
-		exit(KSFT_SKIP);
-	}
-
-	n_matched = fscanf(fp, "%llu", &addr);
-	if (n_matched != 1) {
-		ksft_print_msg("Failed to read /proc/sys/vm/mmap_min_addr: %s\n",
-			strerror(errno));
-		fclose(fp);
-		exit(KSFT_SKIP);
-	}
-
-	fclose(fp);
-	return addr;
-}
-
-/*
  * Returns the start address of the mapping on success, else returns
  * NULL on failure.
  */
diff --git a/tools/thermal/tmon/sysfs.c b/tools/thermal/tmon/sysfs.c
index b00b1bfd9d8e..cb1108bc9249 100644
--- a/tools/thermal/tmon/sysfs.c
+++ b/tools/thermal/tmon/sysfs.c
@@ -13,6 +13,7 @@
 #include <stdint.h>
 #include <dirent.h>
 #include <libintl.h>
+#include <limits.h>
 #include <ctype.h>
 #include <time.h>
 #include <syslog.h>
@@ -33,9 +34,9 @@ int sysfs_set_ulong(char *path, char *filename, unsigned long val)
 {
 	FILE *fd;
 	int ret = -1;
-	char filepath[256];
+	char filepath[PATH_MAX + 2]; /* NUL and '/' */
 
-	snprintf(filepath, 256, "%s/%s", path, filename);
+	snprintf(filepath, sizeof(filepath), "%s/%s", path, filename);
 
 	fd = fopen(filepath, "w");
 	if (!fd) {
@@ -57,9 +58,9 @@ static int sysfs_get_ulong(char *path, char *filename, unsigned long *p_ulong)
 {
 	FILE *fd;
 	int ret = -1;
-	char filepath[256];
+	char filepath[PATH_MAX + 2]; /* NUL and '/' */
 
-	snprintf(filepath, 256, "%s/%s", path, filename);
+	snprintf(filepath, sizeof(filepath), "%s/%s", path, filename);
 
 	fd = fopen(filepath, "r");
 	if (!fd) {
@@ -76,9 +77,9 @@ static int sysfs_get_string(char *path, char *filename, char *str)
 {
 	FILE *fd;
 	int ret = -1;
-	char filepath[256];
+	char filepath[PATH_MAX + 2]; /* NUL and '/' */
 
-	snprintf(filepath, 256, "%s/%s", path, filename);
+	snprintf(filepath, sizeof(filepath), "%s/%s", path, filename);
 
 	fd = fopen(filepath, "r");
 	if (!fd) {
@@ -199,8 +200,8 @@ static int find_tzone_cdev(struct dirent *nl, char *tz_name,
 {
 	unsigned long trip_instance = 0;
 	char cdev_name_linked[256];
-	char cdev_name[256];
-	char cdev_trip_name[256];
+	char cdev_name[PATH_MAX];
+	char cdev_trip_name[PATH_MAX];
 	int cdev_id;
 
 	if (nl->d_type == DT_LNK) {
@@ -213,7 +214,8 @@ static int find_tzone_cdev(struct dirent *nl, char *tz_name,
 			return -EINVAL;
 		}
 		/* find the link to real cooling device record binding */
-		snprintf(cdev_name, 256, "%s/%s", tz_name, nl->d_name);
+		snprintf(cdev_name, sizeof(cdev_name) - 2, "%s/%s",
+			 tz_name, nl->d_name);
 		memset(cdev_name_linked, 0, sizeof(cdev_name_linked));
 		if (readlink(cdev_name, cdev_name_linked,
 				sizeof(cdev_name_linked) - 1) != -1) {
@@ -226,8 +228,8 @@ static int find_tzone_cdev(struct dirent *nl, char *tz_name,
 			/* find the trip point in which the cdev is binded to
 			 * in this tzone
 			 */
-			snprintf(cdev_trip_name, 256, "%s%s", nl->d_name,
-				"_trip_point");
+			snprintf(cdev_trip_name, sizeof(cdev_trip_name) - 1,
+				"%s%s", nl->d_name, "_trip_point");
 			sysfs_get_ulong(tz_name, cdev_trip_name,
 					&trip_instance);
 			/* validate trip point range, e.g. trip could return -1
diff --git a/tools/thermal/tmon/tmon.h b/tools/thermal/tmon/tmon.h
index c9066ec104dd..44d16d778f04 100644
--- a/tools/thermal/tmon/tmon.h
+++ b/tools/thermal/tmon/tmon.h
@@ -27,6 +27,9 @@
 #define NR_LINES_TZDATA 1
 #define TMON_LOG_FILE "/var/tmp/tmon.log"
 
+#include <sys/time.h>
+#include <pthread.h>
+
 extern unsigned long ticktime;
 extern double time_elapsed;
 extern unsigned long target_temp_user;
diff --git a/tools/vm/slabinfo.c b/tools/vm/slabinfo.c
index 9b68658b6bb8..0fffaeedee76 100644
--- a/tools/vm/slabinfo.c
+++ b/tools/vm/slabinfo.c
@@ -125,7 +125,7 @@ static void usage(void)
 		"-n|--numa              Show NUMA information\n"
 		"-N|--lines=K           Show the first K slabs\n"
 		"-o|--ops               Show kmem_cache_ops\n"
-		"-P|--partial		Sort by number of partial slabs\n"
+		"-P|--partial           Sort by number of partial slabs\n"
 		"-r|--report            Detailed report on single slabs\n"
 		"-s|--shrink            Shrink slabs\n"
 		"-S|--Size              Sort by size\n"
@@ -233,6 +233,24 @@ static unsigned long read_slab_obj(struct slabinfo *s, const char *name)
 	return l;
 }
 
+static unsigned long read_debug_slab_obj(struct slabinfo *s, const char *name)
+{
+	char x[128];
+	FILE *f;
+	size_t l;
+
+	snprintf(x, 128, "/sys/kernel/debug/slab/%s/%s", s->name, name);
+	f = fopen(x, "r");
+	if (!f) {
+		buffer[0] = 0;
+		l = 0;
+	} else {
+		l = fread(buffer, 1, sizeof(buffer), f);
+		buffer[l] = 0;
+		fclose(f);
+	}
+	return l;
+}
 
 /*
  * Put a size string together
@@ -409,14 +427,18 @@ static void show_tracking(struct slabinfo *s)
 {
 	printf("\n%s: Kernel object allocation\n", s->name);
 	printf("-----------------------------------------------------------------------\n");
-	if (read_slab_obj(s, "alloc_calls"))
+	if (read_debug_slab_obj(s, "alloc_traces"))
+		printf("%s", buffer);
+	else if (read_slab_obj(s, "alloc_calls"))
 		printf("%s", buffer);
 	else
 		printf("No Data\n");
 
 	printf("\n%s: Kernel object freeing\n", s->name);
 	printf("------------------------------------------------------------------------\n");
-	if (read_slab_obj(s, "free_calls"))
+	if (read_debug_slab_obj(s, "free_traces"))
+		printf("%s", buffer);
+	else if (read_slab_obj(s, "free_calls"))
 		printf("%s", buffer);
 	else
 		printf("No Data\n");
@@ -1045,15 +1067,27 @@ static void sort_slabs(void)
 		for (s2 = s1 + 1; s2 < slabinfo + slabs; s2++) {
 			int result;
 
-			if (sort_size)
-				result = slab_size(s1) < slab_size(s2);
-			else if (sort_active)
-				result = slab_activity(s1) < slab_activity(s2);
-			else if (sort_loss)
-				result = slab_waste(s1) < slab_waste(s2);
-			else if (sort_partial)
-				result = s1->partial < s2->partial;
-			else
+			if (sort_size) {
+				if (slab_size(s1) == slab_size(s2))
+					result = strcasecmp(s1->name, s2->name);
+				else
+					result = slab_size(s1) < slab_size(s2);
+			} else if (sort_active) {
+				if (slab_activity(s1) == slab_activity(s2))
+					result = strcasecmp(s1->name, s2->name);
+				else
+					result = slab_activity(s1) < slab_activity(s2);
+			} else if (sort_loss) {
+				if (slab_waste(s1) == slab_waste(s2))
+					result = strcasecmp(s1->name, s2->name);
+				else
+					result = slab_waste(s1) < slab_waste(s2);
+			} else if (sort_partial) {
+				if (s1->partial == s2->partial)
+					result = strcasecmp(s1->name, s2->name);
+				else
+					result = s1->partial < s2->partial;
+			} else
 				result = strcasecmp(s1->name, s2->name);
 
 			if (show_inverted)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index fefdf3a6dae3..3ae5f6a3eae4 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -162,6 +162,10 @@ __weak void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
 {
 }
 
+__weak void kvm_arch_guest_memory_reclaimed(struct kvm *kvm)
+{
+}
+
 bool kvm_is_zone_device_pfn(kvm_pfn_t pfn)
 {
 	/*
@@ -353,6 +357,12 @@ void kvm_reload_remote_mmus(struct kvm *kvm)
 	kvm_make_all_cpus_request(kvm, KVM_REQ_MMU_RELOAD);
 }
 
+static void kvm_flush_shadow_all(struct kvm *kvm)
+{
+	kvm_arch_flush_shadow_all(kvm);
+	kvm_arch_guest_memory_reclaimed(kvm);
+}
+
 #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE
 static inline void *mmu_memory_cache_alloc_obj(struct kvm_mmu_memory_cache *mc,
 					       gfp_t gfp_flags)
@@ -469,12 +479,15 @@ typedef bool (*hva_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range);
 typedef void (*on_lock_fn_t)(struct kvm *kvm, unsigned long start,
 			     unsigned long end);
 
+typedef void (*on_unlock_fn_t)(struct kvm *kvm);
+
 struct kvm_hva_range {
 	unsigned long start;
 	unsigned long end;
 	pte_t pte;
 	hva_handler_t handler;
 	on_lock_fn_t on_lock;
+	on_unlock_fn_t on_unlock;
 	bool flush_on_ret;
 	bool may_block;
 };
@@ -551,8 +564,11 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
 	if (range->flush_on_ret && ret)
 		kvm_flush_remote_tlbs(kvm);
 
-	if (locked)
+	if (locked) {
 		KVM_MMU_UNLOCK(kvm);
+		if (!IS_KVM_NULL_FN(range->on_unlock))
+			range->on_unlock(kvm);
+	}
 
 	srcu_read_unlock(&kvm->srcu, idx);
 
@@ -573,6 +589,7 @@ static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn,
 		.pte		= pte,
 		.handler	= handler,
 		.on_lock	= (void *)kvm_null_fn,
+		.on_unlock	= (void *)kvm_null_fn,
 		.flush_on_ret	= true,
 		.may_block	= false,
 	};
@@ -592,6 +609,7 @@ static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn
 		.pte		= __pte(0),
 		.handler	= handler,
 		.on_lock	= (void *)kvm_null_fn,
+		.on_unlock	= (void *)kvm_null_fn,
 		.flush_on_ret	= false,
 		.may_block	= false,
 	};
@@ -660,6 +678,7 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 		.pte		= __pte(0),
 		.handler	= kvm_unmap_gfn_range,
 		.on_lock	= kvm_inc_notifier_count,
+		.on_unlock	= kvm_arch_guest_memory_reclaimed,
 		.flush_on_ret	= true,
 		.may_block	= mmu_notifier_range_blockable(range),
 	};
@@ -711,6 +730,7 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
 		.pte		= __pte(0),
 		.handler	= (void *)kvm_null_fn,
 		.on_lock	= kvm_dec_notifier_count,
+		.on_unlock	= (void *)kvm_null_fn,
 		.flush_on_ret	= false,
 		.may_block	= mmu_notifier_range_blockable(range),
 	};
@@ -783,7 +803,7 @@ static void kvm_mmu_notifier_release(struct mmu_notifier *mn,
 	int idx;
 
 	idx = srcu_read_lock(&kvm->srcu);
-	kvm_arch_flush_shadow_all(kvm);
+	kvm_flush_shadow_all(kvm);
 	srcu_read_unlock(&kvm->srcu, idx);
 }
 
@@ -911,7 +931,7 @@ static void kvm_destroy_vm_debugfs(struct kvm *kvm)
 	int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc +
 				      kvm_vcpu_stats_header.num_desc;
 
-	if (!kvm->debugfs_dentry)
+	if (IS_ERR(kvm->debugfs_dentry))
 		return;
 
 	debugfs_remove_recursive(kvm->debugfs_dentry);
@@ -1034,6 +1054,9 @@ static struct kvm *kvm_create_vm(unsigned long type)
 	if (!kvm)
 		return ERR_PTR(-ENOMEM);
 
+	/* KVM is pinned via open("/dev/kvm"), the fd passed to this ioctl(). */
+	__module_get(kvm_chardev_ops.owner);
+
 	KVM_MMU_LOCK_INIT(kvm);
 	mmgrab(current->mm);
 	kvm->mm = current->mm;
@@ -1049,6 +1072,12 @@ static struct kvm *kvm_create_vm(unsigned long type)
 
 	BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX);
 
+	/*
+	 * Force subsequent debugfs file creations to fail if the VM directory
+	 * is not created (by kvm_create_vm_debugfs()).
+	 */
+	kvm->debugfs_dentry = ERR_PTR(-ENOENT);
+
 	if (init_srcu_struct(&kvm->srcu))
 		goto out_err_no_srcu;
 	if (init_srcu_struct(&kvm->irq_srcu))
@@ -1101,16 +1130,6 @@ static struct kvm *kvm_create_vm(unsigned long type)
 	preempt_notifier_inc();
 	kvm_init_pm_notifier(kvm);
 
-	/*
-	 * When the fd passed to this ioctl() is opened it pins the module,
-	 * but try_module_get() also prevents getting a reference if the module
-	 * is in MODULE_STATE_GOING (e.g. if someone ran "rmmod --wait").
-	 */
-	if (!try_module_get(kvm_chardev_ops.owner)) {
-		r = -ENODEV;
-		goto out_err;
-	}
-
 	return kvm;
 
 out_err:
@@ -1134,6 +1153,7 @@ out_err_no_irq_srcu:
 out_err_no_srcu:
 	kvm_arch_free_vm(kvm);
 	mmdrop(current->mm);
+	module_put(kvm_chardev_ops.owner);
 	return ERR_PTR(r);
 }
 
@@ -1188,7 +1208,7 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	WARN_ON(rcuwait_active(&kvm->mn_memslots_update_rcuwait));
 	kvm->mn_active_invalidate_count = 0;
 #else
-	kvm_arch_flush_shadow_all(kvm);
+	kvm_flush_shadow_all(kvm);
 #endif
 	kvm_arch_destroy_vm(kvm);
 	kvm_destroy_devices(kvm);
@@ -1255,9 +1275,9 @@ static int kvm_vm_release(struct inode *inode, struct file *filp)
  */
 static int kvm_alloc_dirty_bitmap(struct kvm_memory_slot *memslot)
 {
-	unsigned long dirty_bytes = 2 * kvm_dirty_bitmap_bytes(memslot);
+	unsigned long dirty_bytes = kvm_dirty_bitmap_bytes(memslot);
 
-	memslot->dirty_bitmap = kvzalloc(dirty_bytes, GFP_KERNEL_ACCOUNT);
+	memslot->dirty_bitmap = __vcalloc(2, dirty_bytes, GFP_KERNEL_ACCOUNT);
 	if (!memslot->dirty_bitmap)
 		return -ENOMEM;
 
@@ -1588,6 +1608,7 @@ static int kvm_set_memslot(struct kvm *kvm,
 		 *	- kvm_is_visible_gfn (mmu_check_root)
 		 */
 		kvm_arch_flush_shadow_memslot(kvm, slot);
+		kvm_arch_guest_memory_reclaimed(kvm);
 
 		/* Released in install_new_memslots. */
 		mutex_lock(&kvm->slots_arch_lock);
@@ -2756,16 +2777,28 @@ void kvm_release_pfn_dirty(kvm_pfn_t pfn)
 }
 EXPORT_SYMBOL_GPL(kvm_release_pfn_dirty);
 
+static bool kvm_is_ad_tracked_pfn(kvm_pfn_t pfn)
+{
+	if (!pfn_valid(pfn))
+		return false;
+
+	/*
+	 * Per page-flags.h, pages tagged PG_reserved "should in general not be
+	 * touched (e.g. set dirty) except by its owner".
+	 */
+	return !PageReserved(pfn_to_page(pfn));
+}
+
 void kvm_set_pfn_dirty(kvm_pfn_t pfn)
 {
-	if (!kvm_is_reserved_pfn(pfn) && !kvm_is_zone_device_pfn(pfn))
+	if (kvm_is_ad_tracked_pfn(pfn))
 		SetPageDirty(pfn_to_page(pfn));
 }
 EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty);
 
 void kvm_set_pfn_accessed(kvm_pfn_t pfn)
 {
-	if (!kvm_is_reserved_pfn(pfn) && !kvm_is_zone_device_pfn(pfn))
+	if (kvm_is_ad_tracked_pfn(pfn))
 		mark_page_accessed(pfn_to_page(pfn));
 }
 EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed);
@@ -4166,8 +4199,11 @@ static int kvm_ioctl_create_device(struct kvm *kvm,
 		kvm_put_kvm_no_destroy(kvm);
 		mutex_lock(&kvm->lock);
 		list_del(&dev->vm_node);
+		if (ops->release)
+			ops->release(dev);
 		mutex_unlock(&kvm->lock);
-		ops->destroy(dev);
+		if (ops->destroy)
+			ops->destroy(dev);
 		return ret;
 	}
 
@@ -5373,7 +5409,7 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm)
 	}
 	add_uevent_var(env, "PID=%d", kvm->userspace_pid);
 
-	if (kvm->debugfs_dentry) {
+	if (!IS_ERR(kvm->debugfs_dentry)) {
 		char *tmp, *p = kmalloc(PATH_MAX, GFP_KERNEL_ACCOUNT);
 
 		if (p) {